{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "IqM-T1RTzY6C" }, "source": [ "To run this, press \"*Runtime*\" and press \"*Run all*\" on a **free** Tesla T4 Google Colab instance!\n", "
\n", " \n", " \n", " Join Discord if you need help + โญ Star us on Github โญ\n", "
\n", "\n", "To install Unsloth on your own computer, follow the installation instructions on our Github page [here](https://github.com/unslothai/unsloth?tab=readme-ov-file#-installation-instructions).\n", "\n", "You will learn how to do [data prep](#Data), how to [train](#Train), how to [run the model](#Inference), & [how to save it](#Save) (eg for Llama.cpp).\n", "\n", "[NEW] Llama-3.1 8b, 70b & 405b are trained on a crazy 15 trillion tokens with 128K long context lengths!\n", "\n", "**[NEW] Try 2x faster inference in a free Colab for Llama-3.1 8b Instruct [here](https://colab.research.google.com/drive/1T-YBVfnphoVc8E2E854qF3jdia2Ll2W2?usp=sharing)**" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "2eSvM9zX_2d3" }, "outputs": [], "source": [ "%%capture\n", "!pip install unsloth\n", "# Also get the latest nightly Unsloth!\n", "!pip uninstall unsloth -y && pip install --upgrade --no-cache-dir \"unsloth[colab-new] @ git+https://github.com/unslothai/unsloth.git\"" ] }, { "cell_type": "markdown", "metadata": { "id": "r2v_X2fA0Df5" }, "source": [ "* We support Llama, Mistral, Phi-3, Gemma, Yi, DeepSeek, Qwen, TinyLlama, Vicuna, Open Hermes etc\n", "* We support 16bit LoRA or 4bit QLoRA. Both 2x faster.\n", "* `max_seq_length` can be set to anything, since we do automatic RoPE Scaling via [kaiokendev's](https://kaiokendev.github.io/til) method.\n", "* [**NEW**] We make Gemma-2 9b / 27b **2x faster**! See our [Gemma-2 9b notebook](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing)\n", "* [**NEW**] To finetune and auto export to Ollama, try our [Ollama notebook](https://colab.research.google.com/drive/1WZDi7APtQ9VsvOrQSSC5DDtxq159j8iZ?usp=sharing)\n", "* [**NEW**] We make Mistral NeMo 12B 2x faster and fit in under 12GB of VRAM! [Mistral NeMo notebook](https://colab.research.google.com/drive/17d3U-CAIwzmbDRqbZ9NnpHxCkmXB6LZ0?usp=sharing)" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 300, "referenced_widgets": [ "6e3c281f112b4a86af7a3ef95933d221", "92395f250a154006923aaf9ea0a9c30b", "f84bfc5390054ec687c157c4d68199a6", "4228734651ca45e19fc7bda79817f9b3", "4613edbbec6846edb5b1677c25d542b6", "d032fe2ba5d647d99026fdade758c0cd", "e9971d220fe24552a1e9aa299765cfb9", "2be29a4553ad4dfea8a9bc620c81a3ae", "94cbb87829d1486899e2ff6325c2ecdf", "f878c2e00bc240c7b0333cce950080e1", "6b908368de51428585552dfef6a83088", "ac5eacaaee8346c080e54ea7a52648a4", "7981edf408d54d41bbeac42da7492c6b", "2b848e5a85bc42bc87945fd9ed5db038", "e88c33f37d6849e0b1a6b41254104cb9", "33843107b93647b28985bfc37ea781ca", "76e5410e286a4a5abd6c213a38aa38bb", "ae7e90a811f94e75997d6a9ed1be8596", "bb9f3379310d4b04be694996f3137b28", "75082ba15db445df907f5612976590ae", "89934c4f26834f15b9889ec36fee3b65", "e887160635cb4803b9f33845df615ec6", "1c7bc5fdb7dd4c39af8d4c2c504ec3ed", "843a27e619534ea8914f9d36386c364b", "8f5adc70fbf248f2811527f620553be5", "4ffb4b2f015046fb94c1115ed0397a20", "5a232ed040f94633a2a374031284c1f6", "2006be31c09349738e221295bb84939f", "07055fc12b0841aaa5317f8252b5d347", "1eb90e686e214122ae763b1b79ae321d", "7a935956348e47c68fbdf05ddf4752f3", "8653acb618ad4e76bbf1daa00ea71238", "e3c3bd9c4c124b0a8c88c83c1fc747d3", "1bd75ddaf57c4438a4e2c3070b9cef65", "a3a3ef6d6337403cabea8b23f7c3021b", "c2ea0a3f01f34ffa8c94ab9b5098e9da", "68ea1d7cb8274a639b3fb5326f4218c3", "39fef7b257614a0595f39355fa226b69", "d125995cc0934239a01ba01b78529f21", "634ae4c6cfe04673b1cdc9c9cac4cbf9", "d7f92e8332374313bee87ccd427446a4", "36799fbcd90d43128620ff98225a825d", "5310346dd579424fa676b8e8e64790e7", "0c1835f404db4846bb13b5da8d8f4447", "29c5b713f07043dda51820523e5c8ff3", "d7375f0f048841b29a20601c122666e8", "f433ced9bfcd4a57ba691d3c1caeed08", "da8ffc70820a48f5a12c6d4b5967015b", "1a6db9aea6a64ae3aaef51d6265b35b2", "331f516c7a76456d801bc2a2feb228aa", "9be9074028da42d39d044a78393a861f", "51cd9026b1664819a67712996ca97bd5", "ea55293415ca48a4be97c2e1e4769122", "8ea52b105a7e44978caca33c0e7e815b", "3662f1445ef34a50b462e601ed31bb69" ] }, "id": "QmUBVEnvCDJv", "outputId": "0a47b925-663d-4543-9c61-994a6302f3c5" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n", " from .autonotebook import tqdm as notebook_tqdm\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "๐Ÿฆฅ Unsloth: Will patch your computer to enable 2x faster free finetuning.\n", "[2024-09-18 21:27:01,596] [INFO] [real_accelerator.py:203:get_accelerator] Setting ds_accelerator to cuda (auto detect)\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/kurogane/anaconda3/envs/llmfact/bin/../lib/gcc/x86_64-conda-linux-gnu/11.2.0/../../../../x86_64-conda-linux-gnu/bin/ld: cannot find -laio: ใใฎใ‚ˆใ†ใชใƒ•ใ‚กใ‚คใƒซใ‚„ใƒ‡ใ‚ฃใƒฌใ‚ฏใƒˆใƒชใฏใ‚ใ‚Šใพใ›ใ‚“\n", "collect2: error: ld returned 1 exit status\n", "nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used\n", "/home/kurogane/anaconda3/envs/llmfact/bin/../lib/gcc/x86_64-conda-linux-gnu/11.2.0/../../../../x86_64-conda-linux-gnu/bin/ld: cannot find -laio: ใใฎใ‚ˆใ†ใชใƒ•ใ‚กใ‚คใƒซใ‚„ใƒ‡ใ‚ฃใƒฌใ‚ฏใƒˆใƒชใฏใ‚ใ‚Šใพใ›ใ‚“\n", "collect2: error: ld returned 1 exit status\n", "nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used\n", "nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used\n", "nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used\n", "nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used\n", "nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used\n", "nvcc warning : incompatible redefinition for option 'compiler-bindir', the last value of this option was used\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "==((====))== Unsloth 2024.8: Fast Llama patching. Transformers = 4.45.0.dev0.\n", " \\\\ /| GPU: NVIDIA RTX A6000. Max memory: 47.521 GB. Platform = Linux.\n", "O^O/ \\_/ \\ Pytorch: 2.4.0+cu121. CUDA = 8.6. CUDA Toolkit = 12.1.\n", "\\ / Bfloat16 = TRUE. FA [Xformers = 0.0.27.post2. FA2 = True]\n", " \"-____-\" Free Apache license: http://github.com/unslothai/unsloth\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "Loading checkpoint shards: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 2/2 [00:01<00:00, 1.26it/s]\n", "Magpie-Align/MagpieLM-4B-Chat-v0.1 does not have a padding token! Will use pad_token = <|finetune_right_pad_id|>.\n", ":204: SyntaxWarning: invalid escape sequence '\\ '\n", ":205: SyntaxWarning: invalid escape sequence '\\_'\n", ":206: SyntaxWarning: invalid escape sequence '\\ '\n", ":204: SyntaxWarning: invalid escape sequence '\\ '\n", ":205: SyntaxWarning: invalid escape sequence '\\_'\n", ":206: SyntaxWarning: invalid escape sequence '\\ '\n" ] } ], "source": [ "from unsloth import FastLanguageModel\n", "import torch\n", "max_seq_length = 2048 # Choose any! We auto support RoPE Scaling internally!\n", "dtype = None # None for auto detection. Float16 for Tesla T4, V100, Bfloat16 for Ampere+\n", "load_in_4bit = True # Use 4bit quantization to reduce memory usage. Can be False.\n", "\n", "# 4bit pre quantized models we support for 4x faster downloading + no OOMs.\n", "fourbit_models = [\n", " \"unsloth/Meta-Llama-3.1-8B-bnb-4bit\", # Llama-3.1 15 trillion tokens model 2x faster!\n", " \"unsloth/Meta-Llama-3.1-8B-Instruct-bnb-4bit\",\n", " \"unsloth/Meta-Llama-3.1-70B-bnb-4bit\",\n", " \"unsloth/Meta-Llama-3.1-405B-bnb-4bit\", # We also uploaded 4bit for 405b!\n", " \"unsloth/Mistral-Nemo-Base-2407-bnb-4bit\", # New Mistral 12b 2x faster!\n", " \"unsloth/Mistral-Nemo-Instruct-2407-bnb-4bit\",\n", " \"unsloth/mistral-7b-v0.3-bnb-4bit\", # Mistral v3 2x faster!\n", " \"unsloth/mistral-7b-instruct-v0.3-bnb-4bit\",\n", " \"unsloth/Phi-3.5-mini-instruct\", # Phi-3.5 2x faster!\n", " \"unsloth/Phi-3-medium-4k-instruct\",\n", " \"unsloth/gemma-2-9b-bnb-4bit\",\n", " \"unsloth/gemma-2-27b-bnb-4bit\", # Gemma 2x faster!\n", "] # More models at https://huggingface.co/unsloth\n", "\n", "model, tokenizer = FastLanguageModel.from_pretrained(\n", " model_name = \"Magpie-Align/MagpieLM-4B-Chat-v0.1\",\n", " max_seq_length = max_seq_length,\n", " dtype = dtype,\n", " load_in_4bit = load_in_4bit,\n", " # token = \"hf_...\", # use one if using gated models like meta-llama/Llama-2-7b-hf\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "SXd9bTZd1aaL" }, "source": [ "We now add LoRA adapters so we only need to update 1 to 10% of all parameters!" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "6bZsfBuZDeCL", "outputId": "3e2a4618-6aa0-4f1c-d3a0-0ec45eb33237" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Unsloth 2024.8 patched 32 layers with 32 QKV layers, 32 O layers and 32 MLP layers.\n" ] } ], "source": [ "model = FastLanguageModel.get_peft_model(\n", " model,\n", " r = 16, # Choose any number > 0 ! Suggested 8, 16, 32, 64, 128\n", " target_modules = [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n", " \"gate_proj\", \"up_proj\", \"down_proj\",],\n", " lora_alpha = 16,\n", " lora_dropout = 0, # Supports any, but = 0 is optimized\n", " bias = \"none\", # Supports any, but = \"none\" is optimized\n", " # [NEW] \"unsloth\" uses 30% less VRAM, fits 2x larger batch sizes!\n", " use_gradient_checkpointing = \"unsloth\", # True or \"unsloth\" for very long context\n", " random_state = 3407,\n", " use_rslora = False, # We support rank stabilized LoRA\n", " loftq_config = None, # And LoftQ\n", ")" ] }, { "cell_type": "markdown", "metadata": { "id": "vITh0KVJ10qX" }, "source": [ "\n", "### Data Prep\n", "We now use the Alpaca dataset from [yahma](https://huggingface.co/datasets/yahma/alpaca-cleaned), which is a filtered version of 52K of the original [Alpaca dataset](https://crfm.stanford.edu/2023/03/13/alpaca.html). You can replace this code section with your own data prep.\n", "\n", "**[NOTE]** To train only on completions (ignoring the user's input) read TRL's docs [here](https://huggingface.co/docs/trl/sft_trainer#train-on-completions-only).\n", "\n", "**[NOTE]** Remember to add the **EOS_TOKEN** to the tokenized output!! Otherwise you'll get infinite generations!\n", "\n", "If you want to use the `llama-3` template for ShareGPT datasets, try our conversational [notebook](https://colab.research.google.com/drive/1XamvWYinY6FOSX9GLvnqSjjsNflxdhNc?usp=sharing).\n", "\n", "For text completions like novel writing, try this [notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing)." ] }, { "cell_type": "code", "execution_count": 18, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 145, "referenced_widgets": [ "5e8825fb770b41529f2129113cebc4a9", "0a9dc233674e4096b7a988a5e4ebaf84", "374fa9beda4042e1bf9a9b13de6e6674", "e6533d3c91fd4359bc84ffd8e59af5a3", "f9b01aebcbdc48a585b7942b0ee60a2d", "d4b3770433bc41818372b7aed243fb31", "19bcefcc1d874840ae9a9ca983e474b6", "4011ce9370d74fad857ec8e1e99d314f", "41f5fed060ad4c8d87b24602b720ef04", "88fcd51819b5483c9ab22df7ef89ab64", "e6ffac074f1b476ba2ade11b37732af3", "98a6716e7438429ea322adb3e3264f91", "68c686291b50430faeef0de7840e2c4b", "953625aa1e824f8a8d203197b316b302", "f899a815142542219bde22ff792fb60c", "51ca174d26e94b5cb1e895aa3c770655", "f4519637bb43400a80ce83505101e8a5", "805676b197c94f5aa45956daa354640b", "ce9fcc5eff1f460d80b703a4ca32dad1", "3fef797403d14440afe599a3bf06b626", "4e7cb8e988114ed4b6fe09ff9f682dff", "a14bc1c2130842568a5fde6698731e5f", "85cc6f24cba54563acb5598f54fed7b9", "80a72037771e4da9be989eefabbc8e76", "ba68b274c50b44ec9e02642378d271a6", "f84d2fe4f1c24a34948755abf1f32b7f", "86511967834f4484a5ec4af387b7d7a9", "c97c40c2bf2a41a8ae1c75e0a9c8ebff", "484e507f14424f2b9173595b985f4101", "68a32b398e1c490393e01befdc260785", "04cc963133d242779572d2e847fa3d65", "94730f13e92a4c9aac35c2cfb21fc48c", "620c0de28ec74f71a021a2be96dccf3a", "6e1aff64771c402ab070f650562fa4c9", "0078f897f2174217a307d95d4f9bd775", "ecdeaab4f8c94d6dade63bb06857c969", "735b85f0a0e9411cac4d704a504fcfc1", "8e992e60416145a8b6eed744287ca0fb", "8c195b5809604905b5e404baa30e8449", "2247efac4283489bbd228330344388ab", "e93d063faf984cc4aa51462418d9b57e", "9d45b9a5de3e4cba9ac35ad2cb187f51", "e99423a1ed3f4f72886b39368468b7c1", "5f174718e5974a7cab024d113f662513" ] }, "id": "LjY75GoYUCB8", "outputId": "80d6c3b9-28c2-4ebf-9c57-6a0b77ce82b1" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Downloading readme: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 1.76k/1.76k [00:00<00:00, 21.6MB/s]\n", "Downloading data: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 25.5M/25.5M [00:03<00:00, 7.64MB/s]\n", "Generating train split: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 51716/51716 [00:00<00:00, 265036.01 examples/s]\n", "Generating test split: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 51716/51716 [00:00<00:00, 290444.83 examples/s]\n", "Map: 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 51716/51716 [00:00<00:00, 222945.99 examples/s]\n" ] } ], "source": [ "alpaca_prompt = \"\"\"Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", "\n", "### Instruction:\n", "{}\n", "\n", "### Input:\n", "{}\n", "\n", "### Response:\n", "{}\"\"\"\n", "\n", "EOS_TOKEN = tokenizer.eos_token # Must add EOS_TOKEN\n", "def formatting_prompts_func(examples):\n", " instructions = examples[\"instruction\"]\n", " inputs = examples[\"input\"]\n", " outputs = examples[\"output\"]\n", " texts = []\n", " for instruction, input, output in zip(instructions, inputs, outputs):\n", " # Must add EOS_TOKEN, otherwise your generation will go on forever!\n", " text = alpaca_prompt.format(instruction, input, output) + EOS_TOKEN\n", " texts.append(text)\n", " return { \"text\" : texts, }\n", "pass\n", "\n", "from datasets import load_dataset\n", "dataset = load_dataset(\"shi3z/alpaca_cleaned_ja_json\", split = \"train\")\n", "dataset = dataset.map(formatting_prompts_func, batched = True,)" ] }, { "cell_type": "markdown", "metadata": { "id": "idAEIeSQ3xdS" }, "source": [ "\n", "### Train the model\n", "Now let's use Huggingface TRL's `SFTTrainer`! More docs here: [TRL SFT docs](https://huggingface.co/docs/trl/sft_trainer). We do 60 steps to speed things up, but you can set `num_train_epochs=1` for a full run, and turn off `max_steps=None`. We also support TRL's `DPOTrainer`!" ] }, { "cell_type": "code", "execution_count": 19, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 67, "referenced_widgets": [ "3719bf6f9c6a4c6fbef93c5328c11a07", "03f492b4b56f4d8e80e9395a65058b1b", "39d9ef9fb35f47119f319f48eb222070", "3d7cfb33ceaf417e851ac4393c65148b", "ece66fa2f128456fa2a82b8a28d1211c", "9695a640b0ff4e91af495bb59548e4b6", "d4bd5559d4134d64a943d57972c6ef39", "fbae6e599d1644f39e5d86efa0f9f997", "00d425bca350451da6400f9f05c4a659", "6a27d9ad4f064586a87636b10455d15b", "77f4367616964a01a8c42416f5f4c147" ] }, "id": "95_Nn-89DhsL", "outputId": "29798478-b975-42d3-b32b-020a805cac35" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Map (num_proc=2): 100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 51716/51716 [00:04<00:00, 10877.39 examples/s]\n" ] } ], "source": [ "from trl import SFTTrainer\n", "from transformers import TrainingArguments\n", "from unsloth import is_bfloat16_supported\n", "\n", "trainer = SFTTrainer(\n", " model = model,\n", " tokenizer = tokenizer,\n", " train_dataset = dataset,\n", " dataset_text_field = \"text\",\n", " max_seq_length = max_seq_length,\n", " dataset_num_proc = 2,\n", " packing = False, # Can make training 5x faster for short sequences.\n", " args = TrainingArguments(\n", " per_device_train_batch_size = 2,\n", " gradient_accumulation_steps = 4,\n", " warmup_steps = 5,\n", " # num_train_epochs = 1, # Set this for 1 full training run.\n", " max_steps = 600,\n", " learning_rate = 2e-4,\n", " fp16 = not is_bfloat16_supported(),\n", " bf16 = is_bfloat16_supported(),\n", " logging_steps = 1,\n", " optim = \"adamw_8bit\",\n", " weight_decay = 0.01,\n", " lr_scheduler_type = \"linear\",\n", " seed = 3407,\n", " output_dir = \"outputs\",\n", " ),\n", ")" ] }, { "cell_type": "code", "execution_count": 20, "metadata": { "cellView": "form", "colab": { "base_uri": "https://localhost:8080/" }, "id": "2ejIt2xSNKKp", "outputId": "d397dd48-304c-4f42-ecbc-d5c9ce14989c" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "GPU = NVIDIA RTX A6000. Max memory = 47.521 GB.\n", "11.314 GB of memory reserved.\n" ] } ], "source": [ "#@title Show current memory stats\n", "gpu_stats = torch.cuda.get_device_properties(0)\n", "start_gpu_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)\n", "max_memory = round(gpu_stats.total_memory / 1024 / 1024 / 1024, 3)\n", "print(f\"GPU = {gpu_stats.name}. Max memory = {max_memory} GB.\")\n", "print(f\"{start_gpu_memory} GB of memory reserved.\")" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 1000 }, "id": "yqxqAZ7KJ4oL", "outputId": "76534fb4-5f9a-4da4-9740-fcff4583fd1c" }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 30/6470 [07:52<28:10:47, 15.75s/it]\n", "==((====))== Unsloth - 2x faster free finetuning | Num GPUs = 1\n", " \\\\ /| Num examples = 51,716 | Num Epochs = 1\n", "O^O/ \\_/ \\ Batch size per device = 2 | Gradient Accumulation steps = 4\n", "\\ / Total batch size = 8 | Total steps = 6,464\n", " \"-____-\" Number of trainable parameters = 30,408,704\n", " 0%| | 1/6464 [00:00<1:40:29, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.8246, 'grad_norm': 1.2843562364578247, 'learning_rate': 4e-05, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 2/6464 [00:01<1:39:57, 1.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.8611, 'grad_norm': 1.064693808555603, 'learning_rate': 8e-05, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 3/6464 [00:03<1:52:19, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.7312, 'grad_norm': 0.9926161766052246, 'learning_rate': 0.00012, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 4/6464 [00:03<1:47:53, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.8281, 'grad_norm': 1.0245428085327148, 'learning_rate': 0.00016, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 5/6464 [00:04<1:46:31, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6593, 'grad_norm': 0.959937572479248, 'learning_rate': 0.0002, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 6/6464 [00:06<1:57:49, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6774, 'grad_norm': 0.8117990493774414, 'learning_rate': 0.0001999690354544047, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 7/6464 [00:07<1:50:41, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6001, 'grad_norm': 0.7537485957145691, 'learning_rate': 0.00019993807090880943, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 8/6464 [00:08<1:45:22, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6925, 'grad_norm': 0.9046045541763306, 'learning_rate': 0.00019990710636321412, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 9/6464 [00:08<1:40:02, 1.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4953, 'grad_norm': 0.7860299348831177, 'learning_rate': 0.00019987614181761886, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 10/6464 [00:09<1:37:06, 1.11it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4617, 'grad_norm': 0.7824344635009766, 'learning_rate': 0.00019984517727202354, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 11/6464 [00:10<1:38:07, 1.10it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3623, 'grad_norm': 0.7296981811523438, 'learning_rate': 0.00019981421272642825, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 12/6464 [00:11<1:37:59, 1.10it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5014, 'grad_norm': 0.7208553552627563, 'learning_rate': 0.00019978324818083296, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 13/6464 [00:12<1:40:58, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5631, 'grad_norm': 0.6817415952682495, 'learning_rate': 0.00019975228363523765, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 14/6464 [00:13<1:40:44, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5051, 'grad_norm': 0.669787585735321, 'learning_rate': 0.00019972131908964238, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 15/6464 [00:14<1:40:44, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.603, 'grad_norm': 0.70687335729599, 'learning_rate': 0.00019969035454404707, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 16/6464 [00:15<1:41:39, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3271, 'grad_norm': 0.6717482209205627, 'learning_rate': 0.00019965938999845178, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 17/6464 [00:16<1:40:47, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4431, 'grad_norm': 0.6711722016334534, 'learning_rate': 0.0001996284254528565, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 18/6464 [00:17<1:46:33, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4072, 'grad_norm': 0.5941587090492249, 'learning_rate': 0.0001995974609072612, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 19/6464 [00:18<1:42:19, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2024, 'grad_norm': 0.6636744141578674, 'learning_rate': 0.00019956649636166591, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 20/6464 [00:19<1:41:52, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5725, 'grad_norm': 0.7600715756416321, 'learning_rate': 0.0001995355318160706, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 21/6464 [00:20<1:50:43, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.493, 'grad_norm': 0.6301363110542297, 'learning_rate': 0.0001995045672704753, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 22/6464 [00:21<1:48:57, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6297, 'grad_norm': 0.7425809502601624, 'learning_rate': 0.00019947360272488002, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 23/6464 [00:22<1:52:29, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.34, 'grad_norm': 0.5897881984710693, 'learning_rate': 0.00019944263817928473, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 24/6464 [00:23<1:45:41, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3234, 'grad_norm': 0.8878046870231628, 'learning_rate': 0.00019941167363368944, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 25/6464 [00:24<1:45:44, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1104, 'grad_norm': 0.6818695664405823, 'learning_rate': 0.00019938070908809416, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 26/6464 [00:25<1:44:32, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.452, 'grad_norm': 0.6549364924430847, 'learning_rate': 0.00019934974454249884, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 27/6464 [00:26<1:40:52, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3394, 'grad_norm': 0.8414393067359924, 'learning_rate': 0.00019931877999690355, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 28/6464 [00:27<1:48:28, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4036, 'grad_norm': 0.6974133849143982, 'learning_rate': 0.00019928781545130826, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 29/6464 [00:28<1:55:36, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.291, 'grad_norm': 0.5414274334907532, 'learning_rate': 0.00019925685090571297, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 30/6464 [00:29<1:57:17, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4193, 'grad_norm': 0.5583032369613647, 'learning_rate': 0.00019922588636011769, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 31/6464 [00:30<2:01:33, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2839, 'grad_norm': 0.565670907497406, 'learning_rate': 0.00019919492181452237, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 0%| | 32/6464 [00:31<1:52:03, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5194, 'grad_norm': 0.7766227126121521, 'learning_rate': 0.00019916395726892708, 'epoch': 0.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 33/6464 [00:32<1:52:50, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1921, 'grad_norm': 0.548317015171051, 'learning_rate': 0.0001991329927233318, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 34/6464 [00:33<1:54:31, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5173, 'grad_norm': 0.619870662689209, 'learning_rate': 0.0001991020281777365, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 35/6464 [00:34<1:51:22, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6515, 'grad_norm': 0.6796827912330627, 'learning_rate': 0.00019907106363214121, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 36/6464 [00:36<2:06:35, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6248, 'grad_norm': 0.532484769821167, 'learning_rate': 0.0001990400990865459, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 37/6464 [00:37<1:56:37, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3515, 'grad_norm': 0.6079678535461426, 'learning_rate': 0.00019900913454095064, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 38/6464 [00:38<1:50:02, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2047, 'grad_norm': 0.5996971130371094, 'learning_rate': 0.00019897816999535532, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 39/6464 [00:39<1:49:26, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2576, 'grad_norm': 0.5708647966384888, 'learning_rate': 0.00019894720544976003, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 40/6464 [00:40<1:44:47, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4711, 'grad_norm': 0.6743505001068115, 'learning_rate': 0.00019891624090416474, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 41/6464 [00:41<1:49:37, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3159, 'grad_norm': 0.5865897536277771, 'learning_rate': 0.00019888527635856943, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 42/6464 [00:42<1:48:08, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.406, 'grad_norm': 0.6205792427062988, 'learning_rate': 0.00019885431181297417, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 43/6464 [00:43<1:46:02, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2324, 'grad_norm': 0.627467155456543, 'learning_rate': 0.00019882334726737885, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 44/6464 [00:44<1:50:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2882, 'grad_norm': 0.5671675205230713, 'learning_rate': 0.0001987923827217836, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 45/6464 [00:45<1:54:32, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6283, 'grad_norm': 0.5259122848510742, 'learning_rate': 0.00019876141817618827, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 46/6464 [00:46<1:51:41, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5934, 'grad_norm': 0.8283041715621948, 'learning_rate': 0.00019873045363059299, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 47/6464 [00:47<1:56:55, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2995, 'grad_norm': 0.4615996181964874, 'learning_rate': 0.0001986994890849977, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 48/6464 [00:48<1:51:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4712, 'grad_norm': 0.7745299935340881, 'learning_rate': 0.00019866852453940238, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 49/6464 [00:49<1:48:24, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5201, 'grad_norm': 0.6031115651130676, 'learning_rate': 0.00019863755999380712, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 50/6464 [00:50<1:44:30, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3538, 'grad_norm': 0.9472135901451111, 'learning_rate': 0.0001986065954482118, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 51/6464 [00:51<1:42:56, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5812, 'grad_norm': 0.7753434777259827, 'learning_rate': 0.00019857563090261652, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 52/6464 [00:52<1:42:57, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2405, 'grad_norm': 0.694286048412323, 'learning_rate': 0.00019854466635702123, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 53/6464 [00:53<1:41:55, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6056, 'grad_norm': 0.6958706378936768, 'learning_rate': 0.0001985137018114259, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 54/6464 [00:54<1:41:08, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3122, 'grad_norm': 0.665744423866272, 'learning_rate': 0.00019848273726583065, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 55/6464 [00:55<1:41:08, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4639, 'grad_norm': 1.064523696899414, 'learning_rate': 0.00019845177272023533, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 56/6464 [00:56<1:46:48, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6855, 'grad_norm': 0.6452624201774597, 'learning_rate': 0.00019842080817464004, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 57/6464 [00:57<1:44:26, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6351, 'grad_norm': 0.676138699054718, 'learning_rate': 0.00019838984362904476, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 58/6464 [00:58<1:43:59, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5758, 'grad_norm': 0.6124588847160339, 'learning_rate': 0.00019835887908344947, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 59/6464 [00:59<1:43:03, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3471, 'grad_norm': 0.5864742994308472, 'learning_rate': 0.00019832791453785418, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 60/6464 [01:00<1:47:08, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5204, 'grad_norm': 0.6233710646629333, 'learning_rate': 0.00019829694999225886, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 61/6464 [01:00<1:42:51, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3125, 'grad_norm': 0.7705268263816833, 'learning_rate': 0.00019826598544666357, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 62/6464 [01:01<1:39:29, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2308, 'grad_norm': 0.8518182039260864, 'learning_rate': 0.00019823502090106829, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 63/6464 [01:02<1:44:52, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1912, 'grad_norm': 0.551417887210846, 'learning_rate': 0.000198204056355473, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 64/6464 [01:03<1:42:54, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5595, 'grad_norm': 0.6418909430503845, 'learning_rate': 0.0001981730918098777, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 65/6464 [01:04<1:40:54, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1921, 'grad_norm': 0.5942518711090088, 'learning_rate': 0.00019814212726428242, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 66/6464 [01:05<1:34:58, 1.12it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2227, 'grad_norm': 0.7811775803565979, 'learning_rate': 0.0001981111627186871, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 67/6464 [01:06<1:31:53, 1.16it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1838, 'grad_norm': 0.7477265000343323, 'learning_rate': 0.00019808019817309182, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 68/6464 [01:07<1:33:55, 1.14it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4602, 'grad_norm': 0.5646738409996033, 'learning_rate': 0.00019804923362749653, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 69/6464 [01:08<1:32:21, 1.15it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.33, 'grad_norm': 0.6185688972473145, 'learning_rate': 0.00019801826908190124, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 70/6464 [01:09<1:42:26, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4692, 'grad_norm': 0.5273575782775879, 'learning_rate': 0.00019798730453630595, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 71/6464 [01:10<1:38:43, 1.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2005, 'grad_norm': 0.6623416543006897, 'learning_rate': 0.00019795633999071063, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 72/6464 [01:11<1:40:54, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4198, 'grad_norm': 0.5849572420120239, 'learning_rate': 0.00019792537544511535, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 73/6464 [01:12<1:47:47, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3752, 'grad_norm': 0.5358637571334839, 'learning_rate': 0.00019789441089952006, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 74/6464 [01:13<1:53:21, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4037, 'grad_norm': 0.5067455768585205, 'learning_rate': 0.00019786344635392477, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 75/6464 [01:14<1:49:52, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1491, 'grad_norm': 0.558538556098938, 'learning_rate': 0.00019783248180832948, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 76/6464 [01:15<1:43:32, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2234, 'grad_norm': 0.6357735991477966, 'learning_rate': 0.00019780151726273416, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 77/6464 [01:16<1:45:17, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2046, 'grad_norm': 0.5810099244117737, 'learning_rate': 0.0001977705527171389, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 78/6464 [01:17<1:50:27, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.672, 'grad_norm': 0.5435113310813904, 'learning_rate': 0.00019773958817154359, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 79/6464 [01:18<1:45:35, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.396, 'grad_norm': 0.5776435136795044, 'learning_rate': 0.0001977086236259483, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%| | 80/6464 [01:19<1:46:17, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3949, 'grad_norm': 0.6215222477912903, 'learning_rate': 0.000197677659080353, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 81/6464 [01:20<1:47:14, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4554, 'grad_norm': 0.5664784908294678, 'learning_rate': 0.0001976466945347577, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 82/6464 [01:21<1:46:55, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.217, 'grad_norm': 0.5930476784706116, 'learning_rate': 0.00019761572998916243, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 83/6464 [01:22<1:45:57, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4901, 'grad_norm': 0.624519944190979, 'learning_rate': 0.00019758476544356712, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 84/6464 [01:23<1:47:09, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5937, 'grad_norm': 0.6473777294158936, 'learning_rate': 0.00019755380089797185, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 85/6464 [01:24<1:49:58, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4691, 'grad_norm': 0.5615217089653015, 'learning_rate': 0.00019752283635237654, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 86/6464 [01:25<1:46:32, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2459, 'grad_norm': 0.5900341272354126, 'learning_rate': 0.00019749187180678125, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 87/6464 [01:26<1:44:50, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5196, 'grad_norm': 0.5923058390617371, 'learning_rate': 0.00019746090726118596, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 88/6464 [01:27<1:40:36, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2411, 'grad_norm': 0.7405860424041748, 'learning_rate': 0.00019742994271559065, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 89/6464 [01:28<1:49:45, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4428, 'grad_norm': 0.623981237411499, 'learning_rate': 0.00019739897816999538, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 90/6464 [01:29<1:44:02, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3078, 'grad_norm': 0.6930555105209351, 'learning_rate': 0.00019736801362440007, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 91/6464 [01:30<1:49:42, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3185, 'grad_norm': 0.5249105095863342, 'learning_rate': 0.00019733704907880478, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 92/6464 [01:31<1:51:04, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4955, 'grad_norm': 0.5554251074790955, 'learning_rate': 0.0001973060845332095, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 93/6464 [01:32<1:47:51, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0517, 'grad_norm': 0.7111521363258362, 'learning_rate': 0.00019727511998761418, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 94/6464 [01:33<1:42:27, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0389, 'grad_norm': 0.6177617311477661, 'learning_rate': 0.00019724415544201891, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 95/6464 [01:34<1:39:47, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1341, 'grad_norm': 0.5987043976783752, 'learning_rate': 0.0001972131908964236, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 1%|โ– | 96/6464 [01:35<1:44:01, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4968, 'grad_norm': 0.5643767714500427, 'learning_rate': 0.0001971822263508283, 'epoch': 0.01}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 97/6464 [01:36<1:45:03, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4748, 'grad_norm': 0.6140109896659851, 'learning_rate': 0.00019715126180523302, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 98/6464 [01:37<1:41:58, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4166, 'grad_norm': 0.6579088568687439, 'learning_rate': 0.00019712029725963773, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 99/6464 [01:38<1:46:31, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3771, 'grad_norm': 0.5445241928100586, 'learning_rate': 0.00019708933271404244, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 100/6464 [01:39<1:48:07, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6328, 'grad_norm': 0.7143931984901428, 'learning_rate': 0.00019705836816844713, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 101/6464 [01:40<1:42:41, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2568, 'grad_norm': 0.691895067691803, 'learning_rate': 0.00019702740362285184, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 102/6464 [01:41<1:47:46, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6198, 'grad_norm': 0.6337792873382568, 'learning_rate': 0.00019699643907725655, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 103/6464 [01:42<1:51:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4351, 'grad_norm': 0.5876798629760742, 'learning_rate': 0.00019696547453166126, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 104/6464 [01:43<1:53:42, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.436, 'grad_norm': 0.6287674307823181, 'learning_rate': 0.00019693450998606597, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 105/6464 [01:44<1:51:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3518, 'grad_norm': 0.593627393245697, 'learning_rate': 0.00019690354544047068, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 106/6464 [01:45<1:53:26, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3248, 'grad_norm': 0.5485449433326721, 'learning_rate': 0.00019687258089487537, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 107/6464 [01:46<1:54:58, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4448, 'grad_norm': 0.5822558403015137, 'learning_rate': 0.00019684161634928008, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 108/6464 [01:47<1:57:07, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4684, 'grad_norm': 0.5995234251022339, 'learning_rate': 0.0001968106518036848, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 109/6464 [01:48<1:51:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.475, 'grad_norm': 0.7585017681121826, 'learning_rate': 0.0001967796872580895, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 110/6464 [01:49<1:52:04, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4975, 'grad_norm': 0.5720056295394897, 'learning_rate': 0.00019674872271249421, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 111/6464 [01:50<1:46:23, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2073, 'grad_norm': 0.6087788343429565, 'learning_rate': 0.0001967177581668989, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 112/6464 [01:51<1:44:09, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.344, 'grad_norm': 0.6590687036514282, 'learning_rate': 0.0001966867936213036, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 113/6464 [01:52<1:47:08, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2708, 'grad_norm': 0.5478231906890869, 'learning_rate': 0.00019665582907570832, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 114/6464 [01:53<1:45:19, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2334, 'grad_norm': 0.6059114336967468, 'learning_rate': 0.00019662486453011303, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 115/6464 [01:54<1:43:04, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1851, 'grad_norm': 0.697286069393158, 'learning_rate': 0.00019659389998451774, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 116/6464 [01:55<1:47:17, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1824, 'grad_norm': 0.594581127166748, 'learning_rate': 0.00019656293543892243, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 117/6464 [01:56<1:49:15, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3024, 'grad_norm': 0.5771292448043823, 'learning_rate': 0.00019653197089332717, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 118/6464 [01:57<1:46:50, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1571, 'grad_norm': 0.5673888921737671, 'learning_rate': 0.00019650100634773185, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 119/6464 [01:58<1:50:49, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4609, 'grad_norm': 0.634513258934021, 'learning_rate': 0.00019647004180213656, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 120/6464 [01:59<1:45:46, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3263, 'grad_norm': 0.6539722681045532, 'learning_rate': 0.00019643907725654127, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 121/6464 [02:01<1:50:19, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5356, 'grad_norm': 0.5994091629981995, 'learning_rate': 0.00019640811271094596, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 122/6464 [02:01<1:44:25, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.407, 'grad_norm': 0.656477689743042, 'learning_rate': 0.0001963771481653507, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 123/6464 [02:02<1:46:26, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3451, 'grad_norm': 0.5184924006462097, 'learning_rate': 0.00019634618361975538, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 124/6464 [02:03<1:43:50, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3801, 'grad_norm': 0.6516755223274231, 'learning_rate': 0.00019631521907416012, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 125/6464 [02:04<1:45:35, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4785, 'grad_norm': 0.6195762753486633, 'learning_rate': 0.0001962842545285648, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 126/6464 [02:06<1:58:01, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4116, 'grad_norm': 0.5185932517051697, 'learning_rate': 0.00019625328998296951, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 127/6464 [02:07<1:59:58, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4465, 'grad_norm': 0.5480249524116516, 'learning_rate': 0.00019622232543737423, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 128/6464 [02:08<1:56:51, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3505, 'grad_norm': 0.6016959547996521, 'learning_rate': 0.0001961913608917789, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 129/6464 [02:09<1:55:27, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4494, 'grad_norm': 0.6617076396942139, 'learning_rate': 0.00019616039634618365, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 130/6464 [02:10<1:52:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1933, 'grad_norm': 0.5284921526908875, 'learning_rate': 0.00019612943180058833, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 131/6464 [02:11<1:50:31, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3263, 'grad_norm': 0.5788498520851135, 'learning_rate': 0.00019609846725499304, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 132/6464 [02:12<1:47:27, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2324, 'grad_norm': 0.5701682567596436, 'learning_rate': 0.00019606750270939776, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 133/6464 [02:13<1:51:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6003, 'grad_norm': 0.5961871147155762, 'learning_rate': 0.00019603653816380244, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 134/6464 [02:14<1:52:11, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4341, 'grad_norm': 0.5770149230957031, 'learning_rate': 0.00019600557361820718, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 135/6464 [02:15<1:51:04, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4644, 'grad_norm': 0.5868358612060547, 'learning_rate': 0.00019597460907261186, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 136/6464 [02:16<1:53:20, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.516, 'grad_norm': 0.5399515628814697, 'learning_rate': 0.00019594364452701657, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 137/6464 [02:17<1:47:22, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2456, 'grad_norm': 0.7158103585243225, 'learning_rate': 0.00019591267998142129, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 138/6464 [02:18<1:46:00, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2875, 'grad_norm': 0.59195876121521, 'learning_rate': 0.000195881715435826, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 139/6464 [02:19<1:41:32, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1543, 'grad_norm': 0.6045067310333252, 'learning_rate': 0.0001958507508902307, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 140/6464 [02:20<1:38:16, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2932, 'grad_norm': 0.7166385650634766, 'learning_rate': 0.0001958197863446354, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 141/6464 [02:21<1:40:49, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4739, 'grad_norm': 0.6920706629753113, 'learning_rate': 0.0001957888217990401, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 142/6464 [02:22<1:43:24, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3532, 'grad_norm': 0.5903937220573425, 'learning_rate': 0.00019575785725344481, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 143/6464 [02:23<1:46:24, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.284, 'grad_norm': 0.5672841668128967, 'learning_rate': 0.00019572689270784953, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 144/6464 [02:24<1:40:23, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1294, 'grad_norm': 0.6793231964111328, 'learning_rate': 0.00019569592816225424, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 145/6464 [02:25<1:43:09, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2129, 'grad_norm': 0.5622747540473938, 'learning_rate': 0.00019566496361665895, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 146/6464 [02:26<1:46:36, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4091, 'grad_norm': 0.5912714600563049, 'learning_rate': 0.00019563399907106363, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 147/6464 [02:27<1:46:14, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2478, 'grad_norm': 0.6467005610466003, 'learning_rate': 0.00019560303452546834, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 148/6464 [02:28<1:48:38, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.269, 'grad_norm': 0.5535518527030945, 'learning_rate': 0.00019557206997987306, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 149/6464 [02:29<1:44:43, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1222, 'grad_norm': 0.5883463621139526, 'learning_rate': 0.00019554110543427777, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 150/6464 [02:30<1:47:06, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2233, 'grad_norm': 0.5589303970336914, 'learning_rate': 0.00019551014088868248, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 151/6464 [02:31<1:44:32, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3649, 'grad_norm': 0.6352980732917786, 'learning_rate': 0.00019547917634308716, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 152/6464 [02:32<1:47:55, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3121, 'grad_norm': 0.5507774949073792, 'learning_rate': 0.00019544821179749187, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 153/6464 [02:33<1:54:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3698, 'grad_norm': 0.5739220380783081, 'learning_rate': 0.00019541724725189659, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 154/6464 [02:34<1:53:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4418, 'grad_norm': 0.5756464004516602, 'learning_rate': 0.0001953862827063013, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 155/6464 [02:36<1:56:37, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6033, 'grad_norm': 0.6310089230537415, 'learning_rate': 0.000195355318160706, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 156/6464 [02:37<1:51:30, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4783, 'grad_norm': 0.6247748732566833, 'learning_rate': 0.0001953243536151107, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 157/6464 [02:38<1:48:11, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.544, 'grad_norm': 0.6321399211883545, 'learning_rate': 0.00019529338906951543, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 158/6464 [02:38<1:42:47, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.347, 'grad_norm': 0.6461014747619629, 'learning_rate': 0.00019526242452392012, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 159/6464 [02:39<1:41:30, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4, 'grad_norm': 0.619521975517273, 'learning_rate': 0.00019523145997832483, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 160/6464 [02:40<1:42:08, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4401, 'grad_norm': 0.67606121301651, 'learning_rate': 0.00019520049543272954, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 2%|โ– | 161/6464 [02:41<1:42:04, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5531, 'grad_norm': 0.643559992313385, 'learning_rate': 0.00019516953088713422, 'epoch': 0.02}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 162/6464 [02:42<1:40:55, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2939, 'grad_norm': 0.726882815361023, 'learning_rate': 0.00019513856634153896, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 163/6464 [02:43<1:40:10, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3824, 'grad_norm': 1.0285048484802246, 'learning_rate': 0.00019510760179594364, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 164/6464 [02:44<1:48:47, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5152, 'grad_norm': 0.5549235343933105, 'learning_rate': 0.00019507663725034838, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 165/6464 [02:45<1:48:14, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2772, 'grad_norm': 0.6342753171920776, 'learning_rate': 0.00019504567270475307, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 166/6464 [02:47<1:51:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3971, 'grad_norm': 0.5930852293968201, 'learning_rate': 0.00019501470815915778, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 167/6464 [02:48<1:51:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1915, 'grad_norm': 0.5367887616157532, 'learning_rate': 0.0001949837436135625, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 168/6464 [02:49<1:49:13, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3046, 'grad_norm': 0.602185845375061, 'learning_rate': 0.00019495277906796717, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 169/6464 [02:50<1:54:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5562, 'grad_norm': 0.6814662218093872, 'learning_rate': 0.0001949218145223719, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 170/6464 [02:51<1:55:13, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3793, 'grad_norm': 0.5028030276298523, 'learning_rate': 0.0001948908499767766, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 171/6464 [02:52<1:58:15, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2594, 'grad_norm': 0.5324199795722961, 'learning_rate': 0.0001948598854311813, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 172/6464 [02:53<1:52:28, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1965, 'grad_norm': 0.5782201886177063, 'learning_rate': 0.00019482892088558602, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 173/6464 [02:54<1:55:21, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3223, 'grad_norm': 0.68146151304245, 'learning_rate': 0.0001947979563399907, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 174/6464 [02:55<1:49:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1231, 'grad_norm': 0.6733139753341675, 'learning_rate': 0.00019476699179439544, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 175/6464 [02:56<1:48:05, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2726, 'grad_norm': 0.8229575157165527, 'learning_rate': 0.00019473602724880013, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 176/6464 [02:57<1:49:57, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6088, 'grad_norm': 0.5828347206115723, 'learning_rate': 0.00019470506270320484, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 177/6464 [02:58<1:47:22, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6102, 'grad_norm': 0.7470994591712952, 'learning_rate': 0.00019467409815760955, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 178/6464 [02:59<1:46:39, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3933, 'grad_norm': 0.6452146172523499, 'learning_rate': 0.00019464313361201426, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 179/6464 [03:00<1:41:06, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1234, 'grad_norm': 0.6071380972862244, 'learning_rate': 0.00019461216906641897, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 180/6464 [03:01<1:45:32, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3219, 'grad_norm': 0.6014086604118347, 'learning_rate': 0.00019458120452082366, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 181/6464 [03:02<1:43:56, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0551, 'grad_norm': 0.5578067302703857, 'learning_rate': 0.00019455023997522837, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 182/6464 [03:03<1:40:33, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4473, 'grad_norm': 0.7128034234046936, 'learning_rate': 0.00019451927542963308, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 183/6464 [03:04<1:55:36, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4304, 'grad_norm': 0.6208721995353699, 'learning_rate': 0.0001944883108840378, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 184/6464 [03:05<1:48:58, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.371, 'grad_norm': 0.7708938717842102, 'learning_rate': 0.0001944573463384425, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 185/6464 [03:06<1:47:48, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4794, 'grad_norm': 0.6285572648048401, 'learning_rate': 0.0001944263817928472, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 186/6464 [03:07<1:40:34, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1135, 'grad_norm': 0.6674680113792419, 'learning_rate': 0.0001943954172472519, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 187/6464 [03:08<1:50:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3605, 'grad_norm': 0.5045372843742371, 'learning_rate': 0.0001943644527016566, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 188/6464 [03:09<1:49:44, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2032, 'grad_norm': 0.6092396378517151, 'learning_rate': 0.00019433348815606132, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 189/6464 [03:11<1:49:50, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4695, 'grad_norm': 0.731529176235199, 'learning_rate': 0.00019430252361046603, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 190/6464 [03:12<1:53:06, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3788, 'grad_norm': 0.5624423623085022, 'learning_rate': 0.00019427155906487074, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 191/6464 [03:13<1:56:07, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4761, 'grad_norm': 0.62505704164505, 'learning_rate': 0.00019424059451927543, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 192/6464 [03:14<1:49:29, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4147, 'grad_norm': 0.7121075391769409, 'learning_rate': 0.00019420962997368014, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 193/6464 [03:15<1:55:31, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6131, 'grad_norm': 0.5758931040763855, 'learning_rate': 0.00019417866542808485, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 194/6464 [03:16<1:50:03, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2738, 'grad_norm': 0.6509066820144653, 'learning_rate': 0.00019414770088248956, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 195/6464 [03:17<1:51:01, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3487, 'grad_norm': 0.5458537936210632, 'learning_rate': 0.00019411673633689427, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 196/6464 [03:18<1:43:57, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0919, 'grad_norm': 0.6946782469749451, 'learning_rate': 0.00019408577179129896, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 197/6464 [03:19<1:50:21, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4789, 'grad_norm': 0.5352119207382202, 'learning_rate': 0.0001940548072457037, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 198/6464 [03:20<1:48:20, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2211, 'grad_norm': 0.6044583320617676, 'learning_rate': 0.00019402384270010838, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 199/6464 [03:21<1:58:00, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5846, 'grad_norm': 0.5940085053443909, 'learning_rate': 0.0001939928781545131, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 200/6464 [03:22<1:48:27, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2524, 'grad_norm': 0.7412678003311157, 'learning_rate': 0.0001939619136089178, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 201/6464 [03:23<1:49:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2926, 'grad_norm': 0.5699357390403748, 'learning_rate': 0.0001939309490633225, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 202/6464 [03:24<1:47:02, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2406, 'grad_norm': 0.6283614635467529, 'learning_rate': 0.00019389998451772723, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 203/6464 [03:25<1:43:18, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3481, 'grad_norm': 0.5904780626296997, 'learning_rate': 0.0001938690199721319, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 204/6464 [03:26<1:46:41, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.518, 'grad_norm': 0.6723483204841614, 'learning_rate': 0.00019383805542653665, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 205/6464 [03:27<1:49:26, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4486, 'grad_norm': 0.6068739295005798, 'learning_rate': 0.00019380709088094133, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 206/6464 [03:29<1:55:44, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5578, 'grad_norm': 0.5768620371818542, 'learning_rate': 0.00019377612633534604, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 207/6464 [03:30<1:54:34, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2692, 'grad_norm': 0.6216483116149902, 'learning_rate': 0.00019374516178975075, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 208/6464 [03:31<1:48:29, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2334, 'grad_norm': 0.6384607553482056, 'learning_rate': 0.00019371419724415544, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 209/6464 [03:32<1:47:46, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.34, 'grad_norm': 0.5521968007087708, 'learning_rate': 0.00019368323269856018, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 210/6464 [03:33<1:58:13, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3902, 'grad_norm': 0.5146721601486206, 'learning_rate': 0.00019365226815296486, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 211/6464 [03:34<1:55:25, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4771, 'grad_norm': 0.612355649471283, 'learning_rate': 0.00019362130360736957, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 212/6464 [03:35<1:58:43, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6005, 'grad_norm': 0.5612614750862122, 'learning_rate': 0.00019359033906177428, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 213/6464 [03:36<1:57:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2863, 'grad_norm': 0.6484649181365967, 'learning_rate': 0.00019355937451617897, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 214/6464 [03:37<1:54:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3294, 'grad_norm': 0.5962160229682922, 'learning_rate': 0.0001935284099705837, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 215/6464 [03:39<2:07:17, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5012, 'grad_norm': 0.5970625877380371, 'learning_rate': 0.0001934974454249884, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 216/6464 [03:40<2:00:15, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.466, 'grad_norm': 0.6384586691856384, 'learning_rate': 0.0001934664808793931, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 217/6464 [03:41<1:50:32, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2604, 'grad_norm': 0.6346481442451477, 'learning_rate': 0.00019343551633379781, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 218/6464 [03:42<1:54:25, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2443, 'grad_norm': 0.5566921830177307, 'learning_rate': 0.00019340455178820253, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 219/6464 [03:43<1:56:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.384, 'grad_norm': 0.6114303469657898, 'learning_rate': 0.00019337358724260724, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 220/6464 [03:44<1:55:05, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4809, 'grad_norm': 0.5692293643951416, 'learning_rate': 0.00019334262269701192, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 221/6464 [03:45<1:53:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6066, 'grad_norm': 0.5901232361793518, 'learning_rate': 0.00019331165815141663, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 222/6464 [03:46<1:52:22, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4236, 'grad_norm': 0.6450479030609131, 'learning_rate': 0.00019328069360582134, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 223/6464 [03:47<1:54:17, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2068, 'grad_norm': 0.6326045393943787, 'learning_rate': 0.00019324972906022606, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 224/6464 [03:48<1:48:47, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4641, 'grad_norm': 0.7565138936042786, 'learning_rate': 0.00019321876451463077, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 225/6464 [03:50<1:56:06, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5751, 'grad_norm': 0.6480894684791565, 'learning_rate': 0.00019318779996903548, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 3%|โ–Ž | 226/6464 [03:51<1:53:10, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.475, 'grad_norm': 0.674237847328186, 'learning_rate': 0.00019315683542344016, 'epoch': 0.03}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 227/6464 [03:52<1:58:19, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3977, 'grad_norm': 0.5694662928581238, 'learning_rate': 0.00019312587087784487, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 228/6464 [03:53<1:57:45, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2686, 'grad_norm': 0.5956376791000366, 'learning_rate': 0.00019309490633224958, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 229/6464 [03:54<1:55:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4317, 'grad_norm': 0.6654650568962097, 'learning_rate': 0.0001930639417866543, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 230/6464 [03:55<1:56:47, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5257, 'grad_norm': 0.549347996711731, 'learning_rate': 0.000193032977241059, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 231/6464 [03:56<1:49:43, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1789, 'grad_norm': 0.6379307508468628, 'learning_rate': 0.0001930020126954637, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 232/6464 [03:57<1:57:49, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5886, 'grad_norm': 0.5662992000579834, 'learning_rate': 0.0001929710481498684, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 233/6464 [03:59<1:56:41, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3347, 'grad_norm': 0.6122046709060669, 'learning_rate': 0.00019294008360427311, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 234/6464 [04:00<1:54:28, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3419, 'grad_norm': 0.7502700686454773, 'learning_rate': 0.00019290911905867783, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 235/6464 [04:01<1:55:39, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4817, 'grad_norm': 0.6580245494842529, 'learning_rate': 0.00019287815451308254, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 236/6464 [04:02<1:51:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2631, 'grad_norm': 0.662095844745636, 'learning_rate': 0.00019284718996748722, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 237/6464 [04:03<1:50:48, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3725, 'grad_norm': 0.5982234477996826, 'learning_rate': 0.00019281622542189196, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 238/6464 [04:04<1:48:10, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2048, 'grad_norm': 0.6591340899467468, 'learning_rate': 0.00019278526087629664, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 239/6464 [04:05<1:50:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2052, 'grad_norm': 0.5488467216491699, 'learning_rate': 0.00019275429633070136, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 240/6464 [04:06<1:58:21, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4961, 'grad_norm': 0.5611937046051025, 'learning_rate': 0.00019272333178510607, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 241/6464 [04:07<1:52:47, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3551, 'grad_norm': 0.68928062915802, 'learning_rate': 0.00019269236723951075, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ–Ž | 242/6464 [04:08<1:48:34, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1862, 'grad_norm': 0.5805150270462036, 'learning_rate': 0.0001926614026939155, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 243/6464 [04:09<1:44:48, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1657, 'grad_norm': 0.5748918652534485, 'learning_rate': 0.00019263043814832017, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 244/6464 [04:10<1:46:13, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5399, 'grad_norm': 0.6559778451919556, 'learning_rate': 0.0001925994736027249, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 245/6464 [04:11<1:42:14, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2973, 'grad_norm': 0.7758539915084839, 'learning_rate': 0.0001925685090571296, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 246/6464 [04:12<1:39:34, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0972, 'grad_norm': 0.5874989628791809, 'learning_rate': 0.0001925375445115343, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 247/6464 [04:13<1:47:11, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4585, 'grad_norm': 0.5892620086669922, 'learning_rate': 0.00019250657996593902, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 248/6464 [04:14<1:46:25, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2207, 'grad_norm': 0.7287330627441406, 'learning_rate': 0.0001924756154203437, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 249/6464 [04:15<1:46:01, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3493, 'grad_norm': 0.6179761290550232, 'learning_rate': 0.00019244465087474844, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 250/6464 [04:16<1:49:00, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4421, 'grad_norm': 0.5836701989173889, 'learning_rate': 0.00019241368632915313, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 251/6464 [04:17<1:40:39, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0719, 'grad_norm': 0.7415968179702759, 'learning_rate': 0.00019238272178355784, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 252/6464 [04:18<1:39:23, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2067, 'grad_norm': 0.6145604848861694, 'learning_rate': 0.00019235175723796255, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 253/6464 [04:19<1:43:30, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4491, 'grad_norm': 0.6726418733596802, 'learning_rate': 0.00019232079269236723, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 254/6464 [04:20<1:44:20, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3261, 'grad_norm': 0.6317542791366577, 'learning_rate': 0.00019228982814677194, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 255/6464 [04:21<1:46:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2729, 'grad_norm': 0.5361437797546387, 'learning_rate': 0.00019225886360117666, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 256/6464 [04:22<1:47:46, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3103, 'grad_norm': 0.6072362065315247, 'learning_rate': 0.00019222789905558137, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 257/6464 [04:23<1:47:15, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5693, 'grad_norm': 0.6770271062850952, 'learning_rate': 0.00019219693450998608, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 258/6464 [04:24<1:53:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.36, 'grad_norm': 0.5300812125205994, 'learning_rate': 0.0001921659699643908, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 259/6464 [04:26<1:52:23, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2284, 'grad_norm': 0.5749597549438477, 'learning_rate': 0.00019213500541879547, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 260/6464 [04:26<1:43:11, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1061, 'grad_norm': 0.6650879383087158, 'learning_rate': 0.00019210404087320019, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 261/6464 [04:27<1:42:00, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4997, 'grad_norm': 0.7547794580459595, 'learning_rate': 0.0001920730763276049, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 262/6464 [04:28<1:39:37, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1517, 'grad_norm': 0.7519833445549011, 'learning_rate': 0.0001920421117820096, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 263/6464 [04:29<1:44:54, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1074, 'grad_norm': 0.6710019707679749, 'learning_rate': 0.00019201114723641432, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 264/6464 [04:30<1:46:37, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4788, 'grad_norm': 0.6496911644935608, 'learning_rate': 0.000191980182690819, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 265/6464 [04:31<1:43:02, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2189, 'grad_norm': 0.6145163178443909, 'learning_rate': 0.00019194921814522374, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 266/6464 [04:32<1:42:13, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2805, 'grad_norm': 0.6406363248825073, 'learning_rate': 0.00019191825359962843, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 267/6464 [04:33<1:48:04, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4609, 'grad_norm': 0.6571307182312012, 'learning_rate': 0.00019188728905403314, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 268/6464 [04:35<1:52:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3629, 'grad_norm': 0.8645737171173096, 'learning_rate': 0.00019185632450843785, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 269/6464 [04:36<1:52:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5586, 'grad_norm': 0.8662606477737427, 'learning_rate': 0.00019182535996284253, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 270/6464 [04:37<1:51:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3843, 'grad_norm': 0.6360623240470886, 'learning_rate': 0.00019179439541724727, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 271/6464 [04:38<1:53:06, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3627, 'grad_norm': 0.521999180316925, 'learning_rate': 0.00019176343087165196, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 272/6464 [04:39<1:50:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3126, 'grad_norm': 0.5977190732955933, 'learning_rate': 0.00019173246632605667, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 273/6464 [04:40<1:41:52, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3087, 'grad_norm': 0.6742759346961975, 'learning_rate': 0.00019170150178046138, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 274/6464 [04:41<1:41:16, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.411, 'grad_norm': 0.7088914513587952, 'learning_rate': 0.00019167053723486606, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 275/6464 [04:42<1:43:46, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4326, 'grad_norm': 0.5969992876052856, 'learning_rate': 0.0001916395726892708, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 276/6464 [04:43<1:43:05, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4046, 'grad_norm': 0.6666600108146667, 'learning_rate': 0.00019160860814367549, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 277/6464 [04:44<1:40:52, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2359, 'grad_norm': 0.6732454299926758, 'learning_rate': 0.00019157764359808022, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 278/6464 [04:45<1:48:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6556, 'grad_norm': 0.6003813743591309, 'learning_rate': 0.0001915466790524849, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 279/6464 [04:46<1:47:25, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2957, 'grad_norm': 0.5810785293579102, 'learning_rate': 0.00019151571450688962, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 280/6464 [04:47<1:51:21, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3579, 'grad_norm': 0.5229300856590271, 'learning_rate': 0.00019148474996129433, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 281/6464 [04:48<1:53:59, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.535, 'grad_norm': 0.6213581562042236, 'learning_rate': 0.00019145378541569902, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 282/6464 [04:49<1:46:40, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0131, 'grad_norm': 0.6047224998474121, 'learning_rate': 0.00019142282087010375, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 283/6464 [04:50<1:43:07, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2072, 'grad_norm': 0.7357116341590881, 'learning_rate': 0.00019139185632450844, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 284/6464 [04:51<1:41:11, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4232, 'grad_norm': 0.6887807846069336, 'learning_rate': 0.00019136089177891315, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 285/6464 [04:52<1:44:04, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3501, 'grad_norm': 0.627408504486084, 'learning_rate': 0.00019132992723331786, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 286/6464 [04:53<1:45:17, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3348, 'grad_norm': 0.632453441619873, 'learning_rate': 0.00019129896268772257, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 287/6464 [04:54<1:48:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6042, 'grad_norm': 0.6444559097290039, 'learning_rate': 0.00019126799814212728, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 288/6464 [04:55<1:45:12, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3082, 'grad_norm': 0.6618703007698059, 'learning_rate': 0.00019123703359653197, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 289/6464 [04:56<1:45:03, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3367, 'grad_norm': 0.6282414793968201, 'learning_rate': 0.00019120606905093668, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 4%|โ– | 290/6464 [04:57<1:47:41, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3354, 'grad_norm': 0.5636264085769653, 'learning_rate': 0.0001911751045053414, 'epoch': 0.04}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 291/6464 [04:58<1:42:47, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2284, 'grad_norm': 0.81828773021698, 'learning_rate': 0.0001911441399597461, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 292/6464 [04:59<1:48:45, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5959, 'grad_norm': 0.5975520014762878, 'learning_rate': 0.0001911131754141508, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 293/6464 [05:00<1:48:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3047, 'grad_norm': 0.6285060048103333, 'learning_rate': 0.00019108221086855552, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 294/6464 [05:01<1:42:36, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2471, 'grad_norm': 0.6959381699562073, 'learning_rate': 0.0001910512463229602, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 295/6464 [05:02<1:43:32, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3233, 'grad_norm': 0.6023738384246826, 'learning_rate': 0.00019102028177736492, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 296/6464 [05:04<1:52:28, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5835, 'grad_norm': 0.602087140083313, 'learning_rate': 0.00019098931723176963, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 297/6464 [05:05<1:46:09, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9971, 'grad_norm': 0.6175980567932129, 'learning_rate': 0.00019095835268617434, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 298/6464 [05:06<1:45:31, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0576, 'grad_norm': 0.6349269151687622, 'learning_rate': 0.00019092738814057905, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 299/6464 [05:06<1:41:26, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2799, 'grad_norm': 0.6603456735610962, 'learning_rate': 0.00019089642359498374, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 300/6464 [05:07<1:40:52, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1976, 'grad_norm': 0.6212698221206665, 'learning_rate': 0.00019086545904938845, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 301/6464 [05:09<1:44:55, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2728, 'grad_norm': 0.5680500864982605, 'learning_rate': 0.00019083449450379316, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 302/6464 [05:10<1:46:29, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5632, 'grad_norm': 0.6160039305686951, 'learning_rate': 0.00019080352995819787, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 303/6464 [05:10<1:41:19, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0705, 'grad_norm': 0.820730984210968, 'learning_rate': 0.00019077256541260258, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 304/6464 [05:11<1:38:41, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9477, 'grad_norm': 0.5580445528030396, 'learning_rate': 0.00019074160086700727, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 305/6464 [05:13<1:47:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4562, 'grad_norm': 0.5699657797813416, 'learning_rate': 0.000190710636321412, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 306/6464 [05:14<1:46:14, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3298, 'grad_norm': 0.6363015174865723, 'learning_rate': 0.0001906796717758167, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 307/6464 [05:15<1:44:39, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.448, 'grad_norm': 0.6569076776504517, 'learning_rate': 0.0001906487072302214, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 308/6464 [05:16<1:43:52, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1723, 'grad_norm': 0.658168375492096, 'learning_rate': 0.00019061774268462611, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 309/6464 [05:17<1:43:28, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3416, 'grad_norm': 0.6609898209571838, 'learning_rate': 0.0001905867781390308, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 310/6464 [05:18<1:40:44, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5053, 'grad_norm': 0.6916245818138123, 'learning_rate': 0.00019055581359343554, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 311/6464 [05:19<1:40:03, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2803, 'grad_norm': 0.7222450375556946, 'learning_rate': 0.00019052484904784022, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 312/6464 [05:19<1:36:21, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0825, 'grad_norm': 0.648995041847229, 'learning_rate': 0.00019049388450224496, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 313/6464 [05:20<1:34:51, 1.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1035, 'grad_norm': 0.6116306781768799, 'learning_rate': 0.00019046291995664964, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 314/6464 [05:21<1:36:28, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3202, 'grad_norm': 0.6234920620918274, 'learning_rate': 0.00019043195541105435, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 315/6464 [05:22<1:34:55, 1.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0814, 'grad_norm': 0.6094616055488586, 'learning_rate': 0.00019040099086545907, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 316/6464 [05:23<1:35:32, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3192, 'grad_norm': 0.5890501141548157, 'learning_rate': 0.00019037002631986375, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 317/6464 [05:24<1:35:04, 1.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2797, 'grad_norm': 0.6974156498908997, 'learning_rate': 0.0001903390617742685, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 318/6464 [05:25<1:38:25, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5204, 'grad_norm': 0.6476534008979797, 'learning_rate': 0.00019030809722867317, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 319/6464 [05:26<1:42:25, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1996, 'grad_norm': 0.6261109709739685, 'learning_rate': 0.00019027713268307788, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 320/6464 [05:27<1:41:20, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1408, 'grad_norm': 0.6500852108001709, 'learning_rate': 0.0001902461681374826, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 321/6464 [05:28<1:49:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.8173, 'grad_norm': 0.6267198920249939, 'learning_rate': 0.00019021520359188728, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 322/6464 [05:29<1:47:53, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3751, 'grad_norm': 0.6302520632743835, 'learning_rate': 0.00019018423904629202, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ– | 323/6464 [05:31<1:55:48, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4231, 'grad_norm': 0.5922490358352661, 'learning_rate': 0.0001901532745006967, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 324/6464 [05:32<1:54:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1387, 'grad_norm': 0.6204228401184082, 'learning_rate': 0.00019012230995510141, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 325/6464 [05:33<2:00:19, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4174, 'grad_norm': 0.5553603768348694, 'learning_rate': 0.00019009134540950613, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 326/6464 [05:34<1:55:13, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2722, 'grad_norm': 0.6723055243492126, 'learning_rate': 0.00019006038086391084, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 327/6464 [05:35<1:51:24, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1969, 'grad_norm': 0.6824229955673218, 'learning_rate': 0.00019002941631831555, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 328/6464 [05:36<1:46:53, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3363, 'grad_norm': 0.6455178260803223, 'learning_rate': 0.00018999845177272023, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 329/6464 [05:37<2:00:06, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9949, 'grad_norm': 0.484945684671402, 'learning_rate': 0.00018996748722712494, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 330/6464 [05:39<2:02:04, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3367, 'grad_norm': 0.5638633370399475, 'learning_rate': 0.00018993652268152966, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 331/6464 [05:40<1:54:45, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2147, 'grad_norm': 0.7158960103988647, 'learning_rate': 0.00018990555813593437, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 332/6464 [05:41<1:49:06, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2216, 'grad_norm': 0.6710487604141235, 'learning_rate': 0.00018987459359033908, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 333/6464 [05:42<1:47:34, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2911, 'grad_norm': 0.6590655446052551, 'learning_rate': 0.0001898436290447438, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 334/6464 [05:43<1:57:50, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4498, 'grad_norm': 0.5592907667160034, 'learning_rate': 0.00018981266449914847, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 335/6464 [05:44<1:55:13, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2346, 'grad_norm': 0.630017101764679, 'learning_rate': 0.00018978169995355318, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 336/6464 [05:45<1:57:46, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2853, 'grad_norm': 0.552105188369751, 'learning_rate': 0.0001897507354079579, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 337/6464 [05:46<1:57:55, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3502, 'grad_norm': 0.6221782565116882, 'learning_rate': 0.0001897197708623626, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 338/6464 [05:48<1:57:22, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5384, 'grad_norm': 0.5872494578361511, 'learning_rate': 0.00018968880631676732, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 339/6464 [05:49<1:52:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5665, 'grad_norm': 0.6707834005355835, 'learning_rate': 0.000189657841771172, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 340/6464 [05:50<1:49:24, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3044, 'grad_norm': 0.5752859711647034, 'learning_rate': 0.00018962687722557671, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 341/6464 [05:51<1:53:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5514, 'grad_norm': 0.6183071136474609, 'learning_rate': 0.00018959591267998143, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 342/6464 [05:52<1:53:57, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3372, 'grad_norm': 0.7550036311149597, 'learning_rate': 0.00018956494813438614, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 343/6464 [05:53<1:46:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2086, 'grad_norm': 0.7344180941581726, 'learning_rate': 0.00018953398358879085, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 344/6464 [05:54<1:43:15, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2566, 'grad_norm': 0.6655396819114685, 'learning_rate': 0.00018950301904319553, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 345/6464 [05:55<1:40:21, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2206, 'grad_norm': 0.7382570505142212, 'learning_rate': 0.00018947205449760027, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 346/6464 [05:56<1:38:20, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1735, 'grad_norm': 0.6117857098579407, 'learning_rate': 0.00018944108995200496, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 347/6464 [05:57<1:44:27, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5138, 'grad_norm': 0.6087351441383362, 'learning_rate': 0.00018941012540640967, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 348/6464 [05:58<1:47:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4919, 'grad_norm': 0.6673876643180847, 'learning_rate': 0.00018937916086081438, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 349/6464 [05:59<1:45:45, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3708, 'grad_norm': 0.6455504894256592, 'learning_rate': 0.00018934819631521906, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 350/6464 [06:00<1:47:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4598, 'grad_norm': 0.7351162433624268, 'learning_rate': 0.0001893172317696238, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 351/6464 [06:01<1:52:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6634, 'grad_norm': 0.6012604832649231, 'learning_rate': 0.00018928626722402849, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 352/6464 [06:02<1:45:24, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1587, 'grad_norm': 0.6704577207565308, 'learning_rate': 0.00018925530267843322, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 353/6464 [06:03<1:49:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1944, 'grad_norm': 0.5623053312301636, 'learning_rate': 0.0001892243381328379, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 354/6464 [06:04<1:52:49, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4024, 'grad_norm': 0.5289216637611389, 'learning_rate': 0.00018919337358724262, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 5%|โ–Œ | 355/6464 [06:06<1:56:56, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5403, 'grad_norm': 0.5465351343154907, 'learning_rate': 0.00018916240904164733, 'epoch': 0.05}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 356/6464 [06:07<1:55:53, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1935, 'grad_norm': 0.6316732168197632, 'learning_rate': 0.00018913144449605201, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 357/6464 [06:08<1:56:06, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2259, 'grad_norm': 0.6376016139984131, 'learning_rate': 0.00018910047995045675, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 358/6464 [06:09<1:52:21, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2691, 'grad_norm': 0.624446451663971, 'learning_rate': 0.00018906951540486144, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 359/6464 [06:10<1:49:51, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2159, 'grad_norm': 0.5561191439628601, 'learning_rate': 0.00018903855085926615, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 360/6464 [06:11<1:47:18, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4422, 'grad_norm': 0.6153368949890137, 'learning_rate': 0.00018900758631367086, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 361/6464 [06:12<1:49:18, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6773, 'grad_norm': 0.6552212238311768, 'learning_rate': 0.00018897662176807554, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 362/6464 [06:13<1:46:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.239, 'grad_norm': 0.6304934024810791, 'learning_rate': 0.00018894565722248028, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 363/6464 [06:14<1:56:23, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6563, 'grad_norm': 0.6097458004951477, 'learning_rate': 0.00018891469267688497, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 364/6464 [06:16<1:54:58, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4076, 'grad_norm': 0.6049959659576416, 'learning_rate': 0.00018888372813128968, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 365/6464 [06:17<1:51:37, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5251, 'grad_norm': 0.7110066413879395, 'learning_rate': 0.0001888527635856944, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 366/6464 [06:18<1:48:02, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3134, 'grad_norm': 0.6453540325164795, 'learning_rate': 0.0001888217990400991, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 367/6464 [06:19<1:47:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2743, 'grad_norm': 0.6261059045791626, 'learning_rate': 0.0001887908344945038, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 368/6464 [06:20<1:52:31, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5009, 'grad_norm': 0.6580221056938171, 'learning_rate': 0.0001887598699489085, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 369/6464 [06:21<1:47:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3184, 'grad_norm': 0.6331556439399719, 'learning_rate': 0.0001887289054033132, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 370/6464 [06:22<1:45:51, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.559, 'grad_norm': 0.7175160050392151, 'learning_rate': 0.00018869794085771792, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 371/6464 [06:23<1:40:25, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0168, 'grad_norm': 0.6212148070335388, 'learning_rate': 0.00018866697631212263, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 372/6464 [06:24<1:38:20, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.25, 'grad_norm': 0.841271698474884, 'learning_rate': 0.00018863601176652734, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 373/6464 [06:25<1:39:26, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3019, 'grad_norm': 0.6385698914527893, 'learning_rate': 0.00018860504722093205, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 374/6464 [06:26<1:39:23, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.018, 'grad_norm': 0.5348028540611267, 'learning_rate': 0.00018857408267533674, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 375/6464 [06:27<1:39:42, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1389, 'grad_norm': 0.6082679033279419, 'learning_rate': 0.00018854311812974145, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 376/6464 [06:27<1:37:02, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3616, 'grad_norm': 0.7947453260421753, 'learning_rate': 0.00018851215358414616, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 377/6464 [06:28<1:38:09, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1764, 'grad_norm': 0.6452102065086365, 'learning_rate': 0.00018848118903855087, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 378/6464 [06:29<1:40:35, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1137, 'grad_norm': 0.6894034743309021, 'learning_rate': 0.00018845022449295558, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 379/6464 [06:30<1:39:46, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1732, 'grad_norm': 0.6984854936599731, 'learning_rate': 0.00018841925994736027, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 380/6464 [06:31<1:36:10, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.33, 'grad_norm': 0.7500442266464233, 'learning_rate': 0.00018838829540176498, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 381/6464 [06:32<1:43:04, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.572, 'grad_norm': 0.6613882184028625, 'learning_rate': 0.0001883573308561697, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 382/6464 [06:34<1:48:17, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6083, 'grad_norm': 0.6524673104286194, 'learning_rate': 0.0001883263663105744, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 383/6464 [06:35<1:50:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6324, 'grad_norm': 0.6439176201820374, 'learning_rate': 0.0001882954017649791, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 384/6464 [06:36<1:46:13, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3313, 'grad_norm': 0.6569476127624512, 'learning_rate': 0.0001882644372193838, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 385/6464 [06:37<1:45:31, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.43, 'grad_norm': 0.7129829525947571, 'learning_rate': 0.00018823347267378854, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 386/6464 [06:38<1:40:42, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0649, 'grad_norm': 0.6882259845733643, 'learning_rate': 0.00018820250812819322, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 387/6464 [06:39<1:43:33, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4157, 'grad_norm': 0.6444518566131592, 'learning_rate': 0.00018817154358259793, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 388/6464 [06:40<1:37:25, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1525, 'grad_norm': 0.6827400326728821, 'learning_rate': 0.00018814057903700264, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 389/6464 [06:41<1:39:48, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.099, 'grad_norm': 0.5267862677574158, 'learning_rate': 0.00018810961449140733, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 390/6464 [06:42<1:49:01, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.526, 'grad_norm': 0.6057222485542297, 'learning_rate': 0.00018807864994581207, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 391/6464 [06:43<1:46:25, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4316, 'grad_norm': 0.6945450901985168, 'learning_rate': 0.00018804768540021675, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 392/6464 [06:44<1:49:37, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2773, 'grad_norm': 0.5649325251579285, 'learning_rate': 0.0001880167208546215, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 393/6464 [06:45<1:44:38, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3504, 'grad_norm': 0.6842963695526123, 'learning_rate': 0.00018798575630902617, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 394/6464 [06:46<1:41:43, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2731, 'grad_norm': 0.6500676274299622, 'learning_rate': 0.00018795479176343088, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 395/6464 [06:47<1:44:20, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4797, 'grad_norm': 0.5939017534255981, 'learning_rate': 0.0001879238272178356, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 396/6464 [06:48<1:44:50, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.279, 'grad_norm': 0.656455934047699, 'learning_rate': 0.00018789286267224028, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 397/6464 [06:49<1:40:34, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1954, 'grad_norm': 0.7031834721565247, 'learning_rate': 0.00018786189812664502, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 398/6464 [06:50<1:38:33, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2485, 'grad_norm': 0.7740602493286133, 'learning_rate': 0.0001878309335810497, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 399/6464 [06:51<1:40:31, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3483, 'grad_norm': 0.7033870220184326, 'learning_rate': 0.0001877999690354544, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 400/6464 [06:52<1:41:47, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1792, 'grad_norm': 0.6336675882339478, 'learning_rate': 0.00018776900448985912, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 401/6464 [06:53<1:44:30, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3395, 'grad_norm': 0.628842294216156, 'learning_rate': 0.0001877380399442638, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 402/6464 [06:54<1:48:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4799, 'grad_norm': 0.601578414440155, 'learning_rate': 0.00018770707539866855, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–Œ | 403/6464 [06:55<1:47:16, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4218, 'grad_norm': 0.6932883262634277, 'learning_rate': 0.00018767611085307323, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 404/6464 [06:56<1:42:21, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3896, 'grad_norm': 0.7157435417175293, 'learning_rate': 0.00018764514630747794, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 405/6464 [06:57<1:39:53, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4589, 'grad_norm': 0.7246978878974915, 'learning_rate': 0.00018761418176188265, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 406/6464 [06:58<1:39:27, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.387, 'grad_norm': 0.7454100251197815, 'learning_rate': 0.00018758321721628737, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 407/6464 [06:59<1:36:06, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.311, 'grad_norm': 0.6879433989524841, 'learning_rate': 0.00018755225267069208, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 408/6464 [07:00<1:43:03, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4211, 'grad_norm': 0.63804030418396, 'learning_rate': 0.00018752128812509676, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 409/6464 [07:01<1:44:52, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2738, 'grad_norm': 0.5726004838943481, 'learning_rate': 0.00018749032357950147, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 410/6464 [07:02<1:46:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4069, 'grad_norm': 1.035254716873169, 'learning_rate': 0.00018745935903390618, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 411/6464 [07:03<1:48:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3743, 'grad_norm': 0.764550507068634, 'learning_rate': 0.0001874283944883109, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 412/6464 [07:04<1:45:17, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3923, 'grad_norm': 0.6781448721885681, 'learning_rate': 0.0001873974299427156, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 413/6464 [07:05<1:43:16, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.345, 'grad_norm': 0.6478217840194702, 'learning_rate': 0.00018736646539712032, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 414/6464 [07:07<1:47:39, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1789, 'grad_norm': 0.5554861426353455, 'learning_rate': 0.000187335500851525, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 415/6464 [07:08<1:55:18, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5613, 'grad_norm': 0.5726887583732605, 'learning_rate': 0.00018730453630592971, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 416/6464 [07:09<1:45:04, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0105, 'grad_norm': 0.6610287427902222, 'learning_rate': 0.00018727357176033443, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 417/6464 [07:10<1:56:51, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4175, 'grad_norm': 0.6036642789840698, 'learning_rate': 0.00018724260721473914, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 418/6464 [07:11<1:57:57, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3458, 'grad_norm': 0.6367062330245972, 'learning_rate': 0.00018721164266914385, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 419/6464 [07:12<1:50:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2275, 'grad_norm': 0.8096060156822205, 'learning_rate': 0.00018718067812354853, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 6%|โ–‹ | 420/6464 [07:13<1:49:14, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3385, 'grad_norm': 0.6296610236167908, 'learning_rate': 0.00018714971357795324, 'epoch': 0.06}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 421/6464 [07:14<1:48:23, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4084, 'grad_norm': 0.6889966726303101, 'learning_rate': 0.00018711874903235795, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 422/6464 [07:15<1:44:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3879, 'grad_norm': 0.7082970142364502, 'learning_rate': 0.00018708778448676267, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 423/6464 [07:16<1:46:05, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1787, 'grad_norm': 0.603065550327301, 'learning_rate': 0.00018705681994116738, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 424/6464 [07:17<1:41:46, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0212, 'grad_norm': 0.5849025845527649, 'learning_rate': 0.00018702585539557206, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 425/6464 [07:18<1:40:45, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1884, 'grad_norm': 0.6241864562034607, 'learning_rate': 0.0001869948908499768, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 426/6464 [07:19<1:45:06, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1031, 'grad_norm': 0.5835994482040405, 'learning_rate': 0.00018696392630438148, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 427/6464 [07:21<1:50:08, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2655, 'grad_norm': 0.6011258959770203, 'learning_rate': 0.0001869329617587862, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 428/6464 [07:22<1:54:11, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5593, 'grad_norm': 0.7691524624824524, 'learning_rate': 0.0001869019972131909, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 429/6464 [07:23<1:59:56, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2756, 'grad_norm': 0.5659970641136169, 'learning_rate': 0.0001868710326675956, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 430/6464 [07:24<1:58:28, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4142, 'grad_norm': 0.7100356817245483, 'learning_rate': 0.00018684006812200033, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 431/6464 [07:25<1:53:15, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2743, 'grad_norm': 0.6980211734771729, 'learning_rate': 0.00018680910357640501, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 432/6464 [07:27<1:55:46, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6196, 'grad_norm': 0.7051894068717957, 'learning_rate': 0.00018677813903080975, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 433/6464 [07:27<1:50:53, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2837, 'grad_norm': 0.7014017105102539, 'learning_rate': 0.00018674717448521444, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 434/6464 [07:29<1:50:39, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2556, 'grad_norm': 0.6412485241889954, 'learning_rate': 0.00018671620993961915, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 435/6464 [07:30<1:48:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3482, 'grad_norm': 0.6549200415611267, 'learning_rate': 0.00018668524539402386, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 436/6464 [07:31<1:50:01, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3698, 'grad_norm': 0.5979213118553162, 'learning_rate': 0.00018665428084842854, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 437/6464 [07:32<1:47:32, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3566, 'grad_norm': 0.6416441202163696, 'learning_rate': 0.00018662331630283328, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 438/6464 [07:33<1:44:27, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2287, 'grad_norm': 0.7449135184288025, 'learning_rate': 0.00018659235175723797, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 439/6464 [07:34<1:41:42, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.269, 'grad_norm': 0.730431318283081, 'learning_rate': 0.00018656138721164268, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 440/6464 [07:35<1:42:40, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2983, 'grad_norm': 0.6513187289237976, 'learning_rate': 0.0001865304226660474, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 441/6464 [07:36<1:41:20, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5622, 'grad_norm': 0.763578474521637, 'learning_rate': 0.00018649945812045207, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 442/6464 [07:37<1:40:57, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3085, 'grad_norm': 0.6614786982536316, 'learning_rate': 0.0001864684935748568, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 443/6464 [07:38<1:43:14, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2595, 'grad_norm': 0.6914593577384949, 'learning_rate': 0.0001864375290292615, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 444/6464 [07:39<1:46:22, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3541, 'grad_norm': 0.6383671760559082, 'learning_rate': 0.0001864065644836662, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 445/6464 [07:40<1:42:01, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2377, 'grad_norm': 0.6646133661270142, 'learning_rate': 0.00018637559993807092, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 446/6464 [07:41<1:43:38, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2349, 'grad_norm': 0.5771443843841553, 'learning_rate': 0.00018634463539247563, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 447/6464 [07:42<1:49:39, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3023, 'grad_norm': 0.5894744992256165, 'learning_rate': 0.00018631367084688034, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 448/6464 [07:43<1:50:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.558, 'grad_norm': 0.8453249335289001, 'learning_rate': 0.00018628270630128503, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 449/6464 [07:44<1:51:27, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4575, 'grad_norm': 0.6072988510131836, 'learning_rate': 0.00018625174175568974, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 450/6464 [07:46<1:55:01, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1353, 'grad_norm': 0.5226827263832092, 'learning_rate': 0.00018622077721009445, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 451/6464 [07:47<1:51:44, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1495, 'grad_norm': 0.7289111018180847, 'learning_rate': 0.00018618981266449916, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 452/6464 [07:48<1:50:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3292, 'grad_norm': 0.6560667157173157, 'learning_rate': 0.00018615884811890387, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 453/6464 [07:49<1:50:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3271, 'grad_norm': 0.5791686773300171, 'learning_rate': 0.00018612788357330858, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 454/6464 [07:50<1:52:11, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2908, 'grad_norm': 0.6070128083229065, 'learning_rate': 0.00018609691902771327, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 455/6464 [07:51<1:56:36, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4169, 'grad_norm': 0.6122997999191284, 'learning_rate': 0.00018606595448211798, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 456/6464 [07:52<1:49:36, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1147, 'grad_norm': 0.682248592376709, 'learning_rate': 0.0001860349899365227, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 457/6464 [07:53<1:52:21, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4233, 'grad_norm': 0.6817961931228638, 'learning_rate': 0.0001860040253909274, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 458/6464 [07:55<1:54:51, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4097, 'grad_norm': 0.5957437753677368, 'learning_rate': 0.0001859730608453321, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 459/6464 [07:56<1:49:51, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0467, 'grad_norm': 0.5895008444786072, 'learning_rate': 0.0001859420962997368, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 460/6464 [07:57<1:48:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4851, 'grad_norm': 0.6646673679351807, 'learning_rate': 0.0001859111317541415, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 461/6464 [07:58<1:49:50, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3705, 'grad_norm': 0.6682156324386597, 'learning_rate': 0.00018588016720854622, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 462/6464 [07:59<1:51:44, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3357, 'grad_norm': 0.6084144115447998, 'learning_rate': 0.00018584920266295093, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 463/6464 [08:00<1:47:53, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3729, 'grad_norm': 0.6850485801696777, 'learning_rate': 0.00018581823811735564, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 464/6464 [08:01<1:48:18, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2077, 'grad_norm': 0.5915889739990234, 'learning_rate': 0.00018578727357176033, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 465/6464 [08:02<1:41:23, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4487, 'grad_norm': 0.7743158340454102, 'learning_rate': 0.00018575630902616506, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 466/6464 [08:03<1:38:14, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3511, 'grad_norm': 0.6811110973358154, 'learning_rate': 0.00018572534448056975, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 467/6464 [08:04<1:41:08, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2693, 'grad_norm': 0.6041170358657837, 'learning_rate': 0.00018569437993497446, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 468/6464 [08:05<1:49:01, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3543, 'grad_norm': 0.6149229407310486, 'learning_rate': 0.00018566341538937917, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 469/6464 [08:06<1:51:11, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1459, 'grad_norm': 0.5810067057609558, 'learning_rate': 0.00018563245084378386, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 470/6464 [08:07<1:52:47, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3639, 'grad_norm': 0.5970298051834106, 'learning_rate': 0.0001856014862981886, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 471/6464 [08:09<1:52:43, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2195, 'grad_norm': 0.6231582164764404, 'learning_rate': 0.00018557052175259328, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 472/6464 [08:09<1:46:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.268, 'grad_norm': 0.6678935289382935, 'learning_rate': 0.00018553955720699802, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 473/6464 [08:10<1:43:38, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2773, 'grad_norm': 0.7098174691200256, 'learning_rate': 0.0001855085926614027, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 474/6464 [08:12<1:44:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2009, 'grad_norm': 0.6712576746940613, 'learning_rate': 0.0001854776281158074, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 475/6464 [08:13<2:00:02, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2446, 'grad_norm': 0.5416594743728638, 'learning_rate': 0.00018544666357021212, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 476/6464 [08:14<1:56:15, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2903, 'grad_norm': 0.6549713611602783, 'learning_rate': 0.0001854156990246168, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 477/6464 [08:16<2:04:47, 1.25s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4465, 'grad_norm': 0.5791281461715698, 'learning_rate': 0.00018538473447902155, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 478/6464 [08:17<1:56:31, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2532, 'grad_norm': 0.6354987025260925, 'learning_rate': 0.00018535376993342623, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 479/6464 [08:18<1:50:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1428, 'grad_norm': 0.6057274341583252, 'learning_rate': 0.00018532280538783094, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 480/6464 [08:19<1:47:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2284, 'grad_norm': 0.6454637050628662, 'learning_rate': 0.00018529184084223565, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 481/6464 [08:20<1:54:35, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3005, 'grad_norm': 0.6857359409332275, 'learning_rate': 0.00018526087629664034, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 482/6464 [08:21<1:55:10, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3781, 'grad_norm': 0.6520510911941528, 'learning_rate': 0.00018522991175104508, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 483/6464 [08:22<1:52:19, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3097, 'grad_norm': 0.6591082215309143, 'learning_rate': 0.00018519894720544976, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 7%|โ–‹ | 484/6464 [08:24<2:01:48, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5334, 'grad_norm': 0.6129874587059021, 'learning_rate': 0.00018516798265985447, 'epoch': 0.07}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 485/6464 [08:25<1:56:10, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4565, 'grad_norm': 0.7120752334594727, 'learning_rate': 0.00018513701811425918, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 486/6464 [08:26<1:53:42, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1909, 'grad_norm': 0.5942409634590149, 'learning_rate': 0.0001851060535686639, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 487/6464 [08:27<1:52:42, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2576, 'grad_norm': 0.6043729186058044, 'learning_rate': 0.0001850750890230686, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 488/6464 [08:28<1:47:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2891, 'grad_norm': 0.6909900903701782, 'learning_rate': 0.0001850441244774733, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 489/6464 [08:29<1:53:31, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.372, 'grad_norm': 0.6129227876663208, 'learning_rate': 0.000185013159931878, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 490/6464 [08:30<1:50:47, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3773, 'grad_norm': 0.6480892896652222, 'learning_rate': 0.0001849821953862827, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 491/6464 [08:31<1:52:41, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5362, 'grad_norm': 0.6442572474479675, 'learning_rate': 0.00018495123084068742, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 492/6464 [08:32<1:47:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0489, 'grad_norm': 0.7325566411018372, 'learning_rate': 0.00018492026629509214, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 493/6464 [08:33<1:49:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1847, 'grad_norm': 0.6041309833526611, 'learning_rate': 0.00018488930174949685, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 494/6464 [08:34<1:43:05, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1816, 'grad_norm': 0.7153550982475281, 'learning_rate': 0.00018485833720390153, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 495/6464 [08:35<1:44:15, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2046, 'grad_norm': 0.6799542307853699, 'learning_rate': 0.00018482737265830624, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 496/6464 [08:37<1:48:17, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5096, 'grad_norm': 0.6426007151603699, 'learning_rate': 0.00018479640811271095, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 497/6464 [08:38<1:45:11, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2654, 'grad_norm': 0.6168568134307861, 'learning_rate': 0.00018476544356711567, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 498/6464 [08:38<1:37:21, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2703, 'grad_norm': 0.768956184387207, 'learning_rate': 0.00018473447902152038, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 499/6464 [08:40<1:50:04, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4512, 'grad_norm': 0.5688309669494629, 'learning_rate': 0.00018470351447592506, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 500/6464 [08:41<1:45:57, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2463, 'grad_norm': 0.8061095476150513, 'learning_rate': 0.00018467254993032977, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/other.py:619: UserWarning: Unable to fetch remote file due to the following error (ReadTimeoutError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)\"), '(Request ID: 5f69a74d-b268-4eab-aba9-bcd8c989666f)') - silently ignoring the lookup for the file config.json in Magpie-Align/MagpieLM-4B-Chat-v0.1.\n", " warnings.warn(\n", "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/save_and_load.py:218: UserWarning: Could not find a config file in Magpie-Align/MagpieLM-4B-Chat-v0.1 - will assume that the vocabulary was not modified.\n", " warnings.warn(\n", " 8%|โ–Š | 501/6464 [08:52<6:53:47, 4.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3804, 'grad_norm': 0.7122378349304199, 'learning_rate': 0.00018464158538473448, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 502/6464 [08:53<5:31:39, 3.34s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6653, 'grad_norm': 0.8943649530410767, 'learning_rate': 0.0001846106208391392, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 503/6464 [08:54<4:17:55, 2.60s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1533, 'grad_norm': 0.6341132521629333, 'learning_rate': 0.0001845796562935439, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 504/6464 [08:55<3:28:52, 2.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2689, 'grad_norm': 0.6471198797225952, 'learning_rate': 0.0001845486917479486, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 505/6464 [08:56<2:56:40, 1.78s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.221, 'grad_norm': 0.6563035845756531, 'learning_rate': 0.00018451772720235333, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 506/6464 [08:57<2:37:12, 1.58s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2885, 'grad_norm': 0.6305603384971619, 'learning_rate': 0.000184486762656758, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 507/6464 [08:59<2:23:48, 1.45s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4984, 'grad_norm': 0.6592463850975037, 'learning_rate': 0.00018445579811116272, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 508/6464 [08:59<2:05:44, 1.27s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2542, 'grad_norm': 0.7742272615432739, 'learning_rate': 0.00018442483356556744, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 509/6464 [09:00<1:59:18, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2336, 'grad_norm': 0.6137072443962097, 'learning_rate': 0.00018439386901997212, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 510/6464 [09:02<1:59:06, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3572, 'grad_norm': 0.545074999332428, 'learning_rate': 0.00018436290447437686, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 511/6464 [09:03<1:55:52, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4901, 'grad_norm': 0.6097828149795532, 'learning_rate': 0.00018433193992878154, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 512/6464 [09:04<1:54:55, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5615, 'grad_norm': 0.677962064743042, 'learning_rate': 0.00018430097538318628, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 513/6464 [09:05<1:46:53, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1513, 'grad_norm': 0.6452435851097107, 'learning_rate': 0.00018427001083759097, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 514/6464 [09:06<1:50:19, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2511, 'grad_norm': 0.5782728791236877, 'learning_rate': 0.00018423904629199568, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 515/6464 [09:07<1:53:47, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1465, 'grad_norm': 0.5671456456184387, 'learning_rate': 0.0001842080817464004, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 516/6464 [09:08<1:56:28, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4382, 'grad_norm': 0.6238467693328857, 'learning_rate': 0.00018417711720080507, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 517/6464 [09:09<1:47:54, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2576, 'grad_norm': 0.6405999660491943, 'learning_rate': 0.0001841461526552098, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 518/6464 [09:11<1:56:50, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4367, 'grad_norm': 0.5168840885162354, 'learning_rate': 0.0001841151881096145, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 519/6464 [09:12<1:54:23, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5367, 'grad_norm': 0.7225912809371948, 'learning_rate': 0.0001840842235640192, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 520/6464 [09:13<1:51:08, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.506, 'grad_norm': 0.6676433086395264, 'learning_rate': 0.00018405325901842392, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 521/6464 [09:14<1:44:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2827, 'grad_norm': 0.7840597629547119, 'learning_rate': 0.0001840222944728286, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 522/6464 [09:15<1:43:16, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0998, 'grad_norm': 0.5992004871368408, 'learning_rate': 0.00018399132992723334, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 523/6464 [09:16<1:37:15, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.192, 'grad_norm': 0.6944208741188049, 'learning_rate': 0.00018396036538163803, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 524/6464 [09:17<1:38:42, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1525, 'grad_norm': 0.5833666324615479, 'learning_rate': 0.00018392940083604274, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 525/6464 [09:18<1:44:15, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0234, 'grad_norm': 0.5915395021438599, 'learning_rate': 0.00018389843629044745, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 526/6464 [09:19<1:43:25, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3311, 'grad_norm': 0.7167230844497681, 'learning_rate': 0.00018386747174485216, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 527/6464 [09:20<1:39:59, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3353, 'grad_norm': 0.7022106647491455, 'learning_rate': 0.00018383650719925687, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 528/6464 [09:21<1:45:41, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3898, 'grad_norm': 0.676047146320343, 'learning_rate': 0.00018380554265366155, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 529/6464 [09:22<1:47:31, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4164, 'grad_norm': 0.6653611063957214, 'learning_rate': 0.00018377457810806627, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 530/6464 [09:23<1:49:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3868, 'grad_norm': 0.6388504505157471, 'learning_rate': 0.00018374361356247098, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 531/6464 [09:24<1:48:52, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1313, 'grad_norm': 0.7092154622077942, 'learning_rate': 0.0001837126490168757, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 532/6464 [09:26<1:52:41, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4658, 'grad_norm': 0.5820891857147217, 'learning_rate': 0.0001836816844712804, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 533/6464 [09:27<1:49:19, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2921, 'grad_norm': 0.6441729068756104, 'learning_rate': 0.0001836507199256851, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 534/6464 [09:28<1:46:30, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1961, 'grad_norm': 0.6727623343467712, 'learning_rate': 0.0001836197553800898, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 535/6464 [09:29<1:50:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3742, 'grad_norm': 0.6444843411445618, 'learning_rate': 0.0001835887908344945, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 536/6464 [09:30<1:49:42, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3499, 'grad_norm': 0.6701230406761169, 'learning_rate': 0.00018355782628889922, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 537/6464 [09:31<1:51:51, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3968, 'grad_norm': 0.5841596722602844, 'learning_rate': 0.00018352686174330393, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 538/6464 [09:32<1:51:58, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2616, 'grad_norm': 0.6487729549407959, 'learning_rate': 0.00018349589719770864, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 539/6464 [09:33<1:45:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.266, 'grad_norm': 0.6571005582809448, 'learning_rate': 0.00018346493265211333, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 540/6464 [09:34<1:41:47, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1557, 'grad_norm': 0.5923891067504883, 'learning_rate': 0.00018343396810651804, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 541/6464 [09:35<1:40:39, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4337, 'grad_norm': 0.636939287185669, 'learning_rate': 0.00018340300356092275, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 542/6464 [09:36<1:41:18, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4185, 'grad_norm': 0.732945442199707, 'learning_rate': 0.00018337203901532746, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 543/6464 [09:37<1:42:42, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3316, 'grad_norm': 0.5833582878112793, 'learning_rate': 0.00018334107446973217, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 544/6464 [09:38<1:40:51, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3064, 'grad_norm': 0.6515349745750427, 'learning_rate': 0.00018331010992413686, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 545/6464 [09:39<1:48:33, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1733, 'grad_norm': 0.5454240441322327, 'learning_rate': 0.0001832791453785416, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 546/6464 [09:41<1:51:14, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.365, 'grad_norm': 0.577640950679779, 'learning_rate': 0.00018324818083294628, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 547/6464 [09:42<1:54:33, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2876, 'grad_norm': 0.557013750076294, 'learning_rate': 0.000183217216287351, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 548/6464 [09:43<1:50:54, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3503, 'grad_norm': 0.6413142681121826, 'learning_rate': 0.0001831862517417557, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 8%|โ–Š | 549/6464 [09:44<1:47:42, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2882, 'grad_norm': 0.7350944876670837, 'learning_rate': 0.00018315528719616038, 'epoch': 0.08}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 550/6464 [09:45<1:45:47, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2645, 'grad_norm': 0.6448454260826111, 'learning_rate': 0.00018312432265056512, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 551/6464 [09:46<1:40:38, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3434, 'grad_norm': 0.7725984454154968, 'learning_rate': 0.0001830933581049698, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 552/6464 [09:47<1:38:11, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1434, 'grad_norm': 0.6138293743133545, 'learning_rate': 0.00018306239355937455, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 553/6464 [09:48<1:36:43, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2657, 'grad_norm': 0.6848613023757935, 'learning_rate': 0.00018303142901377923, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 554/6464 [09:49<1:40:59, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3066, 'grad_norm': 0.6070721745491028, 'learning_rate': 0.00018300046446818394, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 555/6464 [09:50<1:41:18, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0463, 'grad_norm': 0.6308752298355103, 'learning_rate': 0.00018296949992258865, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 556/6464 [09:51<1:36:11, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9629, 'grad_norm': 0.6968003511428833, 'learning_rate': 0.00018293853537699334, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 557/6464 [09:52<1:46:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1508, 'grad_norm': 0.5357530117034912, 'learning_rate': 0.00018290757083139808, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 558/6464 [09:53<1:52:52, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.7026, 'grad_norm': 0.6478086113929749, 'learning_rate': 0.00018287660628580276, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 559/6464 [09:55<1:56:15, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5122, 'grad_norm': 0.625495970249176, 'learning_rate': 0.00018284564174020747, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 560/6464 [09:56<1:56:26, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2409, 'grad_norm': 0.6736916899681091, 'learning_rate': 0.00018281467719461218, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 561/6464 [09:57<1:47:39, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2199, 'grad_norm': 0.7344272136688232, 'learning_rate': 0.00018278371264901687, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 562/6464 [09:58<1:54:49, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3733, 'grad_norm': 0.65505051612854, 'learning_rate': 0.0001827527481034216, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 563/6464 [09:59<1:49:47, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.302, 'grad_norm': 0.6552541255950928, 'learning_rate': 0.0001827217835578263, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 564/6464 [10:01<1:59:20, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2479, 'grad_norm': 0.6678647398948669, 'learning_rate': 0.000182690819012231, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–Š | 565/6464 [10:02<1:54:31, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.237, 'grad_norm': 0.6405931115150452, 'learning_rate': 0.0001826598544666357, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 566/6464 [10:03<1:52:09, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3181, 'grad_norm': 0.5934795141220093, 'learning_rate': 0.00018262888992104042, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 567/6464 [10:04<1:51:20, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5655, 'grad_norm': 0.6494017243385315, 'learning_rate': 0.00018259792537544514, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 568/6464 [10:05<1:55:33, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.269, 'grad_norm': 0.64083331823349, 'learning_rate': 0.00018256696082984982, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 569/6464 [10:06<1:48:22, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1856, 'grad_norm': 0.7396567463874817, 'learning_rate': 0.00018253599628425453, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 570/6464 [10:07<1:48:51, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4371, 'grad_norm': 0.6018744707107544, 'learning_rate': 0.00018250503173865924, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 571/6464 [10:08<1:50:08, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4701, 'grad_norm': 0.6131743788719177, 'learning_rate': 0.00018247406719306395, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 572/6464 [10:09<1:46:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3045, 'grad_norm': 0.645088255405426, 'learning_rate': 0.00018244310264746866, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 573/6464 [10:10<1:44:29, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2408, 'grad_norm': 0.6827605366706848, 'learning_rate': 0.00018241213810187338, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 574/6464 [10:12<1:51:20, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0908, 'grad_norm': 0.4829760193824768, 'learning_rate': 0.00018238117355627806, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 575/6464 [10:13<1:49:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2289, 'grad_norm': 0.5755229592323303, 'learning_rate': 0.00018235020901068277, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 576/6464 [10:14<1:49:01, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3313, 'grad_norm': 0.7355183362960815, 'learning_rate': 0.00018231924446508748, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 577/6464 [10:15<1:43:57, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1154, 'grad_norm': 0.7006844282150269, 'learning_rate': 0.0001822882799194922, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 578/6464 [10:16<1:41:42, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3036, 'grad_norm': 0.678719699382782, 'learning_rate': 0.0001822573153738969, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 579/6464 [10:17<1:48:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2881, 'grad_norm': 0.6250877976417542, 'learning_rate': 0.0001822263508283016, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 580/6464 [10:18<1:45:25, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3953, 'grad_norm': 0.7238830924034119, 'learning_rate': 0.00018219538628270633, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 581/6464 [10:19<1:39:51, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3097, 'grad_norm': 0.7525674104690552, 'learning_rate': 0.000182164421737111, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 582/6464 [10:20<1:43:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5107, 'grad_norm': 0.617756724357605, 'learning_rate': 0.00018213345719151572, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 583/6464 [10:21<1:39:35, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2086, 'grad_norm': 0.6568235754966736, 'learning_rate': 0.00018210249264592044, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 584/6464 [10:22<1:36:44, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1162, 'grad_norm': 0.6846972703933716, 'learning_rate': 0.00018207152810032512, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 585/6464 [10:23<1:36:19, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1444, 'grad_norm': 0.6624796390533447, 'learning_rate': 0.00018204056355472986, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 586/6464 [10:24<1:37:54, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3437, 'grad_norm': 0.6996397972106934, 'learning_rate': 0.00018200959900913454, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 587/6464 [10:25<1:37:18, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.268, 'grad_norm': 0.6912115216255188, 'learning_rate': 0.00018197863446353925, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 588/6464 [10:26<1:39:05, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2662, 'grad_norm': 0.6069871187210083, 'learning_rate': 0.00018194766991794397, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 589/6464 [10:27<1:35:35, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1019, 'grad_norm': 0.6900389790534973, 'learning_rate': 0.00018191670537234865, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 590/6464 [10:28<1:38:49, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4152, 'grad_norm': 0.6076063513755798, 'learning_rate': 0.0001818857408267534, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 591/6464 [10:29<1:38:39, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1965, 'grad_norm': 0.6054360866546631, 'learning_rate': 0.00018185477628115807, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 592/6464 [10:30<1:36:03, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3747, 'grad_norm': 0.7312862277030945, 'learning_rate': 0.0001818238117355628, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 593/6464 [10:31<1:41:12, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4304, 'grad_norm': 0.6371950507164001, 'learning_rate': 0.0001817928471899675, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 594/6464 [10:32<1:46:57, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1707, 'grad_norm': 0.5732420682907104, 'learning_rate': 0.0001817618826443722, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 595/6464 [10:33<1:51:21, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2355, 'grad_norm': 0.5501779317855835, 'learning_rate': 0.00018173091809877692, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 596/6464 [10:35<1:54:11, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3751, 'grad_norm': 0.5875047445297241, 'learning_rate': 0.0001816999535531816, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 597/6464 [10:36<1:49:51, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3704, 'grad_norm': 0.6248720288276672, 'learning_rate': 0.00018166898900758634, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 598/6464 [10:37<1:52:34, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3158, 'grad_norm': 0.5779315233230591, 'learning_rate': 0.00018163802446199102, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 599/6464 [10:38<1:49:28, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4961, 'grad_norm': 0.7738173604011536, 'learning_rate': 0.00018160705991639574, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 600/6464 [10:39<1:40:58, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1162, 'grad_norm': 0.7450604438781738, 'learning_rate': 0.00018157609537080045, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 601/6464 [10:40<1:41:25, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2221, 'grad_norm': 0.6200721263885498, 'learning_rate': 0.00018154513082520516, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 602/6464 [10:41<1:51:27, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5364, 'grad_norm': 0.6080955862998962, 'learning_rate': 0.00018151416627960987, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 603/6464 [10:42<1:50:23, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3062, 'grad_norm': 0.5760658383369446, 'learning_rate': 0.00018148320173401455, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 604/6464 [10:43<1:47:28, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3597, 'grad_norm': 0.6681116223335266, 'learning_rate': 0.00018145223718841927, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 605/6464 [10:44<1:41:20, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.152, 'grad_norm': 0.6718209385871887, 'learning_rate': 0.00018142127264282398, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 606/6464 [10:45<1:44:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1836, 'grad_norm': 0.594205915927887, 'learning_rate': 0.0001813903080972287, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 607/6464 [10:47<1:49:57, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4672, 'grad_norm': 0.6093713641166687, 'learning_rate': 0.0001813593435516334, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 608/6464 [10:48<1:49:38, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.055, 'grad_norm': 0.6052086353302002, 'learning_rate': 0.00018132837900603808, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 609/6464 [10:49<1:45:22, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.339, 'grad_norm': 0.7161657810211182, 'learning_rate': 0.0001812974144604428, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 610/6464 [10:50<1:47:38, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3936, 'grad_norm': 0.644142210483551, 'learning_rate': 0.0001812664499148475, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 611/6464 [10:51<1:47:12, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2638, 'grad_norm': 0.8340812921524048, 'learning_rate': 0.00018123548536925222, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 612/6464 [10:52<1:43:33, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4441, 'grad_norm': 0.8448610305786133, 'learning_rate': 0.00018120452082365693, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 613/6464 [10:53<1:44:30, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3069, 'grad_norm': 0.6599171161651611, 'learning_rate': 0.00018117355627806164, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 9%|โ–‰ | 614/6464 [10:54<1:46:25, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4256, 'grad_norm': 0.6400619745254517, 'learning_rate': 0.00018114259173246632, 'epoch': 0.09}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 615/6464 [10:55<1:41:35, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1074, 'grad_norm': 0.6935392618179321, 'learning_rate': 0.00018111162718687104, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 616/6464 [10:56<1:40:06, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2085, 'grad_norm': 0.7057802677154541, 'learning_rate': 0.00018108066264127575, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 617/6464 [10:57<1:43:08, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2682, 'grad_norm': 0.6204772591590881, 'learning_rate': 0.00018104969809568046, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 618/6464 [10:58<1:36:11, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.116, 'grad_norm': 0.7256143093109131, 'learning_rate': 0.00018101873355008517, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 619/6464 [11:00<1:54:17, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6029, 'grad_norm': 0.5668016076087952, 'learning_rate': 0.00018098776900448985, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 620/6464 [11:01<1:53:59, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5591, 'grad_norm': 0.7544592618942261, 'learning_rate': 0.0001809568044588946, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 621/6464 [11:02<1:57:29, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0924, 'grad_norm': 0.5241140127182007, 'learning_rate': 0.00018092583991329928, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 622/6464 [11:03<1:52:12, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4612, 'grad_norm': 0.7055848836898804, 'learning_rate': 0.000180894875367704, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 623/6464 [11:04<1:55:43, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4677, 'grad_norm': 0.6866674423217773, 'learning_rate': 0.0001808639108221087, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 624/6464 [11:06<1:59:08, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5358, 'grad_norm': 0.6218596696853638, 'learning_rate': 0.00018083294627651338, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 625/6464 [11:07<1:59:33, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6046, 'grad_norm': 0.8246408700942993, 'learning_rate': 0.00018080198173091812, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 626/6464 [11:08<1:54:28, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3975, 'grad_norm': 0.6479426622390747, 'learning_rate': 0.0001807710171853228, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 627/6464 [11:09<1:55:10, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3941, 'grad_norm': 0.6267897486686707, 'learning_rate': 0.00018074005263972752, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 628/6464 [11:10<1:46:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1154, 'grad_norm': 0.6757596731185913, 'learning_rate': 0.00018070908809413223, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 629/6464 [11:11<1:42:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0604, 'grad_norm': 0.5732041001319885, 'learning_rate': 0.00018067812354853691, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 630/6464 [11:12<1:47:53, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.794, 'grad_norm': 0.6873054504394531, 'learning_rate': 0.00018064715900294165, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 631/6464 [11:13<1:43:19, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2606, 'grad_norm': 0.705112874507904, 'learning_rate': 0.00018061619445734634, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 632/6464 [11:15<1:51:48, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3349, 'grad_norm': 0.4935089945793152, 'learning_rate': 0.00018058522991175108, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 633/6464 [11:16<1:48:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2712, 'grad_norm': 0.6734300255775452, 'learning_rate': 0.00018055426536615576, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 634/6464 [11:17<1:54:39, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2766, 'grad_norm': 0.5963389873504639, 'learning_rate': 0.00018052330082056047, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 635/6464 [11:18<1:49:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0677, 'grad_norm': 0.5900353789329529, 'learning_rate': 0.00018049233627496518, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 636/6464 [11:19<1:46:19, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.985, 'grad_norm': 0.5666995048522949, 'learning_rate': 0.00018046137172936987, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 637/6464 [11:20<1:46:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3582, 'grad_norm': 0.6485527753829956, 'learning_rate': 0.0001804304071837746, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 638/6464 [11:21<1:46:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1758, 'grad_norm': 0.6364041566848755, 'learning_rate': 0.0001803994426381793, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 639/6464 [11:22<1:44:57, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2263, 'grad_norm': 0.6395701169967651, 'learning_rate': 0.000180368478092584, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 640/6464 [11:23<1:46:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3903, 'grad_norm': 0.6271600127220154, 'learning_rate': 0.0001803375135469887, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 641/6464 [11:24<1:43:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.462, 'grad_norm': 0.7400071620941162, 'learning_rate': 0.00018030654900139342, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 642/6464 [11:25<1:42:52, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.138, 'grad_norm': 0.7230068445205688, 'learning_rate': 0.00018027558445579813, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 643/6464 [11:26<1:39:25, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1129, 'grad_norm': 0.7320564389228821, 'learning_rate': 0.00018024461991020282, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 644/6464 [11:27<1:36:16, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0709, 'grad_norm': 0.6625928282737732, 'learning_rate': 0.00018021365536460753, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 645/6464 [11:29<1:48:02, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4651, 'grad_norm': 0.657093346118927, 'learning_rate': 0.00018018269081901224, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–‰ | 646/6464 [11:30<1:47:40, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4169, 'grad_norm': 0.7055764198303223, 'learning_rate': 0.00018015172627341695, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 647/6464 [11:31<1:50:20, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1729, 'grad_norm': 0.6096594929695129, 'learning_rate': 0.00018012076172782166, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 648/6464 [11:32<1:51:26, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2256, 'grad_norm': 0.6067058444023132, 'learning_rate': 0.00018008979718222635, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 649/6464 [11:34<1:59:02, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3997, 'grad_norm': 0.5712780952453613, 'learning_rate': 0.00018005883263663106, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 650/6464 [11:35<1:57:39, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4081, 'grad_norm': 0.6572537422180176, 'learning_rate': 0.00018002786809103577, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 651/6464 [11:36<1:57:08, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2678, 'grad_norm': 0.6658502221107483, 'learning_rate': 0.00017999690354544048, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 652/6464 [11:37<1:56:57, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1548, 'grad_norm': 0.6620053648948669, 'learning_rate': 0.0001799659389998452, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 653/6464 [11:38<1:54:17, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4282, 'grad_norm': 0.7522715330123901, 'learning_rate': 0.0001799349744542499, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 654/6464 [11:39<1:46:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1493, 'grad_norm': 0.6800196766853333, 'learning_rate': 0.0001799040099086546, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 655/6464 [11:40<1:37:49, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0379, 'grad_norm': 0.6909316778182983, 'learning_rate': 0.0001798730453630593, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 656/6464 [11:41<1:36:24, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4248, 'grad_norm': 0.7930105924606323, 'learning_rate': 0.000179842080817464, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 657/6464 [11:42<1:40:30, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1461, 'grad_norm': 0.6149068474769592, 'learning_rate': 0.00017981111627186872, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 658/6464 [11:43<1:41:26, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4309, 'grad_norm': 0.6952453255653381, 'learning_rate': 0.00017978015172627343, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 659/6464 [11:44<1:43:23, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4803, 'grad_norm': 0.6510500311851501, 'learning_rate': 0.00017974918718067812, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 660/6464 [11:46<1:51:26, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2806, 'grad_norm': 0.5861773490905762, 'learning_rate': 0.00017971822263508286, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 661/6464 [11:47<1:45:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.34, 'grad_norm': 0.6934307813644409, 'learning_rate': 0.00017968725808948754, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 662/6464 [11:48<1:42:17, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3527, 'grad_norm': 0.7563983798027039, 'learning_rate': 0.00017965629354389225, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 663/6464 [11:49<1:40:25, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9672, 'grad_norm': 0.5997810363769531, 'learning_rate': 0.00017962532899829696, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 664/6464 [11:50<1:52:56, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4532, 'grad_norm': 0.632053017616272, 'learning_rate': 0.00017959436445270165, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 665/6464 [11:51<1:51:31, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4751, 'grad_norm': 0.6341217160224915, 'learning_rate': 0.0001795633999071064, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 666/6464 [11:52<1:46:30, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9414, 'grad_norm': 0.5864584445953369, 'learning_rate': 0.00017953243536151107, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 667/6464 [11:53<1:51:17, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2868, 'grad_norm': 0.5522401332855225, 'learning_rate': 0.00017950147081591578, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 668/6464 [11:54<1:43:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0027, 'grad_norm': 0.6258779764175415, 'learning_rate': 0.0001794705062703205, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 669/6464 [11:55<1:47:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3986, 'grad_norm': 0.6515432000160217, 'learning_rate': 0.00017943954172472518, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 670/6464 [11:56<1:41:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1969, 'grad_norm': 0.7054334282875061, 'learning_rate': 0.00017940857717912992, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 671/6464 [11:58<1:46:51, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2588, 'grad_norm': 0.5856925845146179, 'learning_rate': 0.0001793776126335346, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 672/6464 [11:59<1:50:19, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4513, 'grad_norm': 0.643762469291687, 'learning_rate': 0.00017934664808793934, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 673/6464 [12:00<1:55:00, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4729, 'grad_norm': 0.6844478845596313, 'learning_rate': 0.00017931568354234402, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 674/6464 [12:01<1:51:32, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2181, 'grad_norm': 0.5462308526039124, 'learning_rate': 0.00017928471899674874, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 675/6464 [12:02<1:52:58, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4027, 'grad_norm': 0.6980212926864624, 'learning_rate': 0.00017925375445115345, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 676/6464 [12:04<1:57:04, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.291, 'grad_norm': 0.6174968481063843, 'learning_rate': 0.00017922278990555813, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 677/6464 [12:05<1:57:13, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1563, 'grad_norm': 0.5394848585128784, 'learning_rate': 0.00017919182535996287, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 10%|โ–ˆ | 678/6464 [12:06<1:53:19, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3564, 'grad_norm': 0.7047010064125061, 'learning_rate': 0.00017916086081436755, 'epoch': 0.1}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 679/6464 [12:07<1:54:30, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2887, 'grad_norm': 0.692888617515564, 'learning_rate': 0.00017912989626877226, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 680/6464 [12:08<1:46:37, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2901, 'grad_norm': 0.7061126828193665, 'learning_rate': 0.00017909893172317698, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 681/6464 [12:09<1:48:28, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2603, 'grad_norm': 0.6129163503646851, 'learning_rate': 0.0001790679671775817, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 682/6464 [12:10<1:42:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0541, 'grad_norm': 0.635997474193573, 'learning_rate': 0.0001790370026319864, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 683/6464 [12:11<1:47:03, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2799, 'grad_norm': 0.6487647891044617, 'learning_rate': 0.00017900603808639108, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 684/6464 [12:13<1:46:41, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2787, 'grad_norm': 0.6295060515403748, 'learning_rate': 0.0001789750735407958, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 685/6464 [12:14<1:46:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2561, 'grad_norm': 0.7028217911720276, 'learning_rate': 0.0001789441089952005, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 686/6464 [12:15<1:46:24, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1272, 'grad_norm': 0.7085093855857849, 'learning_rate': 0.00017891314444960522, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 687/6464 [12:16<1:42:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2221, 'grad_norm': 0.6843736171722412, 'learning_rate': 0.00017888217990400993, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 688/6464 [12:17<1:43:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2276, 'grad_norm': 0.6058115363121033, 'learning_rate': 0.0001788512153584146, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 689/6464 [12:18<1:40:12, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2167, 'grad_norm': 0.6865342855453491, 'learning_rate': 0.00017882025081281932, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 690/6464 [12:19<1:43:56, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3021, 'grad_norm': 0.6341883540153503, 'learning_rate': 0.00017878928626722404, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 691/6464 [12:20<1:42:12, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1989, 'grad_norm': 0.6917895078659058, 'learning_rate': 0.00017875832172162875, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 692/6464 [12:21<1:41:56, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1685, 'grad_norm': 0.6987338066101074, 'learning_rate': 0.00017872735717603346, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 693/6464 [12:22<1:42:09, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3088, 'grad_norm': 0.6177701950073242, 'learning_rate': 0.00017869639263043817, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 694/6464 [12:23<1:35:27, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0411, 'grad_norm': 0.7914184331893921, 'learning_rate': 0.00017866542808484285, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 695/6464 [12:24<1:42:16, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5467, 'grad_norm': 0.681692361831665, 'learning_rate': 0.00017863446353924757, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 696/6464 [12:25<1:44:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1458, 'grad_norm': 0.6598331928253174, 'learning_rate': 0.00017860349899365228, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 697/6464 [12:26<1:45:45, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3308, 'grad_norm': 0.667193591594696, 'learning_rate': 0.000178572534448057, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 698/6464 [12:27<1:41:50, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3317, 'grad_norm': 0.6941635012626648, 'learning_rate': 0.0001785415699024617, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 699/6464 [12:29<1:43:08, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0251, 'grad_norm': 0.6130887269973755, 'learning_rate': 0.00017851060535686638, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 700/6464 [12:29<1:37:51, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2584, 'grad_norm': 0.7004032731056213, 'learning_rate': 0.00017847964081127112, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 701/6464 [12:31<1:42:10, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2533, 'grad_norm': 0.6177932024002075, 'learning_rate': 0.0001784486762656758, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 702/6464 [12:32<1:38:58, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1623, 'grad_norm': 0.8020581603050232, 'learning_rate': 0.00017841771172008052, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 703/6464 [12:33<1:44:53, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4927, 'grad_norm': 0.6142789721488953, 'learning_rate': 0.00017838674717448523, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 704/6464 [12:34<1:47:36, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4327, 'grad_norm': 0.6622915863990784, 'learning_rate': 0.0001783557826288899, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 705/6464 [12:35<1:43:14, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1031, 'grad_norm': 0.663366973400116, 'learning_rate': 0.00017832481808329465, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 706/6464 [12:36<1:38:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1622, 'grad_norm': 0.6797729134559631, 'learning_rate': 0.00017829385353769934, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 707/6464 [12:37<1:40:04, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2187, 'grad_norm': 0.6271393299102783, 'learning_rate': 0.00017826288899210405, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 708/6464 [12:38<1:38:17, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2373, 'grad_norm': 0.7305917143821716, 'learning_rate': 0.00017823192444650876, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 709/6464 [12:39<1:40:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3934, 'grad_norm': 0.6890833377838135, 'learning_rate': 0.00017820095990091344, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 710/6464 [12:40<1:40:24, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0984, 'grad_norm': 0.5821309089660645, 'learning_rate': 0.00017816999535531818, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 711/6464 [12:41<1:42:36, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3758, 'grad_norm': 0.643352210521698, 'learning_rate': 0.00017813903080972287, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 712/6464 [12:42<1:45:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3226, 'grad_norm': 0.5854964852333069, 'learning_rate': 0.0001781080662641276, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 713/6464 [12:43<1:38:30, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2514, 'grad_norm': 0.7065591216087341, 'learning_rate': 0.0001780771017185323, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 714/6464 [12:44<1:38:25, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4377, 'grad_norm': 0.7550712823867798, 'learning_rate': 0.000178046137172937, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 715/6464 [12:46<1:45:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3866, 'grad_norm': 0.6116141080856323, 'learning_rate': 0.0001780151726273417, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 716/6464 [12:47<1:44:41, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4475, 'grad_norm': 0.6596786379814148, 'learning_rate': 0.0001779842080817464, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 717/6464 [12:48<1:43:07, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1847, 'grad_norm': 0.5941349864006042, 'learning_rate': 0.00017795324353615113, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 718/6464 [12:49<1:44:13, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2016, 'grad_norm': 0.6067343950271606, 'learning_rate': 0.00017792227899055582, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 719/6464 [12:50<1:41:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9982, 'grad_norm': 0.6707989573478699, 'learning_rate': 0.00017789131444496053, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 720/6464 [12:51<1:45:00, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3369, 'grad_norm': 0.6616510152816772, 'learning_rate': 0.00017786034989936524, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 721/6464 [12:52<1:41:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1942, 'grad_norm': 0.5998879075050354, 'learning_rate': 0.00017782938535376995, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 722/6464 [12:53<1:49:57, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4488, 'grad_norm': 0.6079655289649963, 'learning_rate': 0.00017779842080817466, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 723/6464 [12:54<1:47:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4105, 'grad_norm': 0.6826537847518921, 'learning_rate': 0.00017776745626257935, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 724/6464 [12:55<1:44:59, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3926, 'grad_norm': 0.7266408205032349, 'learning_rate': 0.00017773649171698406, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 725/6464 [12:56<1:42:57, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3346, 'grad_norm': 0.6653958559036255, 'learning_rate': 0.00017770552717138877, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 726/6464 [12:57<1:39:21, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1755, 'grad_norm': 0.7641742825508118, 'learning_rate': 0.00017767456262579348, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆ | 727/6464 [12:59<1:43:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2534, 'grad_norm': 0.5877199172973633, 'learning_rate': 0.0001776435980801982, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 728/6464 [13:00<1:43:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2798, 'grad_norm': 0.7365729808807373, 'learning_rate': 0.00017761263353460288, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 729/6464 [13:01<1:46:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.36, 'grad_norm': 0.6041240096092224, 'learning_rate': 0.0001775816689890076, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 730/6464 [13:02<1:48:19, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5174, 'grad_norm': 0.7002406120300293, 'learning_rate': 0.0001775507044434123, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 731/6464 [13:03<1:42:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2138, 'grad_norm': 0.6556395292282104, 'learning_rate': 0.000177519739897817, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 732/6464 [13:04<1:41:55, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0097, 'grad_norm': 0.5966368913650513, 'learning_rate': 0.00017748877535222172, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 733/6464 [13:05<1:43:36, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.187, 'grad_norm': 0.5946320295333862, 'learning_rate': 0.00017745781080662643, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 734/6464 [13:06<1:42:35, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3608, 'grad_norm': 0.7163423895835876, 'learning_rate': 0.00017742684626103112, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 735/6464 [13:07<1:47:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2081, 'grad_norm': 0.5746209621429443, 'learning_rate': 0.00017739588171543583, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 736/6464 [13:09<1:53:12, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2574, 'grad_norm': 0.5209437608718872, 'learning_rate': 0.00017736491716984054, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 737/6464 [13:10<1:44:34, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1409, 'grad_norm': 0.7710665464401245, 'learning_rate': 0.00017733395262424525, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 738/6464 [13:11<1:45:28, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1713, 'grad_norm': 0.5884336829185486, 'learning_rate': 0.00017730298807864996, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 739/6464 [13:12<1:43:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.124, 'grad_norm': 0.6079782843589783, 'learning_rate': 0.00017727202353305465, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 740/6464 [13:13<1:47:07, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4055, 'grad_norm': 0.7033126354217529, 'learning_rate': 0.0001772410589874594, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 741/6464 [13:14<1:48:45, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3022, 'grad_norm': 0.6113366484642029, 'learning_rate': 0.00017721009444186407, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 742/6464 [13:15<1:46:54, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.243, 'grad_norm': 0.641823410987854, 'learning_rate': 0.00017717912989626878, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 11%|โ–ˆโ– | 743/6464 [13:16<1:42:35, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3108, 'grad_norm': 0.7083572745323181, 'learning_rate': 0.0001771481653506735, 'epoch': 0.11}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 744/6464 [13:17<1:41:14, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2152, 'grad_norm': 0.6615543961524963, 'learning_rate': 0.00017711720080507818, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 745/6464 [13:18<1:43:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3265, 'grad_norm': 0.6788278222084045, 'learning_rate': 0.00017708623625948292, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 746/6464 [13:19<1:40:17, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1567, 'grad_norm': 0.7679731249809265, 'learning_rate': 0.0001770552717138876, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 747/6464 [13:20<1:40:34, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1241, 'grad_norm': 0.6204165816307068, 'learning_rate': 0.0001770243071682923, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 748/6464 [13:22<1:49:23, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3089, 'grad_norm': 0.5940727591514587, 'learning_rate': 0.00017699334262269702, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 749/6464 [13:23<1:44:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1039, 'grad_norm': 0.6365938782691956, 'learning_rate': 0.0001769623780771017, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 750/6464 [13:24<1:40:31, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2466, 'grad_norm': 0.7721778154373169, 'learning_rate': 0.00017693141353150645, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 751/6464 [13:25<1:37:19, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2317, 'grad_norm': 0.7411234974861145, 'learning_rate': 0.00017690044898591113, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 752/6464 [13:26<1:39:49, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.315, 'grad_norm': 0.6572111248970032, 'learning_rate': 0.00017686948444031584, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 753/6464 [13:27<1:40:46, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1483, 'grad_norm': 0.6023356914520264, 'learning_rate': 0.00017683851989472055, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 754/6464 [13:28<1:41:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1928, 'grad_norm': 0.6919096112251282, 'learning_rate': 0.00017680755534912526, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 755/6464 [13:29<1:38:27, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2723, 'grad_norm': 0.6892973184585571, 'learning_rate': 0.00017677659080352998, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 756/6464 [13:30<1:40:03, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.409, 'grad_norm': 0.7556528449058533, 'learning_rate': 0.00017674562625793466, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 757/6464 [13:31<1:42:35, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2916, 'grad_norm': 0.6147202253341675, 'learning_rate': 0.00017671466171233937, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 758/6464 [13:32<1:35:45, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1987, 'grad_norm': 0.8202833533287048, 'learning_rate': 0.00017668369716674408, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 759/6464 [13:33<1:43:56, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2939, 'grad_norm': 0.672617495059967, 'learning_rate': 0.0001766527326211488, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 760/6464 [13:34<1:38:53, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2723, 'grad_norm': 0.7026349306106567, 'learning_rate': 0.0001766217680755535, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 761/6464 [13:35<1:39:57, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3211, 'grad_norm': 0.6915060877799988, 'learning_rate': 0.00017659080352995822, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 762/6464 [13:36<1:43:21, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3012, 'grad_norm': 0.751083493232727, 'learning_rate': 0.0001765598389843629, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 763/6464 [13:38<1:45:24, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3188, 'grad_norm': 0.6383609175682068, 'learning_rate': 0.0001765288744387676, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 764/6464 [13:39<1:43:57, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3107, 'grad_norm': 0.6055516004562378, 'learning_rate': 0.00017649790989317232, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 765/6464 [13:40<1:38:13, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9156, 'grad_norm': 0.7901120781898499, 'learning_rate': 0.00017646694534757703, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 766/6464 [13:41<1:46:55, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2637, 'grad_norm': 0.49006137251853943, 'learning_rate': 0.00017643598080198175, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 767/6464 [13:42<1:51:23, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2531, 'grad_norm': 0.65828537940979, 'learning_rate': 0.00017640501625638643, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 768/6464 [13:43<1:46:08, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0243, 'grad_norm': 0.6586660742759705, 'learning_rate': 0.00017637405171079114, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 769/6464 [13:44<1:47:16, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1787, 'grad_norm': 0.6869193315505981, 'learning_rate': 0.00017634308716519585, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 770/6464 [13:45<1:47:17, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2253, 'grad_norm': 0.6169970035552979, 'learning_rate': 0.00017631212261960056, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 771/6464 [13:46<1:42:36, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3257, 'grad_norm': 0.7023926973342896, 'learning_rate': 0.00017628115807400528, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 772/6464 [13:47<1:41:13, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2848, 'grad_norm': 0.6841822266578674, 'learning_rate': 0.00017625019352840996, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 773/6464 [13:49<1:43:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9737, 'grad_norm': 0.5352315902709961, 'learning_rate': 0.0001762192289828147, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 774/6464 [13:50<1:43:08, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9197, 'grad_norm': 0.5514433979988098, 'learning_rate': 0.00017618826443721938, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 775/6464 [13:51<1:46:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.256, 'grad_norm': 0.677016019821167, 'learning_rate': 0.0001761572998916241, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 776/6464 [13:52<1:48:19, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4784, 'grad_norm': 0.6139114499092102, 'learning_rate': 0.0001761263353460288, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 777/6464 [13:53<1:43:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2031, 'grad_norm': 0.6575068235397339, 'learning_rate': 0.0001760953708004335, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 778/6464 [13:54<1:46:44, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4218, 'grad_norm': 0.6873417496681213, 'learning_rate': 0.00017606440625483823, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 779/6464 [13:55<1:40:52, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1104, 'grad_norm': 0.6660227179527283, 'learning_rate': 0.0001760334417092429, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 780/6464 [13:56<1:39:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3852, 'grad_norm': 0.6767476201057434, 'learning_rate': 0.00017600247716364765, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 781/6464 [13:57<1:38:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1399, 'grad_norm': 0.5805649161338806, 'learning_rate': 0.00017597151261805234, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 782/6464 [13:59<1:50:16, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5718, 'grad_norm': 0.6092204451560974, 'learning_rate': 0.00017594054807245705, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 783/6464 [14:00<1:55:02, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4394, 'grad_norm': 0.6298264861106873, 'learning_rate': 0.00017590958352686176, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 784/6464 [14:01<1:50:06, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.28, 'grad_norm': 0.6744271516799927, 'learning_rate': 0.00017587861898126644, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 785/6464 [14:02<1:57:02, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4327, 'grad_norm': 0.6180481910705566, 'learning_rate': 0.00017584765443567118, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 786/6464 [14:04<1:54:40, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4366, 'grad_norm': 0.6864517331123352, 'learning_rate': 0.00017581668989007586, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 787/6464 [14:05<1:51:22, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2635, 'grad_norm': 0.6572307348251343, 'learning_rate': 0.00017578572534448058, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 788/6464 [14:06<1:46:22, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0614, 'grad_norm': 0.7017739415168762, 'learning_rate': 0.0001757547607988853, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 789/6464 [14:07<1:42:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1952, 'grad_norm': 0.6740489602088928, 'learning_rate': 0.00017572379625328997, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 790/6464 [14:08<1:42:54, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3676, 'grad_norm': 0.6654466390609741, 'learning_rate': 0.0001756928317076947, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 791/6464 [14:09<1:44:59, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3392, 'grad_norm': 0.6398711204528809, 'learning_rate': 0.0001756618671620994, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 792/6464 [14:10<1:43:57, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2493, 'grad_norm': 0.6121693253517151, 'learning_rate': 0.0001756309026165041, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 793/6464 [14:11<1:44:00, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9571, 'grad_norm': 0.6583244800567627, 'learning_rate': 0.00017559993807090882, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 794/6464 [14:12<1:41:40, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4303, 'grad_norm': 0.6882501840591431, 'learning_rate': 0.00017556897352531353, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 795/6464 [14:13<1:45:08, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0165, 'grad_norm': 0.5661895275115967, 'learning_rate': 0.00017553800897971824, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 796/6464 [14:14<1:43:15, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0206, 'grad_norm': 0.657825767993927, 'learning_rate': 0.00017550704443412292, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 797/6464 [14:15<1:43:25, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1028, 'grad_norm': 0.648900032043457, 'learning_rate': 0.00017547607988852764, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 798/6464 [14:17<1:42:37, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1622, 'grad_norm': 0.6597365140914917, 'learning_rate': 0.00017544511534293235, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 799/6464 [14:18<1:40:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0946, 'grad_norm': 0.6698225140571594, 'learning_rate': 0.00017541415079733706, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 800/6464 [14:19<1:41:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2692, 'grad_norm': 0.6472558379173279, 'learning_rate': 0.00017538318625174177, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 801/6464 [14:20<1:38:06, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2124, 'grad_norm': 0.7566421031951904, 'learning_rate': 0.00017535222170614648, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 802/6464 [14:21<1:36:24, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.311, 'grad_norm': 0.7909039258956909, 'learning_rate': 0.00017532125716055117, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 803/6464 [14:22<1:35:07, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3266, 'grad_norm': 1.0802475214004517, 'learning_rate': 0.00017529029261495588, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 804/6464 [14:23<1:40:56, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4421, 'grad_norm': 0.6324787139892578, 'learning_rate': 0.0001752593280693606, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 805/6464 [14:24<1:39:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2104, 'grad_norm': 0.8303648233413696, 'learning_rate': 0.0001752283635237653, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 806/6464 [14:25<1:43:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3391, 'grad_norm': 0.6875859498977661, 'learning_rate': 0.00017519739897817, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ– | 807/6464 [14:26<1:42:12, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.278, 'grad_norm': 0.6471733450889587, 'learning_rate': 0.0001751664344325747, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 12%|โ–ˆโ–Ž | 808/6464 [14:27<1:45:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3384, 'grad_norm': 0.6498260498046875, 'learning_rate': 0.0001751354698869794, 'epoch': 0.12}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 809/6464 [14:28<1:42:30, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3864, 'grad_norm': 0.6878655552864075, 'learning_rate': 0.00017510450534138412, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 810/6464 [14:29<1:39:18, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1649, 'grad_norm': 0.6564275026321411, 'learning_rate': 0.00017507354079578883, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 811/6464 [14:30<1:43:43, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3402, 'grad_norm': 0.6388240456581116, 'learning_rate': 0.00017504257625019354, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 812/6464 [14:32<1:49:56, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4279, 'grad_norm': 0.5504449009895325, 'learning_rate': 0.00017501161170459822, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 813/6464 [14:33<1:45:49, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3256, 'grad_norm': 0.7646299004554749, 'learning_rate': 0.00017498064715900296, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 814/6464 [14:34<1:41:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1677, 'grad_norm': 0.7368467450141907, 'learning_rate': 0.00017494968261340765, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 815/6464 [14:35<1:44:31, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3745, 'grad_norm': 0.6722725033760071, 'learning_rate': 0.00017491871806781236, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 816/6464 [14:36<1:42:56, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0855, 'grad_norm': 0.5960257649421692, 'learning_rate': 0.00017488775352221707, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 817/6464 [14:37<1:39:28, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2697, 'grad_norm': 0.7308486700057983, 'learning_rate': 0.00017485678897662175, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 818/6464 [14:38<1:45:03, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1852, 'grad_norm': 0.6092515587806702, 'learning_rate': 0.0001748258244310265, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 819/6464 [14:40<1:51:32, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1847, 'grad_norm': 0.6297078728675842, 'learning_rate': 0.00017479485988543118, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 820/6464 [14:40<1:42:50, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3581, 'grad_norm': 0.8034083247184753, 'learning_rate': 0.00017476389533983592, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 821/6464 [14:42<1:44:48, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2913, 'grad_norm': 0.6905854344367981, 'learning_rate': 0.0001747329307942406, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 822/6464 [14:43<1:43:49, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1733, 'grad_norm': 0.6566025614738464, 'learning_rate': 0.0001747019662486453, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 823/6464 [14:44<1:49:57, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3421, 'grad_norm': 0.5622793436050415, 'learning_rate': 0.00017467100170305002, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 824/6464 [14:45<1:48:51, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1874, 'grad_norm': 0.6111335754394531, 'learning_rate': 0.0001746400371574547, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 825/6464 [14:46<1:42:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0341, 'grad_norm': 0.7344348430633545, 'learning_rate': 0.00017460907261185945, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 826/6464 [14:47<1:42:21, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3082, 'grad_norm': 0.6451380848884583, 'learning_rate': 0.00017457810806626413, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 827/6464 [14:48<1:36:08, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1883, 'grad_norm': 0.7485331892967224, 'learning_rate': 0.00017454714352066884, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 828/6464 [14:49<1:35:39, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3497, 'grad_norm': 0.6726934909820557, 'learning_rate': 0.00017451617897507355, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 829/6464 [14:50<1:39:50, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4363, 'grad_norm': 0.6610798239707947, 'learning_rate': 0.00017448521442947824, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 830/6464 [14:51<1:41:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2365, 'grad_norm': 0.6277110576629639, 'learning_rate': 0.00017445424988388297, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 831/6464 [14:52<1:39:56, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1663, 'grad_norm': 0.6750337481498718, 'learning_rate': 0.00017442328533828766, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 832/6464 [14:53<1:38:06, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1031, 'grad_norm': 0.6374592781066895, 'learning_rate': 0.00017439232079269237, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 833/6464 [14:54<1:35:58, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1235, 'grad_norm': 0.675443708896637, 'learning_rate': 0.00017436135624709708, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 834/6464 [14:55<1:33:47, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0031, 'grad_norm': 0.6583724021911621, 'learning_rate': 0.0001743303917015018, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 835/6464 [14:56<1:30:33, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0329, 'grad_norm': 0.7474125027656555, 'learning_rate': 0.0001742994271559065, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 836/6464 [14:57<1:28:11, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3369, 'grad_norm': 0.6841525435447693, 'learning_rate': 0.0001742684626103112, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 837/6464 [14:58<1:36:24, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2555, 'grad_norm': 0.5985449552536011, 'learning_rate': 0.0001742374980647159, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 838/6464 [14:59<1:37:36, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4109, 'grad_norm': 0.7487847805023193, 'learning_rate': 0.0001742065335191206, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 839/6464 [15:00<1:38:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.072, 'grad_norm': 0.5500527620315552, 'learning_rate': 0.00017417556897352532, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 840/6464 [15:01<1:34:46, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.257, 'grad_norm': 0.702649712562561, 'learning_rate': 0.00017414460442793003, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 841/6464 [15:03<1:55:17, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4266, 'grad_norm': 0.5473799705505371, 'learning_rate': 0.00017411363988233475, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 842/6464 [15:04<1:49:31, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3087, 'grad_norm': 0.6637792587280273, 'learning_rate': 0.00017408267533673943, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 843/6464 [15:05<1:48:21, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2964, 'grad_norm': 0.6201562881469727, 'learning_rate': 0.00017405171079114414, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 844/6464 [15:06<1:48:38, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3217, 'grad_norm': 0.6310684084892273, 'learning_rate': 0.00017402074624554885, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 845/6464 [15:07<1:46:45, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0904, 'grad_norm': 0.5885483622550964, 'learning_rate': 0.00017398978169995356, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 846/6464 [15:09<1:43:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1419, 'grad_norm': 0.645257294178009, 'learning_rate': 0.00017395881715435828, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 847/6464 [15:10<1:40:31, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1473, 'grad_norm': 0.6436446905136108, 'learning_rate': 0.00017392785260876296, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 848/6464 [15:11<1:46:16, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4015, 'grad_norm': 0.6237598657608032, 'learning_rate': 0.0001738968880631677, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 849/6464 [15:12<1:45:46, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1693, 'grad_norm': 0.6100257039070129, 'learning_rate': 0.00017386592351757238, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 850/6464 [15:13<1:47:34, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2769, 'grad_norm': 0.7363349795341492, 'learning_rate': 0.0001738349589719771, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 851/6464 [15:14<1:48:19, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4222, 'grad_norm': 0.7503136396408081, 'learning_rate': 0.0001738039944263818, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 852/6464 [15:15<1:45:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3012, 'grad_norm': 0.7260336875915527, 'learning_rate': 0.0001737730298807865, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 853/6464 [15:17<1:47:39, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2881, 'grad_norm': 0.6492506861686707, 'learning_rate': 0.00017374206533519123, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 854/6464 [15:18<1:43:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2032, 'grad_norm': 0.7159489393234253, 'learning_rate': 0.0001737111007895959, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 855/6464 [15:19<1:44:53, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1319, 'grad_norm': 0.6138157248497009, 'learning_rate': 0.00017368013624400062, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 856/6464 [15:20<1:46:03, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2886, 'grad_norm': 0.5989621877670288, 'learning_rate': 0.00017364917169840533, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 857/6464 [15:21<1:36:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0181, 'grad_norm': 0.7076424360275269, 'learning_rate': 0.00017361820715281002, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 858/6464 [15:22<1:34:06, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.97, 'grad_norm': 0.6969763040542603, 'learning_rate': 0.00017358724260721476, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 859/6464 [15:22<1:29:05, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1479, 'grad_norm': 0.7426488995552063, 'learning_rate': 0.00017355627806161944, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 860/6464 [15:24<1:33:52, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0598, 'grad_norm': 0.6336402893066406, 'learning_rate': 0.00017352531351602418, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 861/6464 [15:25<1:38:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3186, 'grad_norm': 0.7161359786987305, 'learning_rate': 0.00017349434897042886, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 862/6464 [15:26<1:37:26, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1692, 'grad_norm': 0.674864649772644, 'learning_rate': 0.00017346338442483358, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 863/6464 [15:27<1:38:15, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4023, 'grad_norm': 0.6805716156959534, 'learning_rate': 0.0001734324198792383, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 864/6464 [15:28<1:41:53, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3946, 'grad_norm': 0.7239888906478882, 'learning_rate': 0.00017340145533364297, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 865/6464 [15:29<1:39:49, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0957, 'grad_norm': 0.6613406538963318, 'learning_rate': 0.0001733704907880477, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 866/6464 [15:30<1:37:34, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2474, 'grad_norm': 0.714076042175293, 'learning_rate': 0.0001733395262424524, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 867/6464 [15:31<1:37:39, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1776, 'grad_norm': 0.6231953501701355, 'learning_rate': 0.0001733085616968571, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 868/6464 [15:32<1:38:32, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2603, 'grad_norm': 0.6638737916946411, 'learning_rate': 0.00017327759715126182, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 869/6464 [15:33<1:40:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0907, 'grad_norm': 0.5897013545036316, 'learning_rate': 0.00017324663260566653, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 870/6464 [15:34<1:37:01, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2728, 'grad_norm': 0.7740921378135681, 'learning_rate': 0.00017321566806007124, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 871/6464 [15:35<1:39:08, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2011, 'grad_norm': 0.8611716032028198, 'learning_rate': 0.00017318470351447592, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 13%|โ–ˆโ–Ž | 872/6464 [15:36<1:36:34, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1918, 'grad_norm': 0.6606082916259766, 'learning_rate': 0.00017315373896888063, 'epoch': 0.13}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 873/6464 [15:38<1:45:01, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3892, 'grad_norm': 0.5772320032119751, 'learning_rate': 0.00017312277442328535, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 874/6464 [15:39<1:50:01, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1722, 'grad_norm': 0.5253010392189026, 'learning_rate': 0.00017309180987769006, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 875/6464 [15:41<2:00:37, 1.29s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4996, 'grad_norm': 0.5425624847412109, 'learning_rate': 0.00017306084533209477, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 876/6464 [15:42<1:56:55, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4521, 'grad_norm': 0.6443965435028076, 'learning_rate': 0.00017302988078649945, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 877/6464 [15:43<1:49:57, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1014, 'grad_norm': 0.667320966720581, 'learning_rate': 0.00017299891624090416, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 878/6464 [15:44<1:54:19, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3755, 'grad_norm': 0.6281020045280457, 'learning_rate': 0.00017296795169530888, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 879/6464 [15:45<1:49:02, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2714, 'grad_norm': 0.6484799385070801, 'learning_rate': 0.0001729369871497136, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 880/6464 [15:46<1:50:37, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3269, 'grad_norm': 0.6293825507164001, 'learning_rate': 0.0001729060226041183, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 881/6464 [15:48<1:52:02, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4313, 'grad_norm': 0.6501870155334473, 'learning_rate': 0.000172875058058523, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 882/6464 [15:49<1:48:25, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4044, 'grad_norm': 0.6932122111320496, 'learning_rate': 0.0001728440935129277, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 883/6464 [15:50<1:50:11, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5035, 'grad_norm': 0.667942464351654, 'learning_rate': 0.0001728131289673324, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 884/6464 [15:51<1:50:01, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1952, 'grad_norm': 0.65732342004776, 'learning_rate': 0.00017278216442173712, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 885/6464 [15:52<1:43:41, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0651, 'grad_norm': 0.7510630488395691, 'learning_rate': 0.00017275119987614183, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 886/6464 [15:53<1:47:32, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3662, 'grad_norm': 0.6944143176078796, 'learning_rate': 0.00017272023533054654, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 887/6464 [15:54<1:46:40, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2801, 'grad_norm': 0.6640189290046692, 'learning_rate': 0.00017268927078495122, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ–Ž | 888/6464 [15:55<1:40:52, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1909, 'grad_norm': 0.6743807792663574, 'learning_rate': 0.00017265830623935596, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 889/6464 [15:56<1:35:34, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2581, 'grad_norm': 0.7954981923103333, 'learning_rate': 0.00017262734169376065, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 890/6464 [15:57<1:36:59, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.291, 'grad_norm': 0.6686195135116577, 'learning_rate': 0.00017259637714816536, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 891/6464 [15:58<1:37:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3175, 'grad_norm': 0.7627065777778625, 'learning_rate': 0.00017256541260257007, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 892/6464 [15:59<1:36:43, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0962, 'grad_norm': 0.6138887405395508, 'learning_rate': 0.00017253444805697475, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 893/6464 [16:00<1:39:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1778, 'grad_norm': 0.5856194496154785, 'learning_rate': 0.0001725034835113795, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 894/6464 [16:01<1:37:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1362, 'grad_norm': 0.6904652118682861, 'learning_rate': 0.00017247251896578418, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 895/6464 [16:02<1:32:26, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0274, 'grad_norm': 0.73096764087677, 'learning_rate': 0.0001724415544201889, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 896/6464 [16:03<1:32:10, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2975, 'grad_norm': 0.6537982225418091, 'learning_rate': 0.0001724105898745936, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 897/6464 [16:05<1:41:13, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3877, 'grad_norm': 0.6007570624351501, 'learning_rate': 0.00017237962532899828, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 898/6464 [16:06<1:47:35, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3805, 'grad_norm': 0.6074231266975403, 'learning_rate': 0.00017234866078340302, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 899/6464 [16:07<1:42:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1122, 'grad_norm': 0.6570443511009216, 'learning_rate': 0.0001723176962378077, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 900/6464 [16:08<1:41:24, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3112, 'grad_norm': 0.7189629077911377, 'learning_rate': 0.00017228673169221244, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 901/6464 [16:09<1:37:13, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1634, 'grad_norm': 0.7659637331962585, 'learning_rate': 0.00017225576714661713, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 902/6464 [16:10<1:38:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3367, 'grad_norm': 0.5876296758651733, 'learning_rate': 0.00017222480260102184, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 903/6464 [16:11<1:40:36, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2876, 'grad_norm': 0.6898085474967957, 'learning_rate': 0.00017219383805542655, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 904/6464 [16:12<1:37:24, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0776, 'grad_norm': 0.6933792233467102, 'learning_rate': 0.00017216287350983124, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 905/6464 [16:13<1:38:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2067, 'grad_norm': 0.6697400212287903, 'learning_rate': 0.00017213190896423597, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 906/6464 [16:15<1:44:22, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4197, 'grad_norm': 0.7873298525810242, 'learning_rate': 0.00017210094441864066, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 907/6464 [16:15<1:39:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0457, 'grad_norm': 0.5898991823196411, 'learning_rate': 0.00017206997987304537, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 908/6464 [16:17<1:40:16, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2985, 'grad_norm': 0.8436338305473328, 'learning_rate': 0.00017203901532745008, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 909/6464 [16:18<1:39:48, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.179, 'grad_norm': 0.7638314366340637, 'learning_rate': 0.0001720080507818548, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 910/6464 [16:19<1:37:38, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3309, 'grad_norm': 0.6499229073524475, 'learning_rate': 0.0001719770862362595, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 911/6464 [16:20<1:36:39, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2352, 'grad_norm': 0.6285813450813293, 'learning_rate': 0.0001719461216906642, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 912/6464 [16:21<1:40:03, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3279, 'grad_norm': 0.6781837940216064, 'learning_rate': 0.0001719151571450689, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 913/6464 [16:22<1:48:32, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2765, 'grad_norm': 0.5269970297813416, 'learning_rate': 0.0001718841925994736, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 914/6464 [16:23<1:47:21, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4599, 'grad_norm': 0.6461402773857117, 'learning_rate': 0.00017185322805387832, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 915/6464 [16:25<1:49:11, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.341, 'grad_norm': 0.5988991260528564, 'learning_rate': 0.00017182226350828303, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 916/6464 [16:26<1:51:22, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3853, 'grad_norm': 0.6329673528671265, 'learning_rate': 0.00017179129896268772, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 917/6464 [16:27<1:53:49, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4273, 'grad_norm': 0.6334714889526367, 'learning_rate': 0.00017176033441709243, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 918/6464 [16:28<1:53:20, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3728, 'grad_norm': 0.700648844242096, 'learning_rate': 0.00017172936987149714, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 919/6464 [16:29<1:49:26, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3022, 'grad_norm': 0.883124053478241, 'learning_rate': 0.00017169840532590185, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 920/6464 [16:31<1:46:37, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0863, 'grad_norm': 0.590599000453949, 'learning_rate': 0.00017166744078030656, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 921/6464 [16:32<1:43:44, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.477, 'grad_norm': 0.6711313724517822, 'learning_rate': 0.00017163647623471127, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 922/6464 [16:33<1:43:14, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4073, 'grad_norm': 0.6651897430419922, 'learning_rate': 0.00017160551168911596, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 923/6464 [16:34<1:40:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0944, 'grad_norm': 0.6390888094902039, 'learning_rate': 0.00017157454714352067, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 924/6464 [16:35<1:38:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2978, 'grad_norm': 0.6236753463745117, 'learning_rate': 0.00017154358259792538, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 925/6464 [16:36<1:39:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2528, 'grad_norm': 0.6570532321929932, 'learning_rate': 0.0001715126180523301, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 926/6464 [16:37<1:39:40, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.413, 'grad_norm': 0.8138312101364136, 'learning_rate': 0.0001714816535067348, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 927/6464 [16:38<1:35:29, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1294, 'grad_norm': 0.7108273506164551, 'learning_rate': 0.0001714506889611395, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 928/6464 [16:39<1:46:19, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2563, 'grad_norm': 0.5360896587371826, 'learning_rate': 0.00017141972441554423, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 929/6464 [16:40<1:45:16, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3085, 'grad_norm': 0.5890526175498962, 'learning_rate': 0.0001713887598699489, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 930/6464 [16:42<1:47:25, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4035, 'grad_norm': 0.6390001773834229, 'learning_rate': 0.00017135779532435362, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 931/6464 [16:43<1:41:18, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0917, 'grad_norm': 0.6644165515899658, 'learning_rate': 0.00017132683077875833, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 932/6464 [16:44<1:40:35, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2107, 'grad_norm': 0.6733497977256775, 'learning_rate': 0.00017129586623316302, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 933/6464 [16:45<1:39:51, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3589, 'grad_norm': 0.7149885892868042, 'learning_rate': 0.00017126490168756776, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 934/6464 [16:46<1:39:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2192, 'grad_norm': 0.6680464744567871, 'learning_rate': 0.00017123393714197244, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 935/6464 [16:47<1:50:05, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6735, 'grad_norm': 0.5948333740234375, 'learning_rate': 0.00017120297259637715, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 936/6464 [16:49<1:52:41, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4828, 'grad_norm': 0.6744933724403381, 'learning_rate': 0.00017117200805078186, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 14%|โ–ˆโ– | 937/6464 [16:50<1:46:56, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1217, 'grad_norm': 0.7231170535087585, 'learning_rate': 0.00017114104350518655, 'epoch': 0.14}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 938/6464 [16:51<1:46:58, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2105, 'grad_norm': 0.6965036392211914, 'learning_rate': 0.00017111007895959129, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 939/6464 [16:52<1:48:18, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3337, 'grad_norm': 0.6276719570159912, 'learning_rate': 0.00017107911441399597, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 940/6464 [16:53<1:47:32, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2387, 'grad_norm': 0.579397976398468, 'learning_rate': 0.0001710481498684007, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 941/6464 [16:54<1:48:36, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2379, 'grad_norm': 0.624982476234436, 'learning_rate': 0.0001710171853228054, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 942/6464 [16:55<1:42:04, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2434, 'grad_norm': 0.6626005172729492, 'learning_rate': 0.0001709862207772101, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 943/6464 [16:56<1:36:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1267, 'grad_norm': 0.6646596193313599, 'learning_rate': 0.00017095525623161482, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 944/6464 [16:57<1:45:19, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5051, 'grad_norm': 0.6112967133522034, 'learning_rate': 0.0001709242916860195, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 945/6464 [16:58<1:40:28, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2489, 'grad_norm': 0.7445712685585022, 'learning_rate': 0.00017089332714042424, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 946/6464 [16:59<1:36:18, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2619, 'grad_norm': 0.6588544249534607, 'learning_rate': 0.00017086236259482892, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 947/6464 [17:00<1:34:04, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0888, 'grad_norm': 0.6190716028213501, 'learning_rate': 0.00017083139804923363, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 948/6464 [17:02<1:43:18, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.264, 'grad_norm': 0.545595109462738, 'learning_rate': 0.00017080043350363835, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 949/6464 [17:03<1:40:15, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3561, 'grad_norm': 0.7159931659698486, 'learning_rate': 0.00017076946895804306, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 950/6464 [17:04<1:39:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0955, 'grad_norm': 0.5605778694152832, 'learning_rate': 0.00017073850441244777, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 951/6464 [17:05<1:43:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1254, 'grad_norm': 0.6373831629753113, 'learning_rate': 0.00017070753986685245, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 952/6464 [17:06<1:41:08, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2222, 'grad_norm': 0.6726678609848022, 'learning_rate': 0.00017067657532125716, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 953/6464 [17:07<1:45:18, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3255, 'grad_norm': 0.7058420181274414, 'learning_rate': 0.00017064561077566188, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 954/6464 [17:09<1:52:09, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1715, 'grad_norm': 0.645699679851532, 'learning_rate': 0.0001706146462300666, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 955/6464 [17:10<1:51:21, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1499, 'grad_norm': 0.6359080076217651, 'learning_rate': 0.0001705836816844713, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 956/6464 [17:11<1:47:36, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0556, 'grad_norm': 0.7924046516418457, 'learning_rate': 0.00017055271713887598, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 957/6464 [17:12<1:40:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1378, 'grad_norm': 0.6161453723907471, 'learning_rate': 0.0001705217525932807, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 958/6464 [17:13<1:33:22, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1365, 'grad_norm': 0.799090564250946, 'learning_rate': 0.0001704907880476854, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 959/6464 [17:14<1:31:13, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1764, 'grad_norm': 0.7382569909095764, 'learning_rate': 0.00017045982350209012, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 960/6464 [17:15<1:36:00, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0527, 'grad_norm': 0.732258141040802, 'learning_rate': 0.00017042885895649483, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 961/6464 [17:16<1:33:59, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3669, 'grad_norm': 0.6916087865829468, 'learning_rate': 0.00017039789441089954, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 962/6464 [17:17<1:39:41, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2377, 'grad_norm': 0.6293312907218933, 'learning_rate': 0.00017036692986530422, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 963/6464 [17:18<1:38:20, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1833, 'grad_norm': 0.6925315260887146, 'learning_rate': 0.00017033596531970893, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 964/6464 [17:19<1:44:20, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2264, 'grad_norm': 0.5718787908554077, 'learning_rate': 0.00017030500077411365, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 965/6464 [17:20<1:42:20, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2774, 'grad_norm': 0.6800561547279358, 'learning_rate': 0.00017027403622851836, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 966/6464 [17:22<1:44:57, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2888, 'grad_norm': 0.6077072620391846, 'learning_rate': 0.00017024307168292307, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 967/6464 [17:23<1:43:03, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3681, 'grad_norm': 0.7419540286064148, 'learning_rate': 0.00017021210713732775, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 968/6464 [17:24<1:46:06, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2594, 'grad_norm': 0.6459929347038269, 'learning_rate': 0.0001701811425917325, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ– | 969/6464 [17:25<1:42:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1911, 'grad_norm': 0.6715732216835022, 'learning_rate': 0.00017015017804613718, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 970/6464 [17:26<1:41:40, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.206, 'grad_norm': 0.6617540121078491, 'learning_rate': 0.0001701192135005419, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 971/6464 [17:27<1:36:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.097, 'grad_norm': 0.6537230014801025, 'learning_rate': 0.0001700882489549466, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 972/6464 [17:28<1:37:17, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.107, 'grad_norm': 0.5808826088905334, 'learning_rate': 0.00017005728440935128, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 973/6464 [17:29<1:45:32, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5194, 'grad_norm': 0.5669182538986206, 'learning_rate': 0.00017002631986375602, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 974/6464 [17:31<1:48:31, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3285, 'grad_norm': 0.6518660187721252, 'learning_rate': 0.0001699953553181607, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 975/6464 [17:32<1:47:27, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1407, 'grad_norm': 0.6185245513916016, 'learning_rate': 0.00016996439077256542, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 976/6464 [17:33<1:50:54, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4154, 'grad_norm': 0.6128184795379639, 'learning_rate': 0.00016993342622697013, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 977/6464 [17:34<1:46:09, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1824, 'grad_norm': 0.6995661854743958, 'learning_rate': 0.0001699024616813748, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 978/6464 [17:35<1:42:39, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0787, 'grad_norm': 0.6052937507629395, 'learning_rate': 0.00016987149713577955, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 979/6464 [17:36<1:46:26, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.417, 'grad_norm': 0.7284356951713562, 'learning_rate': 0.00016984053259018424, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 980/6464 [17:38<1:42:27, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9739, 'grad_norm': 0.668085515499115, 'learning_rate': 0.00016980956804458897, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 981/6464 [17:39<1:42:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1794, 'grad_norm': 0.7083295583724976, 'learning_rate': 0.00016977860349899366, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 982/6464 [17:40<1:40:51, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0877, 'grad_norm': 0.6290879845619202, 'learning_rate': 0.00016974763895339837, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 983/6464 [17:41<1:42:46, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4666, 'grad_norm': 0.6507346630096436, 'learning_rate': 0.00016971667440780308, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 984/6464 [17:42<1:42:59, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2467, 'grad_norm': 0.6480516195297241, 'learning_rate': 0.00016968570986220776, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 985/6464 [17:43<1:38:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2105, 'grad_norm': 0.8091142177581787, 'learning_rate': 0.0001696547453166125, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 986/6464 [17:44<1:40:43, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.099, 'grad_norm': 0.6570078730583191, 'learning_rate': 0.0001696237807710172, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 987/6464 [17:45<1:39:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2816, 'grad_norm': 0.7402425408363342, 'learning_rate': 0.0001695928162254219, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 988/6464 [17:46<1:38:56, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2005, 'grad_norm': 0.6850535273551941, 'learning_rate': 0.0001695618516798266, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 989/6464 [17:47<1:36:25, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2545, 'grad_norm': 0.6444434523582458, 'learning_rate': 0.00016953088713423132, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 990/6464 [17:48<1:34:10, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3111, 'grad_norm': 0.7628388404846191, 'learning_rate': 0.00016949992258863603, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 991/6464 [17:49<1:35:26, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2098, 'grad_norm': 0.6936285495758057, 'learning_rate': 0.00016946895804304072, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 992/6464 [17:50<1:34:07, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2354, 'grad_norm': 0.7918984889984131, 'learning_rate': 0.00016943799349744543, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 993/6464 [17:51<1:32:38, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.257, 'grad_norm': 0.6931885480880737, 'learning_rate': 0.00016940702895185014, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 994/6464 [17:52<1:29:52, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3666, 'grad_norm': 0.7987148761749268, 'learning_rate': 0.00016937606440625485, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 995/6464 [17:53<1:32:54, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0884, 'grad_norm': 0.6485492587089539, 'learning_rate': 0.00016934509986065956, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 996/6464 [17:54<1:36:39, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2805, 'grad_norm': 0.633255124092102, 'learning_rate': 0.00016931413531506425, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 997/6464 [17:56<1:36:41, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1923, 'grad_norm': 0.7008618712425232, 'learning_rate': 0.00016928317076946896, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 998/6464 [17:57<1:35:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3226, 'grad_norm': 0.6937047839164734, 'learning_rate': 0.00016925220622387367, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 999/6464 [17:58<1:36:19, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3159, 'grad_norm': 0.7181409001350403, 'learning_rate': 0.00016922124167827838, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 1000/6464 [17:59<1:47:19, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4491, 'grad_norm': 0.6380652785301208, 'learning_rate': 0.0001691902771326831, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 15%|โ–ˆโ–Œ | 1001/6464 [18:02<2:44:00, 1.80s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1113, 'grad_norm': 0.6957496404647827, 'learning_rate': 0.0001691593125870878, 'epoch': 0.15}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1002/6464 [18:04<2:29:12, 1.64s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5027, 'grad_norm': 0.6269171833992004, 'learning_rate': 0.0001691283480414925, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1003/6464 [18:05<2:12:48, 1.46s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1344, 'grad_norm': 0.6372864246368408, 'learning_rate': 0.0001690973834958972, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1004/6464 [18:06<2:03:24, 1.36s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3268, 'grad_norm': 0.6904846429824829, 'learning_rate': 0.0001690664189503019, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1005/6464 [18:07<1:52:02, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2423, 'grad_norm': 0.7102606296539307, 'learning_rate': 0.00016903545440470662, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1006/6464 [18:08<1:46:03, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0244, 'grad_norm': 0.6041479706764221, 'learning_rate': 0.00016900448985911133, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1007/6464 [18:09<2:02:39, 1.35s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6326, 'grad_norm': 0.61473548412323, 'learning_rate': 0.00016897352531351602, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1008/6464 [18:11<1:58:15, 1.30s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2188, 'grad_norm': 0.7099564075469971, 'learning_rate': 0.00016894256076792076, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1009/6464 [18:12<1:55:04, 1.27s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.335, 'grad_norm': 0.6809927821159363, 'learning_rate': 0.00016891159622232544, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1010/6464 [18:13<1:46:44, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1853, 'grad_norm': 0.8289364576339722, 'learning_rate': 0.00016888063167673015, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1011/6464 [18:14<1:42:39, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1416, 'grad_norm': 0.6582660675048828, 'learning_rate': 0.00016884966713113486, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1012/6464 [18:15<1:39:18, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0912, 'grad_norm': 0.711924135684967, 'learning_rate': 0.00016881870258553955, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1013/6464 [18:16<1:35:34, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1175, 'grad_norm': 0.6823379993438721, 'learning_rate': 0.00016878773803994429, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1014/6464 [18:17<1:36:33, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4538, 'grad_norm': 0.7676555514335632, 'learning_rate': 0.00016875677349434897, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1015/6464 [18:18<1:37:20, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5022, 'grad_norm': 0.626075267791748, 'learning_rate': 0.00016872580894875368, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1016/6464 [18:19<1:36:29, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.309, 'grad_norm': 0.7269840836524963, 'learning_rate': 0.0001686948444031584, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1017/6464 [18:20<1:31:30, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2682, 'grad_norm': 0.809637725353241, 'learning_rate': 0.00016866387985756308, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1018/6464 [18:21<1:29:54, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3818, 'grad_norm': 0.7251566052436829, 'learning_rate': 0.00016863291531196782, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1019/6464 [18:22<1:42:18, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4846, 'grad_norm': 0.6357067227363586, 'learning_rate': 0.0001686019507663725, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1020/6464 [18:23<1:41:22, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1391, 'grad_norm': 0.6112419962882996, 'learning_rate': 0.00016857098622077724, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1021/6464 [18:24<1:39:33, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2992, 'grad_norm': 0.6750810146331787, 'learning_rate': 0.00016854002167518192, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1022/6464 [18:26<1:44:37, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3726, 'grad_norm': 0.6048667430877686, 'learning_rate': 0.00016850905712958663, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1023/6464 [18:27<1:38:52, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9771, 'grad_norm': 0.6320006847381592, 'learning_rate': 0.00016847809258399134, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1024/6464 [18:28<1:38:14, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3596, 'grad_norm': 0.7662308812141418, 'learning_rate': 0.00016844712803839603, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1025/6464 [18:29<1:38:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.282, 'grad_norm': 0.7348275780677795, 'learning_rate': 0.00016841616349280077, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1026/6464 [18:30<1:36:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2711, 'grad_norm': 0.7169001698493958, 'learning_rate': 0.00016838519894720545, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1027/6464 [18:31<1:36:48, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2279, 'grad_norm': 0.6673872470855713, 'learning_rate': 0.00016835423440161016, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1028/6464 [18:32<1:35:37, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1041, 'grad_norm': 0.6596084237098694, 'learning_rate': 0.00016832326985601487, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1029/6464 [18:33<1:35:15, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2255, 'grad_norm': 0.644482433795929, 'learning_rate': 0.00016829230531041959, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1030/6464 [18:34<1:34:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2123, 'grad_norm': 0.6886928677558899, 'learning_rate': 0.0001682613407648243, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1031/6464 [18:35<1:31:20, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1578, 'grad_norm': 0.7429509162902832, 'learning_rate': 0.00016823037621922898, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1032/6464 [18:36<1:37:35, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2933, 'grad_norm': 0.6499183177947998, 'learning_rate': 0.0001681994116736337, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1033/6464 [18:37<1:38:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3101, 'grad_norm': 0.5713036060333252, 'learning_rate': 0.0001681684471280384, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1034/6464 [18:39<1:44:15, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4239, 'grad_norm': 0.6731314063072205, 'learning_rate': 0.00016813748258244312, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1035/6464 [18:40<1:44:34, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1723, 'grad_norm': 0.5770828723907471, 'learning_rate': 0.00016810651803684783, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1036/6464 [18:41<1:41:00, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.332, 'grad_norm': 0.6199793815612793, 'learning_rate': 0.0001680755534912525, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1037/6464 [18:42<1:40:23, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0821, 'grad_norm': 0.607599675655365, 'learning_rate': 0.00016804458894565722, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1038/6464 [18:43<1:39:50, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.194, 'grad_norm': 0.6184940934181213, 'learning_rate': 0.00016801362440006193, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1039/6464 [18:44<1:36:10, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2244, 'grad_norm': 0.69674152135849, 'learning_rate': 0.00016798265985446665, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1040/6464 [18:45<1:35:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3348, 'grad_norm': 0.6957740783691406, 'learning_rate': 0.00016795169530887136, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1041/6464 [18:46<1:38:22, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2682, 'grad_norm': 0.5796874761581421, 'learning_rate': 0.00016792073076327607, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1042/6464 [18:47<1:34:16, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2354, 'grad_norm': 0.8035773038864136, 'learning_rate': 0.00016788976621768075, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1043/6464 [18:48<1:34:05, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3047, 'grad_norm': 0.6727426052093506, 'learning_rate': 0.00016785880167208546, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1044/6464 [18:49<1:31:36, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0954, 'grad_norm': 0.6634526252746582, 'learning_rate': 0.00016782783712649017, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1045/6464 [18:50<1:33:28, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2373, 'grad_norm': 0.7403863072395325, 'learning_rate': 0.00016779687258089489, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1046/6464 [18:51<1:37:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2946, 'grad_norm': 0.7127357721328735, 'learning_rate': 0.0001677659080352996, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1047/6464 [18:53<1:43:20, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.7085, 'grad_norm': 0.6847476959228516, 'learning_rate': 0.00016773494348970428, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1048/6464 [18:54<1:47:52, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.355, 'grad_norm': 0.6294713616371155, 'learning_rate': 0.00016770397894410902, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1049/6464 [18:55<1:45:54, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1953, 'grad_norm': 0.6495004892349243, 'learning_rate': 0.0001676730143985137, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–Œ | 1050/6464 [18:56<1:42:55, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2463, 'grad_norm': 0.7145437002182007, 'learning_rate': 0.00016764204985291842, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1051/6464 [18:57<1:40:46, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2539, 'grad_norm': 0.583686113357544, 'learning_rate': 0.00016761108530732313, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1052/6464 [18:58<1:34:50, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0149, 'grad_norm': 0.7178903818130493, 'learning_rate': 0.0001675801207617278, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1053/6464 [18:59<1:34:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3124, 'grad_norm': 0.6741315722465515, 'learning_rate': 0.00016754915621613255, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1054/6464 [19:00<1:33:18, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1946, 'grad_norm': 0.6510870456695557, 'learning_rate': 0.00016751819167053723, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1055/6464 [19:01<1:38:47, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.288, 'grad_norm': 0.572540283203125, 'learning_rate': 0.00016748722712494195, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1056/6464 [19:02<1:35:37, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.316, 'grad_norm': 0.6368159651756287, 'learning_rate': 0.00016745626257934666, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1057/6464 [19:03<1:36:53, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4251, 'grad_norm': 0.7091423869132996, 'learning_rate': 0.00016742529803375134, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1058/6464 [19:04<1:35:28, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3261, 'grad_norm': 0.6624607443809509, 'learning_rate': 0.00016739433348815608, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1059/6464 [19:06<1:36:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1557, 'grad_norm': 0.6099175214767456, 'learning_rate': 0.00016736336894256076, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1060/6464 [19:07<1:35:31, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.314, 'grad_norm': 0.6366916298866272, 'learning_rate': 0.0001673324043969655, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1061/6464 [19:08<1:36:33, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2798, 'grad_norm': 0.6700979471206665, 'learning_rate': 0.0001673014398513702, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1062/6464 [19:09<1:41:56, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2365, 'grad_norm': 0.6491148471832275, 'learning_rate': 0.0001672704753057749, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1063/6464 [19:10<1:42:54, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1951, 'grad_norm': 0.5968238115310669, 'learning_rate': 0.0001672395107601796, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1064/6464 [19:11<1:38:52, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2561, 'grad_norm': 0.7381719946861267, 'learning_rate': 0.0001672085462145843, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1065/6464 [19:12<1:33:25, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0726, 'grad_norm': 0.7183232307434082, 'learning_rate': 0.00016717758166898903, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 16%|โ–ˆโ–‹ | 1066/6464 [19:13<1:32:24, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1358, 'grad_norm': 0.723585844039917, 'learning_rate': 0.00016714661712339372, 'epoch': 0.16}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1067/6464 [19:14<1:30:57, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1724, 'grad_norm': 0.7641095519065857, 'learning_rate': 0.00016711565257779843, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1068/6464 [19:15<1:32:51, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5527, 'grad_norm': 1.0566219091415405, 'learning_rate': 0.00016708468803220314, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1069/6464 [19:16<1:31:38, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2679, 'grad_norm': 0.7364678382873535, 'learning_rate': 0.00016705372348660785, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1070/6464 [19:17<1:39:08, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3026, 'grad_norm': 0.5922139286994934, 'learning_rate': 0.00016702275894101256, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1071/6464 [19:18<1:33:49, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3508, 'grad_norm': 0.7387281656265259, 'learning_rate': 0.00016699179439541725, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1072/6464 [19:19<1:36:16, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2737, 'grad_norm': 0.6414243578910828, 'learning_rate': 0.00016696082984982196, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1073/6464 [19:20<1:30:59, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0035, 'grad_norm': 0.7747313976287842, 'learning_rate': 0.00016692986530422667, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1074/6464 [19:21<1:28:56, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0874, 'grad_norm': 0.6679930090904236, 'learning_rate': 0.00016689890075863138, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1075/6464 [19:22<1:30:29, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2134, 'grad_norm': 0.6160483360290527, 'learning_rate': 0.0001668679362130361, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1076/6464 [19:23<1:29:36, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0671, 'grad_norm': 0.6787537336349487, 'learning_rate': 0.00016683697166744078, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1077/6464 [19:24<1:34:52, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2896, 'grad_norm': 0.8499875664710999, 'learning_rate': 0.0001668060071218455, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1078/6464 [19:26<1:38:35, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2208, 'grad_norm': 0.727834165096283, 'learning_rate': 0.0001667750425762502, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1079/6464 [19:27<1:35:53, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3239, 'grad_norm': 0.7146049737930298, 'learning_rate': 0.0001667440780306549, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1080/6464 [19:28<1:37:55, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3338, 'grad_norm': 0.6561218500137329, 'learning_rate': 0.00016671311348505962, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1081/6464 [19:29<1:35:08, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1594, 'grad_norm': 0.7516222596168518, 'learning_rate': 0.00016668214893946433, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1082/6464 [19:30<1:36:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3009, 'grad_norm': 0.6560037732124329, 'learning_rate': 0.00016665118439386902, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1083/6464 [19:31<1:36:37, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1135, 'grad_norm': 0.633585512638092, 'learning_rate': 0.00016662021984827373, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1084/6464 [19:32<1:39:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4368, 'grad_norm': 0.6277974843978882, 'learning_rate': 0.00016658925530267844, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1085/6464 [19:33<1:35:35, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1251, 'grad_norm': 0.6698349714279175, 'learning_rate': 0.00016655829075708315, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1086/6464 [19:34<1:33:13, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2769, 'grad_norm': 0.8174813985824585, 'learning_rate': 0.00016652732621148786, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1087/6464 [19:35<1:32:10, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2351, 'grad_norm': 0.694889485836029, 'learning_rate': 0.00016649636166589255, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1088/6464 [19:36<1:35:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3427, 'grad_norm': 0.6126196384429932, 'learning_rate': 0.00016646539712029728, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1089/6464 [19:37<1:32:09, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2206, 'grad_norm': 0.6505956053733826, 'learning_rate': 0.00016643443257470197, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1090/6464 [19:38<1:36:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3715, 'grad_norm': 0.6780340075492859, 'learning_rate': 0.00016640346802910668, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1091/6464 [19:40<1:38:11, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3734, 'grad_norm': 0.6447031497955322, 'learning_rate': 0.0001663725034835114, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1092/6464 [19:41<1:38:48, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4825, 'grad_norm': 0.6198911070823669, 'learning_rate': 0.00016634153893791608, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1093/6464 [19:42<1:41:50, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8496, 'grad_norm': 0.5614982843399048, 'learning_rate': 0.00016631057439232081, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1094/6464 [19:43<1:38:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4261, 'grad_norm': 0.651168704032898, 'learning_rate': 0.0001662796098467255, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1095/6464 [19:44<1:35:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0533, 'grad_norm': 0.6769419312477112, 'learning_rate': 0.0001662486453011302, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1096/6464 [19:45<1:38:23, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3345, 'grad_norm': 0.5981125235557556, 'learning_rate': 0.00016621768075553492, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1097/6464 [19:46<1:37:49, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1179, 'grad_norm': 0.5892458558082581, 'learning_rate': 0.0001661867162099396, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1098/6464 [19:47<1:34:23, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1987, 'grad_norm': 0.684824526309967, 'learning_rate': 0.00016615575166434434, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1099/6464 [19:48<1:29:44, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2877, 'grad_norm': 0.7009289860725403, 'learning_rate': 0.00016612478711874903, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1100/6464 [19:49<1:34:43, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1157, 'grad_norm': 0.6628972291946411, 'learning_rate': 0.00016609382257315377, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1101/6464 [19:50<1:33:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1687, 'grad_norm': 0.6807486414909363, 'learning_rate': 0.00016606285802755845, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1102/6464 [19:51<1:33:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2536, 'grad_norm': 0.6344581246376038, 'learning_rate': 0.00016603189348196316, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1103/6464 [19:52<1:32:04, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2568, 'grad_norm': 0.6462639570236206, 'learning_rate': 0.00016600092893636787, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1104/6464 [19:53<1:31:16, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3668, 'grad_norm': 0.6929206848144531, 'learning_rate': 0.00016596996439077256, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1105/6464 [19:54<1:32:49, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2263, 'grad_norm': 0.6396748423576355, 'learning_rate': 0.0001659389998451773, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1106/6464 [19:55<1:31:41, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2838, 'grad_norm': 0.6749036908149719, 'learning_rate': 0.00016590803529958198, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1107/6464 [19:56<1:32:10, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3746, 'grad_norm': 0.7071032524108887, 'learning_rate': 0.0001658770707539867, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1108/6464 [19:58<1:44:15, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1505, 'grad_norm': 0.5552220940589905, 'learning_rate': 0.0001658461062083914, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1109/6464 [19:59<1:38:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2226, 'grad_norm': 0.6827331781387329, 'learning_rate': 0.00016581514166279611, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1110/6464 [20:00<1:35:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1766, 'grad_norm': 0.6575499176979065, 'learning_rate': 0.00016578417711720083, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1111/6464 [20:01<1:40:19, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4241, 'grad_norm': 0.6173574328422546, 'learning_rate': 0.0001657532125716055, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1112/6464 [20:02<1:41:18, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.223, 'grad_norm': 0.7000895738601685, 'learning_rate': 0.00016572224802601022, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1113/6464 [20:03<1:38:38, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1832, 'grad_norm': 0.6658180356025696, 'learning_rate': 0.00016569128348041493, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1114/6464 [20:04<1:34:28, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3009, 'grad_norm': 0.8094417452812195, 'learning_rate': 0.00016566031893481964, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1115/6464 [20:05<1:30:46, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3481, 'grad_norm': 0.8197205066680908, 'learning_rate': 0.00016562935438922436, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1116/6464 [20:06<1:32:18, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.284, 'grad_norm': 0.6921061873435974, 'learning_rate': 0.00016559838984362904, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1117/6464 [20:07<1:27:58, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1627, 'grad_norm': 0.7112550139427185, 'learning_rate': 0.00016556742529803375, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1118/6464 [20:08<1:26:29, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3854, 'grad_norm': 0.7594210505485535, 'learning_rate': 0.00016553646075243846, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1119/6464 [20:09<1:34:19, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5354, 'grad_norm': 0.6119380593299866, 'learning_rate': 0.00016550549620684317, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1120/6464 [20:10<1:33:17, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0181, 'grad_norm': 0.588208794593811, 'learning_rate': 0.00016547453166124789, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1121/6464 [20:11<1:30:38, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2005, 'grad_norm': 0.7522181272506714, 'learning_rate': 0.0001654435671156526, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1122/6464 [20:12<1:31:17, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2227, 'grad_norm': 0.7105264663696289, 'learning_rate': 0.00016541260257005728, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1123/6464 [20:13<1:28:27, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2518, 'grad_norm': 0.7409966588020325, 'learning_rate': 0.000165381638024462, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1124/6464 [20:14<1:31:37, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2912, 'grad_norm': 0.6325370073318481, 'learning_rate': 0.0001653506734788667, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1125/6464 [20:15<1:29:30, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9779, 'grad_norm': 0.6317875385284424, 'learning_rate': 0.00016531970893327142, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1126/6464 [20:16<1:28:58, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3285, 'grad_norm': 0.7246634364128113, 'learning_rate': 0.00016528874438767613, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1127/6464 [20:17<1:28:06, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2194, 'grad_norm': 0.6862521767616272, 'learning_rate': 0.0001652577798420808, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1128/6464 [20:18<1:32:35, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0334, 'grad_norm': 0.5518355369567871, 'learning_rate': 0.00016522681529648555, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1129/6464 [20:20<1:36:37, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2433, 'grad_norm': 0.6914048194885254, 'learning_rate': 0.00016519585075089023, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1130/6464 [20:21<1:43:24, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3635, 'grad_norm': 0.6111675500869751, 'learning_rate': 0.00016516488620529495, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 17%|โ–ˆโ–‹ | 1131/6464 [20:22<1:47:57, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3479, 'grad_norm': 0.5941988825798035, 'learning_rate': 0.00016513392165969966, 'epoch': 0.17}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1132/6464 [20:23<1:45:49, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2786, 'grad_norm': 0.6099510192871094, 'learning_rate': 0.00016510295711410434, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1133/6464 [20:24<1:40:36, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4088, 'grad_norm': 0.6847008466720581, 'learning_rate': 0.00016507199256850908, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1134/6464 [20:25<1:36:55, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9924, 'grad_norm': 0.7401003241539001, 'learning_rate': 0.00016504102802291376, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1135/6464 [20:26<1:33:57, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2849, 'grad_norm': 0.7006213068962097, 'learning_rate': 0.0001650100634773185, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1136/6464 [20:27<1:34:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.391, 'grad_norm': 0.7470983862876892, 'learning_rate': 0.00016497909893172319, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1137/6464 [20:28<1:34:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2821, 'grad_norm': 0.6761350631713867, 'learning_rate': 0.00016494813438612787, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1138/6464 [20:29<1:32:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1275, 'grad_norm': 0.7275453805923462, 'learning_rate': 0.0001649171698405326, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1139/6464 [20:30<1:32:09, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2625, 'grad_norm': 0.6367722749710083, 'learning_rate': 0.0001648862052949373, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1140/6464 [20:31<1:31:12, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3262, 'grad_norm': 0.7159121632575989, 'learning_rate': 0.00016485524074934203, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1141/6464 [20:33<1:34:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2756, 'grad_norm': 0.5977429747581482, 'learning_rate': 0.00016482427620374672, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1142/6464 [20:34<1:31:49, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3675, 'grad_norm': 0.7561242580413818, 'learning_rate': 0.00016479331165815143, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1143/6464 [20:35<1:31:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4819, 'grad_norm': 0.7401590943336487, 'learning_rate': 0.00016476234711255614, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1144/6464 [20:36<1:31:05, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1008, 'grad_norm': 0.6319532990455627, 'learning_rate': 0.00016473138256696082, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1145/6464 [20:37<1:26:40, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.966, 'grad_norm': 0.7793903350830078, 'learning_rate': 0.00016470041802136556, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1146/6464 [20:38<1:31:45, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3311, 'grad_norm': 0.669772207736969, 'learning_rate': 0.00016466945347577025, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1147/6464 [20:39<1:38:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2531, 'grad_norm': 0.6499928832054138, 'learning_rate': 0.00016463848893017496, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1148/6464 [20:40<1:32:03, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1034, 'grad_norm': 0.664147138595581, 'learning_rate': 0.00016460752438457967, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1149/6464 [20:41<1:32:37, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1985, 'grad_norm': 0.6713077425956726, 'learning_rate': 0.00016457655983898438, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1150/6464 [20:42<1:40:45, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5912, 'grad_norm': 0.5987495183944702, 'learning_rate': 0.0001645455952933891, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1151/6464 [20:43<1:37:35, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2549, 'grad_norm': 0.7973735928535461, 'learning_rate': 0.00016451463074779378, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1152/6464 [20:44<1:35:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2241, 'grad_norm': 0.7245017886161804, 'learning_rate': 0.00016448366620219849, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1153/6464 [20:45<1:37:03, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2087, 'grad_norm': 0.5973483920097351, 'learning_rate': 0.0001644527016566032, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1154/6464 [20:47<1:39:48, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4646, 'grad_norm': 0.7414206266403198, 'learning_rate': 0.0001644217371110079, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1155/6464 [20:48<1:35:18, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1193, 'grad_norm': 0.6737897992134094, 'learning_rate': 0.00016439077256541262, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1156/6464 [20:49<1:37:18, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2702, 'grad_norm': 0.6543324589729309, 'learning_rate': 0.00016435980801981733, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1157/6464 [20:50<1:42:22, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3896, 'grad_norm': 0.7568091750144958, 'learning_rate': 0.00016432884347422202, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1158/6464 [20:51<1:38:37, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2959, 'grad_norm': 0.6853204369544983, 'learning_rate': 0.00016429787892862673, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1159/6464 [20:52<1:35:23, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1405, 'grad_norm': 0.639733076095581, 'learning_rate': 0.00016426691438303144, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1160/6464 [20:53<1:33:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0407, 'grad_norm': 0.6835911870002747, 'learning_rate': 0.00016423594983743615, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1161/6464 [20:54<1:36:33, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2205, 'grad_norm': 0.7174513339996338, 'learning_rate': 0.00016420498529184086, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1162/6464 [20:55<1:34:11, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2896, 'grad_norm': 0.770932674407959, 'learning_rate': 0.00016417402074624555, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1163/6464 [20:56<1:39:31, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1485, 'grad_norm': 0.6140007376670837, 'learning_rate': 0.00016414305620065026, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1164/6464 [20:57<1:33:30, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1185, 'grad_norm': 0.7903020977973938, 'learning_rate': 0.00016411209165505497, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1165/6464 [20:59<1:42:07, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.393, 'grad_norm': 0.6401047110557556, 'learning_rate': 0.00016408112710945968, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1166/6464 [21:00<1:39:07, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2774, 'grad_norm': 0.6866500973701477, 'learning_rate': 0.0001640501625638644, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1167/6464 [21:01<1:33:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3779, 'grad_norm': 0.859097957611084, 'learning_rate': 0.00016401919801826908, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1168/6464 [21:02<1:33:29, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2534, 'grad_norm': 0.6785029768943787, 'learning_rate': 0.00016398823347267381, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1169/6464 [21:03<1:35:38, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5892, 'grad_norm': 0.6587054133415222, 'learning_rate': 0.0001639572689270785, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1170/6464 [21:04<1:36:58, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3874, 'grad_norm': 0.6697266697883606, 'learning_rate': 0.0001639263043814832, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1171/6464 [21:05<1:32:16, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9892, 'grad_norm': 0.701181173324585, 'learning_rate': 0.00016389533983588792, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1172/6464 [21:06<1:36:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2781, 'grad_norm': 0.5927637815475464, 'learning_rate': 0.0001638643752902926, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1173/6464 [21:07<1:32:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9842, 'grad_norm': 0.6442838311195374, 'learning_rate': 0.00016383341074469734, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1174/6464 [21:08<1:33:26, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.149, 'grad_norm': 0.6278336048126221, 'learning_rate': 0.00016380244619910203, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1175/6464 [21:09<1:32:39, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8577, 'grad_norm': 0.5610106587409973, 'learning_rate': 0.00016377148165350677, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1176/6464 [21:10<1:34:18, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3327, 'grad_norm': 0.6931418776512146, 'learning_rate': 0.00016374051710791145, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1177/6464 [21:12<1:39:08, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3858, 'grad_norm': 0.7038500905036926, 'learning_rate': 0.00016370955256231616, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1178/6464 [21:13<1:35:38, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2838, 'grad_norm': 0.787181556224823, 'learning_rate': 0.00016367858801672087, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1179/6464 [21:14<1:36:59, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3162, 'grad_norm': 0.6524350047111511, 'learning_rate': 0.00016364762347112556, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1180/6464 [21:15<1:39:03, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2132, 'grad_norm': 0.6753104329109192, 'learning_rate': 0.0001636166589255303, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1181/6464 [21:16<1:43:58, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2346, 'grad_norm': 0.5568897724151611, 'learning_rate': 0.00016358569437993498, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1182/6464 [21:17<1:43:01, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2171, 'grad_norm': 0.6637329459190369, 'learning_rate': 0.0001635547298343397, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1183/6464 [21:18<1:37:44, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3357, 'grad_norm': 0.6777571439743042, 'learning_rate': 0.0001635237652887444, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1184/6464 [21:19<1:37:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2853, 'grad_norm': 0.6111904382705688, 'learning_rate': 0.0001634928007431491, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1185/6464 [21:21<1:41:51, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4126, 'grad_norm': 0.6159718632698059, 'learning_rate': 0.00016346183619755383, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1186/6464 [21:22<1:45:22, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4509, 'grad_norm': 0.6456118226051331, 'learning_rate': 0.0001634308716519585, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1187/6464 [21:23<1:42:16, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3697, 'grad_norm': 0.7194255590438843, 'learning_rate': 0.00016339990710636322, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1188/6464 [21:24<1:44:05, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1516, 'grad_norm': 0.7116672396659851, 'learning_rate': 0.00016336894256076793, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1189/6464 [21:26<1:43:34, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2354, 'grad_norm': 0.7308868765830994, 'learning_rate': 0.00016333797801517264, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1190/6464 [21:26<1:37:20, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9652, 'grad_norm': 0.6081112027168274, 'learning_rate': 0.00016330701346957736, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1191/6464 [21:27<1:34:58, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1418, 'grad_norm': 0.650433361530304, 'learning_rate': 0.00016327604892398204, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1192/6464 [21:29<1:35:17, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2105, 'grad_norm': 0.6867871880531311, 'learning_rate': 0.00016324508437838675, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1193/6464 [21:30<1:32:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.205, 'grad_norm': 0.6548858880996704, 'learning_rate': 0.00016321411983279146, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1194/6464 [21:31<1:31:18, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0643, 'grad_norm': 0.6592373251914978, 'learning_rate': 0.00016318315528719617, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 18%|โ–ˆโ–Š | 1195/6464 [21:32<1:33:54, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.304, 'grad_norm': 0.6204409003257751, 'learning_rate': 0.00016315219074160088, 'epoch': 0.18}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1196/6464 [21:33<1:35:32, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2578, 'grad_norm': 0.6806817054748535, 'learning_rate': 0.0001631212261960056, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1197/6464 [21:34<1:32:52, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1348, 'grad_norm': 0.6285042762756348, 'learning_rate': 0.00016309026165041028, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1198/6464 [21:35<1:34:48, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1279, 'grad_norm': 0.6363532543182373, 'learning_rate': 0.000163059297104815, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1199/6464 [21:36<1:33:42, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1327, 'grad_norm': 0.7297397255897522, 'learning_rate': 0.0001630283325592197, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1200/6464 [21:37<1:45:02, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4041, 'grad_norm': 0.5907027125358582, 'learning_rate': 0.00016299736801362441, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1201/6464 [21:39<1:57:28, 1.34s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.7511, 'grad_norm': 0.5920285582542419, 'learning_rate': 0.00016296640346802913, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1202/6464 [21:40<1:54:02, 1.30s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1501, 'grad_norm': 0.5720888376235962, 'learning_rate': 0.0001629354389224338, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1203/6464 [21:42<1:49:41, 1.25s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2283, 'grad_norm': 0.7137517929077148, 'learning_rate': 0.00016290447437683852, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1204/6464 [21:43<1:44:00, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3267, 'grad_norm': 0.7419721484184265, 'learning_rate': 0.00016287350983124323, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1205/6464 [21:44<1:43:48, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4649, 'grad_norm': 0.6505071520805359, 'learning_rate': 0.00016284254528564794, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1206/6464 [21:45<1:41:37, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3979, 'grad_norm': 0.6785904765129089, 'learning_rate': 0.00016281158074005266, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1207/6464 [21:46<1:41:14, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3167, 'grad_norm': 0.6897298097610474, 'learning_rate': 0.00016278061619445734, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1208/6464 [21:47<1:41:14, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.36, 'grad_norm': 0.6154904961585999, 'learning_rate': 0.00016274965164886208, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1209/6464 [21:48<1:38:34, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1068, 'grad_norm': 0.6825777888298035, 'learning_rate': 0.00016271868710326676, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1210/6464 [21:49<1:41:18, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4204, 'grad_norm': 0.6963024139404297, 'learning_rate': 0.00016268772255767147, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–Š | 1211/6464 [21:50<1:36:31, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2989, 'grad_norm': 0.6820192933082581, 'learning_rate': 0.00016265675801207619, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1212/6464 [21:52<1:37:22, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2259, 'grad_norm': 0.680338442325592, 'learning_rate': 0.00016262579346648087, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1213/6464 [21:53<1:35:18, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2389, 'grad_norm': 0.6815621852874756, 'learning_rate': 0.0001625948289208856, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1214/6464 [21:54<1:38:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6039, 'grad_norm': 0.6476475596427917, 'learning_rate': 0.0001625638643752903, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1215/6464 [21:55<1:32:49, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1469, 'grad_norm': 0.7290582656860352, 'learning_rate': 0.00016253289982969503, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1216/6464 [21:56<1:29:32, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2072, 'grad_norm': 0.7274240851402283, 'learning_rate': 0.00016250193528409972, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1217/6464 [21:56<1:24:59, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1605, 'grad_norm': 0.7088478803634644, 'learning_rate': 0.00016247097073850443, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1218/6464 [21:58<1:29:20, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2471, 'grad_norm': 0.6422321200370789, 'learning_rate': 0.00016244000619290914, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1219/6464 [21:59<1:31:29, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1311, 'grad_norm': 0.7911797761917114, 'learning_rate': 0.00016240904164731382, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1220/6464 [22:00<1:35:01, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.408, 'grad_norm': 0.5906097888946533, 'learning_rate': 0.00016237807710171856, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1221/6464 [22:01<1:37:32, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.239, 'grad_norm': 0.6328639388084412, 'learning_rate': 0.00016234711255612324, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1222/6464 [22:02<1:35:48, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3018, 'grad_norm': 0.6082860231399536, 'learning_rate': 0.00016231614801052796, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1223/6464 [22:03<1:41:02, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1, 'grad_norm': 0.6856006979942322, 'learning_rate': 0.00016228518346493267, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1224/6464 [22:04<1:36:48, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2153, 'grad_norm': 0.7551881670951843, 'learning_rate': 0.00016225421891933735, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1225/6464 [22:06<1:36:50, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4072, 'grad_norm': 0.6317940950393677, 'learning_rate': 0.0001622232543737421, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1226/6464 [22:07<1:38:51, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1959, 'grad_norm': 0.5526986122131348, 'learning_rate': 0.00016219228982814677, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1227/6464 [22:08<1:35:26, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.092, 'grad_norm': 0.6616318225860596, 'learning_rate': 0.00016216132528255149, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1228/6464 [22:09<1:32:09, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1795, 'grad_norm': 0.6385276913642883, 'learning_rate': 0.0001621303607369562, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1229/6464 [22:10<1:32:48, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2828, 'grad_norm': 0.6673714518547058, 'learning_rate': 0.0001620993961913609, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1230/6464 [22:11<1:30:49, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0544, 'grad_norm': 0.739454448223114, 'learning_rate': 0.00016206843164576562, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1231/6464 [22:12<1:28:07, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0404, 'grad_norm': 0.6982868909835815, 'learning_rate': 0.0001620374671001703, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1232/6464 [22:13<1:33:49, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5295, 'grad_norm': 0.6346362829208374, 'learning_rate': 0.00016200650255457502, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1233/6464 [22:14<1:32:10, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0239, 'grad_norm': 0.572722315788269, 'learning_rate': 0.00016197553800897973, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1234/6464 [22:15<1:32:32, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2892, 'grad_norm': 0.6865055561065674, 'learning_rate': 0.00016194457346338444, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1235/6464 [22:16<1:30:58, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2079, 'grad_norm': 0.6975094079971313, 'learning_rate': 0.00016191360891778915, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1236/6464 [22:17<1:29:38, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0166, 'grad_norm': 0.6835157871246338, 'learning_rate': 0.00016188264437219386, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1237/6464 [22:18<1:31:48, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1739, 'grad_norm': 0.5843218564987183, 'learning_rate': 0.00016185167982659855, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1238/6464 [22:19<1:28:24, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2072, 'grad_norm': 0.6482160687446594, 'learning_rate': 0.00016182071528100326, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1239/6464 [22:20<1:30:18, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1365, 'grad_norm': 0.5994418859481812, 'learning_rate': 0.00016178975073540797, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1240/6464 [22:21<1:28:13, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1383, 'grad_norm': 0.7678951025009155, 'learning_rate': 0.00016175878618981268, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1241/6464 [22:22<1:28:24, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3615, 'grad_norm': 0.7155693173408508, 'learning_rate': 0.0001617278216442174, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1242/6464 [22:23<1:32:49, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4856, 'grad_norm': 0.7157745361328125, 'learning_rate': 0.00016169685709862207, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1243/6464 [22:24<1:33:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0075, 'grad_norm': 0.6526820063591003, 'learning_rate': 0.00016166589255302679, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1244/6464 [22:25<1:29:12, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0743, 'grad_norm': 0.7517542839050293, 'learning_rate': 0.0001616349280074315, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1245/6464 [22:26<1:29:54, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2737, 'grad_norm': 0.6211302280426025, 'learning_rate': 0.0001616039634618362, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1246/6464 [22:27<1:31:05, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1114, 'grad_norm': 0.6691896319389343, 'learning_rate': 0.00016157299891624092, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1247/6464 [22:29<1:39:19, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2836, 'grad_norm': 0.6259803175926208, 'learning_rate': 0.0001615420343706456, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1248/6464 [22:30<1:43:42, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.367, 'grad_norm': 0.5972505807876587, 'learning_rate': 0.00016151106982505034, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1249/6464 [22:31<1:44:24, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3278, 'grad_norm': 0.575127363204956, 'learning_rate': 0.00016148010527945503, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1250/6464 [22:32<1:36:34, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1661, 'grad_norm': 0.7697415351867676, 'learning_rate': 0.00016144914073385974, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1251/6464 [22:33<1:39:39, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1718, 'grad_norm': 0.5824877023696899, 'learning_rate': 0.00016141817618826445, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1252/6464 [22:35<1:38:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0654, 'grad_norm': 0.6562953591346741, 'learning_rate': 0.00016138721164266913, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1253/6464 [22:35<1:32:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2344, 'grad_norm': 0.7341590523719788, 'learning_rate': 0.00016135624709707387, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1254/6464 [22:37<1:35:31, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6171, 'grad_norm': 0.709833562374115, 'learning_rate': 0.00016132528255147856, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1255/6464 [22:38<1:34:15, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3635, 'grad_norm': 0.6714110374450684, 'learning_rate': 0.00016129431800588327, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1256/6464 [22:39<1:33:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1515, 'grad_norm': 0.6003995537757874, 'learning_rate': 0.00016126335346028798, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1257/6464 [22:40<1:32:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2018, 'grad_norm': 0.6410068869590759, 'learning_rate': 0.0001612323889146927, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1258/6464 [22:41<1:29:27, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.018, 'grad_norm': 0.780199408531189, 'learning_rate': 0.0001612014243690974, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1259/6464 [22:42<1:27:03, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1423, 'grad_norm': 0.7277089357376099, 'learning_rate': 0.0001611704598235021, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 19%|โ–ˆโ–‰ | 1260/6464 [22:43<1:26:55, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3179, 'grad_norm': 0.7636054158210754, 'learning_rate': 0.0001611394952779068, 'epoch': 0.19}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1261/6464 [22:44<1:26:49, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0753, 'grad_norm': 0.7145235538482666, 'learning_rate': 0.0001611085307323115, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1262/6464 [22:45<1:32:16, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2691, 'grad_norm': 0.545897364616394, 'learning_rate': 0.00016107756618671622, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1263/6464 [22:46<1:38:18, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4532, 'grad_norm': 0.6020378470420837, 'learning_rate': 0.00016104660164112093, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1264/6464 [22:47<1:38:48, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4351, 'grad_norm': 0.6528218984603882, 'learning_rate': 0.00016101563709552562, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1265/6464 [22:48<1:34:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1249, 'grad_norm': 0.7434120178222656, 'learning_rate': 0.00016098467254993033, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1266/6464 [22:49<1:34:58, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2694, 'grad_norm': 0.6759999990463257, 'learning_rate': 0.00016095370800433504, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1267/6464 [22:51<1:34:25, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2863, 'grad_norm': 0.6840894818305969, 'learning_rate': 0.00016092274345873975, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1268/6464 [22:52<1:32:11, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1352, 'grad_norm': 0.7227759957313538, 'learning_rate': 0.00016089177891314446, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1269/6464 [22:53<1:32:57, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4515, 'grad_norm': 0.6536543965339661, 'learning_rate': 0.00016086081436754917, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1270/6464 [22:54<1:31:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0889, 'grad_norm': 0.7137835025787354, 'learning_rate': 0.00016082984982195386, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1271/6464 [22:55<1:27:31, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2659, 'grad_norm': 0.8897273540496826, 'learning_rate': 0.00016079888527635857, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1272/6464 [22:56<1:32:30, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2172, 'grad_norm': 0.8051400184631348, 'learning_rate': 0.00016076792073076328, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1273/6464 [22:57<1:31:57, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2435, 'grad_norm': 0.6370776295661926, 'learning_rate': 0.000160736956185168, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1274/6464 [22:58<1:29:46, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3125, 'grad_norm': 0.7557817101478577, 'learning_rate': 0.0001607059916395727, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1275/6464 [22:59<1:33:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4485, 'grad_norm': 0.7118207812309265, 'learning_rate': 0.0001606750270939774, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1276/6464 [23:00<1:33:50, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.183, 'grad_norm': 0.8120574951171875, 'learning_rate': 0.00016064406254838213, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1277/6464 [23:01<1:36:37, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3422, 'grad_norm': 0.699009895324707, 'learning_rate': 0.0001606130980027868, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1278/6464 [23:02<1:36:50, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3307, 'grad_norm': 0.6051947474479675, 'learning_rate': 0.00016058213345719152, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1279/6464 [23:03<1:34:38, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2021, 'grad_norm': 0.6619096994400024, 'learning_rate': 0.00016055116891159623, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1280/6464 [23:04<1:33:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1012, 'grad_norm': 0.6227601766586304, 'learning_rate': 0.00016052020436600092, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1281/6464 [23:06<1:34:12, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1692, 'grad_norm': 0.6502869129180908, 'learning_rate': 0.00016048923982040565, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1282/6464 [23:06<1:29:15, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1845, 'grad_norm': 0.6981345415115356, 'learning_rate': 0.00016045827527481034, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1283/6464 [23:08<1:36:17, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1249, 'grad_norm': 0.5552336573600769, 'learning_rate': 0.00016042731072921505, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1284/6464 [23:09<1:37:06, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2014, 'grad_norm': 0.669259786605835, 'learning_rate': 0.00016039634618361976, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1285/6464 [23:10<1:43:49, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3134, 'grad_norm': 0.6320682764053345, 'learning_rate': 0.00016036538163802445, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1286/6464 [23:11<1:36:50, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0529, 'grad_norm': 0.6909686923027039, 'learning_rate': 0.00016033441709242918, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1287/6464 [23:12<1:35:29, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1911, 'grad_norm': 0.6100388169288635, 'learning_rate': 0.00016030345254683387, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1288/6464 [23:13<1:36:58, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.335, 'grad_norm': 0.6273375749588013, 'learning_rate': 0.0001602724880012386, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1289/6464 [23:15<1:36:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1484, 'grad_norm': 0.6109949946403503, 'learning_rate': 0.0001602415234556433, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1290/6464 [23:15<1:31:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3186, 'grad_norm': 0.704802930355072, 'learning_rate': 0.000160210558910048, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1291/6464 [23:17<1:32:58, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2231, 'grad_norm': 0.6551849246025085, 'learning_rate': 0.00016017959436445271, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–‰ | 1292/6464 [23:18<1:29:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2389, 'grad_norm': 0.6735955476760864, 'learning_rate': 0.0001601486298188574, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1293/6464 [23:19<1:26:45, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0252, 'grad_norm': 0.779159426689148, 'learning_rate': 0.00016011766527326214, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1294/6464 [23:20<1:28:43, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3946, 'grad_norm': 0.7497272491455078, 'learning_rate': 0.00016008670072766682, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1295/6464 [23:21<1:29:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2859, 'grad_norm': 0.6676772832870483, 'learning_rate': 0.00016005573618207153, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1296/6464 [23:22<1:30:59, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4608, 'grad_norm': 0.6619618535041809, 'learning_rate': 0.00016002477163647624, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1297/6464 [23:23<1:32:01, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3878, 'grad_norm': 0.6405979990959167, 'learning_rate': 0.00015999380709088096, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1298/6464 [23:24<1:28:54, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2063, 'grad_norm': 0.7581241130828857, 'learning_rate': 0.00015996284254528567, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1299/6464 [23:25<1:29:52, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4537, 'grad_norm': 0.7916601896286011, 'learning_rate': 0.00015993187799969035, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1300/6464 [23:26<1:26:00, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2735, 'grad_norm': 0.766437828540802, 'learning_rate': 0.00015990091345409506, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1301/6464 [23:27<1:30:41, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1388, 'grad_norm': 0.6646949648857117, 'learning_rate': 0.00015986994890849977, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1302/6464 [23:28<1:26:39, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1432, 'grad_norm': 0.6985604763031006, 'learning_rate': 0.00015983898436290449, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1303/6464 [23:29<1:27:28, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3224, 'grad_norm': 0.6898908615112305, 'learning_rate': 0.0001598080198173092, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1304/6464 [23:30<1:30:05, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2743, 'grad_norm': 0.6630969047546387, 'learning_rate': 0.00015977705527171388, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1305/6464 [23:31<1:35:15, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3466, 'grad_norm': 0.6850925087928772, 'learning_rate': 0.0001597460907261186, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1306/6464 [23:32<1:35:14, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2952, 'grad_norm': 0.7216028571128845, 'learning_rate': 0.0001597151261805233, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1307/6464 [23:33<1:36:08, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0911, 'grad_norm': 0.5939040184020996, 'learning_rate': 0.00015968416163492801, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1308/6464 [23:35<1:36:27, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1176, 'grad_norm': 0.6265830397605896, 'learning_rate': 0.00015965319708933273, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1309/6464 [23:36<1:40:05, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4727, 'grad_norm': 0.5722485184669495, 'learning_rate': 0.00015962223254373744, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1310/6464 [23:37<1:35:28, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1932, 'grad_norm': 0.7237120270729065, 'learning_rate': 0.00015959126799814212, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1311/6464 [23:38<1:29:54, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0679, 'grad_norm': 0.7383067011833191, 'learning_rate': 0.00015956030345254683, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1312/6464 [23:39<1:29:28, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0548, 'grad_norm': 0.633732259273529, 'learning_rate': 0.00015952933890695154, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1313/6464 [23:40<1:26:13, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0498, 'grad_norm': 0.6102151870727539, 'learning_rate': 0.00015949837436135626, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1314/6464 [23:41<1:24:31, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2692, 'grad_norm': 0.8230485916137695, 'learning_rate': 0.00015946740981576097, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1315/6464 [23:42<1:33:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2882, 'grad_norm': 0.5974907875061035, 'learning_rate': 0.00015943644527016565, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1316/6464 [23:43<1:34:05, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2177, 'grad_norm': 0.6692088842391968, 'learning_rate': 0.0001594054807245704, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1317/6464 [23:44<1:35:07, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2614, 'grad_norm': 0.746277928352356, 'learning_rate': 0.00015937451617897507, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1318/6464 [23:45<1:34:27, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1553, 'grad_norm': 0.7024368047714233, 'learning_rate': 0.00015934355163337979, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1319/6464 [23:47<1:37:36, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4874, 'grad_norm': 0.684596598148346, 'learning_rate': 0.0001593125870877845, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1320/6464 [23:48<1:35:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2275, 'grad_norm': 0.7617688775062561, 'learning_rate': 0.00015928162254218918, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1321/6464 [23:49<1:33:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1691, 'grad_norm': 0.750312328338623, 'learning_rate': 0.00015925065799659392, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1322/6464 [23:50<1:28:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2103, 'grad_norm': 0.7184588313102722, 'learning_rate': 0.0001592196934509986, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1323/6464 [23:51<1:27:18, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2378, 'grad_norm': 0.6789484620094299, 'learning_rate': 0.00015918872890540332, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1324/6464 [23:51<1:23:17, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.014, 'grad_norm': 0.9821763634681702, 'learning_rate': 0.00015915776435980803, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 20%|โ–ˆโ–ˆ | 1325/6464 [23:52<1:24:41, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2075, 'grad_norm': 0.7118375301361084, 'learning_rate': 0.0001591267998142127, 'epoch': 0.2}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1326/6464 [23:54<1:27:19, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3126, 'grad_norm': 0.731356143951416, 'learning_rate': 0.00015909583526861745, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1327/6464 [23:55<1:26:40, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3058, 'grad_norm': 0.7522069811820984, 'learning_rate': 0.00015906487072302213, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1328/6464 [23:56<1:30:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1794, 'grad_norm': 0.5951176881790161, 'learning_rate': 0.00015903390617742687, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1329/6464 [23:57<1:32:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1895, 'grad_norm': 0.6554211378097534, 'learning_rate': 0.00015900294163183156, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1330/6464 [23:58<1:37:50, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2897, 'grad_norm': 0.6957224011421204, 'learning_rate': 0.00015897197708623627, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1331/6464 [23:59<1:35:54, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4462, 'grad_norm': 0.7123897075653076, 'learning_rate': 0.00015894101254064098, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1332/6464 [24:00<1:30:00, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9864, 'grad_norm': 0.6517543196678162, 'learning_rate': 0.00015891004799504566, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1333/6464 [24:01<1:35:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3701, 'grad_norm': 0.7203919887542725, 'learning_rate': 0.0001588790834494504, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1334/6464 [24:02<1:37:17, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4231, 'grad_norm': 0.5967193245887756, 'learning_rate': 0.00015884811890385509, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1335/6464 [24:04<1:35:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1762, 'grad_norm': 0.6930286288261414, 'learning_rate': 0.0001588171543582598, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1336/6464 [24:04<1:29:46, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0991, 'grad_norm': 0.6755741238594055, 'learning_rate': 0.0001587861898126645, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1337/6464 [24:05<1:28:59, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.192, 'grad_norm': 0.7596101760864258, 'learning_rate': 0.00015875522526706922, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1338/6464 [24:07<1:29:53, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0229, 'grad_norm': 0.6301757097244263, 'learning_rate': 0.00015872426072147393, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1339/6464 [24:08<1:32:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2736, 'grad_norm': 0.6375821828842163, 'learning_rate': 0.00015869329617587862, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1340/6464 [24:09<1:25:36, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0596, 'grad_norm': 0.7512208819389343, 'learning_rate': 0.00015866233163028333, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1341/6464 [24:10<1:30:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3925, 'grad_norm': 0.5898826122283936, 'learning_rate': 0.00015863136708468804, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1342/6464 [24:11<1:27:02, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0353, 'grad_norm': 1.443055272102356, 'learning_rate': 0.00015860040253909275, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1343/6464 [24:12<1:29:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1798, 'grad_norm': 0.711217999458313, 'learning_rate': 0.00015856943799349746, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1344/6464 [24:13<1:34:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5474, 'grad_norm': 0.5712283849716187, 'learning_rate': 0.00015853847344790215, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1345/6464 [24:14<1:35:00, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2724, 'grad_norm': 0.5640129446983337, 'learning_rate': 0.00015850750890230686, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1346/6464 [24:15<1:30:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1313, 'grad_norm': 0.7282416224479675, 'learning_rate': 0.00015847654435671157, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1347/6464 [24:16<1:27:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0234, 'grad_norm': 0.7083675265312195, 'learning_rate': 0.00015844557981111628, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1348/6464 [24:17<1:24:16, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1539, 'grad_norm': 0.6465892791748047, 'learning_rate': 0.000158414615265521, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1349/6464 [24:18<1:26:31, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0815, 'grad_norm': 0.6500471234321594, 'learning_rate': 0.0001583836507199257, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1350/6464 [24:19<1:24:17, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1331, 'grad_norm': 0.702157199382782, 'learning_rate': 0.00015835268617433039, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1351/6464 [24:20<1:24:47, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0377, 'grad_norm': 0.6085435748100281, 'learning_rate': 0.0001583217216287351, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1352/6464 [24:21<1:25:26, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2507, 'grad_norm': 0.7138630151748657, 'learning_rate': 0.0001582907570831398, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1353/6464 [24:22<1:23:39, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1747, 'grad_norm': 0.6576623916625977, 'learning_rate': 0.00015825979253754452, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1354/6464 [24:23<1:29:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2114, 'grad_norm': 0.5796277523040771, 'learning_rate': 0.00015822882799194923, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1355/6464 [24:24<1:29:07, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1284, 'grad_norm': 0.6555061936378479, 'learning_rate': 0.00015819786344635392, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1356/6464 [24:25<1:25:28, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1207, 'grad_norm': 0.7249251008033752, 'learning_rate': 0.00015816689890075865, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1357/6464 [24:26<1:22:19, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0789, 'grad_norm': 0.7339731454849243, 'learning_rate': 0.00015813593435516334, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1358/6464 [24:27<1:22:54, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1162, 'grad_norm': 0.7113840579986572, 'learning_rate': 0.00015810496980956805, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1359/6464 [24:28<1:20:53, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0979, 'grad_norm': 0.6759682297706604, 'learning_rate': 0.00015807400526397276, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1360/6464 [24:29<1:19:54, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1471, 'grad_norm': 0.7138275504112244, 'learning_rate': 0.00015804304071837745, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1361/6464 [24:30<1:24:04, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2941, 'grad_norm': 0.7117326259613037, 'learning_rate': 0.00015801207617278218, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1362/6464 [24:31<1:26:59, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0506, 'grad_norm': 0.596228837966919, 'learning_rate': 0.00015798111162718687, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1363/6464 [24:32<1:26:11, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2352, 'grad_norm': 0.7313979864120483, 'learning_rate': 0.00015795014708159158, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1364/6464 [24:33<1:24:20, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.185, 'grad_norm': 0.83744215965271, 'learning_rate': 0.0001579191825359963, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1365/6464 [24:34<1:22:04, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2703, 'grad_norm': 0.7036506533622742, 'learning_rate': 0.00015788821799040098, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1366/6464 [24:35<1:22:06, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0559, 'grad_norm': 0.6694735884666443, 'learning_rate': 0.00015785725344480571, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1367/6464 [24:36<1:24:16, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3315, 'grad_norm': 0.6382951736450195, 'learning_rate': 0.0001578262888992104, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1368/6464 [24:37<1:23:13, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2021, 'grad_norm': 0.7162744998931885, 'learning_rate': 0.00015779532435361514, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1369/6464 [24:38<1:30:27, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2267, 'grad_norm': 0.562848687171936, 'learning_rate': 0.00015776435980801982, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1370/6464 [24:39<1:28:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0324, 'grad_norm': 0.8623954653739929, 'learning_rate': 0.00015773339526242453, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1371/6464 [24:40<1:31:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1513, 'grad_norm': 0.6234351992607117, 'learning_rate': 0.00015770243071682924, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1372/6464 [24:41<1:31:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0331, 'grad_norm': 0.6214213967323303, 'learning_rate': 0.00015767146617123393, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆ | 1373/6464 [24:42<1:27:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1937, 'grad_norm': 0.6644359827041626, 'learning_rate': 0.00015764050162563867, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1374/6464 [24:43<1:27:14, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1495, 'grad_norm': 0.7063112258911133, 'learning_rate': 0.00015760953708004335, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1375/6464 [24:44<1:29:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3605, 'grad_norm': 0.7028414011001587, 'learning_rate': 0.00015757857253444806, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1376/6464 [24:45<1:33:25, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2348, 'grad_norm': 0.5798746347427368, 'learning_rate': 0.00015754760798885277, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1377/6464 [24:47<1:39:43, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1848, 'grad_norm': 0.577583372592926, 'learning_rate': 0.00015751664344325748, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1378/6464 [24:48<1:36:13, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1728, 'grad_norm': 0.6748248934745789, 'learning_rate': 0.0001574856788976622, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1379/6464 [24:49<1:33:59, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3139, 'grad_norm': 0.8507205247879028, 'learning_rate': 0.00015745471435206688, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1380/6464 [24:50<1:28:19, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1788, 'grad_norm': 0.7257240414619446, 'learning_rate': 0.0001574237498064716, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1381/6464 [24:51<1:27:26, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3311, 'grad_norm': 0.7269107699394226, 'learning_rate': 0.0001573927852608763, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1382/6464 [24:52<1:30:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1089, 'grad_norm': 0.5962716937065125, 'learning_rate': 0.00015736182071528101, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1383/6464 [24:53<1:30:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1219, 'grad_norm': 0.6090005040168762, 'learning_rate': 0.00015733085616968573, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1384/6464 [24:54<1:30:04, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1714, 'grad_norm': 0.6338492631912231, 'learning_rate': 0.0001572998916240904, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1385/6464 [24:55<1:29:59, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1833, 'grad_norm': 0.6638948917388916, 'learning_rate': 0.00015726892707849512, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1386/6464 [24:56<1:35:50, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3783, 'grad_norm': 0.6692507266998291, 'learning_rate': 0.00015723796253289983, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1387/6464 [24:58<1:39:45, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5652, 'grad_norm': 0.6708948016166687, 'learning_rate': 0.00015720699798730454, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1388/6464 [24:59<1:37:48, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2456, 'grad_norm': 0.6968979239463806, 'learning_rate': 0.00015717603344170926, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 21%|โ–ˆโ–ˆโ– | 1389/6464 [25:00<1:30:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1042, 'grad_norm': 0.7204927802085876, 'learning_rate': 0.00015714506889611397, 'epoch': 0.21}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1390/6464 [25:01<1:29:49, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.263, 'grad_norm': 0.6852726340293884, 'learning_rate': 0.00015711410435051865, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1391/6464 [25:02<1:30:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3753, 'grad_norm': 0.7156842350959778, 'learning_rate': 0.00015708313980492336, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1392/6464 [25:03<1:36:32, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5639, 'grad_norm': 0.7144286036491394, 'learning_rate': 0.00015705217525932807, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1393/6464 [25:04<1:38:12, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.314, 'grad_norm': 0.6382092237472534, 'learning_rate': 0.00015702121071373278, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1394/6464 [25:05<1:35:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2909, 'grad_norm': 0.7034395337104797, 'learning_rate': 0.0001569902461681375, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1395/6464 [25:06<1:33:06, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1567, 'grad_norm': 0.7568709850311279, 'learning_rate': 0.00015695928162254218, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1396/6464 [25:08<1:33:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4343, 'grad_norm': 0.6212263107299805, 'learning_rate': 0.00015692831707694692, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1397/6464 [25:09<1:36:55, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3921, 'grad_norm': 0.6377658843994141, 'learning_rate': 0.0001568973525313516, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1398/6464 [25:10<1:30:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3302, 'grad_norm': 0.7595241665840149, 'learning_rate': 0.00015686638798575631, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1399/6464 [25:11<1:33:29, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2155, 'grad_norm': 0.6041324734687805, 'learning_rate': 0.00015683542344016103, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1400/6464 [25:12<1:35:17, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0388, 'grad_norm': 0.6624418497085571, 'learning_rate': 0.0001568044588945657, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1401/6464 [25:13<1:39:58, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2444, 'grad_norm': 0.6100479364395142, 'learning_rate': 0.00015677349434897045, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1402/6464 [25:15<1:45:26, 1.25s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4063, 'grad_norm': 0.5452893376350403, 'learning_rate': 0.00015674252980337513, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1403/6464 [25:16<1:40:30, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1513, 'grad_norm': 0.722697913646698, 'learning_rate': 0.00015671156525777987, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1404/6464 [25:17<1:31:33, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0581, 'grad_norm': 0.721843957901001, 'learning_rate': 0.00015668060071218456, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1405/6464 [25:18<1:31:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3788, 'grad_norm': 0.7445011138916016, 'learning_rate': 0.00015664963616658924, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1406/6464 [25:19<1:29:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1286, 'grad_norm': 0.6950291395187378, 'learning_rate': 0.00015661867162099398, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1407/6464 [25:20<1:29:47, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2092, 'grad_norm': 0.6823598742485046, 'learning_rate': 0.00015658770707539866, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1408/6464 [25:21<1:39:35, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4436, 'grad_norm': 0.5832319259643555, 'learning_rate': 0.0001565567425298034, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1409/6464 [25:22<1:37:31, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2946, 'grad_norm': 0.7805693745613098, 'learning_rate': 0.00015652577798420809, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1410/6464 [25:23<1:32:29, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2213, 'grad_norm': 0.7696371078491211, 'learning_rate': 0.0001564948134386128, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1411/6464 [25:24<1:31:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3018, 'grad_norm': 0.7212080955505371, 'learning_rate': 0.0001564638488930175, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1412/6464 [25:25<1:30:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3389, 'grad_norm': 0.7005228996276855, 'learning_rate': 0.0001564328843474222, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1413/6464 [25:27<1:31:44, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1194, 'grad_norm': 0.6096085906028748, 'learning_rate': 0.00015640191980182693, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1414/6464 [25:28<1:33:52, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4169, 'grad_norm': 0.658119261264801, 'learning_rate': 0.00015637095525623161, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1415/6464 [25:29<1:31:33, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0747, 'grad_norm': 0.7392678260803223, 'learning_rate': 0.00015633999071063633, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1416/6464 [25:30<1:29:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2369, 'grad_norm': 0.7999203205108643, 'learning_rate': 0.00015630902616504104, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1417/6464 [25:31<1:38:36, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2686, 'grad_norm': 0.6234851479530334, 'learning_rate': 0.00015627806161944575, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1418/6464 [25:32<1:36:38, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.343, 'grad_norm': 0.7664402723312378, 'learning_rate': 0.00015624709707385046, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1419/6464 [25:33<1:35:49, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4899, 'grad_norm': 0.6673983335494995, 'learning_rate': 0.00015621613252825514, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1420/6464 [25:35<1:38:02, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1829, 'grad_norm': 0.7096257209777832, 'learning_rate': 0.00015618516798265986, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1421/6464 [25:36<1:33:05, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1553, 'grad_norm': 0.6456478238105774, 'learning_rate': 0.00015615420343706457, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1422/6464 [25:37<1:33:54, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1339, 'grad_norm': 0.6378785967826843, 'learning_rate': 0.00015612323889146928, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1423/6464 [25:38<1:29:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9352, 'grad_norm': 0.6526550054550171, 'learning_rate': 0.000156092274345874, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1424/6464 [25:39<1:30:20, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1032, 'grad_norm': 0.5851911306381226, 'learning_rate': 0.0001560613098002787, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1425/6464 [25:40<1:38:55, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.212, 'grad_norm': 0.5676997303962708, 'learning_rate': 0.00015603034525468339, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1426/6464 [25:41<1:38:32, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0939, 'grad_norm': 0.6658063530921936, 'learning_rate': 0.0001559993807090881, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1427/6464 [25:43<1:39:22, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.306, 'grad_norm': 0.607096791267395, 'learning_rate': 0.0001559684161634928, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1428/6464 [25:44<1:39:12, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1995, 'grad_norm': 0.6733632683753967, 'learning_rate': 0.00015593745161789752, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1429/6464 [25:45<1:38:32, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2987, 'grad_norm': 0.7004309296607971, 'learning_rate': 0.00015590648707230223, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1430/6464 [25:46<1:39:36, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3391, 'grad_norm': 0.6022968292236328, 'learning_rate': 0.00015587552252670692, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1431/6464 [25:47<1:35:53, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3811, 'grad_norm': 0.827049970626831, 'learning_rate': 0.00015584455798111163, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1432/6464 [25:48<1:33:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3163, 'grad_norm': 0.7939745187759399, 'learning_rate': 0.00015581359343551634, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1433/6464 [25:49<1:31:44, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.124, 'grad_norm': 0.6507219672203064, 'learning_rate': 0.00015578262888992105, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1434/6464 [25:50<1:32:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1982, 'grad_norm': 0.6783691048622131, 'learning_rate': 0.00015575166434432576, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1435/6464 [25:51<1:28:19, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1538, 'grad_norm': 0.7029439806938171, 'learning_rate': 0.00015572069979873044, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1436/6464 [25:53<1:30:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2615, 'grad_norm': 0.7329919934272766, 'learning_rate': 0.00015568973525313518, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1437/6464 [25:53<1:26:28, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.236, 'grad_norm': 0.7403175234794617, 'learning_rate': 0.00015565877070753987, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1438/6464 [25:55<1:32:25, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4322, 'grad_norm': 0.6211287975311279, 'learning_rate': 0.00015562780616194458, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1439/6464 [25:56<1:34:55, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5118, 'grad_norm': 0.6627631783485413, 'learning_rate': 0.0001555968416163493, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1440/6464 [25:57<1:36:35, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2336, 'grad_norm': 0.6271306276321411, 'learning_rate': 0.00015556587707075397, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1441/6464 [25:58<1:35:51, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3918, 'grad_norm': 0.701585590839386, 'learning_rate': 0.0001555349125251587, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1442/6464 [25:59<1:30:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1054, 'grad_norm': 0.6627111434936523, 'learning_rate': 0.0001555039479795634, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1443/6464 [26:00<1:23:46, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1067, 'grad_norm': 0.766843318939209, 'learning_rate': 0.00015547298343396814, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1444/6464 [26:01<1:31:50, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4277, 'grad_norm': 0.5752751231193542, 'learning_rate': 0.00015544201888837282, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1445/6464 [26:02<1:28:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0144, 'grad_norm': 0.6194652915000916, 'learning_rate': 0.00015541105434277753, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1446/6464 [26:03<1:30:24, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3672, 'grad_norm': 0.6535847783088684, 'learning_rate': 0.00015538008979718224, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1447/6464 [26:04<1:30:37, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.368, 'grad_norm': 0.6666772365570068, 'learning_rate': 0.00015534912525158693, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1448/6464 [26:06<1:28:42, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1706, 'grad_norm': 0.6449906826019287, 'learning_rate': 0.00015531816070599167, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1449/6464 [26:07<1:28:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0725, 'grad_norm': 0.6082242131233215, 'learning_rate': 0.00015528719616039635, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1450/6464 [26:07<1:25:05, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0631, 'grad_norm': 0.6029212474822998, 'learning_rate': 0.00015525623161480106, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1451/6464 [26:08<1:23:42, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4085, 'grad_norm': 0.7704929113388062, 'learning_rate': 0.00015522526706920577, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1452/6464 [26:10<1:26:17, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1036, 'grad_norm': 0.6530149579048157, 'learning_rate': 0.00015519430252361046, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1453/6464 [26:11<1:24:57, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0875, 'grad_norm': 0.6402894854545593, 'learning_rate': 0.0001551633379780152, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 22%|โ–ˆโ–ˆโ– | 1454/6464 [26:11<1:21:50, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.146, 'grad_norm': 0.7249789237976074, 'learning_rate': 0.00015513237343241988, 'epoch': 0.22}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1455/6464 [26:12<1:23:52, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0515, 'grad_norm': 0.6359533667564392, 'learning_rate': 0.0001551014088868246, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1456/6464 [26:14<1:25:20, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9704, 'grad_norm': 0.5943448543548584, 'learning_rate': 0.0001550704443412293, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1457/6464 [26:15<1:32:28, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.185, 'grad_norm': 0.5762034058570862, 'learning_rate': 0.000155039479795634, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1458/6464 [26:16<1:28:21, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3552, 'grad_norm': 0.9158902168273926, 'learning_rate': 0.00015500851525003872, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1459/6464 [26:17<1:27:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9493, 'grad_norm': 0.6016368865966797, 'learning_rate': 0.0001549775507044434, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1460/6464 [26:18<1:28:48, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3177, 'grad_norm': 0.7296281456947327, 'learning_rate': 0.00015494658615884812, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1461/6464 [26:19<1:33:35, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4779, 'grad_norm': 0.6236805319786072, 'learning_rate': 0.00015491562161325283, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1462/6464 [26:20<1:34:40, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1737, 'grad_norm': 0.606135904788971, 'learning_rate': 0.00015488465706765754, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1463/6464 [26:21<1:32:23, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1087, 'grad_norm': 0.6059948205947876, 'learning_rate': 0.00015485369252206225, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1464/6464 [26:22<1:32:08, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2753, 'grad_norm': 0.7386787533760071, 'learning_rate': 0.00015482272797646697, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1465/6464 [26:23<1:25:37, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0976, 'grad_norm': 0.7265202403068542, 'learning_rate': 0.00015479176343087165, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1466/6464 [26:24<1:27:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1652, 'grad_norm': 0.6344661712646484, 'learning_rate': 0.00015476079888527636, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1467/6464 [26:26<1:30:56, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2885, 'grad_norm': 0.5714784860610962, 'learning_rate': 0.00015472983433968107, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1468/6464 [26:27<1:25:58, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1291, 'grad_norm': 0.6892774105072021, 'learning_rate': 0.00015469886979408578, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1469/6464 [26:28<1:26:41, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1619, 'grad_norm': 0.6722917556762695, 'learning_rate': 0.0001546679052484905, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1470/6464 [26:29<1:24:23, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2016, 'grad_norm': 0.6506637334823608, 'learning_rate': 0.00015463694070289518, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1471/6464 [26:30<1:24:36, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2177, 'grad_norm': 0.6505963206291199, 'learning_rate': 0.0001546059761572999, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1472/6464 [26:31<1:26:11, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2019, 'grad_norm': 0.636719286441803, 'learning_rate': 0.0001545750116117046, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1473/6464 [26:32<1:29:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3253, 'grad_norm': 0.6390586495399475, 'learning_rate': 0.00015454404706610931, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1474/6464 [26:33<1:32:43, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4622, 'grad_norm': 0.7206825017929077, 'learning_rate': 0.00015451308252051403, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1475/6464 [26:34<1:30:49, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1498, 'grad_norm': 0.6089661717414856, 'learning_rate': 0.0001544821179749187, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1476/6464 [26:35<1:23:56, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0235, 'grad_norm': 0.7821279764175415, 'learning_rate': 0.00015445115342932345, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1477/6464 [26:36<1:27:54, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2455, 'grad_norm': 0.8109956979751587, 'learning_rate': 0.00015442018888372813, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1478/6464 [26:37<1:26:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4288, 'grad_norm': 0.7446058392524719, 'learning_rate': 0.00015438922433813284, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1479/6464 [26:38<1:30:26, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3587, 'grad_norm': 0.710636556148529, 'learning_rate': 0.00015435825979253755, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1480/6464 [26:39<1:29:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.178, 'grad_norm': 0.746069610118866, 'learning_rate': 0.00015432729524694224, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1481/6464 [26:41<1:34:05, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1688, 'grad_norm': 0.5945873260498047, 'learning_rate': 0.00015429633070134698, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1482/6464 [26:42<1:33:43, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3014, 'grad_norm': 0.6926012635231018, 'learning_rate': 0.00015426536615575166, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1483/6464 [26:43<1:30:38, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2544, 'grad_norm': 0.7894001007080078, 'learning_rate': 0.0001542344016101564, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1484/6464 [26:44<1:30:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1668, 'grad_norm': 0.6175690293312073, 'learning_rate': 0.00015420343706456108, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1485/6464 [26:45<1:23:06, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.014, 'grad_norm': 0.7473037838935852, 'learning_rate': 0.0001541724725189658, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1486/6464 [26:46<1:27:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3351, 'grad_norm': 0.6157557964324951, 'learning_rate': 0.0001541415079733705, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1487/6464 [26:47<1:25:54, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1419, 'grad_norm': 0.6482983231544495, 'learning_rate': 0.0001541105434277752, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1488/6464 [26:48<1:26:14, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3193, 'grad_norm': 0.6379923224449158, 'learning_rate': 0.00015407957888217993, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1489/6464 [26:49<1:34:24, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5454, 'grad_norm': 0.637908935546875, 'learning_rate': 0.00015404861433658461, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1490/6464 [26:50<1:34:14, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.328, 'grad_norm': 0.6149629950523376, 'learning_rate': 0.00015401764979098933, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1491/6464 [26:51<1:34:11, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3228, 'grad_norm': 0.6619742512702942, 'learning_rate': 0.00015398668524539404, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1492/6464 [26:53<1:35:16, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1138, 'grad_norm': 0.6754102110862732, 'learning_rate': 0.00015395572069979872, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1493/6464 [26:53<1:29:00, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2561, 'grad_norm': 0.7290665507316589, 'learning_rate': 0.00015392475615420346, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1494/6464 [26:55<1:32:20, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1586, 'grad_norm': 0.624560534954071, 'learning_rate': 0.00015389379160860814, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1495/6464 [26:56<1:31:29, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4287, 'grad_norm': 0.7872563600540161, 'learning_rate': 0.00015386282706301286, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1496/6464 [26:57<1:28:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3748, 'grad_norm': 0.803788423538208, 'learning_rate': 0.00015383186251741757, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1497/6464 [26:58<1:25:55, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1435, 'grad_norm': 0.6408638954162598, 'learning_rate': 0.00015380089797182228, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1498/6464 [26:59<1:28:12, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1442, 'grad_norm': 0.6200559735298157, 'learning_rate': 0.000153769933426227, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1499/6464 [27:00<1:26:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1853, 'grad_norm': 0.6924797892570496, 'learning_rate': 0.00015373896888063167, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1500/6464 [27:01<1:27:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1088, 'grad_norm': 0.7846211194992065, 'learning_rate': 0.00015370800433503638, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/other.py:619: UserWarning: Unable to fetch remote file due to the following error (ReadTimeoutError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)\"), '(Request ID: 95038f59-2da7-494b-b887-33138b946764)') - silently ignoring the lookup for the file config.json in Magpie-Align/MagpieLM-4B-Chat-v0.1.\n", " warnings.warn(\n", "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/save_and_load.py:218: UserWarning: Could not find a config file in Magpie-Align/MagpieLM-4B-Chat-v0.1 - will assume that the vocabulary was not modified.\n", " warnings.warn(\n", " 23%|โ–ˆโ–ˆโ–Ž | 1501/6464 [27:12<5:39:54, 4.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2057, 'grad_norm': 0.7587661147117615, 'learning_rate': 0.0001536770397894411, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1502/6464 [27:13<4:26:33, 3.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2675, 'grad_norm': 0.7754412293434143, 'learning_rate': 0.0001536460752438458, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1503/6464 [27:14<3:33:27, 2.58s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3899, 'grad_norm': 0.6805928349494934, 'learning_rate': 0.00015361511069825052, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1504/6464 [27:16<2:57:59, 2.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2061, 'grad_norm': 0.7386242747306824, 'learning_rate': 0.00015358414615265523, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1505/6464 [27:17<2:30:31, 1.82s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0533, 'grad_norm': 0.5981537699699402, 'learning_rate': 0.00015355318160705991, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1506/6464 [27:18<2:08:45, 1.56s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0918, 'grad_norm': 0.6561291217803955, 'learning_rate': 0.00015352221706146463, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1507/6464 [27:19<1:57:33, 1.42s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4722, 'grad_norm': 0.7243315577507019, 'learning_rate': 0.00015349125251586934, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1508/6464 [27:20<1:46:48, 1.29s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2016, 'grad_norm': 0.673053503036499, 'learning_rate': 0.00015346028797027405, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1509/6464 [27:21<1:44:43, 1.27s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2296, 'grad_norm': 0.582831621170044, 'learning_rate': 0.00015342932342467876, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1510/6464 [27:22<1:38:32, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2462, 'grad_norm': 0.7234540581703186, 'learning_rate': 0.00015339835887908344, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1511/6464 [27:23<1:36:36, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3379, 'grad_norm': 0.6100758910179138, 'learning_rate': 0.00015336739433348816, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1512/6464 [27:24<1:31:31, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4138, 'grad_norm': 0.7626834511756897, 'learning_rate': 0.00015333642978789287, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1513/6464 [27:25<1:30:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2685, 'grad_norm': 0.6472445130348206, 'learning_rate': 0.00015330546524229758, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1514/6464 [27:26<1:34:55, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2705, 'grad_norm': 0.6830433011054993, 'learning_rate': 0.0001532745006967023, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1515/6464 [27:27<1:33:32, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3112, 'grad_norm': 0.6912378668785095, 'learning_rate': 0.00015324353615110697, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1516/6464 [27:28<1:29:39, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3272, 'grad_norm': 0.808320164680481, 'learning_rate': 0.0001532125716055117, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1517/6464 [27:30<1:37:29, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6305, 'grad_norm': 0.6296589970588684, 'learning_rate': 0.0001531816070599164, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1518/6464 [27:31<1:36:01, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1166, 'grad_norm': 0.6317994594573975, 'learning_rate': 0.0001531506425143211, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 23%|โ–ˆโ–ˆโ–Ž | 1519/6464 [27:32<1:33:50, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3252, 'grad_norm': 0.6980863213539124, 'learning_rate': 0.00015311967796872582, 'epoch': 0.23}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1520/6464 [27:33<1:33:29, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0872, 'grad_norm': 0.6480008363723755, 'learning_rate': 0.0001530887134231305, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1521/6464 [27:34<1:27:28, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9786, 'grad_norm': 0.6660850644111633, 'learning_rate': 0.00015305774887753524, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1522/6464 [27:35<1:28:22, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0965, 'grad_norm': 0.687590479850769, 'learning_rate': 0.00015302678433193993, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1523/6464 [27:36<1:30:15, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3508, 'grad_norm': 0.6819323301315308, 'learning_rate': 0.00015299581978634466, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1524/6464 [27:37<1:33:01, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2642, 'grad_norm': 0.7383971214294434, 'learning_rate': 0.00015296485524074935, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1525/6464 [27:39<1:31:39, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9909, 'grad_norm': 0.5926058292388916, 'learning_rate': 0.00015293389069515406, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1526/6464 [27:40<1:31:47, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.211, 'grad_norm': 0.6182388663291931, 'learning_rate': 0.00015290292614955877, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1527/6464 [27:41<1:30:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1752, 'grad_norm': 0.6019041538238525, 'learning_rate': 0.00015287196160396346, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1528/6464 [27:42<1:31:28, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1369, 'grad_norm': 0.6823365688323975, 'learning_rate': 0.0001528409970583682, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1529/6464 [27:43<1:35:19, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5173, 'grad_norm': 0.6232258677482605, 'learning_rate': 0.00015281003251277288, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1530/6464 [27:44<1:31:07, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3065, 'grad_norm': 0.7050153613090515, 'learning_rate': 0.0001527790679671776, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1531/6464 [27:45<1:29:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3269, 'grad_norm': 0.7510757446289062, 'learning_rate': 0.0001527481034215823, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1532/6464 [27:47<1:37:14, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0335, 'grad_norm': 0.581794798374176, 'learning_rate': 0.00015271713887598699, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1533/6464 [27:48<1:34:48, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.21, 'grad_norm': 0.6721566915512085, 'learning_rate': 0.00015268617433039172, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1534/6464 [27:49<1:34:01, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2575, 'grad_norm': 0.6623930931091309, 'learning_rate': 0.0001526552097847964, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ–Ž | 1535/6464 [27:50<1:28:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2633, 'grad_norm': 0.7711536288261414, 'learning_rate': 0.00015262424523920112, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1536/6464 [27:51<1:27:09, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2568, 'grad_norm': 0.6899026036262512, 'learning_rate': 0.00015259328069360583, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1537/6464 [27:52<1:25:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2739, 'grad_norm': 0.666733980178833, 'learning_rate': 0.00015256231614801054, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1538/6464 [27:53<1:34:01, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3691, 'grad_norm': 0.6357513070106506, 'learning_rate': 0.00015253135160241525, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1539/6464 [27:54<1:33:40, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2108, 'grad_norm': 0.6277012825012207, 'learning_rate': 0.00015250038705681994, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1540/6464 [27:55<1:34:02, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2864, 'grad_norm': 0.709863543510437, 'learning_rate': 0.00015246942251122465, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1541/6464 [27:57<1:43:15, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4109, 'grad_norm': 0.5610412359237671, 'learning_rate': 0.00015243845796562936, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1542/6464 [27:58<1:41:28, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.308, 'grad_norm': 0.5826546549797058, 'learning_rate': 0.00015240749342003407, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1543/6464 [27:59<1:36:41, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4497, 'grad_norm': 0.7340690493583679, 'learning_rate': 0.00015237652887443878, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1544/6464 [28:00<1:30:58, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0864, 'grad_norm': 0.6895474195480347, 'learning_rate': 0.0001523455643288435, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1545/6464 [28:01<1:30:22, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4716, 'grad_norm': 0.9430215358734131, 'learning_rate': 0.00015231459978324818, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1546/6464 [28:02<1:28:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3303, 'grad_norm': 0.6574228405952454, 'learning_rate': 0.0001522836352376529, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1547/6464 [28:03<1:26:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1203, 'grad_norm': 0.5759912729263306, 'learning_rate': 0.0001522526706920576, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1548/6464 [28:04<1:23:29, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0578, 'grad_norm': 0.6527823805809021, 'learning_rate': 0.0001522217061464623, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1549/6464 [28:05<1:31:12, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3452, 'grad_norm': 0.6414220333099365, 'learning_rate': 0.00015219074160086702, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1550/6464 [28:07<1:29:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2162, 'grad_norm': 0.6841395497322083, 'learning_rate': 0.0001521597770552717, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1551/6464 [28:08<1:28:56, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2117, 'grad_norm': 0.630158543586731, 'learning_rate': 0.00015212881250967642, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1552/6464 [28:09<1:28:46, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1756, 'grad_norm': 0.632027268409729, 'learning_rate': 0.00015209784796408113, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1553/6464 [28:10<1:26:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.204, 'grad_norm': 0.7294105887413025, 'learning_rate': 0.00015206688341848584, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1554/6464 [28:11<1:25:27, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3107, 'grad_norm': 0.7094262838363647, 'learning_rate': 0.00015203591887289055, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1555/6464 [28:11<1:18:37, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9889, 'grad_norm': 0.8963695168495178, 'learning_rate': 0.00015200495432729524, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1556/6464 [28:12<1:17:06, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0615, 'grad_norm': 0.8352545499801636, 'learning_rate': 0.00015197398978169998, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1557/6464 [28:13<1:20:33, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2924, 'grad_norm': 0.7156710028648376, 'learning_rate': 0.00015194302523610466, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1558/6464 [28:15<1:24:11, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1518, 'grad_norm': 0.6539190411567688, 'learning_rate': 0.00015191206069050937, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1559/6464 [28:16<1:23:43, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1006, 'grad_norm': 0.7437371611595154, 'learning_rate': 0.00015188109614491408, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1560/6464 [28:17<1:24:43, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2591, 'grad_norm': 0.8494769930839539, 'learning_rate': 0.00015185013159931877, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1561/6464 [28:18<1:22:26, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0954, 'grad_norm': 0.839184045791626, 'learning_rate': 0.0001518191670537235, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1562/6464 [28:19<1:24:32, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3345, 'grad_norm': 0.6971377730369568, 'learning_rate': 0.0001517882025081282, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1563/6464 [28:20<1:20:28, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0904, 'grad_norm': 0.9587531089782715, 'learning_rate': 0.00015175723796253293, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1564/6464 [28:20<1:18:12, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1834, 'grad_norm': 0.9033886194229126, 'learning_rate': 0.0001517262734169376, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1565/6464 [28:22<1:25:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3575, 'grad_norm': 0.6319893002510071, 'learning_rate': 0.00015169530887134232, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1566/6464 [28:23<1:26:14, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.175, 'grad_norm': 0.6238691806793213, 'learning_rate': 0.00015166434432574704, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1567/6464 [28:24<1:23:38, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2473, 'grad_norm': 0.7542547583580017, 'learning_rate': 0.00015163337978015172, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1568/6464 [28:25<1:24:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1988, 'grad_norm': 0.6563936471939087, 'learning_rate': 0.00015160241523455646, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1569/6464 [28:26<1:28:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1414, 'grad_norm': 0.5770760774612427, 'learning_rate': 0.00015157145068896114, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1570/6464 [28:27<1:24:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0858, 'grad_norm': 0.6601766347885132, 'learning_rate': 0.00015154048614336585, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1571/6464 [28:28<1:24:01, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3033, 'grad_norm': 0.6354166865348816, 'learning_rate': 0.00015150952159777057, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1572/6464 [28:29<1:22:59, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3077, 'grad_norm': 0.657871425151825, 'learning_rate': 0.00015147855705217525, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1573/6464 [28:30<1:20:12, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2277, 'grad_norm': 1.0104358196258545, 'learning_rate': 0.00015144759250658, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1574/6464 [28:31<1:17:56, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0959, 'grad_norm': 0.6936097145080566, 'learning_rate': 0.00015141662796098467, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1575/6464 [28:32<1:20:19, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3718, 'grad_norm': 0.7096662521362305, 'learning_rate': 0.00015138566341538938, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1576/6464 [28:33<1:20:29, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8463, 'grad_norm': 0.5667175054550171, 'learning_rate': 0.0001513546988697941, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1577/6464 [28:34<1:25:58, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.287, 'grad_norm': 0.6053897142410278, 'learning_rate': 0.0001513237343241988, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1578/6464 [28:35<1:26:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1074, 'grad_norm': 0.6128722429275513, 'learning_rate': 0.00015129276977860352, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1579/6464 [28:36<1:26:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.368, 'grad_norm': 0.7143658995628357, 'learning_rate': 0.0001512618052330082, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1580/6464 [28:37<1:25:54, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2662, 'grad_norm': 0.6452208161354065, 'learning_rate': 0.00015123084068741291, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1581/6464 [28:38<1:24:49, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3806, 'grad_norm': 0.7318915724754333, 'learning_rate': 0.00015119987614181763, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1582/6464 [28:39<1:25:16, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2806, 'grad_norm': 0.6900926232337952, 'learning_rate': 0.00015116891159622234, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 24%|โ–ˆโ–ˆโ– | 1583/6464 [28:40<1:23:34, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1339, 'grad_norm': 0.7062177658081055, 'learning_rate': 0.00015113794705062705, 'epoch': 0.24}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1584/6464 [28:41<1:26:39, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0835, 'grad_norm': 0.6216686367988586, 'learning_rate': 0.00015110698250503176, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1585/6464 [28:42<1:25:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1923, 'grad_norm': 0.6823495626449585, 'learning_rate': 0.00015107601795943644, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1586/6464 [28:44<1:35:43, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2202, 'grad_norm': 0.6300709247589111, 'learning_rate': 0.00015104505341384115, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1587/6464 [28:45<1:31:40, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0354, 'grad_norm': 0.649096667766571, 'learning_rate': 0.00015101408886824587, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1588/6464 [28:46<1:30:34, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.993, 'grad_norm': 0.5722672939300537, 'learning_rate': 0.00015098312432265058, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1589/6464 [28:47<1:26:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2417, 'grad_norm': 0.7319905757904053, 'learning_rate': 0.0001509521597770553, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1590/6464 [28:48<1:30:00, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2203, 'grad_norm': 0.5780161023139954, 'learning_rate': 0.00015092119523145997, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1591/6464 [28:49<1:29:40, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3498, 'grad_norm': 0.7168540954589844, 'learning_rate': 0.00015089023068586468, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1592/6464 [28:50<1:27:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1978, 'grad_norm': 0.7439079284667969, 'learning_rate': 0.0001508592661402694, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1593/6464 [28:51<1:30:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1002, 'grad_norm': 0.6356058120727539, 'learning_rate': 0.0001508283015946741, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1594/6464 [28:53<1:34:35, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.388, 'grad_norm': 0.6363085508346558, 'learning_rate': 0.00015079733704907882, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1595/6464 [28:54<1:33:46, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3717, 'grad_norm': 0.6426194310188293, 'learning_rate': 0.0001507663725034835, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1596/6464 [28:55<1:36:02, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4973, 'grad_norm': 0.6508749127388, 'learning_rate': 0.00015073540795788824, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1597/6464 [28:56<1:35:09, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8475, 'grad_norm': 0.5540292263031006, 'learning_rate': 0.00015070444341229293, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1598/6464 [28:57<1:29:18, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1108, 'grad_norm': 0.6924321055412292, 'learning_rate': 0.00015067347886669764, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1599/6464 [28:58<1:30:06, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0665, 'grad_norm': 0.5922529101371765, 'learning_rate': 0.00015064251432110235, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1600/6464 [28:59<1:31:58, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1675, 'grad_norm': 0.6553547978401184, 'learning_rate': 0.00015061154977550703, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1601/6464 [29:00<1:27:07, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2776, 'grad_norm': 0.734102725982666, 'learning_rate': 0.00015058058522991177, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1602/6464 [29:01<1:24:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0204, 'grad_norm': 0.7536888718605042, 'learning_rate': 0.00015054962068431646, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1603/6464 [29:03<1:28:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1803, 'grad_norm': 0.6139588952064514, 'learning_rate': 0.0001505186561387212, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1604/6464 [29:04<1:27:36, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1816, 'grad_norm': 0.6498744487762451, 'learning_rate': 0.00015048769159312588, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1605/6464 [29:05<1:29:24, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1334, 'grad_norm': 0.6366518139839172, 'learning_rate': 0.0001504567270475306, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1606/6464 [29:06<1:29:09, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.201, 'grad_norm': 0.674414873123169, 'learning_rate': 0.0001504257625019353, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1607/6464 [29:07<1:30:44, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3914, 'grad_norm': 0.6861807107925415, 'learning_rate': 0.00015039479795633998, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1608/6464 [29:08<1:29:50, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4011, 'grad_norm': 0.7294487357139587, 'learning_rate': 0.00015036383341074472, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1609/6464 [29:09<1:25:52, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0062, 'grad_norm': 0.6042083501815796, 'learning_rate': 0.0001503328688651494, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1610/6464 [29:10<1:26:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3641, 'grad_norm': 0.7305752635002136, 'learning_rate': 0.00015030190431955412, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1611/6464 [29:11<1:23:35, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1723, 'grad_norm': 0.6686708927154541, 'learning_rate': 0.00015027093977395883, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1612/6464 [29:12<1:22:54, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0171, 'grad_norm': 0.6082514524459839, 'learning_rate': 0.00015023997522836351, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1613/6464 [29:13<1:29:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4923, 'grad_norm': 0.6435635089874268, 'learning_rate': 0.00015020901068276825, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1614/6464 [29:15<1:31:08, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2291, 'grad_norm': 0.5930275321006775, 'learning_rate': 0.00015017804613717294, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ– | 1615/6464 [29:16<1:27:38, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1469, 'grad_norm': 0.7570124268531799, 'learning_rate': 0.00015014708159157765, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1616/6464 [29:17<1:25:06, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1216, 'grad_norm': 0.7093691229820251, 'learning_rate': 0.00015011611704598236, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1617/6464 [29:17<1:21:47, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1813, 'grad_norm': 0.7816886305809021, 'learning_rate': 0.00015008515250038707, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1618/6464 [29:18<1:20:46, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3081, 'grad_norm': 0.752727210521698, 'learning_rate': 0.00015005418795479178, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1619/6464 [29:19<1:19:44, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0332, 'grad_norm': 0.7019944190979004, 'learning_rate': 0.00015002322340919647, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1620/6464 [29:20<1:20:45, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1486, 'grad_norm': 0.6911996603012085, 'learning_rate': 0.00014999225886360118, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1621/6464 [29:22<1:26:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3202, 'grad_norm': 0.6059245467185974, 'learning_rate': 0.0001499612943180059, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1622/6464 [29:23<1:27:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4039, 'grad_norm': 0.7482999563217163, 'learning_rate': 0.0001499303297724106, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1623/6464 [29:24<1:24:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0235, 'grad_norm': 0.646668016910553, 'learning_rate': 0.0001498993652268153, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1624/6464 [29:25<1:24:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1015, 'grad_norm': 0.6935965418815613, 'learning_rate': 0.00014986840068122002, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1625/6464 [29:26<1:27:53, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2442, 'grad_norm': 0.6025964617729187, 'learning_rate': 0.0001498374361356247, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1626/6464 [29:27<1:30:36, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0321, 'grad_norm': 0.5732932090759277, 'learning_rate': 0.00014980647159002942, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1627/6464 [29:28<1:28:51, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1625, 'grad_norm': 0.6346207857131958, 'learning_rate': 0.00014977550704443413, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1628/6464 [29:29<1:28:23, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2994, 'grad_norm': 0.5726943612098694, 'learning_rate': 0.00014974454249883884, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1629/6464 [29:30<1:28:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0857, 'grad_norm': 0.6371219158172607, 'learning_rate': 0.00014971357795324355, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1630/6464 [29:32<1:29:44, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3151, 'grad_norm': 0.633431077003479, 'learning_rate': 0.00014968261340764824, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1631/6464 [29:33<1:30:37, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6453, 'grad_norm': 0.7610368728637695, 'learning_rate': 0.00014965164886205295, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1632/6464 [29:34<1:30:23, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3096, 'grad_norm': 0.7177454233169556, 'learning_rate': 0.00014962068431645766, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1633/6464 [29:35<1:30:03, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3887, 'grad_norm': 0.6242338418960571, 'learning_rate': 0.00014958971977086237, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1634/6464 [29:36<1:29:02, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1232, 'grad_norm': 0.5967841744422913, 'learning_rate': 0.00014955875522526708, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1635/6464 [29:37<1:27:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2189, 'grad_norm': 0.780767023563385, 'learning_rate': 0.00014952779067967177, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1636/6464 [29:38<1:28:29, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.307, 'grad_norm': 0.6486875414848328, 'learning_rate': 0.0001494968261340765, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1637/6464 [29:39<1:26:04, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1405, 'grad_norm': 0.6515658497810364, 'learning_rate': 0.0001494658615884812, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1638/6464 [29:40<1:20:47, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9943, 'grad_norm': 0.666729211807251, 'learning_rate': 0.0001494348970428859, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1639/6464 [29:41<1:18:58, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0044, 'grad_norm': 0.645969569683075, 'learning_rate': 0.0001494039324972906, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1640/6464 [29:42<1:25:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3067, 'grad_norm': 0.57364821434021, 'learning_rate': 0.0001493729679516953, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1641/6464 [29:43<1:21:13, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9991, 'grad_norm': 0.7195519804954529, 'learning_rate': 0.00014934200340610004, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1642/6464 [29:44<1:23:46, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3664, 'grad_norm': 0.7451553344726562, 'learning_rate': 0.00014931103886050472, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1643/6464 [29:46<1:31:43, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2675, 'grad_norm': 0.7172975540161133, 'learning_rate': 0.00014928007431490946, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1644/6464 [29:47<1:30:19, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1561, 'grad_norm': 0.642739474773407, 'learning_rate': 0.00014924910976931414, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1645/6464 [29:48<1:25:01, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0201, 'grad_norm': 1.9374878406524658, 'learning_rate': 0.00014921814522371885, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1646/6464 [29:49<1:22:41, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0685, 'grad_norm': 0.7499362826347351, 'learning_rate': 0.00014918718067812357, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1647/6464 [29:49<1:18:49, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.006, 'grad_norm': 0.671867847442627, 'learning_rate': 0.00014915621613252825, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 25%|โ–ˆโ–ˆโ–Œ | 1648/6464 [29:50<1:20:12, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2393, 'grad_norm': 0.7398427128791809, 'learning_rate': 0.000149125251586933, 'epoch': 0.25}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1649/6464 [29:52<1:30:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1483, 'grad_norm': 0.710286557674408, 'learning_rate': 0.00014909428704133767, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1650/6464 [29:53<1:28:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4078, 'grad_norm': 0.7532532215118408, 'learning_rate': 0.00014906332249574238, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1651/6464 [29:54<1:34:04, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1306, 'grad_norm': 0.6224991083145142, 'learning_rate': 0.0001490323579501471, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1652/6464 [29:55<1:32:25, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.183, 'grad_norm': 0.6348543763160706, 'learning_rate': 0.00014900139340455178, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1653/6464 [29:56<1:28:48, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1466, 'grad_norm': 0.7158614993095398, 'learning_rate': 0.00014897042885895652, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1654/6464 [29:58<1:37:56, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.235, 'grad_norm': 0.7886353731155396, 'learning_rate': 0.0001489394643133612, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1655/6464 [29:59<1:32:36, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0231, 'grad_norm': 0.5703935027122498, 'learning_rate': 0.0001489084997677659, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1656/6464 [30:00<1:29:08, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2314, 'grad_norm': 0.7086851000785828, 'learning_rate': 0.00014887753522217062, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1657/6464 [30:01<1:27:06, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2731, 'grad_norm': 0.7603851556777954, 'learning_rate': 0.00014884657067657534, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1658/6464 [30:02<1:27:13, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0655, 'grad_norm': 0.5858877301216125, 'learning_rate': 0.00014881560613098005, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1659/6464 [30:03<1:32:44, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2456, 'grad_norm': 0.5817646980285645, 'learning_rate': 0.00014878464158538473, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1660/6464 [30:04<1:31:32, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3044, 'grad_norm': 0.6461383700370789, 'learning_rate': 0.00014875367703978944, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1661/6464 [30:05<1:28:39, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4397, 'grad_norm': 0.7785926461219788, 'learning_rate': 0.00014872271249419415, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1662/6464 [30:07<1:34:56, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1824, 'grad_norm': 0.5364215970039368, 'learning_rate': 0.00014869174794859887, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1663/6464 [30:08<1:36:01, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0097, 'grad_norm': 0.6552878022193909, 'learning_rate': 0.00014866078340300358, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1664/6464 [30:09<1:31:24, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2528, 'grad_norm': 0.6970897316932678, 'learning_rate': 0.0001486298188574083, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1665/6464 [30:10<1:36:20, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5363, 'grad_norm': 0.7655086517333984, 'learning_rate': 0.00014859885431181297, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1666/6464 [30:12<1:38:46, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1474, 'grad_norm': 0.6662802696228027, 'learning_rate': 0.00014856788976621768, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1667/6464 [30:13<1:31:32, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1185, 'grad_norm': 0.7235757112503052, 'learning_rate': 0.0001485369252206224, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1668/6464 [30:14<1:25:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1125, 'grad_norm': 0.7209650278091431, 'learning_rate': 0.0001485059606750271, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1669/6464 [30:15<1:22:19, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.15, 'grad_norm': 0.832464337348938, 'learning_rate': 0.00014847499612943182, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1670/6464 [30:16<1:22:46, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1641, 'grad_norm': 0.6717204451560974, 'learning_rate': 0.0001484440315838365, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1671/6464 [30:17<1:23:54, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0648, 'grad_norm': 0.6444035768508911, 'learning_rate': 0.0001484130670382412, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1672/6464 [30:18<1:24:00, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2729, 'grad_norm': 0.8468247652053833, 'learning_rate': 0.00014838210249264592, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1673/6464 [30:19<1:28:24, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2942, 'grad_norm': 0.6415808796882629, 'learning_rate': 0.00014835113794705064, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1674/6464 [30:20<1:25:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0281, 'grad_norm': 0.6402438879013062, 'learning_rate': 0.00014832017340145535, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1675/6464 [30:21<1:25:00, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1579, 'grad_norm': 0.7406004071235657, 'learning_rate': 0.00014828920885586003, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1676/6464 [30:22<1:25:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.317, 'grad_norm': 0.6619943976402283, 'learning_rate': 0.00014825824431026477, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1677/6464 [30:23<1:25:10, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0888, 'grad_norm': 0.7580053210258484, 'learning_rate': 0.00014822727976466945, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1678/6464 [30:24<1:31:24, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4627, 'grad_norm': 0.6035057306289673, 'learning_rate': 0.00014819631521907417, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1679/6464 [30:26<1:30:22, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2552, 'grad_norm': 0.6298701763153076, 'learning_rate': 0.00014816535067347888, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1680/6464 [30:27<1:30:19, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3363, 'grad_norm': 0.7145634293556213, 'learning_rate': 0.00014813438612788356, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1681/6464 [30:28<1:24:55, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0261, 'grad_norm': 0.8316280245780945, 'learning_rate': 0.0001481034215822883, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1682/6464 [30:29<1:28:21, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2358, 'grad_norm': 0.6475480794906616, 'learning_rate': 0.00014807245703669298, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1683/6464 [30:30<1:28:01, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1783, 'grad_norm': 0.674298107624054, 'learning_rate': 0.00014804149249109772, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1684/6464 [30:31<1:32:20, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0495, 'grad_norm': 0.6804308891296387, 'learning_rate': 0.0001480105279455024, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1685/6464 [30:32<1:34:02, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5067, 'grad_norm': 0.6115831732749939, 'learning_rate': 0.00014797956339990712, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1686/6464 [30:33<1:30:23, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2811, 'grad_norm': 0.7113880515098572, 'learning_rate': 0.00014794859885431183, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1687/6464 [30:34<1:26:44, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.152, 'grad_norm': 0.6465663909912109, 'learning_rate': 0.00014791763430871651, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1688/6464 [30:35<1:24:12, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0825, 'grad_norm': 0.7319929599761963, 'learning_rate': 0.00014788666976312125, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1689/6464 [30:37<1:26:55, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.383, 'grad_norm': 0.6324150562286377, 'learning_rate': 0.00014785570521752594, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1690/6464 [30:38<1:28:27, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1543, 'grad_norm': 0.6491743922233582, 'learning_rate': 0.00014782474067193065, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1691/6464 [30:39<1:27:43, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1687, 'grad_norm': 0.6681495308876038, 'learning_rate': 0.00014779377612633536, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1692/6464 [30:40<1:24:08, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1397, 'grad_norm': 0.6661323308944702, 'learning_rate': 0.00014776281158074004, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1693/6464 [30:41<1:24:20, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2555, 'grad_norm': 0.6887370944023132, 'learning_rate': 0.00014773184703514478, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1694/6464 [30:42<1:32:36, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3104, 'grad_norm': 0.5725392699241638, 'learning_rate': 0.00014770088248954947, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1695/6464 [30:44<1:35:23, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6319, 'grad_norm': 0.6880934238433838, 'learning_rate': 0.00014766991794395418, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–Œ | 1696/6464 [30:45<1:37:21, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1582, 'grad_norm': 0.6409569978713989, 'learning_rate': 0.0001476389533983589, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1697/6464 [30:46<1:32:43, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0963, 'grad_norm': 0.6167311072349548, 'learning_rate': 0.0001476079888527636, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1698/6464 [30:47<1:25:35, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2212, 'grad_norm': 0.7964304089546204, 'learning_rate': 0.0001475770243071683, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1699/6464 [30:48<1:26:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2442, 'grad_norm': 0.7639340758323669, 'learning_rate': 0.000147546059761573, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1700/6464 [30:49<1:28:33, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4344, 'grad_norm': 0.6344501972198486, 'learning_rate': 0.0001475150952159777, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1701/6464 [30:50<1:25:30, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2235, 'grad_norm': 0.6998792290687561, 'learning_rate': 0.00014748413067038242, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1702/6464 [30:51<1:27:46, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4089, 'grad_norm': 0.7581660151481628, 'learning_rate': 0.00014745316612478713, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1703/6464 [30:53<1:33:18, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2919, 'grad_norm': 0.6214884519577026, 'learning_rate': 0.00014742220157919184, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1704/6464 [30:54<1:31:43, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2468, 'grad_norm': 0.6675474643707275, 'learning_rate': 0.00014739123703359655, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1705/6464 [30:55<1:28:38, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0249, 'grad_norm': 0.6415443420410156, 'learning_rate': 0.00014736027248800124, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1706/6464 [30:56<1:24:30, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2221, 'grad_norm': 0.7287996411323547, 'learning_rate': 0.00014732930794240595, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1707/6464 [30:57<1:21:16, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2346, 'grad_norm': 0.6654402017593384, 'learning_rate': 0.00014729834339681066, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1708/6464 [30:57<1:19:41, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1651, 'grad_norm': 0.8124375939369202, 'learning_rate': 0.00014726737885121537, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1709/6464 [30:59<1:22:17, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3953, 'grad_norm': 0.6650646924972534, 'learning_rate': 0.00014723641430562008, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1710/6464 [31:00<1:20:52, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2549, 'grad_norm': 0.6653326153755188, 'learning_rate': 0.00014720544976002477, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1711/6464 [31:01<1:20:08, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1881, 'grad_norm': 0.6451271772384644, 'learning_rate': 0.0001471744852144295, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 26%|โ–ˆโ–ˆโ–‹ | 1712/6464 [31:01<1:17:50, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0123, 'grad_norm': 0.6810344457626343, 'learning_rate': 0.0001471435206688342, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1713/6464 [31:03<1:18:36, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8995, 'grad_norm': 0.6068230271339417, 'learning_rate': 0.0001471125561232389, 'epoch': 0.26}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1714/6464 [31:03<1:18:18, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1583, 'grad_norm': 0.6095733046531677, 'learning_rate': 0.0001470815915776436, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1715/6464 [31:04<1:17:48, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.123, 'grad_norm': 0.6874273419380188, 'learning_rate': 0.0001470506270320483, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1716/6464 [31:06<1:22:01, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1612, 'grad_norm': 0.6869902610778809, 'learning_rate': 0.00014701966248645303, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1717/6464 [31:07<1:25:20, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.264, 'grad_norm': 0.6447158455848694, 'learning_rate': 0.00014698869794085772, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1718/6464 [31:08<1:22:36, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9543, 'grad_norm': 0.6826283931732178, 'learning_rate': 0.00014695773339526243, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1719/6464 [31:09<1:24:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4038, 'grad_norm': 0.7405222058296204, 'learning_rate': 0.00014692676884966714, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1720/6464 [31:10<1:26:32, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2476, 'grad_norm': 0.6666983962059021, 'learning_rate': 0.00014689580430407183, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1721/6464 [31:11<1:23:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0917, 'grad_norm': 0.7333517074584961, 'learning_rate': 0.00014686483975847656, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1722/6464 [31:12<1:24:12, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.322, 'grad_norm': 0.707850992679596, 'learning_rate': 0.00014683387521288125, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1723/6464 [31:14<1:34:26, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4981, 'grad_norm': 0.6035606265068054, 'learning_rate': 0.000146802910667286, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1724/6464 [31:15<1:27:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3294, 'grad_norm': 0.7512994408607483, 'learning_rate': 0.00014677194612169067, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1725/6464 [31:16<1:25:34, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1645, 'grad_norm': 0.6630950570106506, 'learning_rate': 0.00014674098157609538, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1726/6464 [31:16<1:19:30, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2561, 'grad_norm': 0.9699673652648926, 'learning_rate': 0.0001467100170305001, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1727/6464 [31:17<1:16:55, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1249, 'grad_norm': 0.7156279683113098, 'learning_rate': 0.00014667905248490478, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1728/6464 [31:18<1:18:44, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0493, 'grad_norm': 0.6235734224319458, 'learning_rate': 0.00014664808793930952, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1729/6464 [31:19<1:16:00, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2716, 'grad_norm': 0.8166409730911255, 'learning_rate': 0.0001466171233937142, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1730/6464 [31:20<1:15:13, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1627, 'grad_norm': 0.6913957595825195, 'learning_rate': 0.0001465861588481189, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1731/6464 [31:21<1:12:47, 1.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0708, 'grad_norm': 0.6777628064155579, 'learning_rate': 0.00014655519430252362, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1732/6464 [31:22<1:15:44, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3518, 'grad_norm': 0.807628870010376, 'learning_rate': 0.00014652422975692834, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1733/6464 [31:23<1:22:13, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2327, 'grad_norm': 0.5858245491981506, 'learning_rate': 0.00014649326521133305, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1734/6464 [31:24<1:22:14, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1677, 'grad_norm': 0.6360066533088684, 'learning_rate': 0.00014646230066573773, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1735/6464 [31:25<1:23:19, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0497, 'grad_norm': 0.7980700731277466, 'learning_rate': 0.00014643133612014244, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1736/6464 [31:27<1:25:18, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0641, 'grad_norm': 0.6156762838363647, 'learning_rate': 0.00014640037157454715, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1737/6464 [31:28<1:24:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1388, 'grad_norm': 0.5810524821281433, 'learning_rate': 0.00014636940702895186, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1738/6464 [31:29<1:26:51, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1994, 'grad_norm': 0.6189597249031067, 'learning_rate': 0.00014633844248335658, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1739/6464 [31:30<1:27:24, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.033, 'grad_norm': 0.6352214217185974, 'learning_rate': 0.00014630747793776126, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1740/6464 [31:31<1:28:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.33, 'grad_norm': 0.8030977845191956, 'learning_rate': 0.00014627651339216597, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1741/6464 [31:32<1:25:13, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2064, 'grad_norm': 0.7219893336296082, 'learning_rate': 0.00014624554884657068, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1742/6464 [31:33<1:28:39, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3594, 'grad_norm': 0.5993267297744751, 'learning_rate': 0.0001462145843009754, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1743/6464 [31:34<1:26:13, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3412, 'grad_norm': 0.8734257221221924, 'learning_rate': 0.0001461836197553801, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1744/6464 [31:35<1:20:53, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8943, 'grad_norm': 0.7136390209197998, 'learning_rate': 0.00014615265520978482, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1745/6464 [31:36<1:19:47, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1074, 'grad_norm': 0.6309806108474731, 'learning_rate': 0.0001461216906641895, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1746/6464 [31:37<1:20:10, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2488, 'grad_norm': 0.8152421712875366, 'learning_rate': 0.0001460907261185942, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1747/6464 [31:38<1:20:55, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1536, 'grad_norm': 0.6610663533210754, 'learning_rate': 0.00014605976157299892, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1748/6464 [31:40<1:27:37, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4897, 'grad_norm': 0.658872663974762, 'learning_rate': 0.0001460287970274036, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1749/6464 [31:41<1:26:42, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2029, 'grad_norm': 0.7661370635032654, 'learning_rate': 0.00014599783248180835, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1750/6464 [31:42<1:34:35, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3892, 'grad_norm': 0.6208559274673462, 'learning_rate': 0.00014596686793621303, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1751/6464 [31:43<1:37:42, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3172, 'grad_norm': 0.6597883105278015, 'learning_rate': 0.00014593590339061777, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1752/6464 [31:44<1:33:25, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2301, 'grad_norm': 0.7666455507278442, 'learning_rate': 0.00014590493884502245, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1753/6464 [31:45<1:28:57, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2036, 'grad_norm': 0.7914921045303345, 'learning_rate': 0.00014587397429942717, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1754/6464 [31:47<1:31:27, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1456, 'grad_norm': 0.5706140995025635, 'learning_rate': 0.00014584300975383188, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1755/6464 [31:48<1:25:38, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1156, 'grad_norm': 0.7420750856399536, 'learning_rate': 0.00014581204520823656, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1756/6464 [31:49<1:24:25, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2267, 'grad_norm': 0.7324924468994141, 'learning_rate': 0.0001457810806626413, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1757/6464 [31:49<1:18:25, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9468, 'grad_norm': 0.6822887063026428, 'learning_rate': 0.00014575011611704598, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1758/6464 [31:51<1:19:44, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1787, 'grad_norm': 0.7364097833633423, 'learning_rate': 0.0001457191515714507, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1759/6464 [31:52<1:21:08, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3154, 'grad_norm': 0.8187941908836365, 'learning_rate': 0.0001456881870258554, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1760/6464 [31:53<1:19:09, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1526, 'grad_norm': 0.6774740815162659, 'learning_rate': 0.0001456572224802601, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1761/6464 [31:54<1:20:36, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1958, 'grad_norm': 0.6558058857917786, 'learning_rate': 0.00014562625793466483, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1762/6464 [31:55<1:20:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2706, 'grad_norm': 0.7355534434318542, 'learning_rate': 0.0001455952933890695, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1763/6464 [31:56<1:22:31, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1675, 'grad_norm': 0.6504733562469482, 'learning_rate': 0.00014556432884347422, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1764/6464 [31:57<1:21:26, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.204, 'grad_norm': 0.6468796730041504, 'learning_rate': 0.00014553336429787894, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1765/6464 [31:58<1:21:17, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3237, 'grad_norm': 0.7271144986152649, 'learning_rate': 0.00014550239975228365, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1766/6464 [31:59<1:18:41, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2447, 'grad_norm': 0.7355502247810364, 'learning_rate': 0.00014547143520668836, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1767/6464 [32:00<1:20:15, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.07, 'grad_norm': 0.560288667678833, 'learning_rate': 0.00014544047066109304, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1768/6464 [32:01<1:18:02, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0456, 'grad_norm': 0.7453212738037109, 'learning_rate': 0.00014540950611549775, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1769/6464 [32:02<1:18:14, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1786, 'grad_norm': 0.76604825258255, 'learning_rate': 0.00014537854156990247, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1770/6464 [32:03<1:24:21, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.134, 'grad_norm': 0.6322401762008667, 'learning_rate': 0.00014534757702430718, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1771/6464 [32:04<1:23:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3314, 'grad_norm': 0.6900666356086731, 'learning_rate': 0.0001453166124787119, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1772/6464 [32:05<1:21:22, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0545, 'grad_norm': 0.6415703296661377, 'learning_rate': 0.0001452856479331166, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1773/6464 [32:06<1:20:06, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0052, 'grad_norm': 0.6212514042854309, 'learning_rate': 0.00014525468338752128, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1774/6464 [32:07<1:17:54, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1206, 'grad_norm': 0.8848097920417786, 'learning_rate': 0.000145223718841926, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1775/6464 [32:08<1:22:32, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3386, 'grad_norm': 0.6311784982681274, 'learning_rate': 0.0001451927542963307, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1776/6464 [32:09<1:24:31, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1414, 'grad_norm': 0.7411318421363831, 'learning_rate': 0.00014516178975073542, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 27%|โ–ˆโ–ˆโ–‹ | 1777/6464 [32:10<1:20:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0687, 'grad_norm': 0.7537239193916321, 'learning_rate': 0.00014513082520514013, 'epoch': 0.27}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1778/6464 [32:11<1:25:31, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.332, 'grad_norm': 0.6616002917289734, 'learning_rate': 0.0001450998606595448, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1779/6464 [32:13<1:25:52, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3573, 'grad_norm': 0.7296185493469238, 'learning_rate': 0.00014506889611394952, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1780/6464 [32:14<1:22:19, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2825, 'grad_norm': 0.78671795129776, 'learning_rate': 0.00014503793156835424, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1781/6464 [32:15<1:22:29, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1433, 'grad_norm': 0.6479520201683044, 'learning_rate': 0.00014500696702275895, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1782/6464 [32:16<1:23:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2822, 'grad_norm': 0.7151059508323669, 'learning_rate': 0.00014497600247716366, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1783/6464 [32:17<1:21:50, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1325, 'grad_norm': 0.7199093699455261, 'learning_rate': 0.00014494503793156834, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1784/6464 [32:18<1:25:20, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1229, 'grad_norm': 0.5646656155586243, 'learning_rate': 0.00014491407338597308, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1785/6464 [32:19<1:28:39, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0899, 'grad_norm': 0.6567051410675049, 'learning_rate': 0.00014488310884037777, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1786/6464 [32:20<1:28:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5067, 'grad_norm': 0.7268984913825989, 'learning_rate': 0.00014485214429478248, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1787/6464 [32:21<1:22:59, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2796, 'grad_norm': 0.9138290286064148, 'learning_rate': 0.0001448211797491872, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1788/6464 [32:22<1:24:49, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2837, 'grad_norm': 0.6204724907875061, 'learning_rate': 0.00014479021520359187, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1789/6464 [32:23<1:22:14, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0158, 'grad_norm': 0.7414832711219788, 'learning_rate': 0.0001447592506579966, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1790/6464 [32:24<1:24:00, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2965, 'grad_norm': 0.6289912462234497, 'learning_rate': 0.0001447282861124013, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1791/6464 [32:25<1:22:33, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3798, 'grad_norm': 0.7660495638847351, 'learning_rate': 0.00014469732156680603, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1792/6464 [32:26<1:17:33, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1803, 'grad_norm': 0.8482544422149658, 'learning_rate': 0.00014466635702121072, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1793/6464 [32:27<1:16:11, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0075, 'grad_norm': 0.6391054391860962, 'learning_rate': 0.00014463539247561543, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1794/6464 [32:28<1:16:09, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1065, 'grad_norm': 0.6916466355323792, 'learning_rate': 0.00014460442793002014, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1795/6464 [32:29<1:21:03, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.276, 'grad_norm': 0.6728925704956055, 'learning_rate': 0.00014457346338442483, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1796/6464 [32:31<1:23:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3079, 'grad_norm': 0.6703183054924011, 'learning_rate': 0.00014454249883882956, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1797/6464 [32:32<1:22:56, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2423, 'grad_norm': 0.9082999229431152, 'learning_rate': 0.00014451153429323425, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1798/6464 [32:33<1:22:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1532, 'grad_norm': 0.612596333026886, 'learning_rate': 0.00014448056974763896, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1799/6464 [32:34<1:23:55, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2607, 'grad_norm': 0.8452498912811279, 'learning_rate': 0.00014444960520204367, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1800/6464 [32:35<1:23:15, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1102, 'grad_norm': 0.6444496512413025, 'learning_rate': 0.00014441864065644835, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1801/6464 [32:36<1:22:20, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2549, 'grad_norm': 0.7858031988143921, 'learning_rate': 0.0001443876761108531, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1802/6464 [32:37<1:28:53, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2227, 'grad_norm': 0.6550272107124329, 'learning_rate': 0.00014435671156525778, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1803/6464 [32:38<1:26:23, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2118, 'grad_norm': 0.6182945370674133, 'learning_rate': 0.0001443257470196625, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1804/6464 [32:39<1:27:01, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0513, 'grad_norm': 0.6248626112937927, 'learning_rate': 0.0001442947824740672, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1805/6464 [32:40<1:23:55, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.985, 'grad_norm': 0.6547719836235046, 'learning_rate': 0.0001442638179284719, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1806/6464 [32:41<1:22:37, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.115, 'grad_norm': 0.9923617243766785, 'learning_rate': 0.00014423285338287662, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1807/6464 [32:42<1:20:41, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0806, 'grad_norm': 0.8211186528205872, 'learning_rate': 0.0001442018888372813, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1808/6464 [32:43<1:18:37, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9867, 'grad_norm': 0.6192861795425415, 'learning_rate': 0.00014417092429168602, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1809/6464 [32:44<1:19:43, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0384, 'grad_norm': 0.6414330005645752, 'learning_rate': 0.00014413995974609073, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1810/6464 [32:45<1:19:25, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2097, 'grad_norm': 0.694773256778717, 'learning_rate': 0.00014410899520049544, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1811/6464 [32:46<1:16:46, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1329, 'grad_norm': 0.7528817653656006, 'learning_rate': 0.00014407803065490015, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1812/6464 [32:47<1:18:33, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9202, 'grad_norm': 0.632024884223938, 'learning_rate': 0.00014404706610930486, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1813/6464 [32:49<1:24:05, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3293, 'grad_norm': 0.6066598296165466, 'learning_rate': 0.00014401610156370955, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1814/6464 [32:50<1:23:17, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3214, 'grad_norm': 0.7032580971717834, 'learning_rate': 0.00014398513701811426, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1815/6464 [32:51<1:24:33, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1187, 'grad_norm': 0.6834558248519897, 'learning_rate': 0.00014395417247251897, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1816/6464 [32:52<1:24:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2458, 'grad_norm': 0.6882972717285156, 'learning_rate': 0.00014392320792692368, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1817/6464 [32:53<1:30:05, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1926, 'grad_norm': 0.6704021096229553, 'learning_rate': 0.0001438922433813284, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1818/6464 [32:54<1:24:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1124, 'grad_norm': 0.7316025495529175, 'learning_rate': 0.00014386127883573308, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1819/6464 [32:55<1:25:00, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2453, 'grad_norm': 0.6442989110946655, 'learning_rate': 0.0001438303142901378, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1820/6464 [32:56<1:26:12, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1527, 'grad_norm': 0.7428528070449829, 'learning_rate': 0.0001437993497445425, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1821/6464 [32:57<1:25:28, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0208, 'grad_norm': 0.6666395664215088, 'learning_rate': 0.0001437683851989472, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1822/6464 [32:59<1:25:23, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.427, 'grad_norm': 0.6923649311065674, 'learning_rate': 0.00014373742065335192, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1823/6464 [32:59<1:21:16, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8688, 'grad_norm': 0.5845329761505127, 'learning_rate': 0.0001437064561077566, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1824/6464 [33:01<1:25:55, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5946, 'grad_norm': 0.7029290199279785, 'learning_rate': 0.00014367549156216135, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1825/6464 [33:02<1:18:58, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0072, 'grad_norm': 0.9190195202827454, 'learning_rate': 0.00014364452701656603, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1826/6464 [33:03<1:19:45, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0775, 'grad_norm': 0.6926282644271851, 'learning_rate': 0.00014361356247097074, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1827/6464 [33:04<1:17:27, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2404, 'grad_norm': 0.761457085609436, 'learning_rate': 0.00014358259792537545, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1828/6464 [33:05<1:27:02, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5349, 'grad_norm': 0.8612775206565857, 'learning_rate': 0.00014355163337978014, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1829/6464 [33:06<1:26:53, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3523, 'grad_norm': 0.677719235420227, 'learning_rate': 0.00014352066883418488, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1830/6464 [33:07<1:26:02, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2343, 'grad_norm': 0.720720112323761, 'learning_rate': 0.00014348970428858956, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1831/6464 [33:08<1:26:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5022, 'grad_norm': 0.7794167995452881, 'learning_rate': 0.0001434587397429943, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1832/6464 [33:09<1:20:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2002, 'grad_norm': 0.9982826113700867, 'learning_rate': 0.00014342777519739898, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1833/6464 [33:10<1:22:17, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1866, 'grad_norm': 0.659087598323822, 'learning_rate': 0.0001433968106518037, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1834/6464 [33:11<1:16:59, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9585, 'grad_norm': 0.7678914070129395, 'learning_rate': 0.0001433658461062084, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1835/6464 [33:12<1:22:41, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4327, 'grad_norm': 0.6890528798103333, 'learning_rate': 0.0001433348815606131, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1836/6464 [33:13<1:22:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.13, 'grad_norm': 0.6776272654533386, 'learning_rate': 0.00014330391701501783, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1837/6464 [33:15<1:23:52, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.129, 'grad_norm': 0.5780041813850403, 'learning_rate': 0.0001432729524694225, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1838/6464 [33:16<1:29:17, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4324, 'grad_norm': 0.6911560297012329, 'learning_rate': 0.00014324198792382722, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1839/6464 [33:17<1:25:40, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3094, 'grad_norm': 0.7143357992172241, 'learning_rate': 0.00014321102337823194, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1840/6464 [33:18<1:23:44, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0323, 'grad_norm': 0.6484466791152954, 'learning_rate': 0.00014318005883263662, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1841/6464 [33:19<1:24:11, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0308, 'grad_norm': 0.6137610077857971, 'learning_rate': 0.00014314909428704136, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 28%|โ–ˆโ–ˆโ–Š | 1842/6464 [33:20<1:28:19, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1437, 'grad_norm': 0.6003168225288391, 'learning_rate': 0.00014311812974144604, 'epoch': 0.28}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1843/6464 [33:21<1:27:44, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0519, 'grad_norm': 0.6122291088104248, 'learning_rate': 0.00014308716519585075, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1844/6464 [33:22<1:22:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0016, 'grad_norm': 0.6850214004516602, 'learning_rate': 0.00014305620065025546, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1845/6464 [33:24<1:28:40, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3787, 'grad_norm': 0.7567828297615051, 'learning_rate': 0.00014302523610466018, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1846/6464 [33:25<1:24:53, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0491, 'grad_norm': 0.6176290512084961, 'learning_rate': 0.0001429942715590649, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1847/6464 [33:26<1:21:19, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1044, 'grad_norm': 0.745747983455658, 'learning_rate': 0.00014296330701346957, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1848/6464 [33:27<1:18:04, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0748, 'grad_norm': 0.7404491901397705, 'learning_rate': 0.00014293234246787428, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1849/6464 [33:28<1:18:19, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1256, 'grad_norm': 0.6757046580314636, 'learning_rate': 0.000142901377922279, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1850/6464 [33:29<1:20:58, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1908, 'grad_norm': 0.70189368724823, 'learning_rate': 0.0001428704133766837, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1851/6464 [33:30<1:17:35, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0498, 'grad_norm': 0.6453136205673218, 'learning_rate': 0.00014283944883108842, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1852/6464 [33:31<1:18:59, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0767, 'grad_norm': 0.6111382246017456, 'learning_rate': 0.00014280848428549313, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1853/6464 [33:32<1:21:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2555, 'grad_norm': 0.7199217081069946, 'learning_rate': 0.0001427775197398978, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1854/6464 [33:33<1:30:08, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9761, 'grad_norm': 0.5979136228561401, 'learning_rate': 0.00014274655519430252, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1855/6464 [33:34<1:26:00, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0389, 'grad_norm': 0.8373076915740967, 'learning_rate': 0.00014271559064870724, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1856/6464 [33:35<1:24:08, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2642, 'grad_norm': 0.7355744242668152, 'learning_rate': 0.00014268462610311195, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1857/6464 [33:36<1:25:05, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1675, 'grad_norm': 0.6692301630973816, 'learning_rate': 0.00014265366155751666, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–Š | 1858/6464 [33:37<1:19:35, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1744, 'grad_norm': 0.8726731538772583, 'learning_rate': 0.00014262269701192134, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1859/6464 [33:38<1:23:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3004, 'grad_norm': 0.6517997980117798, 'learning_rate': 0.00014259173246632605, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1860/6464 [33:39<1:21:53, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1546, 'grad_norm': 0.6964388489723206, 'learning_rate': 0.00014256076792073077, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1861/6464 [33:40<1:17:37, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9293, 'grad_norm': 0.6604307889938354, 'learning_rate': 0.00014252980337513548, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1862/6464 [33:42<1:20:24, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1137, 'grad_norm': 0.6284521818161011, 'learning_rate': 0.0001424988388295402, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1863/6464 [33:43<1:20:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3227, 'grad_norm': 0.7432446479797363, 'learning_rate': 0.00014246787428394487, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1864/6464 [33:44<1:25:28, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1177, 'grad_norm': 0.5915939211845398, 'learning_rate': 0.0001424369097383496, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1865/6464 [33:45<1:19:10, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8869, 'grad_norm': 0.6366661787033081, 'learning_rate': 0.0001424059451927543, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1866/6464 [33:46<1:22:57, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2494, 'grad_norm': 0.5917152166366577, 'learning_rate': 0.000142374980647159, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1867/6464 [33:47<1:27:45, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5277, 'grad_norm': 0.6687609553337097, 'learning_rate': 0.00014234401610156372, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1868/6464 [33:48<1:28:14, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4461, 'grad_norm': 0.6870551109313965, 'learning_rate': 0.0001423130515559684, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1869/6464 [33:49<1:25:44, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.249, 'grad_norm': 0.8321053981781006, 'learning_rate': 0.00014228208701037314, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1870/6464 [33:51<1:26:50, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2548, 'grad_norm': 0.6960984468460083, 'learning_rate': 0.00014225112246477782, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1871/6464 [33:52<1:29:40, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2235, 'grad_norm': 0.5825527906417847, 'learning_rate': 0.00014222015791918256, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1872/6464 [33:53<1:28:57, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2628, 'grad_norm': 0.6830011010169983, 'learning_rate': 0.00014218919337358725, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1873/6464 [33:54<1:25:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2566, 'grad_norm': 0.7186337113380432, 'learning_rate': 0.00014215822882799196, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1874/6464 [33:55<1:27:52, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3632, 'grad_norm': 0.6922121047973633, 'learning_rate': 0.00014212726428239667, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1875/6464 [33:56<1:27:27, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4474, 'grad_norm': 0.7288295030593872, 'learning_rate': 0.00014209629973680135, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1876/6464 [33:57<1:26:38, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2591, 'grad_norm': 0.6915355920791626, 'learning_rate': 0.0001420653351912061, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1877/6464 [33:59<1:26:29, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2314, 'grad_norm': 0.7371440529823303, 'learning_rate': 0.00014203437064561078, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1878/6464 [34:00<1:27:24, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2044, 'grad_norm': 0.7406036257743835, 'learning_rate': 0.0001420034061000155, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1879/6464 [34:01<1:28:26, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1791, 'grad_norm': 0.6211732625961304, 'learning_rate': 0.0001419724415544202, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1880/6464 [34:02<1:28:10, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5525, 'grad_norm': 0.8001914024353027, 'learning_rate': 0.00014194147700882488, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1881/6464 [34:03<1:24:48, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2257, 'grad_norm': 0.723901093006134, 'learning_rate': 0.00014191051246322962, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1882/6464 [34:04<1:25:05, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3249, 'grad_norm': 0.7094500660896301, 'learning_rate': 0.0001418795479176343, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1883/6464 [34:05<1:23:19, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3837, 'grad_norm': 0.7510587573051453, 'learning_rate': 0.00014184858337203902, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1884/6464 [34:06<1:23:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1136, 'grad_norm': 0.7124989628791809, 'learning_rate': 0.00014181761882644373, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1885/6464 [34:07<1:23:44, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1946, 'grad_norm': 0.6165042519569397, 'learning_rate': 0.00014178665428084844, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1886/6464 [34:09<1:26:02, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3149, 'grad_norm': 0.6404178738594055, 'learning_rate': 0.00014175568973525315, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1887/6464 [34:10<1:23:37, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3119, 'grad_norm': 0.8032846450805664, 'learning_rate': 0.00014172472518965784, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1888/6464 [34:11<1:20:02, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0994, 'grad_norm': 0.730646550655365, 'learning_rate': 0.00014169376064406255, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1889/6464 [34:11<1:16:19, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9186, 'grad_norm': 0.6416664123535156, 'learning_rate': 0.00014166279609846726, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1890/6464 [34:13<1:18:54, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1079, 'grad_norm': 0.729136049747467, 'learning_rate': 0.00014163183155287197, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1891/6464 [34:14<1:19:09, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1337, 'grad_norm': 0.7572920918464661, 'learning_rate': 0.00014160086700727668, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1892/6464 [34:15<1:18:46, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0139, 'grad_norm': 0.7203485369682312, 'learning_rate': 0.0001415699024616814, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1893/6464 [34:16<1:14:45, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0226, 'grad_norm': 0.7237182259559631, 'learning_rate': 0.00014153893791608608, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1894/6464 [34:17<1:16:04, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.466, 'grad_norm': 0.8006652593612671, 'learning_rate': 0.0001415079733704908, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1895/6464 [34:18<1:21:17, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1705, 'grad_norm': 0.6260863542556763, 'learning_rate': 0.0001414770088248955, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1896/6464 [34:19<1:18:09, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.317, 'grad_norm': 0.7511976957321167, 'learning_rate': 0.0001414460442793002, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1897/6464 [34:20<1:16:39, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0647, 'grad_norm': 0.6603690981864929, 'learning_rate': 0.00014141507973370492, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1898/6464 [34:21<1:21:47, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2373, 'grad_norm': 0.6335539817810059, 'learning_rate': 0.0001413841151881096, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1899/6464 [34:22<1:25:09, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1729, 'grad_norm': 0.6119399070739746, 'learning_rate': 0.00014135315064251432, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1900/6464 [34:23<1:19:53, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2156, 'grad_norm': 0.8144897818565369, 'learning_rate': 0.00014132218609691903, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1901/6464 [34:24<1:19:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1143, 'grad_norm': 0.6394504904747009, 'learning_rate': 0.00014129122155132374, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1902/6464 [34:25<1:20:04, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5675, 'grad_norm': 0.73646080493927, 'learning_rate': 0.00014126025700572845, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1903/6464 [34:26<1:19:50, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9857, 'grad_norm': 0.6397032737731934, 'learning_rate': 0.00014122929246013314, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1904/6464 [34:27<1:19:29, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1472, 'grad_norm': 0.625990092754364, 'learning_rate': 0.00014119832791453788, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1905/6464 [34:28<1:23:10, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2184, 'grad_norm': 0.6032334566116333, 'learning_rate': 0.00014116736336894256, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 29%|โ–ˆโ–ˆโ–‰ | 1906/6464 [34:29<1:20:29, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1585, 'grad_norm': 0.6505504846572876, 'learning_rate': 0.00014113639882334727, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1907/6464 [34:31<1:26:51, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3872, 'grad_norm': 0.6473573446273804, 'learning_rate': 0.00014110543427775198, 'epoch': 0.29}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1908/6464 [34:32<1:28:45, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2572, 'grad_norm': 0.6237452030181885, 'learning_rate': 0.00014107446973215667, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1909/6464 [34:33<1:21:54, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.903, 'grad_norm': 0.6648027896881104, 'learning_rate': 0.0001410435051865614, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1910/6464 [34:34<1:20:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1376, 'grad_norm': 0.6626010537147522, 'learning_rate': 0.0001410125406409661, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1911/6464 [34:35<1:15:40, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0848, 'grad_norm': 0.7177520990371704, 'learning_rate': 0.00014098157609537083, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1912/6464 [34:36<1:17:09, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1398, 'grad_norm': 0.6344439387321472, 'learning_rate': 0.0001409506115497755, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1913/6464 [34:37<1:14:54, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0067, 'grad_norm': 0.6795694828033447, 'learning_rate': 0.00014091964700418022, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1914/6464 [34:38<1:15:16, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.27, 'grad_norm': 0.6845034956932068, 'learning_rate': 0.00014088868245858493, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1915/6464 [34:38<1:11:11, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8462, 'grad_norm': 0.6845260262489319, 'learning_rate': 0.00014085771791298962, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1916/6464 [34:40<1:16:46, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2427, 'grad_norm': 0.6168681383132935, 'learning_rate': 0.00014082675336739436, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1917/6464 [34:41<1:21:42, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1622, 'grad_norm': 0.5920812487602234, 'learning_rate': 0.00014079578882179904, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1918/6464 [34:42<1:25:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3659, 'grad_norm': 0.6024805903434753, 'learning_rate': 0.00014076482427620375, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1919/6464 [34:43<1:20:34, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0123, 'grad_norm': 0.6772007942199707, 'learning_rate': 0.00014073385973060846, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1920/6464 [34:44<1:20:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2119, 'grad_norm': 0.7077505588531494, 'learning_rate': 0.00014070289518501315, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1921/6464 [34:45<1:20:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1609, 'grad_norm': 0.66804438829422, 'learning_rate': 0.0001406719306394179, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1922/6464 [34:46<1:20:17, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1523, 'grad_norm': 0.7484270334243774, 'learning_rate': 0.00014064096609382257, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1923/6464 [34:47<1:17:59, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2404, 'grad_norm': 0.6583542227745056, 'learning_rate': 0.00014061000154822728, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1924/6464 [34:48<1:18:39, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.07, 'grad_norm': 0.8879433274269104, 'learning_rate': 0.000140579037002632, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1925/6464 [34:49<1:20:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1856, 'grad_norm': 0.5928547382354736, 'learning_rate': 0.0001405480724570367, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1926/6464 [34:50<1:18:02, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2819, 'grad_norm': 0.7606542110443115, 'learning_rate': 0.00014051710791144142, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1927/6464 [34:51<1:19:30, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2065, 'grad_norm': 0.7368652820587158, 'learning_rate': 0.0001404861433658461, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1928/6464 [34:53<1:25:57, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.14, 'grad_norm': 0.612014651298523, 'learning_rate': 0.0001404551788202508, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1929/6464 [34:54<1:20:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0605, 'grad_norm': 0.7146203517913818, 'learning_rate': 0.00014042421427465552, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1930/6464 [34:55<1:21:13, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2718, 'grad_norm': 0.6546228528022766, 'learning_rate': 0.00014039324972906023, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1931/6464 [34:56<1:23:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3806, 'grad_norm': 0.688432514667511, 'learning_rate': 0.00014036228518346495, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1932/6464 [34:57<1:20:17, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0751, 'grad_norm': 0.6984400749206543, 'learning_rate': 0.00014033132063786966, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1933/6464 [34:58<1:21:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0653, 'grad_norm': 0.6108294129371643, 'learning_rate': 0.00014030035609227434, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1934/6464 [34:59<1:16:29, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9201, 'grad_norm': 0.6255795955657959, 'learning_rate': 0.00014026939154667905, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1935/6464 [35:00<1:17:45, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2341, 'grad_norm': 0.6328851580619812, 'learning_rate': 0.00014023842700108376, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1936/6464 [35:01<1:17:17, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4709, 'grad_norm': 0.8295718431472778, 'learning_rate': 0.00014020746245548848, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1937/6464 [35:02<1:20:26, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3339, 'grad_norm': 0.7901987433433533, 'learning_rate': 0.0001401764979098932, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1938/6464 [35:03<1:20:41, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1939, 'grad_norm': 0.6950175762176514, 'learning_rate': 0.00014014553336429787, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–‰ | 1939/6464 [35:05<1:26:53, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2841, 'grad_norm': 0.6123867630958557, 'learning_rate': 0.00014011456881870258, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1940/6464 [35:06<1:26:05, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1013, 'grad_norm': 0.6310936212539673, 'learning_rate': 0.0001400836042731073, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1941/6464 [35:07<1:24:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2213, 'grad_norm': 0.7399976253509521, 'learning_rate': 0.000140052639727512, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1942/6464 [35:08<1:25:28, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3911, 'grad_norm': 0.628652036190033, 'learning_rate': 0.00014002167518191672, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1943/6464 [35:09<1:29:58, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2181, 'grad_norm': 0.6056503057479858, 'learning_rate': 0.0001399907106363214, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1944/6464 [35:10<1:23:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8901, 'grad_norm': 0.6472386717796326, 'learning_rate': 0.00013995974609072614, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1945/6464 [35:11<1:20:07, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1557, 'grad_norm': 0.7376834750175476, 'learning_rate': 0.00013992878154513082, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1946/6464 [35:12<1:23:21, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0693, 'grad_norm': 0.6404610276222229, 'learning_rate': 0.00013989781699953554, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1947/6464 [35:13<1:23:22, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.153, 'grad_norm': 0.7137904763221741, 'learning_rate': 0.00013986685245394025, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1948/6464 [35:14<1:21:58, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2825, 'grad_norm': 0.6539865732192993, 'learning_rate': 0.00013983588790834493, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1949/6464 [35:16<1:23:20, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2039, 'grad_norm': 0.7001561522483826, 'learning_rate': 0.00013980492336274967, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1950/6464 [35:17<1:21:03, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1504, 'grad_norm': 0.6579002141952515, 'learning_rate': 0.00013977395881715435, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1951/6464 [35:18<1:18:57, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1247, 'grad_norm': 0.6649113893508911, 'learning_rate': 0.0001397429942715591, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1952/6464 [35:19<1:16:54, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2467, 'grad_norm': 0.6854242086410522, 'learning_rate': 0.00013971202972596378, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1953/6464 [35:20<1:22:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4958, 'grad_norm': 0.6181430220603943, 'learning_rate': 0.0001396810651803685, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1954/6464 [35:21<1:18:58, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1944, 'grad_norm': 0.7074693441390991, 'learning_rate': 0.0001396501006347732, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1955/6464 [35:22<1:18:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3597, 'grad_norm': 0.7021893262863159, 'learning_rate': 0.00013961913608917788, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1956/6464 [35:23<1:16:31, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0444, 'grad_norm': 0.7203199863433838, 'learning_rate': 0.00013958817154358262, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1957/6464 [35:24<1:19:43, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3748, 'grad_norm': 0.6670400500297546, 'learning_rate': 0.0001395572069979873, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1958/6464 [35:25<1:16:41, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1613, 'grad_norm': 0.7596177458763123, 'learning_rate': 0.00013952624245239202, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1959/6464 [35:26<1:16:24, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1802, 'grad_norm': 0.7692952156066895, 'learning_rate': 0.00013949527790679673, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1960/6464 [35:27<1:15:03, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2742, 'grad_norm': 0.824395477771759, 'learning_rate': 0.0001394643133612014, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1961/6464 [35:28<1:12:51, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0491, 'grad_norm': 0.7296826839447021, 'learning_rate': 0.00013943334881560615, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1962/6464 [35:29<1:16:06, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2938, 'grad_norm': 0.7010835409164429, 'learning_rate': 0.00013940238427001084, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1963/6464 [35:30<1:20:01, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4537, 'grad_norm': 0.7670226097106934, 'learning_rate': 0.00013937141972441555, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1964/6464 [35:31<1:22:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1565, 'grad_norm': 0.7328709363937378, 'learning_rate': 0.00013934045517882026, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1965/6464 [35:32<1:24:52, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4065, 'grad_norm': 0.6565738320350647, 'learning_rate': 0.00013930949063322497, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1966/6464 [35:34<1:23:47, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4449, 'grad_norm': 0.7715896368026733, 'learning_rate': 0.00013927852608762968, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1967/6464 [35:35<1:24:46, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2078, 'grad_norm': 0.6739420294761658, 'learning_rate': 0.00013924756154203437, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1968/6464 [35:36<1:27:23, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2171, 'grad_norm': 0.6489429473876953, 'learning_rate': 0.00013921659699643908, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1969/6464 [35:37<1:24:39, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1079, 'grad_norm': 0.7661980986595154, 'learning_rate': 0.0001391856324508438, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1970/6464 [35:38<1:27:27, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3472, 'grad_norm': 0.63795006275177, 'learning_rate': 0.0001391546679052485, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 30%|โ–ˆโ–ˆโ–ˆ | 1971/6464 [35:39<1:23:30, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0745, 'grad_norm': 0.7101340293884277, 'learning_rate': 0.0001391237033596532, 'epoch': 0.3}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1972/6464 [35:40<1:19:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1513, 'grad_norm': 0.6755905747413635, 'learning_rate': 0.00013909273881405792, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1973/6464 [35:41<1:20:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2036, 'grad_norm': 0.6856864094734192, 'learning_rate': 0.0001390617742684626, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1974/6464 [35:42<1:19:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1884, 'grad_norm': 0.7324087619781494, 'learning_rate': 0.00013903080972286732, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1975/6464 [35:43<1:17:23, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1291, 'grad_norm': 0.666582465171814, 'learning_rate': 0.00013899984517727203, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1976/6464 [35:44<1:18:44, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3793, 'grad_norm': 0.7134965062141418, 'learning_rate': 0.00013896888063167674, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1977/6464 [35:45<1:19:53, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2033, 'grad_norm': 0.5874163508415222, 'learning_rate': 0.00013893791608608145, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1978/6464 [35:47<1:19:56, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2608, 'grad_norm': 0.8047729134559631, 'learning_rate': 0.00013890695154048614, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1979/6464 [35:48<1:21:20, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2583, 'grad_norm': 0.6384249925613403, 'learning_rate': 0.00013887598699489087, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1980/6464 [35:49<1:17:40, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1854, 'grad_norm': 0.7133757472038269, 'learning_rate': 0.00013884502244929556, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1981/6464 [35:50<1:22:59, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.276, 'grad_norm': 0.6082994341850281, 'learning_rate': 0.00013881405790370027, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1982/6464 [35:51<1:19:19, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.32, 'grad_norm': 0.7634953856468201, 'learning_rate': 0.00013878309335810498, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1983/6464 [35:52<1:21:09, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2369, 'grad_norm': 0.6187676191329956, 'learning_rate': 0.00013875212881250967, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1984/6464 [35:53<1:18:40, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0944, 'grad_norm': 0.6250824928283691, 'learning_rate': 0.0001387211642669144, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1985/6464 [35:54<1:19:11, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3245, 'grad_norm': 0.7445777654647827, 'learning_rate': 0.0001386901997213191, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1986/6464 [35:55<1:20:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2696, 'grad_norm': 0.7405812740325928, 'learning_rate': 0.0001386592351757238, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1987/6464 [35:56<1:17:00, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0861, 'grad_norm': 0.7768813371658325, 'learning_rate': 0.0001386282706301285, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1988/6464 [35:57<1:14:58, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0801, 'grad_norm': 0.65062415599823, 'learning_rate': 0.0001385973060845332, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1989/6464 [35:58<1:11:17, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2465, 'grad_norm': 0.726227879524231, 'learning_rate': 0.00013856634153893793, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1990/6464 [35:59<1:14:17, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3062, 'grad_norm': 0.841984212398529, 'learning_rate': 0.00013853537699334262, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1991/6464 [36:00<1:15:42, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2822, 'grad_norm': 0.6124821901321411, 'learning_rate': 0.00013850441244774736, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1992/6464 [36:01<1:19:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2947, 'grad_norm': 0.768710732460022, 'learning_rate': 0.00013847344790215204, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1993/6464 [36:02<1:22:17, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1153, 'grad_norm': 0.6270116567611694, 'learning_rate': 0.00013844248335655675, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1994/6464 [36:03<1:17:47, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2047, 'grad_norm': 0.7320355176925659, 'learning_rate': 0.00013841151881096146, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1995/6464 [36:04<1:15:59, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0037, 'grad_norm': 0.6547320485115051, 'learning_rate': 0.00013838055426536615, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1996/6464 [36:05<1:12:49, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1015, 'grad_norm': 0.7272984981536865, 'learning_rate': 0.00013834958971977089, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1997/6464 [36:07<1:22:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2839, 'grad_norm': 0.6679256558418274, 'learning_rate': 0.00013831862517417557, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1998/6464 [36:07<1:18:41, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1749, 'grad_norm': 0.7273695468902588, 'learning_rate': 0.00013828766062858028, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 1999/6464 [36:09<1:24:55, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5038, 'grad_norm': 0.7452895641326904, 'learning_rate': 0.000138256696082985, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2000/6464 [36:10<1:29:03, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1908, 'grad_norm': 0.6038113236427307, 'learning_rate': 0.0001382257315373897, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2001/6464 [36:12<1:45:05, 1.41s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2026, 'grad_norm': 0.6847729682922363, 'learning_rate': 0.00013819476699179442, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2002/6464 [36:13<1:35:54, 1.29s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1793, 'grad_norm': 0.6867843866348267, 'learning_rate': 0.0001381638024461991, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2003/6464 [36:14<1:35:11, 1.28s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2093, 'grad_norm': 0.6088529229164124, 'learning_rate': 0.0001381328379006038, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2004/6464 [36:15<1:33:12, 1.25s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2441, 'grad_norm': 0.6735215783119202, 'learning_rate': 0.00013810187335500852, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2005/6464 [36:17<1:28:26, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1008, 'grad_norm': 0.7242269515991211, 'learning_rate': 0.00013807090880941323, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2006/6464 [36:18<1:28:41, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2745, 'grad_norm': 0.6964374780654907, 'learning_rate': 0.00013803994426381795, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2007/6464 [36:19<1:25:11, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3902, 'grad_norm': 0.7516363859176636, 'learning_rate': 0.00013800897971822263, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2008/6464 [36:20<1:25:20, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.065, 'grad_norm': 0.6331027150154114, 'learning_rate': 0.00013797801517262734, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2009/6464 [36:21<1:23:29, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2301, 'grad_norm': 0.6629226207733154, 'learning_rate': 0.00013794705062703205, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2010/6464 [36:22<1:24:54, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1608, 'grad_norm': 0.6007479429244995, 'learning_rate': 0.00013791608608143676, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2011/6464 [36:23<1:24:07, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2617, 'grad_norm': 0.6204743981361389, 'learning_rate': 0.00013788512153584148, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2012/6464 [36:24<1:18:37, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0057, 'grad_norm': 0.7477799654006958, 'learning_rate': 0.0001378541569902462, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2013/6464 [36:25<1:17:53, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1801, 'grad_norm': 0.6416575312614441, 'learning_rate': 0.00013782319244465087, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2014/6464 [36:26<1:17:48, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1601, 'grad_norm': 0.7344391345977783, 'learning_rate': 0.00013779222789905558, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2015/6464 [36:27<1:17:27, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5842, 'grad_norm': 0.7497484087944031, 'learning_rate': 0.0001377612633534603, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2016/6464 [36:28<1:19:10, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3634, 'grad_norm': 0.708260715007782, 'learning_rate': 0.000137730298807865, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2017/6464 [36:29<1:17:24, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2231, 'grad_norm': 0.8634337186813354, 'learning_rate': 0.00013769933426226972, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2018/6464 [36:31<1:20:17, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2923, 'grad_norm': 0.715897798538208, 'learning_rate': 0.0001376683697166744, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆ | 2019/6464 [36:32<1:19:11, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2679, 'grad_norm': 0.6823880076408386, 'learning_rate': 0.00013763740517107914, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2020/6464 [36:33<1:23:15, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.974, 'grad_norm': 0.5586377382278442, 'learning_rate': 0.00013760644062548382, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2021/6464 [36:34<1:19:45, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9465, 'grad_norm': 0.836482584476471, 'learning_rate': 0.00013757547607988853, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2022/6464 [36:35<1:18:26, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1061, 'grad_norm': 0.6606568694114685, 'learning_rate': 0.00013754451153429325, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2023/6464 [36:36<1:20:37, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.256, 'grad_norm': 0.6394343376159668, 'learning_rate': 0.00013751354698869793, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2024/6464 [36:37<1:19:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1835, 'grad_norm': 0.6776270866394043, 'learning_rate': 0.00013748258244310267, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2025/6464 [36:38<1:16:53, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0752, 'grad_norm': 0.6521144509315491, 'learning_rate': 0.00013745161789750735, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2026/6464 [36:39<1:17:09, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4339, 'grad_norm': 0.7261507511138916, 'learning_rate': 0.00013742065335191206, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2027/6464 [36:40<1:16:15, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0076, 'grad_norm': 0.6199666857719421, 'learning_rate': 0.00013738968880631678, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2028/6464 [36:41<1:21:13, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3691, 'grad_norm': 0.6370163559913635, 'learning_rate': 0.00013735872426072146, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2029/6464 [36:43<1:27:01, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3869, 'grad_norm': 0.6655782461166382, 'learning_rate': 0.0001373277597151262, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2030/6464 [36:44<1:23:46, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9599, 'grad_norm': 0.6417722702026367, 'learning_rate': 0.00013729679516953088, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2031/6464 [36:45<1:25:00, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2255, 'grad_norm': 0.7796891331672668, 'learning_rate': 0.00013726583062393562, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2032/6464 [36:46<1:34:12, 1.28s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1585, 'grad_norm': 0.5090940594673157, 'learning_rate': 0.0001372348660783403, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2033/6464 [36:48<1:30:02, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1886, 'grad_norm': 0.6542036533355713, 'learning_rate': 0.00013720390153274502, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2034/6464 [36:49<1:23:56, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0895, 'grad_norm': 0.7577077746391296, 'learning_rate': 0.00013717293698714973, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2035/6464 [36:50<1:26:57, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2745, 'grad_norm': 0.6049309372901917, 'learning_rate': 0.0001371419724415544, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 31%|โ–ˆโ–ˆโ–ˆโ– | 2036/6464 [36:51<1:27:38, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.435, 'grad_norm': 0.7028056979179382, 'learning_rate': 0.00013711100789595915, 'epoch': 0.31}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2037/6464 [36:52<1:25:49, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0942, 'grad_norm': 0.611076831817627, 'learning_rate': 0.00013708004335036383, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2038/6464 [36:53<1:27:47, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3427, 'grad_norm': 0.709429144859314, 'learning_rate': 0.00013704907880476855, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2039/6464 [36:54<1:25:26, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2879, 'grad_norm': 0.7371345162391663, 'learning_rate': 0.00013701811425917326, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2040/6464 [36:55<1:22:03, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1605, 'grad_norm': 0.7175615429878235, 'learning_rate': 0.00013698714971357797, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2041/6464 [36:57<1:21:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1981, 'grad_norm': 0.6764093637466431, 'learning_rate': 0.00013695618516798268, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2042/6464 [36:57<1:14:26, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8537, 'grad_norm': 0.7830266356468201, 'learning_rate': 0.00013692522062238736, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2043/6464 [36:59<1:20:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4, 'grad_norm': 0.7349899411201477, 'learning_rate': 0.00013689425607679208, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2044/6464 [37:00<1:16:36, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1063, 'grad_norm': 0.7999548316001892, 'learning_rate': 0.0001368632915311968, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2045/6464 [37:01<1:18:22, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4102, 'grad_norm': 0.8649895191192627, 'learning_rate': 0.0001368323269856015, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2046/6464 [37:02<1:18:31, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1814, 'grad_norm': 0.6558084487915039, 'learning_rate': 0.0001368013624400062, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2047/6464 [37:03<1:24:09, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3899, 'grad_norm': 0.6064239144325256, 'learning_rate': 0.0001367703978944109, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2048/6464 [37:04<1:21:20, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3756, 'grad_norm': 0.6996934413909912, 'learning_rate': 0.0001367394333488156, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2049/6464 [37:05<1:19:34, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2816, 'grad_norm': 0.7512071132659912, 'learning_rate': 0.00013670846880322032, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2050/6464 [37:06<1:21:37, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2803, 'grad_norm': 0.7289299368858337, 'learning_rate': 0.00013667750425762503, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2051/6464 [37:07<1:22:30, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3048, 'grad_norm': 0.7350072860717773, 'learning_rate': 0.00013664653971202974, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2052/6464 [37:08<1:19:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1055, 'grad_norm': 0.7437074780464172, 'learning_rate': 0.00013661557516643445, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2053/6464 [37:09<1:16:56, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1675, 'grad_norm': 0.7060506939888, 'learning_rate': 0.00013658461062083914, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2054/6464 [37:11<1:26:14, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4516, 'grad_norm': 0.6063777804374695, 'learning_rate': 0.00013655364607524385, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2055/6464 [37:12<1:26:11, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.266, 'grad_norm': 0.6386175751686096, 'learning_rate': 0.00013652268152964856, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2056/6464 [37:13<1:26:22, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0534, 'grad_norm': 0.6636368632316589, 'learning_rate': 0.00013649171698405327, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2057/6464 [37:14<1:25:48, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0516, 'grad_norm': 0.6685531735420227, 'learning_rate': 0.00013646075243845798, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2058/6464 [37:15<1:22:02, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2047, 'grad_norm': 0.7099279165267944, 'learning_rate': 0.00013642978789286266, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2059/6464 [37:16<1:16:59, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1942, 'grad_norm': 0.8156781196594238, 'learning_rate': 0.0001363988233472674, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2060/6464 [37:17<1:17:47, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4594, 'grad_norm': 0.7294090986251831, 'learning_rate': 0.0001363678588016721, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2061/6464 [37:18<1:18:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.152, 'grad_norm': 0.6465137004852295, 'learning_rate': 0.0001363368942560768, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2062/6464 [37:20<1:21:31, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1777, 'grad_norm': 0.6628019213676453, 'learning_rate': 0.0001363059297104815, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2063/6464 [37:21<1:21:45, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2853, 'grad_norm': 0.6301262974739075, 'learning_rate': 0.0001362749651648862, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2064/6464 [37:22<1:18:41, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1531, 'grad_norm': 0.8526490330696106, 'learning_rate': 0.00013624400061929093, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2065/6464 [37:23<1:17:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2648, 'grad_norm': 0.6475807428359985, 'learning_rate': 0.00013621303607369562, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2066/6464 [37:24<1:20:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1838, 'grad_norm': 0.6069791913032532, 'learning_rate': 0.00013618207152810033, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2067/6464 [37:25<1:17:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3384, 'grad_norm': 0.7277417182922363, 'learning_rate': 0.00013615110698250504, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2068/6464 [37:26<1:17:18, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1744, 'grad_norm': 0.6705520749092102, 'learning_rate': 0.00013612014243690972, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2069/6464 [37:27<1:17:46, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2464, 'grad_norm': 0.7256984710693359, 'learning_rate': 0.00013608917789131446, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2070/6464 [37:28<1:19:26, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2149, 'grad_norm': 0.6411280035972595, 'learning_rate': 0.00013605821334571915, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2071/6464 [37:29<1:18:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0973, 'grad_norm': 0.672809898853302, 'learning_rate': 0.00013602724880012389, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2072/6464 [37:30<1:19:09, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2517, 'grad_norm': 0.6911855936050415, 'learning_rate': 0.00013599628425452857, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2073/6464 [37:31<1:17:50, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1878, 'grad_norm': 0.7240766286849976, 'learning_rate': 0.00013596531970893328, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2074/6464 [37:32<1:17:17, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0993, 'grad_norm': 0.6231467723846436, 'learning_rate': 0.000135934355163338, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2075/6464 [37:33<1:18:42, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1396, 'grad_norm': 0.6480361223220825, 'learning_rate': 0.00013590339061774268, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2076/6464 [37:35<1:18:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.278, 'grad_norm': 0.8607900738716125, 'learning_rate': 0.00013587242607214742, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2077/6464 [37:36<1:17:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0963, 'grad_norm': 0.6463894248008728, 'learning_rate': 0.0001358414615265521, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2078/6464 [37:37<1:16:07, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1376, 'grad_norm': 0.7314803004264832, 'learning_rate': 0.0001358104969809568, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2079/6464 [37:38<1:13:54, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.255, 'grad_norm': 0.7634405493736267, 'learning_rate': 0.00013577953243536152, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2080/6464 [37:38<1:10:29, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2348, 'grad_norm': 0.9219048023223877, 'learning_rate': 0.00013574856788976623, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2081/6464 [37:40<1:14:11, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2102, 'grad_norm': 0.6765404343605042, 'learning_rate': 0.00013571760334417094, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2082/6464 [37:41<1:15:24, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0408, 'grad_norm': 0.873667299747467, 'learning_rate': 0.00013568663879857563, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2083/6464 [37:42<1:13:14, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8637, 'grad_norm': 0.598600447177887, 'learning_rate': 0.00013565567425298034, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2084/6464 [37:43<1:14:06, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1214, 'grad_norm': 0.6494306921958923, 'learning_rate': 0.00013562470970738505, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2085/6464 [37:44<1:13:23, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0496, 'grad_norm': 0.6574106216430664, 'learning_rate': 0.00013559374516178976, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2086/6464 [37:45<1:15:01, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3563, 'grad_norm': 0.6829147338867188, 'learning_rate': 0.00013556278061619447, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2087/6464 [37:46<1:18:16, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3741, 'grad_norm': 0.6335734128952026, 'learning_rate': 0.00013553181607059916, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2088/6464 [37:47<1:20:56, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2557, 'grad_norm': 0.6493826508522034, 'learning_rate': 0.00013550085152500387, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2089/6464 [37:48<1:18:22, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3103, 'grad_norm': 0.7381446361541748, 'learning_rate': 0.00013546988697940858, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2090/6464 [37:49<1:16:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2084, 'grad_norm': 0.6742503046989441, 'learning_rate': 0.0001354389224338133, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2091/6464 [37:50<1:15:21, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1662, 'grad_norm': 0.7067678570747375, 'learning_rate': 0.000135407957888218, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2092/6464 [37:51<1:16:48, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2077, 'grad_norm': 0.7280827760696411, 'learning_rate': 0.00013537699334262272, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2093/6464 [37:52<1:22:20, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4038, 'grad_norm': 0.7716567516326904, 'learning_rate': 0.0001353460287970274, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2094/6464 [37:53<1:21:59, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0751, 'grad_norm': 0.6583632826805115, 'learning_rate': 0.0001353150642514321, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2095/6464 [37:54<1:19:03, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2552, 'grad_norm': 0.7963244318962097, 'learning_rate': 0.00013528409970583682, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2096/6464 [37:56<1:19:59, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2306, 'grad_norm': 0.6720103025436401, 'learning_rate': 0.00013525313516024153, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2097/6464 [37:57<1:25:31, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2093, 'grad_norm': 0.6232603192329407, 'learning_rate': 0.00013522217061464625, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2098/6464 [37:58<1:23:42, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2784, 'grad_norm': 0.6996581554412842, 'learning_rate': 0.00013519120606905093, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2099/6464 [37:59<1:20:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0356, 'grad_norm': 0.7032774686813354, 'learning_rate': 0.00013516024152345567, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 32%|โ–ˆโ–ˆโ–ˆโ– | 2100/6464 [38:00<1:18:26, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0608, 'grad_norm': 0.6403271555900574, 'learning_rate': 0.00013512927697786035, 'epoch': 0.32}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2101/6464 [38:01<1:18:01, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4342, 'grad_norm': 0.6839297413825989, 'learning_rate': 0.00013509831243226506, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2102/6464 [38:02<1:21:21, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1135, 'grad_norm': 0.6255170702934265, 'learning_rate': 0.00013506734788666977, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2103/6464 [38:03<1:19:44, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2867, 'grad_norm': 0.7236908078193665, 'learning_rate': 0.00013503638334107446, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2104/6464 [38:05<1:20:29, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.407, 'grad_norm': 0.7435122132301331, 'learning_rate': 0.0001350054187954792, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2105/6464 [38:05<1:16:38, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1985, 'grad_norm': 0.7948437929153442, 'learning_rate': 0.00013497445424988388, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2106/6464 [38:07<1:17:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4067, 'grad_norm': 0.7672603130340576, 'learning_rate': 0.0001349434897042886, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2107/6464 [38:08<1:20:08, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2644, 'grad_norm': 0.638045608997345, 'learning_rate': 0.0001349125251586933, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2108/6464 [38:09<1:18:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2296, 'grad_norm': 0.6962370872497559, 'learning_rate': 0.000134881560613098, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2109/6464 [38:10<1:23:15, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2707, 'grad_norm': 0.6011406779289246, 'learning_rate': 0.00013485059606750273, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2110/6464 [38:11<1:20:16, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1058, 'grad_norm': 0.7122074365615845, 'learning_rate': 0.0001348196315219074, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2111/6464 [38:12<1:13:28, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0588, 'grad_norm': 0.7828997373580933, 'learning_rate': 0.00013478866697631215, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2112/6464 [38:13<1:21:19, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1471, 'grad_norm': 0.5881537795066833, 'learning_rate': 0.00013475770243071683, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2113/6464 [38:14<1:22:47, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0088, 'grad_norm': 0.5519686937332153, 'learning_rate': 0.00013472673788512155, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2114/6464 [38:16<1:23:44, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1892, 'grad_norm': 0.6562479734420776, 'learning_rate': 0.00013469577333952626, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2115/6464 [38:17<1:20:00, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1527, 'grad_norm': 0.6524552702903748, 'learning_rate': 0.00013466480879393094, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2116/6464 [38:18<1:17:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1477, 'grad_norm': 0.6692981123924255, 'learning_rate': 0.00013463384424833568, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2117/6464 [38:19<1:17:12, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0939, 'grad_norm': 0.6660971641540527, 'learning_rate': 0.00013460287970274036, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2118/6464 [38:20<1:16:45, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1066, 'grad_norm': 0.6430761218070984, 'learning_rate': 0.00013457191515714508, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2119/6464 [38:21<1:13:45, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3128, 'grad_norm': 0.8110210299491882, 'learning_rate': 0.0001345409506115498, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2120/6464 [38:22<1:17:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0935, 'grad_norm': 0.6214794516563416, 'learning_rate': 0.0001345099860659545, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2121/6464 [38:23<1:16:12, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1188, 'grad_norm': 0.6669583916664124, 'learning_rate': 0.0001344790215203592, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2122/6464 [38:24<1:19:07, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2282, 'grad_norm': 0.7031278014183044, 'learning_rate': 0.0001344480569747639, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2123/6464 [38:25<1:21:05, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2514, 'grad_norm': 0.7387760281562805, 'learning_rate': 0.0001344170924291686, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2124/6464 [38:26<1:20:27, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.018, 'grad_norm': 0.6582875847816467, 'learning_rate': 0.00013438612788357332, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2125/6464 [38:27<1:19:31, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2574, 'grad_norm': 0.766733705997467, 'learning_rate': 0.00013435516333797803, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2126/6464 [38:28<1:18:12, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1738, 'grad_norm': 0.6758535504341125, 'learning_rate': 0.00013432419879238274, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2127/6464 [38:29<1:15:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0861, 'grad_norm': 0.7342916131019592, 'learning_rate': 0.00013429323424678742, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2128/6464 [38:30<1:13:23, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9494, 'grad_norm': 0.6741942763328552, 'learning_rate': 0.00013426226970119213, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2129/6464 [38:31<1:14:22, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0863, 'grad_norm': 0.6499606370925903, 'learning_rate': 0.00013423130515559685, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2130/6464 [38:32<1:15:24, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1747, 'grad_norm': 0.7160707116127014, 'learning_rate': 0.00013420034061000156, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2131/6464 [38:34<1:21:59, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2219, 'grad_norm': 0.6394792199134827, 'learning_rate': 0.00013416937606440627, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2132/6464 [38:35<1:18:46, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2592, 'grad_norm': 0.7983648777008057, 'learning_rate': 0.00013413841151881098, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2133/6464 [38:36<1:19:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2721, 'grad_norm': 0.7324313521385193, 'learning_rate': 0.00013410744697321566, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2134/6464 [38:37<1:18:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2408, 'grad_norm': 0.6772796511650085, 'learning_rate': 0.00013407648242762038, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2135/6464 [38:38<1:20:35, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2528, 'grad_norm': 0.6726218461990356, 'learning_rate': 0.0001340455178820251, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2136/6464 [38:39<1:20:38, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1533, 'grad_norm': 0.7964836955070496, 'learning_rate': 0.0001340145533364298, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2137/6464 [38:40<1:19:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1745, 'grad_norm': 0.6969051957130432, 'learning_rate': 0.0001339835887908345, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2138/6464 [38:41<1:18:02, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3083, 'grad_norm': 0.6521196961402893, 'learning_rate': 0.0001339526242452392, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2139/6464 [38:43<1:21:00, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.452, 'grad_norm': 0.6583849191665649, 'learning_rate': 0.00013392165969964393, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2140/6464 [38:44<1:18:49, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2535, 'grad_norm': 0.7043436169624329, 'learning_rate': 0.00013389069515404862, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2141/6464 [38:45<1:14:29, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1504, 'grad_norm': 0.7451338768005371, 'learning_rate': 0.00013385973060845333, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2142/6464 [38:46<1:15:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2285, 'grad_norm': 0.7214417457580566, 'learning_rate': 0.00013382876606285804, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2143/6464 [38:47<1:19:01, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1494, 'grad_norm': 0.6428183913230896, 'learning_rate': 0.00013379780151726272, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2144/6464 [38:48<1:20:07, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9644, 'grad_norm': 0.5341562032699585, 'learning_rate': 0.00013376683697166746, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2145/6464 [38:49<1:17:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2898, 'grad_norm': 0.6989049315452576, 'learning_rate': 0.00013373587242607215, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2146/6464 [38:50<1:15:50, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2039, 'grad_norm': 0.7009700536727905, 'learning_rate': 0.00013370490788047686, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2147/6464 [38:51<1:17:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2508, 'grad_norm': 0.7181565761566162, 'learning_rate': 0.00013367394333488157, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2148/6464 [38:52<1:15:40, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2393, 'grad_norm': 0.8633711338043213, 'learning_rate': 0.00013364297878928625, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2149/6464 [38:53<1:15:38, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2254, 'grad_norm': 0.6801091432571411, 'learning_rate': 0.000133612014243691, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2150/6464 [38:54<1:17:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1592, 'grad_norm': 0.6369195580482483, 'learning_rate': 0.00013358104969809568, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2151/6464 [38:56<1:22:28, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1452, 'grad_norm': 0.6315610408782959, 'learning_rate': 0.00013355008515250041, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2152/6464 [38:57<1:17:58, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2033, 'grad_norm': 0.725288987159729, 'learning_rate': 0.0001335191206069051, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2153/6464 [38:58<1:18:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1832, 'grad_norm': 0.6796287894248962, 'learning_rate': 0.0001334881560613098, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2154/6464 [38:59<1:17:42, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3414, 'grad_norm': 0.6832258701324463, 'learning_rate': 0.00013345719151571452, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2155/6464 [39:00<1:17:58, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0137, 'grad_norm': 0.6051576137542725, 'learning_rate': 0.0001334262269701192, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2156/6464 [39:01<1:17:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4643, 'grad_norm': 0.7545695900917053, 'learning_rate': 0.00013339526242452394, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2157/6464 [39:02<1:16:55, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0417, 'grad_norm': 0.720532238483429, 'learning_rate': 0.00013336429787892863, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2158/6464 [39:03<1:22:07, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.398, 'grad_norm': 0.6561177968978882, 'learning_rate': 0.00013333333333333334, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2159/6464 [39:04<1:19:50, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1302, 'grad_norm': 0.6298162341117859, 'learning_rate': 0.00013330236878773805, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2160/6464 [39:05<1:21:35, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0673, 'grad_norm': 0.6496302485466003, 'learning_rate': 0.00013327140424214276, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2161/6464 [39:06<1:16:13, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0282, 'grad_norm': 0.8131847381591797, 'learning_rate': 0.00013324043969654747, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2162/6464 [39:07<1:16:48, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2921, 'grad_norm': 0.7436771988868713, 'learning_rate': 0.00013320947515095216, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2163/6464 [39:09<1:18:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2251, 'grad_norm': 0.7178794145584106, 'learning_rate': 0.00013317851060535687, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2164/6464 [39:10<1:15:58, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.193, 'grad_norm': 0.7819812297821045, 'learning_rate': 0.00013314754605976158, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 33%|โ–ˆโ–ˆโ–ˆโ–Ž | 2165/6464 [39:10<1:13:11, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1976, 'grad_norm': 0.7130656838417053, 'learning_rate': 0.0001331165815141663, 'epoch': 0.33}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2166/6464 [39:12<1:22:45, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5364, 'grad_norm': 0.6072214841842651, 'learning_rate': 0.000133085616968571, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2167/6464 [39:13<1:24:51, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3272, 'grad_norm': 0.6620798110961914, 'learning_rate': 0.0001330546524229757, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2168/6464 [39:14<1:21:20, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0497, 'grad_norm': 0.6117954850196838, 'learning_rate': 0.0001330236878773804, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2169/6464 [39:15<1:20:22, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2795, 'grad_norm': 0.7147088050842285, 'learning_rate': 0.0001329927233317851, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2170/6464 [39:16<1:17:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9393, 'grad_norm': 0.7095597386360168, 'learning_rate': 0.00013296175878618982, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2171/6464 [39:17<1:15:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1681, 'grad_norm': 0.6713696718215942, 'learning_rate': 0.00013293079424059453, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2172/6464 [39:18<1:13:29, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2421, 'grad_norm': 0.8648337125778198, 'learning_rate': 0.00013289982969499924, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2173/6464 [39:19<1:09:29, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9652, 'grad_norm': 0.7053837180137634, 'learning_rate': 0.00013286886514940393, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2174/6464 [39:21<1:19:40, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1361, 'grad_norm': 0.546472430229187, 'learning_rate': 0.00013283790060380864, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2175/6464 [39:21<1:13:56, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2146, 'grad_norm': 0.7709454894065857, 'learning_rate': 0.00013280693605821335, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2176/6464 [39:23<1:18:06, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2726, 'grad_norm': 0.5925881266593933, 'learning_rate': 0.00013277597151261806, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2177/6464 [39:24<1:15:53, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9555, 'grad_norm': 0.6449955105781555, 'learning_rate': 0.00013274500696702277, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2178/6464 [39:25<1:14:42, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.034, 'grad_norm': 0.7210041880607605, 'learning_rate': 0.00013271404242142746, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2179/6464 [39:26<1:16:39, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.026, 'grad_norm': 0.6045144200325012, 'learning_rate': 0.0001326830778758322, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2180/6464 [39:27<1:19:11, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1738, 'grad_norm': 0.789798378944397, 'learning_rate': 0.00013265211333023688, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ–Ž | 2181/6464 [39:28<1:18:11, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2481, 'grad_norm': 0.7678773403167725, 'learning_rate': 0.0001326211487846416, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2182/6464 [39:29<1:13:24, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8818, 'grad_norm': 0.6598886251449585, 'learning_rate': 0.0001325901842390463, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2183/6464 [39:30<1:11:51, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3834, 'grad_norm': 0.9079511761665344, 'learning_rate': 0.000132559219693451, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2184/6464 [39:31<1:12:13, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2692, 'grad_norm': 0.7136762142181396, 'learning_rate': 0.00013252825514785573, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2185/6464 [39:32<1:11:06, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2546, 'grad_norm': 0.8177650570869446, 'learning_rate': 0.0001324972906022604, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2186/6464 [39:33<1:10:41, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1956, 'grad_norm': 0.725995659828186, 'learning_rate': 0.00013246632605666512, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2187/6464 [39:34<1:13:38, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2556, 'grad_norm': 0.6711651682853699, 'learning_rate': 0.00013243536151106983, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2188/6464 [39:35<1:17:58, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2503, 'grad_norm': 0.6650091409683228, 'learning_rate': 0.00013240439696547452, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2189/6464 [39:36<1:19:41, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2202, 'grad_norm': 0.580206036567688, 'learning_rate': 0.00013237343241987926, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2190/6464 [39:38<1:24:32, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3364, 'grad_norm': 0.6784095764160156, 'learning_rate': 0.00013234246787428394, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2191/6464 [39:39<1:23:16, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2426, 'grad_norm': 0.6615576148033142, 'learning_rate': 0.00013231150332868868, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2192/6464 [39:40<1:19:50, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1783, 'grad_norm': 0.7914685010910034, 'learning_rate': 0.00013228053878309336, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2193/6464 [39:41<1:15:31, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9848, 'grad_norm': 0.7177113890647888, 'learning_rate': 0.00013224957423749807, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2194/6464 [39:42<1:18:43, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2141, 'grad_norm': 0.6089293956756592, 'learning_rate': 0.00013221860969190279, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2195/6464 [39:43<1:16:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2929, 'grad_norm': 0.7508900165557861, 'learning_rate': 0.00013218764514630747, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2196/6464 [39:44<1:14:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2058, 'grad_norm': 0.6675375699996948, 'learning_rate': 0.0001321566806007122, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2197/6464 [39:45<1:11:55, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2415, 'grad_norm': 0.7518728971481323, 'learning_rate': 0.0001321257160551169, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2198/6464 [39:46<1:13:19, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3497, 'grad_norm': 0.6646081805229187, 'learning_rate': 0.0001320947515095216, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2199/6464 [39:47<1:14:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1153, 'grad_norm': 0.7369359731674194, 'learning_rate': 0.00013206378696392632, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2200/6464 [39:48<1:17:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2851, 'grad_norm': 0.6675757765769958, 'learning_rate': 0.00013203282241833103, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2201/6464 [39:49<1:18:13, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1076, 'grad_norm': 0.6133784055709839, 'learning_rate': 0.00013200185787273574, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2202/6464 [39:50<1:16:12, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1389, 'grad_norm': 0.707676887512207, 'learning_rate': 0.00013197089332714042, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2203/6464 [39:51<1:14:37, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0897, 'grad_norm': 0.6543403267860413, 'learning_rate': 0.00013193992878154513, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2204/6464 [39:52<1:11:59, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1396, 'grad_norm': 0.6897205114364624, 'learning_rate': 0.00013190896423594985, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2205/6464 [39:53<1:13:31, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2215, 'grad_norm': 0.7509607672691345, 'learning_rate': 0.00013187799969035456, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2206/6464 [39:54<1:13:09, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2821, 'grad_norm': 0.7256897687911987, 'learning_rate': 0.00013184703514475927, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2207/6464 [39:56<1:18:21, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2582, 'grad_norm': 0.6043245196342468, 'learning_rate': 0.00013181607059916395, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2208/6464 [39:57<1:16:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0697, 'grad_norm': 0.6773387789726257, 'learning_rate': 0.00013178510605356866, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2209/6464 [39:58<1:15:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0593, 'grad_norm': 0.7836723327636719, 'learning_rate': 0.00013175414150797337, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2210/6464 [39:59<1:16:38, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3067, 'grad_norm': 0.6727893948554993, 'learning_rate': 0.00013172317696237809, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2211/6464 [40:00<1:18:16, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1031, 'grad_norm': 0.6505188345909119, 'learning_rate': 0.0001316922124167828, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2212/6464 [40:01<1:17:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2454, 'grad_norm': 0.7053961753845215, 'learning_rate': 0.0001316612478711875, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2213/6464 [40:02<1:18:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2449, 'grad_norm': 0.6941934823989868, 'learning_rate': 0.0001316302833255922, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2214/6464 [40:03<1:16:14, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2411, 'grad_norm': 0.7835661172866821, 'learning_rate': 0.0001315993187799969, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2215/6464 [40:04<1:13:54, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.938, 'grad_norm': 0.752612829208374, 'learning_rate': 0.00013156835423440162, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2216/6464 [40:05<1:16:07, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.236, 'grad_norm': 0.6227505207061768, 'learning_rate': 0.00013153738968880633, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2217/6464 [40:06<1:12:44, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.165, 'grad_norm': 0.8985885381698608, 'learning_rate': 0.00013150642514321104, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2218/6464 [40:07<1:11:44, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2744, 'grad_norm': 0.8730579018592834, 'learning_rate': 0.00013147546059761572, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2219/6464 [40:08<1:12:37, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0856, 'grad_norm': 0.6592671871185303, 'learning_rate': 0.00013144449605202046, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2220/6464 [40:09<1:11:36, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.038, 'grad_norm': 0.6704458594322205, 'learning_rate': 0.00013141353150642515, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2221/6464 [40:10<1:14:14, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2054, 'grad_norm': 0.657990038394928, 'learning_rate': 0.00013138256696082986, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2222/6464 [40:11<1:14:16, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1543, 'grad_norm': 0.6694003939628601, 'learning_rate': 0.00013135160241523457, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2223/6464 [40:13<1:18:05, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0881, 'grad_norm': 0.6216986179351807, 'learning_rate': 0.00013132063786963925, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2224/6464 [40:14<1:17:23, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.125, 'grad_norm': 0.6615129113197327, 'learning_rate': 0.000131289673324044, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2225/6464 [40:15<1:21:08, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2644, 'grad_norm': 0.6492277383804321, 'learning_rate': 0.00013125870877844868, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2226/6464 [40:16<1:16:21, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1578, 'grad_norm': 0.8657328486442566, 'learning_rate': 0.0001312277442328534, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2227/6464 [40:17<1:20:17, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.451, 'grad_norm': 0.6366279125213623, 'learning_rate': 0.0001311967796872581, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2228/6464 [40:18<1:16:14, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0488, 'grad_norm': 0.7569692730903625, 'learning_rate': 0.00013116581514166278, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2229/6464 [40:19<1:17:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1633, 'grad_norm': 0.6028938889503479, 'learning_rate': 0.00013113485059606752, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 34%|โ–ˆโ–ˆโ–ˆโ– | 2230/6464 [40:20<1:14:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1545, 'grad_norm': 0.7828092575073242, 'learning_rate': 0.0001311038860504722, 'epoch': 0.34}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2231/6464 [40:21<1:13:06, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9502, 'grad_norm': 0.5955137610435486, 'learning_rate': 0.00013107292150487694, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2232/6464 [40:22<1:15:42, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.124, 'grad_norm': 0.6153571009635925, 'learning_rate': 0.00013104195695928163, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2233/6464 [40:23<1:13:28, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0261, 'grad_norm': 0.6467365622520447, 'learning_rate': 0.00013101099241368634, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2234/6464 [40:24<1:14:28, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3697, 'grad_norm': 0.7410641312599182, 'learning_rate': 0.00013098002786809105, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2235/6464 [40:26<1:14:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1042, 'grad_norm': 0.720120906829834, 'learning_rate': 0.00013094906332249573, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2236/6464 [40:26<1:10:18, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2464, 'grad_norm': 0.8283774256706238, 'learning_rate': 0.00013091809877690047, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2237/6464 [40:28<1:13:16, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2072, 'grad_norm': 0.6903196573257446, 'learning_rate': 0.00013088713423130516, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2238/6464 [40:29<1:13:26, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1676, 'grad_norm': 0.7019917964935303, 'learning_rate': 0.00013085616968570987, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2239/6464 [40:30<1:17:22, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0918, 'grad_norm': 0.6000445485115051, 'learning_rate': 0.00013082520514011458, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2240/6464 [40:31<1:17:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0522, 'grad_norm': 0.6390119791030884, 'learning_rate': 0.0001307942405945193, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2241/6464 [40:32<1:18:15, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4735, 'grad_norm': 0.7027792930603027, 'learning_rate': 0.00013076327604892398, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2242/6464 [40:33<1:17:55, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2132, 'grad_norm': 0.692250669002533, 'learning_rate': 0.0001307323115033287, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2243/6464 [40:34<1:16:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2397, 'grad_norm': 0.6746100187301636, 'learning_rate': 0.0001307013469577334, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2244/6464 [40:35<1:17:18, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3347, 'grad_norm': 0.7028293609619141, 'learning_rate': 0.0001306703824121381, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2245/6464 [40:37<1:19:08, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2088, 'grad_norm': 0.6182698607444763, 'learning_rate': 0.00013063941786654282, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2246/6464 [40:38<1:16:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.218, 'grad_norm': 0.714899480342865, 'learning_rate': 0.0001306084533209475, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2247/6464 [40:39<1:15:56, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0456, 'grad_norm': 0.6823747158050537, 'learning_rate': 0.00013057748877535222, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2248/6464 [40:40<1:16:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2076, 'grad_norm': 0.6714928150177002, 'learning_rate': 0.00013054652422975693, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2249/6464 [40:41<1:14:54, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3202, 'grad_norm': 0.7907822728157043, 'learning_rate': 0.00013051555968416164, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2250/6464 [40:42<1:16:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1356, 'grad_norm': 0.6615204811096191, 'learning_rate': 0.00013048459513856635, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2251/6464 [40:43<1:16:36, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1298, 'grad_norm': 0.664446234703064, 'learning_rate': 0.00013045363059297104, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2252/6464 [40:44<1:18:50, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0748, 'grad_norm': 0.6026772260665894, 'learning_rate': 0.00013042266604737577, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2253/6464 [40:45<1:13:57, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0347, 'grad_norm': 0.6380951404571533, 'learning_rate': 0.00013039170150178046, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2254/6464 [40:46<1:13:46, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1356, 'grad_norm': 0.6976441740989685, 'learning_rate': 0.00013036073695618517, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2255/6464 [40:47<1:13:01, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0216, 'grad_norm': 0.6529916524887085, 'learning_rate': 0.00013032977241058988, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2256/6464 [40:48<1:14:28, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1145, 'grad_norm': 0.7352719306945801, 'learning_rate': 0.00013029880786499456, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2257/6464 [40:49<1:16:17, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4227, 'grad_norm': 0.7326385378837585, 'learning_rate': 0.0001302678433193993, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2258/6464 [40:50<1:15:17, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2762, 'grad_norm': 0.7224805355072021, 'learning_rate': 0.000130236878773804, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2259/6464 [40:51<1:12:01, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1556, 'grad_norm': 0.8482276201248169, 'learning_rate': 0.00013020591422820873, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2260/6464 [40:52<1:09:17, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9674, 'grad_norm': 0.793788731098175, 'learning_rate': 0.0001301749496826134, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2261/6464 [40:53<1:07:29, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0963, 'grad_norm': 0.6915748119354248, 'learning_rate': 0.00013014398513701812, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ– | 2262/6464 [40:54<1:12:43, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3373, 'grad_norm': 0.6805047392845154, 'learning_rate': 0.00013011302059142283, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2263/6464 [40:56<1:16:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2111, 'grad_norm': 0.667134165763855, 'learning_rate': 0.00013008205604582752, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2264/6464 [40:57<1:15:57, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.155, 'grad_norm': 0.7212253212928772, 'learning_rate': 0.00013005109150023226, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2265/6464 [40:58<1:15:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.075, 'grad_norm': 0.6601951122283936, 'learning_rate': 0.00013002012695463694, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2266/6464 [40:59<1:27:19, 1.25s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.351, 'grad_norm': 0.5614665150642395, 'learning_rate': 0.00012998916240904165, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2267/6464 [41:00<1:23:53, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0576, 'grad_norm': 0.6742203235626221, 'learning_rate': 0.00012995819786344636, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2268/6464 [41:02<1:26:18, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2841, 'grad_norm': 0.6402320861816406, 'learning_rate': 0.00012992723331785107, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2269/6464 [41:03<1:21:31, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0597, 'grad_norm': 0.646051824092865, 'learning_rate': 0.00012989626877225579, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2270/6464 [41:04<1:23:01, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2263, 'grad_norm': 0.6517412662506104, 'learning_rate': 0.00012986530422666047, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2271/6464 [41:05<1:19:07, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3921, 'grad_norm': 0.7295291423797607, 'learning_rate': 0.00012983433968106518, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2272/6464 [41:06<1:17:55, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1846, 'grad_norm': 0.6170755624771118, 'learning_rate': 0.0001298033751354699, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2273/6464 [41:07<1:13:03, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0417, 'grad_norm': 0.7706292867660522, 'learning_rate': 0.0001297724105898746, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2274/6464 [41:08<1:13:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1402, 'grad_norm': 0.7492266297340393, 'learning_rate': 0.00012974144604427931, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2275/6464 [41:09<1:12:32, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.039, 'grad_norm': 0.6677970290184021, 'learning_rate': 0.000129710481498684, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2276/6464 [41:10<1:15:11, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1029, 'grad_norm': 0.8455328941345215, 'learning_rate': 0.0001296795169530887, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2277/6464 [41:11<1:13:39, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9186, 'grad_norm': 0.6576171517372131, 'learning_rate': 0.00012964855240749342, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2278/6464 [41:12<1:11:50, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1533, 'grad_norm': 0.7161545753479004, 'learning_rate': 0.00012961758786189813, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2279/6464 [41:13<1:09:35, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2769, 'grad_norm': 0.8805342316627502, 'learning_rate': 0.00012958662331630284, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2280/6464 [41:14<1:15:24, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1221, 'grad_norm': 0.6683967709541321, 'learning_rate': 0.00012955565877070756, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2281/6464 [41:15<1:12:25, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0545, 'grad_norm': 0.725094735622406, 'learning_rate': 0.00012952469422511224, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2282/6464 [41:16<1:13:08, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2316, 'grad_norm': 0.6548943519592285, 'learning_rate': 0.00012949372967951695, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2283/6464 [41:17<1:14:07, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4366, 'grad_norm': 0.7694481611251831, 'learning_rate': 0.00012946276513392166, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2284/6464 [41:19<1:17:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1281, 'grad_norm': 0.6416007876396179, 'learning_rate': 0.00012943180058832637, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2285/6464 [41:20<1:19:16, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3815, 'grad_norm': 0.6448655128479004, 'learning_rate': 0.00012940083604273109, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2286/6464 [41:21<1:15:36, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.084, 'grad_norm': 0.709315299987793, 'learning_rate': 0.00012936987149713577, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2287/6464 [41:22<1:20:09, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2117, 'grad_norm': 0.6863181591033936, 'learning_rate': 0.0001293389069515405, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2288/6464 [41:23<1:18:43, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0585, 'grad_norm': 0.6283682584762573, 'learning_rate': 0.0001293079424059452, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2289/6464 [41:24<1:18:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2858, 'grad_norm': 0.7492963075637817, 'learning_rate': 0.0001292769778603499, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2290/6464 [41:25<1:18:57, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3082, 'grad_norm': 0.6840192079544067, 'learning_rate': 0.00012924601331475462, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2291/6464 [41:27<1:19:37, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0616, 'grad_norm': 0.5944885015487671, 'learning_rate': 0.0001292150487691593, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2292/6464 [41:28<1:14:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1521, 'grad_norm': 0.76264888048172, 'learning_rate': 0.00012918408422356404, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2293/6464 [41:29<1:12:42, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9538, 'grad_norm': 0.6674836874008179, 'learning_rate': 0.00012915311967796872, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 35%|โ–ˆโ–ˆโ–ˆโ–Œ | 2294/6464 [41:30<1:14:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1623, 'grad_norm': 0.664914608001709, 'learning_rate': 0.00012912215513237343, 'epoch': 0.35}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2295/6464 [41:31<1:11:33, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1173, 'grad_norm': 0.6891745924949646, 'learning_rate': 0.00012909119058677814, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2296/6464 [41:32<1:10:12, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.28, 'grad_norm': 0.678162693977356, 'learning_rate': 0.00012906022604118283, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2297/6464 [41:33<1:19:08, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1844, 'grad_norm': 0.6515238285064697, 'learning_rate': 0.00012902926149558757, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2298/6464 [41:34<1:16:31, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1963, 'grad_norm': 0.7406539916992188, 'learning_rate': 0.00012899829694999225, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2299/6464 [41:35<1:20:52, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5013, 'grad_norm': 0.7330207228660583, 'learning_rate': 0.000128967332404397, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2300/6464 [41:37<1:23:06, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3232, 'grad_norm': 0.7004390358924866, 'learning_rate': 0.00012893636785880167, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2301/6464 [41:38<1:20:48, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.175, 'grad_norm': 0.717933714389801, 'learning_rate': 0.00012890540331320639, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2302/6464 [41:39<1:20:28, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2242, 'grad_norm': 0.716082751750946, 'learning_rate': 0.0001288744387676111, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2303/6464 [41:40<1:19:21, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3487, 'grad_norm': 0.7459346055984497, 'learning_rate': 0.00012884347422201578, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2304/6464 [41:41<1:17:54, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1315, 'grad_norm': 0.7100671529769897, 'learning_rate': 0.00012881250967642052, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2305/6464 [41:42<1:17:23, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2068, 'grad_norm': 0.6709000468254089, 'learning_rate': 0.0001287815451308252, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2306/6464 [41:43<1:12:58, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0608, 'grad_norm': 0.8229066133499146, 'learning_rate': 0.00012875058058522992, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2307/6464 [41:44<1:10:40, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1511, 'grad_norm': 0.7277345657348633, 'learning_rate': 0.00012871961603963463, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2308/6464 [41:45<1:14:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3093, 'grad_norm': 0.6592563390731812, 'learning_rate': 0.00012868865149403934, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2309/6464 [41:46<1:14:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0832, 'grad_norm': 0.9403768181800842, 'learning_rate': 0.00012865768694844405, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2310/6464 [41:47<1:11:41, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3303, 'grad_norm': 0.8216241598129272, 'learning_rate': 0.00012862672240284873, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2311/6464 [41:48<1:07:35, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8974, 'grad_norm': 0.6976147294044495, 'learning_rate': 0.00012859575785725345, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2312/6464 [41:49<1:08:05, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0988, 'grad_norm': 0.7345878481864929, 'learning_rate': 0.00012856479331165816, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2313/6464 [41:50<1:09:53, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1349, 'grad_norm': 0.6753637194633484, 'learning_rate': 0.00012853382876606287, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2314/6464 [41:51<1:12:01, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1119, 'grad_norm': 0.6630411148071289, 'learning_rate': 0.00012850286422046758, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2315/6464 [41:52<1:10:32, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2564, 'grad_norm': 0.7309643626213074, 'learning_rate': 0.00012847189967487226, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2316/6464 [41:53<1:12:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0884, 'grad_norm': 0.6766970753669739, 'learning_rate': 0.00012844093512927697, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2317/6464 [41:54<1:12:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1252, 'grad_norm': 0.787224531173706, 'learning_rate': 0.00012840997058368169, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2318/6464 [41:55<1:10:33, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2285, 'grad_norm': 0.7320176959037781, 'learning_rate': 0.0001283790060380864, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2319/6464 [41:56<1:11:09, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2302, 'grad_norm': 0.6666617393493652, 'learning_rate': 0.0001283480414924911, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2320/6464 [41:57<1:09:17, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0177, 'grad_norm': 0.6614634990692139, 'learning_rate': 0.00012831707694689582, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2321/6464 [41:59<1:14:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.396, 'grad_norm': 0.6461401581764221, 'learning_rate': 0.0001282861124013005, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2322/6464 [42:00<1:14:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2334, 'grad_norm': 0.7378998398780823, 'learning_rate': 0.00012825514785570522, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2323/6464 [42:01<1:11:26, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0024, 'grad_norm': 0.7339767813682556, 'learning_rate': 0.00012822418331010993, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2324/6464 [42:01<1:08:13, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2183, 'grad_norm': 0.7963537573814392, 'learning_rate': 0.00012819321876451464, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2325/6464 [42:02<1:08:50, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0488, 'grad_norm': 0.6265960335731506, 'learning_rate': 0.00012816225421891935, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2326/6464 [42:03<1:08:03, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1074, 'grad_norm': 0.6882450580596924, 'learning_rate': 0.00012813128967332403, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2327/6464 [42:04<1:08:30, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9214, 'grad_norm': 0.7016480565071106, 'learning_rate': 0.00012810032512772877, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2328/6464 [42:06<1:10:32, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4543, 'grad_norm': 0.7151551246643066, 'learning_rate': 0.00012806936058213346, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2329/6464 [42:07<1:09:47, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2758, 'grad_norm': 0.7879014015197754, 'learning_rate': 0.00012803839603653817, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2330/6464 [42:07<1:07:03, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.013, 'grad_norm': 0.6617128849029541, 'learning_rate': 0.00012800743149094288, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2331/6464 [42:09<1:09:56, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1533, 'grad_norm': 0.7102147936820984, 'learning_rate': 0.00012797646694534756, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2332/6464 [42:10<1:12:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2208, 'grad_norm': 0.6420800685882568, 'learning_rate': 0.0001279455023997523, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2333/6464 [42:11<1:17:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2164, 'grad_norm': 0.6133599877357483, 'learning_rate': 0.000127914537854157, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2334/6464 [42:12<1:16:52, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0038, 'grad_norm': 0.5871405005455017, 'learning_rate': 0.0001278835733085617, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2335/6464 [42:13<1:13:47, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9695, 'grad_norm': 0.5818210244178772, 'learning_rate': 0.0001278526087629664, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2336/6464 [42:14<1:18:49, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1016, 'grad_norm': 0.5909034609794617, 'learning_rate': 0.0001278216442173711, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2337/6464 [42:15<1:13:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0769, 'grad_norm': 0.8345204591751099, 'learning_rate': 0.00012779067967177583, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2338/6464 [42:16<1:13:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2504, 'grad_norm': 0.6997362375259399, 'learning_rate': 0.00012775971512618052, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2339/6464 [42:17<1:15:08, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3855, 'grad_norm': 0.7203858494758606, 'learning_rate': 0.00012772875058058525, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2340/6464 [42:19<1:16:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1659, 'grad_norm': 0.6259258389472961, 'learning_rate': 0.00012769778603498994, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2341/6464 [42:20<1:14:41, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1415, 'grad_norm': 0.7284425497055054, 'learning_rate': 0.00012766682148939465, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2342/6464 [42:21<1:17:55, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1962, 'grad_norm': 0.663203775882721, 'learning_rate': 0.00012763585694379936, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–Œ | 2343/6464 [42:22<1:16:56, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0589, 'grad_norm': 0.6806567907333374, 'learning_rate': 0.00012760489239820405, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2344/6464 [42:23<1:15:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1701, 'grad_norm': 0.7573460936546326, 'learning_rate': 0.00012757392785260878, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2345/6464 [42:24<1:16:47, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3184, 'grad_norm': 0.7065749168395996, 'learning_rate': 0.00012754296330701347, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2346/6464 [42:25<1:14:46, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2258, 'grad_norm': 0.6482922434806824, 'learning_rate': 0.00012751199876141818, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2347/6464 [42:26<1:17:46, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3697, 'grad_norm': 0.7211980223655701, 'learning_rate': 0.0001274810342158229, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2348/6464 [42:27<1:16:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.205, 'grad_norm': 0.6749225854873657, 'learning_rate': 0.0001274500696702276, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2349/6464 [42:29<1:17:03, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2116, 'grad_norm': 1.0099252462387085, 'learning_rate': 0.00012741910512463231, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2350/6464 [42:30<1:13:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1802, 'grad_norm': 0.756925106048584, 'learning_rate': 0.000127388140579037, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2351/6464 [42:31<1:14:52, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1097, 'grad_norm': 0.6221811771392822, 'learning_rate': 0.0001273571760334417, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2352/6464 [42:32<1:13:51, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4355, 'grad_norm': 0.6704369187355042, 'learning_rate': 0.00012732621148784642, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2353/6464 [42:33<1:13:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2666, 'grad_norm': 0.7991170287132263, 'learning_rate': 0.00012729524694225113, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2354/6464 [42:34<1:13:28, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0917, 'grad_norm': 0.709682047367096, 'learning_rate': 0.00012726428239665584, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2355/6464 [42:35<1:12:25, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2534, 'grad_norm': 0.6982285976409912, 'learning_rate': 0.00012723331785106053, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2356/6464 [42:36<1:15:00, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2331, 'grad_norm': 0.7356491684913635, 'learning_rate': 0.00012720235330546524, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2357/6464 [42:37<1:11:56, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1566, 'grad_norm': 0.715286135673523, 'learning_rate': 0.00012717138875986995, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2358/6464 [42:38<1:10:25, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9673, 'grad_norm': 0.6628265380859375, 'learning_rate': 0.00012714042421427466, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 36%|โ–ˆโ–ˆโ–ˆโ–‹ | 2359/6464 [42:39<1:10:07, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0605, 'grad_norm': 0.7159698605537415, 'learning_rate': 0.00012710945966867937, 'epoch': 0.36}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2360/6464 [42:40<1:10:50, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1163, 'grad_norm': 0.8198400735855103, 'learning_rate': 0.00012707849512308408, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2361/6464 [42:42<1:19:24, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.26, 'grad_norm': 0.6867064833641052, 'learning_rate': 0.00012704753057748877, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2362/6464 [42:43<1:17:48, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1812, 'grad_norm': 0.6301302909851074, 'learning_rate': 0.00012701656603189348, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2363/6464 [42:44<1:15:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.028, 'grad_norm': 0.6163428425788879, 'learning_rate': 0.0001269856014862982, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2364/6464 [42:45<1:17:51, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2206, 'grad_norm': 0.6280454397201538, 'learning_rate': 0.0001269546369407029, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2365/6464 [42:46<1:14:27, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1532, 'grad_norm': 0.8652127385139465, 'learning_rate': 0.00012692367239510761, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2366/6464 [42:47<1:14:33, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4878, 'grad_norm': 0.6972574591636658, 'learning_rate': 0.0001268927078495123, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2367/6464 [42:48<1:16:59, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2373, 'grad_norm': 0.6698517799377441, 'learning_rate': 0.00012686174330391704, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2368/6464 [42:49<1:17:48, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2773, 'grad_norm': 0.6611180305480957, 'learning_rate': 0.00012683077875832172, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2369/6464 [42:50<1:14:31, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1208, 'grad_norm': 0.7605318427085876, 'learning_rate': 0.00012679981421272643, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2370/6464 [42:51<1:14:19, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1, 'grad_norm': 0.6025153994560242, 'learning_rate': 0.00012676884966713114, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2371/6464 [42:52<1:13:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3115, 'grad_norm': 0.7217599153518677, 'learning_rate': 0.00012673788512153583, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2372/6464 [42:54<1:14:41, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0554, 'grad_norm': 0.636311411857605, 'learning_rate': 0.00012670692057594057, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2373/6464 [42:55<1:12:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0062, 'grad_norm': 0.7166135311126709, 'learning_rate': 0.00012667595603034525, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2374/6464 [42:56<1:21:08, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1842, 'grad_norm': 0.5243380665779114, 'learning_rate': 0.00012664499148474996, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2375/6464 [42:57<1:23:34, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2856, 'grad_norm': 0.6366503834724426, 'learning_rate': 0.00012661402693915467, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2376/6464 [42:59<1:21:12, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1113, 'grad_norm': 0.6428415775299072, 'learning_rate': 0.00012658306239355936, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2377/6464 [43:00<1:17:44, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1135, 'grad_norm': 0.6908775568008423, 'learning_rate': 0.0001265520978479641, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2378/6464 [43:01<1:27:21, 1.28s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1095, 'grad_norm': 0.5730183720588684, 'learning_rate': 0.00012652113330236878, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2379/6464 [43:02<1:25:57, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2673, 'grad_norm': 0.6601609587669373, 'learning_rate': 0.00012649016875677352, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2380/6464 [43:04<1:25:22, 1.25s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0298, 'grad_norm': 0.6385210156440735, 'learning_rate': 0.0001264592042111782, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2381/6464 [43:05<1:22:53, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.256, 'grad_norm': 0.7007846832275391, 'learning_rate': 0.00012642823966558291, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2382/6464 [43:06<1:17:20, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0442, 'grad_norm': 0.7128115892410278, 'learning_rate': 0.00012639727511998763, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2383/6464 [43:07<1:15:16, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0679, 'grad_norm': 0.6289597749710083, 'learning_rate': 0.0001263663105743923, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2384/6464 [43:08<1:15:39, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1872, 'grad_norm': 0.6411513090133667, 'learning_rate': 0.00012633534602879705, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2385/6464 [43:09<1:14:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1146, 'grad_norm': 0.6707556247711182, 'learning_rate': 0.00012630438148320173, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2386/6464 [43:10<1:09:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7647, 'grad_norm': 0.7609870433807373, 'learning_rate': 0.00012627341693760644, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2387/6464 [43:11<1:09:12, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1365, 'grad_norm': 0.6925238370895386, 'learning_rate': 0.00012624245239201116, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2388/6464 [43:12<1:05:37, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9455, 'grad_norm': 0.6183074116706848, 'learning_rate': 0.00012621148784641587, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2389/6464 [43:13<1:07:06, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1467, 'grad_norm': 0.674098014831543, 'learning_rate': 0.00012618052330082058, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2390/6464 [43:14<1:11:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2277, 'grad_norm': 0.6852045655250549, 'learning_rate': 0.00012614955875522526, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2391/6464 [43:15<1:09:52, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2364, 'grad_norm': 0.708061158657074, 'learning_rate': 0.00012611859420962997, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2392/6464 [43:16<1:15:37, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0284, 'grad_norm': 0.6284444332122803, 'learning_rate': 0.00012608762966403469, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2393/6464 [43:17<1:10:54, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1387, 'grad_norm': 0.9284452795982361, 'learning_rate': 0.0001260566651184394, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2394/6464 [43:18<1:10:00, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1914, 'grad_norm': 0.704135537147522, 'learning_rate': 0.0001260257005728441, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2395/6464 [43:19<1:10:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9509, 'grad_norm': 0.6010138988494873, 'learning_rate': 0.0001259947360272488, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2396/6464 [43:20<1:14:47, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2677, 'grad_norm': 0.6955588459968567, 'learning_rate': 0.0001259637714816535, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2397/6464 [43:21<1:11:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9516, 'grad_norm': 0.6403724551200867, 'learning_rate': 0.00012593280693605822, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2398/6464 [43:22<1:10:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1617, 'grad_norm': 0.6572265625, 'learning_rate': 0.00012590184239046293, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2399/6464 [43:23<1:11:39, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3927, 'grad_norm': 0.764333188533783, 'learning_rate': 0.00012587087784486764, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2400/6464 [43:24<1:13:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2269, 'grad_norm': 0.6648276448249817, 'learning_rate': 0.00012583991329927235, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2401/6464 [43:26<1:17:54, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3176, 'grad_norm': 0.6393781304359436, 'learning_rate': 0.00012580894875367703, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2402/6464 [43:27<1:14:29, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9698, 'grad_norm': 0.6385271549224854, 'learning_rate': 0.00012577798420808174, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2403/6464 [43:28<1:15:04, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.092, 'grad_norm': 0.6535566449165344, 'learning_rate': 0.00012574701966248646, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2404/6464 [43:29<1:11:26, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0595, 'grad_norm': 0.7273923754692078, 'learning_rate': 0.00012571605511689117, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2405/6464 [43:30<1:07:47, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0698, 'grad_norm': 0.8532751202583313, 'learning_rate': 0.00012568509057129588, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2406/6464 [43:31<1:12:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1135, 'grad_norm': 0.6673892140388489, 'learning_rate': 0.00012565412602570056, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2407/6464 [43:32<1:13:54, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1222, 'grad_norm': 0.648798406124115, 'learning_rate': 0.0001256231614801053, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2408/6464 [43:33<1:17:14, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1627, 'grad_norm': 0.5900324583053589, 'learning_rate': 0.00012559219693450999, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2409/6464 [43:35<1:17:29, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1528, 'grad_norm': 0.6957960724830627, 'learning_rate': 0.0001255612323889147, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2410/6464 [43:36<1:15:35, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1232, 'grad_norm': 0.744186520576477, 'learning_rate': 0.0001255302678433194, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2411/6464 [43:37<1:15:29, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.255, 'grad_norm': 0.8285729885101318, 'learning_rate': 0.0001254993032977241, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2412/6464 [43:38<1:13:12, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0384, 'grad_norm': 0.6534298062324524, 'learning_rate': 0.00012546833875212883, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2413/6464 [43:39<1:15:57, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2021, 'grad_norm': 0.6848970651626587, 'learning_rate': 0.00012543737420653352, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2414/6464 [43:40<1:13:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0614, 'grad_norm': 0.6621701121330261, 'learning_rate': 0.00012540640966093823, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2415/6464 [43:41<1:18:15, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1485, 'grad_norm': 0.560498833656311, 'learning_rate': 0.00012537544511534294, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2416/6464 [43:42<1:17:31, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3303, 'grad_norm': 0.7188926935195923, 'learning_rate': 0.00012534448056974762, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2417/6464 [43:44<1:17:30, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2352, 'grad_norm': 0.6294318437576294, 'learning_rate': 0.00012531351602415236, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2418/6464 [43:44<1:13:49, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3086, 'grad_norm': 0.8096020817756653, 'learning_rate': 0.00012528255147855705, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2419/6464 [43:46<1:15:35, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3282, 'grad_norm': 0.6321954131126404, 'learning_rate': 0.00012525158693296178, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2420/6464 [43:47<1:12:56, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.192, 'grad_norm': 0.7598675489425659, 'learning_rate': 0.00012522062238736647, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2421/6464 [43:48<1:12:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2058, 'grad_norm': 0.7841965556144714, 'learning_rate': 0.00012518965784177118, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2422/6464 [43:49<1:15:06, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1028, 'grad_norm': 0.6508768200874329, 'learning_rate': 0.0001251586932961759, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 37%|โ–ˆโ–ˆโ–ˆโ–‹ | 2423/6464 [43:50<1:12:13, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1109, 'grad_norm': 0.697502613067627, 'learning_rate': 0.00012512772875058058, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2424/6464 [43:51<1:14:16, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1306, 'grad_norm': 0.6003866195678711, 'learning_rate': 0.0001250967642049853, 'epoch': 0.37}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2425/6464 [43:52<1:16:16, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.313, 'grad_norm': 0.6527789831161499, 'learning_rate': 0.00012506579965939, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2426/6464 [43:53<1:15:22, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1625, 'grad_norm': 0.6320488452911377, 'learning_rate': 0.0001250348351137947, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2427/6464 [43:54<1:11:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1235, 'grad_norm': 0.7873493432998657, 'learning_rate': 0.00012500387056819942, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2428/6464 [43:55<1:10:39, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2652, 'grad_norm': 0.7431418299674988, 'learning_rate': 0.00012497290602260413, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2429/6464 [43:57<1:16:13, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2302, 'grad_norm': 0.666659414768219, 'learning_rate': 0.00012494194147700884, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2430/6464 [43:58<1:15:04, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1212, 'grad_norm': 0.7080767750740051, 'learning_rate': 0.00012491097693141353, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2431/6464 [43:59<1:14:27, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2834, 'grad_norm': 0.6984776258468628, 'learning_rate': 0.00012488001238581824, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2432/6464 [44:00<1:13:07, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1915, 'grad_norm': 0.7227702140808105, 'learning_rate': 0.00012484904784022295, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2433/6464 [44:01<1:12:01, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9332, 'grad_norm': 0.578453004360199, 'learning_rate': 0.00012481808329462766, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2434/6464 [44:02<1:12:20, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1611, 'grad_norm': 0.7091525197029114, 'learning_rate': 0.00012478711874903237, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2435/6464 [44:03<1:13:27, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0602, 'grad_norm': 0.6520471572875977, 'learning_rate': 0.00012475615420343706, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2436/6464 [44:04<1:15:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4764, 'grad_norm': 0.7195960879325867, 'learning_rate': 0.00012472518965784177, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2437/6464 [44:05<1:12:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.949, 'grad_norm': 0.6924793720245361, 'learning_rate': 0.00012469422511224648, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2438/6464 [44:06<1:15:23, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.161, 'grad_norm': 0.6402559876441956, 'learning_rate': 0.0001246632605666512, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2439/6464 [44:07<1:11:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0489, 'grad_norm': 0.6731833815574646, 'learning_rate': 0.0001246322960210559, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2440/6464 [44:09<1:16:28, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2391, 'grad_norm': 0.6749169826507568, 'learning_rate': 0.00012460133147546061, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2441/6464 [44:10<1:15:32, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.177, 'grad_norm': 0.7331374883651733, 'learning_rate': 0.0001245703669298653, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2442/6464 [44:11<1:13:51, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0402, 'grad_norm': 0.688179075717926, 'learning_rate': 0.00012453940238427, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2443/6464 [44:12<1:11:21, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2415, 'grad_norm': 0.7185754776000977, 'learning_rate': 0.00012450843783867472, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2444/6464 [44:13<1:12:55, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.221, 'grad_norm': 0.6400700807571411, 'learning_rate': 0.00012447747329307943, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2445/6464 [44:14<1:08:54, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8419, 'grad_norm': 0.6525190472602844, 'learning_rate': 0.00012444650874748414, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2446/6464 [44:15<1:11:18, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2734, 'grad_norm': 0.6545091867446899, 'learning_rate': 0.00012441554420188883, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2447/6464 [44:16<1:15:19, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.155, 'grad_norm': 0.6332250237464905, 'learning_rate': 0.00012438457965629357, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2448/6464 [44:17<1:14:44, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3091, 'grad_norm': 0.720355749130249, 'learning_rate': 0.00012435361511069825, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2449/6464 [44:18<1:09:16, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1417, 'grad_norm': 0.8536850214004517, 'learning_rate': 0.00012432265056510296, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2450/6464 [44:19<1:11:53, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3833, 'grad_norm': 0.7055242657661438, 'learning_rate': 0.00012429168601950767, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2451/6464 [44:20<1:11:15, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1319, 'grad_norm': 0.7912972569465637, 'learning_rate': 0.00012426072147391236, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2452/6464 [44:21<1:09:04, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0869, 'grad_norm': 0.7583369612693787, 'learning_rate': 0.0001242297569283171, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2453/6464 [44:22<1:08:24, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1667, 'grad_norm': 0.6705039143562317, 'learning_rate': 0.00012419879238272178, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2454/6464 [44:23<1:06:41, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1304, 'grad_norm': 0.720089316368103, 'learning_rate': 0.0001241678278371265, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2455/6464 [44:25<1:09:36, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4345, 'grad_norm': 0.7482887506484985, 'learning_rate': 0.0001241368632915312, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2456/6464 [44:26<1:11:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5141, 'grad_norm': 0.7607845067977905, 'learning_rate': 0.0001241058987459359, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2457/6464 [44:26<1:06:46, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0145, 'grad_norm': 0.7605058550834656, 'learning_rate': 0.00012407493420034063, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2458/6464 [44:28<1:12:39, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2215, 'grad_norm': 0.635498583316803, 'learning_rate': 0.0001240439696547453, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2459/6464 [44:29<1:15:33, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1573, 'grad_norm': 0.6819823980331421, 'learning_rate': 0.00012401300510915005, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2460/6464 [44:30<1:12:41, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1033, 'grad_norm': 0.6884157657623291, 'learning_rate': 0.00012398204056355473, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2461/6464 [44:31<1:10:15, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.29, 'grad_norm': 0.7137209177017212, 'learning_rate': 0.00012395107601795944, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2462/6464 [44:32<1:13:07, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2573, 'grad_norm': 0.6648454666137695, 'learning_rate': 0.00012392011147236416, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2463/6464 [44:33<1:10:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0256, 'grad_norm': 0.7362135052680969, 'learning_rate': 0.00012388914692676884, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2464/6464 [44:34<1:10:04, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2006, 'grad_norm': 0.6461507081985474, 'learning_rate': 0.00012385818238117358, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2465/6464 [44:35<1:09:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2222, 'grad_norm': 0.8046846985816956, 'learning_rate': 0.00012382721783557826, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2466/6464 [44:36<1:08:01, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1411, 'grad_norm': 0.7040218710899353, 'learning_rate': 0.00012379625328998297, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2467/6464 [44:38<1:15:22, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1991, 'grad_norm': 0.6510979533195496, 'learning_rate': 0.00012376528874438768, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2468/6464 [44:39<1:12:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1814, 'grad_norm': 0.7344897985458374, 'learning_rate': 0.0001237343241987924, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2469/6464 [44:40<1:14:02, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.077, 'grad_norm': 0.6126841902732849, 'learning_rate': 0.0001237033596531971, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2470/6464 [44:41<1:11:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0901, 'grad_norm': 0.7484666705131531, 'learning_rate': 0.0001236723951076018, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2471/6464 [44:42<1:11:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2418, 'grad_norm': 0.7143591046333313, 'learning_rate': 0.0001236414305620065, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2472/6464 [44:43<1:08:55, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0492, 'grad_norm': 0.6868553757667542, 'learning_rate': 0.00012361046601641121, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2473/6464 [44:44<1:15:55, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3957, 'grad_norm': 0.6138790845870972, 'learning_rate': 0.00012357950147081593, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2474/6464 [44:45<1:16:48, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0849, 'grad_norm': 0.7670282125473022, 'learning_rate': 0.00012354853692522064, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2475/6464 [44:46<1:13:24, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1675, 'grad_norm': 0.7517701387405396, 'learning_rate': 0.00012351757237962532, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2476/6464 [44:47<1:12:22, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1157, 'grad_norm': 0.6269435882568359, 'learning_rate': 0.00012348660783403003, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2477/6464 [44:48<1:09:24, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1688, 'grad_norm': 0.7089906930923462, 'learning_rate': 0.00012345564328843474, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2478/6464 [44:49<1:09:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2076, 'grad_norm': 0.6419612765312195, 'learning_rate': 0.00012342467874283946, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2479/6464 [44:50<1:10:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.269, 'grad_norm': 0.8135958909988403, 'learning_rate': 0.00012339371419724417, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2480/6464 [44:51<1:08:54, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1626, 'grad_norm': 0.620319128036499, 'learning_rate': 0.00012336274965164888, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2481/6464 [44:52<1:09:12, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1658, 'grad_norm': 0.7205575108528137, 'learning_rate': 0.00012333178510605356, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2482/6464 [44:54<1:10:19, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2198, 'grad_norm': 0.6925776600837708, 'learning_rate': 0.00012330082056045827, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2483/6464 [44:54<1:08:02, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0816, 'grad_norm': 0.7468321323394775, 'learning_rate': 0.00012326985601486299, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2484/6464 [44:55<1:07:27, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1043, 'grad_norm': 0.6255449056625366, 'learning_rate': 0.0001232388914692677, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2485/6464 [44:57<1:10:37, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.598, 'grad_norm': 0.6622018814086914, 'learning_rate': 0.0001232079269236724, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2486/6464 [44:58<1:13:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4655, 'grad_norm': 0.7478764057159424, 'learning_rate': 0.0001231769623780771, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2487/6464 [44:59<1:15:18, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2466, 'grad_norm': 0.6540424823760986, 'learning_rate': 0.00012314599783248183, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 38%|โ–ˆโ–ˆโ–ˆโ–Š | 2488/6464 [45:00<1:16:18, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4201, 'grad_norm': 0.6884680390357971, 'learning_rate': 0.00012311503328688651, 'epoch': 0.38}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2489/6464 [45:02<1:18:10, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4196, 'grad_norm': 0.7135350108146667, 'learning_rate': 0.00012308406874129123, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2490/6464 [45:03<1:14:33, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2806, 'grad_norm': 0.667904257774353, 'learning_rate': 0.00012305310419569594, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2491/6464 [45:04<1:12:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8608, 'grad_norm': 0.5788757801055908, 'learning_rate': 0.00012302213965010062, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2492/6464 [45:05<1:13:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1722, 'grad_norm': 0.6323884129524231, 'learning_rate': 0.00012299117510450536, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2493/6464 [45:06<1:12:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2463, 'grad_norm': 0.8078455328941345, 'learning_rate': 0.00012296021055891004, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2494/6464 [45:07<1:12:59, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3947, 'grad_norm': 0.7304614186286926, 'learning_rate': 0.00012292924601331476, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2495/6464 [45:08<1:12:14, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.256, 'grad_norm': 0.6916150450706482, 'learning_rate': 0.00012289828146771947, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2496/6464 [45:09<1:15:08, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1845, 'grad_norm': 0.6408076882362366, 'learning_rate': 0.00012286731692212415, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2497/6464 [45:10<1:14:34, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2992, 'grad_norm': 0.667568027973175, 'learning_rate': 0.0001228363523765289, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2498/6464 [45:11<1:11:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2906, 'grad_norm': 0.8145695328712463, 'learning_rate': 0.00012280538783093357, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2499/6464 [45:12<1:12:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3752, 'grad_norm': 0.6795353293418884, 'learning_rate': 0.0001227744232853383, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2500/6464 [45:14<1:13:59, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2077, 'grad_norm': 0.6789171695709229, 'learning_rate': 0.000122743458739743, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/other.py:619: UserWarning: Unable to fetch remote file due to the following error (ReadTimeoutError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)\"), '(Request ID: 999b1ab1-33eb-4a7f-b972-7686f38d4c3c)') - silently ignoring the lookup for the file config.json in Magpie-Align/MagpieLM-4B-Chat-v0.1.\n", " warnings.warn(\n", "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/save_and_load.py:218: UserWarning: Could not find a config file in Magpie-Align/MagpieLM-4B-Chat-v0.1 - will assume that the vocabulary was not modified.\n", " warnings.warn(\n", " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2501/6464 [45:25<4:41:53, 4.27s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1676, 'grad_norm': 0.708441436290741, 'learning_rate': 0.0001227124941941477, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2502/6464 [45:27<3:47:55, 3.45s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3458, 'grad_norm': 0.5896579623222351, 'learning_rate': 0.00012268152964855242, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2503/6464 [45:28<3:05:33, 2.81s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3849, 'grad_norm': 0.6276963353157043, 'learning_rate': 0.0001226505651029571, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–Š | 2504/6464 [45:29<2:29:33, 2.27s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2644, 'grad_norm': 0.7430272102355957, 'learning_rate': 0.00012261960055736184, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2505/6464 [45:30<2:06:23, 1.92s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2019, 'grad_norm': 0.7271798253059387, 'learning_rate': 0.00012258863601176653, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2506/6464 [45:31<1:51:16, 1.69s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2824, 'grad_norm': 0.6496327519416809, 'learning_rate': 0.00012255767146617124, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2507/6464 [45:32<1:40:34, 1.52s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.094, 'grad_norm': 0.6113007068634033, 'learning_rate': 0.00012252670692057595, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2508/6464 [45:33<1:29:39, 1.36s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.129, 'grad_norm': 0.7133140563964844, 'learning_rate': 0.00012249574237498066, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2509/6464 [45:35<1:30:38, 1.38s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2793, 'grad_norm': 0.6047419309616089, 'learning_rate': 0.00012246477782938537, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2510/6464 [45:36<1:24:43, 1.29s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2921, 'grad_norm': 0.6634052991867065, 'learning_rate': 0.00012243381328379006, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2511/6464 [45:37<1:19:58, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0893, 'grad_norm': 0.6847744584083557, 'learning_rate': 0.00012240284873819477, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2512/6464 [45:39<1:29:57, 1.37s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4012, 'grad_norm': 0.597012460231781, 'learning_rate': 0.00012237188419259948, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2513/6464 [45:39<1:19:28, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9004, 'grad_norm': 0.8520725965499878, 'learning_rate': 0.0001223409196470042, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2514/6464 [45:40<1:15:37, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2934, 'grad_norm': 0.6991528272628784, 'learning_rate': 0.0001223099551014089, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2515/6464 [45:42<1:17:21, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1563, 'grad_norm': 0.6446400284767151, 'learning_rate': 0.00012227899055581359, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2516/6464 [45:43<1:16:55, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1271, 'grad_norm': 0.6161171793937683, 'learning_rate': 0.0001222480260102183, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2517/6464 [45:44<1:16:30, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0352, 'grad_norm': 0.6236775517463684, 'learning_rate': 0.000122217061464623, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2518/6464 [45:45<1:14:12, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2401, 'grad_norm': 0.7241342067718506, 'learning_rate': 0.00012218609691902772, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2519/6464 [45:46<1:13:48, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1636, 'grad_norm': 0.6163601875305176, 'learning_rate': 0.00012215513237343243, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2520/6464 [45:47<1:12:39, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1393, 'grad_norm': 0.671868085861206, 'learning_rate': 0.00012212416782783714, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2521/6464 [45:49<1:15:24, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2509, 'grad_norm': 0.7107478380203247, 'learning_rate': 0.00012209320328224183, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2522/6464 [45:50<1:13:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2794, 'grad_norm': 0.6740983724594116, 'learning_rate': 0.00012206223873664655, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2523/6464 [45:50<1:09:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.921, 'grad_norm': 0.6678535342216492, 'learning_rate': 0.00012203127419105125, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2524/6464 [45:51<1:06:48, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2419, 'grad_norm': 0.8118008971214294, 'learning_rate': 0.00012200030964545597, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2525/6464 [45:52<1:06:46, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7864, 'grad_norm': 0.7691988348960876, 'learning_rate': 0.00012196934509986066, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2526/6464 [45:54<1:14:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3378, 'grad_norm': 0.713624119758606, 'learning_rate': 0.00012193838055426536, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2527/6464 [45:55<1:14:55, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0487, 'grad_norm': 0.6051628589630127, 'learning_rate': 0.00012190741600867008, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2528/6464 [45:56<1:11:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8932, 'grad_norm': 0.6484595537185669, 'learning_rate': 0.00012187645146307478, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2529/6464 [45:57<1:09:50, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0897, 'grad_norm': 0.7010655403137207, 'learning_rate': 0.0001218454869174795, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2530/6464 [45:58<1:09:37, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2724, 'grad_norm': 0.7302774786949158, 'learning_rate': 0.0001218145223718842, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2531/6464 [45:59<1:07:07, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.055, 'grad_norm': 0.7474780082702637, 'learning_rate': 0.0001217835578262889, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2532/6464 [46:00<1:05:45, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.226, 'grad_norm': 0.6986244916915894, 'learning_rate': 0.00012175259328069361, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2533/6464 [46:01<1:05:39, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0855, 'grad_norm': 0.7166180610656738, 'learning_rate': 0.00012172162873509831, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2534/6464 [46:02<1:05:03, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.112, 'grad_norm': 0.7485422492027283, 'learning_rate': 0.00012169066418950303, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2535/6464 [46:03<1:13:43, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0923, 'grad_norm': 0.8144607543945312, 'learning_rate': 0.00012165969964390773, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2536/6464 [46:04<1:11:53, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.032, 'grad_norm': 0.6953937411308289, 'learning_rate': 0.00012162873509831243, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2537/6464 [46:05<1:12:22, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0223, 'grad_norm': 0.8277535438537598, 'learning_rate': 0.00012159777055271715, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2538/6464 [46:07<1:14:57, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1678, 'grad_norm': 0.5935414433479309, 'learning_rate': 0.00012156680600712185, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2539/6464 [46:08<1:11:44, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0127, 'grad_norm': 0.6602077484130859, 'learning_rate': 0.00012153584146152656, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2540/6464 [46:09<1:12:27, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1981, 'grad_norm': 0.7011054158210754, 'learning_rate': 0.00012150487691593126, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2541/6464 [46:10<1:10:42, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0879, 'grad_norm': 0.7724908590316772, 'learning_rate': 0.00012147391237033596, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2542/6464 [46:11<1:10:39, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1606, 'grad_norm': 0.7479102611541748, 'learning_rate': 0.00012144294782474068, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2543/6464 [46:12<1:11:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2572, 'grad_norm': 0.721123218536377, 'learning_rate': 0.00012141198327914538, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2544/6464 [46:13<1:11:48, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2898, 'grad_norm': 0.8309625387191772, 'learning_rate': 0.00012138101873355011, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2545/6464 [46:14<1:12:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1079, 'grad_norm': 0.6866495609283447, 'learning_rate': 0.0001213500541879548, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2546/6464 [46:15<1:09:12, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0049, 'grad_norm': 0.6913415789604187, 'learning_rate': 0.0001213190896423595, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2547/6464 [46:16<1:05:21, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0387, 'grad_norm': 0.7249626517295837, 'learning_rate': 0.00012128812509676421, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2548/6464 [46:17<1:03:13, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1867, 'grad_norm': 0.7364850044250488, 'learning_rate': 0.00012125716055116891, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2549/6464 [46:18<1:03:12, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9507, 'grad_norm': 0.6653650403022766, 'learning_rate': 0.00012122619600557364, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2550/6464 [46:19<1:07:32, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2045, 'grad_norm': 0.6390487551689148, 'learning_rate': 0.00012119523145997833, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2551/6464 [46:20<1:09:07, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2843, 'grad_norm': 0.7229604721069336, 'learning_rate': 0.00012116426691438303, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2552/6464 [46:21<1:08:40, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4548, 'grad_norm': 0.7344944477081299, 'learning_rate': 0.00012113330236878774, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 39%|โ–ˆโ–ˆโ–ˆโ–‰ | 2553/6464 [46:22<1:09:57, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0372, 'grad_norm': 0.6173458695411682, 'learning_rate': 0.00012110233782319244, 'epoch': 0.39}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2554/6464 [46:23<1:08:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9151, 'grad_norm': 0.6641566157341003, 'learning_rate': 0.00012107137327759717, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2555/6464 [46:25<1:10:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1903, 'grad_norm': 0.6743088960647583, 'learning_rate': 0.00012104040873200186, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2556/6464 [46:26<1:08:12, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2907, 'grad_norm': 0.8087514042854309, 'learning_rate': 0.00012100944418640656, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2557/6464 [46:27<1:11:03, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.339, 'grad_norm': 0.7324570417404175, 'learning_rate': 0.00012097847964081129, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2558/6464 [46:28<1:08:37, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0615, 'grad_norm': 0.7377572059631348, 'learning_rate': 0.00012094751509521598, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2559/6464 [46:29<1:11:42, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3328, 'grad_norm': 0.6762503981590271, 'learning_rate': 0.0001209165505496207, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2560/6464 [46:30<1:08:45, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2106, 'grad_norm': 0.6839382648468018, 'learning_rate': 0.0001208855860040254, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2561/6464 [46:31<1:11:11, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2195, 'grad_norm': 0.6599217653274536, 'learning_rate': 0.00012085462145843009, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2562/6464 [46:32<1:08:29, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1545, 'grad_norm': 0.8027071952819824, 'learning_rate': 0.00012082365691283482, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2563/6464 [46:33<1:07:56, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1408, 'grad_norm': 0.7945263981819153, 'learning_rate': 0.00012079269236723951, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2564/6464 [46:34<1:10:08, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0569, 'grad_norm': 0.6722474098205566, 'learning_rate': 0.00012076172782164424, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2565/6464 [46:35<1:08:06, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.29, 'grad_norm': 0.8126551508903503, 'learning_rate': 0.00012073076327604894, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2566/6464 [46:36<1:09:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0828, 'grad_norm': 0.6212537288665771, 'learning_rate': 0.00012069979873045363, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2567/6464 [46:37<1:08:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3602, 'grad_norm': 0.7502990961074829, 'learning_rate': 0.00012066883418485835, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2568/6464 [46:38<1:07:53, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2111, 'grad_norm': 0.7033702731132507, 'learning_rate': 0.00012063786963926304, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2569/6464 [46:39<1:09:56, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4723, 'grad_norm': 0.7039063572883606, 'learning_rate': 0.00012060690509366777, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2570/6464 [46:40<1:08:34, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1138, 'grad_norm': 0.7511486411094666, 'learning_rate': 0.00012057594054807247, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2571/6464 [46:42<1:07:42, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2297, 'grad_norm': 0.7909160852432251, 'learning_rate': 0.00012054497600247716, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2572/6464 [46:43<1:09:03, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1122, 'grad_norm': 0.6874393224716187, 'learning_rate': 0.00012051401145688188, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2573/6464 [46:44<1:11:55, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2554, 'grad_norm': 0.6157068014144897, 'learning_rate': 0.00012048304691128657, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2574/6464 [46:45<1:12:22, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1387, 'grad_norm': 0.6617433428764343, 'learning_rate': 0.0001204520823656913, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2575/6464 [46:46<1:14:24, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.151, 'grad_norm': 0.6269651651382446, 'learning_rate': 0.000120421117820096, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2576/6464 [46:47<1:17:28, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3416, 'grad_norm': 0.6357779502868652, 'learning_rate': 0.0001203901532745007, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2577/6464 [46:49<1:15:41, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.194, 'grad_norm': 0.7208334803581238, 'learning_rate': 0.00012035918872890542, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2578/6464 [46:50<1:13:22, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0919, 'grad_norm': 0.6658256649971008, 'learning_rate': 0.00012032822418331012, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2579/6464 [46:51<1:11:51, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9702, 'grad_norm': 0.6214709281921387, 'learning_rate': 0.00012029725963771483, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2580/6464 [46:52<1:09:38, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.167, 'grad_norm': 0.6715042591094971, 'learning_rate': 0.00012026629509211953, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2581/6464 [46:53<1:11:30, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0705, 'grad_norm': 0.6551666855812073, 'learning_rate': 0.00012023533054652422, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2582/6464 [46:54<1:12:12, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3908, 'grad_norm': 0.716813862323761, 'learning_rate': 0.00012020436600092895, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2583/6464 [46:55<1:10:52, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1393, 'grad_norm': 0.7299016118049622, 'learning_rate': 0.00012017340145533365, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2584/6464 [46:56<1:16:33, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3536, 'grad_norm': 0.5789558291435242, 'learning_rate': 0.00012014243690973837, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–‰ | 2585/6464 [46:58<1:16:49, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4459, 'grad_norm': 0.7112829685211182, 'learning_rate': 0.00012011147236414307, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2586/6464 [46:59<1:14:10, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.989, 'grad_norm': 0.7219147682189941, 'learning_rate': 0.00012008050781854777, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2587/6464 [47:00<1:12:01, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.341, 'grad_norm': 0.6776807308197021, 'learning_rate': 0.00012004954327295248, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2588/6464 [47:01<1:14:16, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2387, 'grad_norm': 0.65440434217453, 'learning_rate': 0.00012001857872735718, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2589/6464 [47:02<1:14:48, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3085, 'grad_norm': 0.6514145135879517, 'learning_rate': 0.0001199876141817619, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2590/6464 [47:03<1:14:10, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0554, 'grad_norm': 0.609254002571106, 'learning_rate': 0.0001199566496361666, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2591/6464 [47:04<1:13:37, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3684, 'grad_norm': 0.7202049493789673, 'learning_rate': 0.0001199256850905713, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2592/6464 [47:06<1:15:22, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3885, 'grad_norm': 0.6651782393455505, 'learning_rate': 0.00011989472054497601, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2593/6464 [47:07<1:12:41, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2301, 'grad_norm': 0.7028008103370667, 'learning_rate': 0.0001198637559993807, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2594/6464 [47:08<1:13:02, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1296, 'grad_norm': 0.6814484000205994, 'learning_rate': 0.00011983279145378543, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2595/6464 [47:09<1:13:09, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3451, 'grad_norm': 0.647330641746521, 'learning_rate': 0.00011980182690819013, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2596/6464 [47:10<1:09:04, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.083, 'grad_norm': 0.7539605498313904, 'learning_rate': 0.00011977086236259483, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2597/6464 [47:11<1:08:11, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9746, 'grad_norm': 0.6154561638832092, 'learning_rate': 0.00011973989781699955, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2598/6464 [47:12<1:10:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2408, 'grad_norm': 0.7147661447525024, 'learning_rate': 0.00011970893327140425, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2599/6464 [47:13<1:08:04, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2109, 'grad_norm': 0.7887043952941895, 'learning_rate': 0.00011967796872580896, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2600/6464 [47:14<1:06:36, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0358, 'grad_norm': 0.7227208018302917, 'learning_rate': 0.00011964700418021366, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2601/6464 [47:15<1:04:50, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9591, 'grad_norm': 0.7001058459281921, 'learning_rate': 0.00011961603963461836, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2602/6464 [47:16<1:03:42, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.993, 'grad_norm': 0.694183349609375, 'learning_rate': 0.00011958507508902308, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2603/6464 [47:17<1:08:30, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3327, 'grad_norm': 0.6202970147132874, 'learning_rate': 0.00011955411054342778, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2604/6464 [47:18<1:07:28, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0353, 'grad_norm': 0.7079253196716309, 'learning_rate': 0.0001195231459978325, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2605/6464 [47:19<1:09:38, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1393, 'grad_norm': 0.7000866532325745, 'learning_rate': 0.0001194921814522372, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2606/6464 [47:20<1:10:30, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.24, 'grad_norm': 0.7094603776931763, 'learning_rate': 0.0001194612169066419, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2607/6464 [47:22<1:16:30, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2924, 'grad_norm': 0.6252573728561401, 'learning_rate': 0.00011943025236104661, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2608/6464 [47:23<1:19:45, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.31, 'grad_norm': 0.611557126045227, 'learning_rate': 0.00011939928781545131, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2609/6464 [47:24<1:15:55, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0122, 'grad_norm': 0.6451966762542725, 'learning_rate': 0.00011936832326985603, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2610/6464 [47:25<1:13:33, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9831, 'grad_norm': 0.6311693787574768, 'learning_rate': 0.00011933735872426073, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2611/6464 [47:27<1:15:45, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4558, 'grad_norm': 0.6695824265480042, 'learning_rate': 0.00011930639417866543, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2612/6464 [47:28<1:11:15, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2035, 'grad_norm': 0.6584888696670532, 'learning_rate': 0.00011927542963307014, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2613/6464 [47:29<1:15:06, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1343, 'grad_norm': 0.6037551760673523, 'learning_rate': 0.00011924446508747484, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2614/6464 [47:30<1:11:38, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.061, 'grad_norm': 0.6701081395149231, 'learning_rate': 0.00011921350054187956, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2615/6464 [47:31<1:07:08, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2136, 'grad_norm': 0.8023768663406372, 'learning_rate': 0.00011918253599628426, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2616/6464 [47:32<1:10:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2201, 'grad_norm': 0.711337149143219, 'learning_rate': 0.00011915157145068896, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 40%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2617/6464 [47:33<1:05:31, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0656, 'grad_norm': 0.7869889140129089, 'learning_rate': 0.00011912060690509368, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2618/6464 [47:34<1:04:15, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9657, 'grad_norm': 0.6829505562782288, 'learning_rate': 0.00011908964235949838, 'epoch': 0.4}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2619/6464 [47:35<1:06:08, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.047, 'grad_norm': 0.6244028806686401, 'learning_rate': 0.00011905867781390309, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2620/6464 [47:36<1:10:11, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3668, 'grad_norm': 0.6466639041900635, 'learning_rate': 0.00011902771326830779, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2621/6464 [47:37<1:12:24, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3175, 'grad_norm': 0.6231934428215027, 'learning_rate': 0.00011899674872271249, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2622/6464 [47:38<1:12:49, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9869, 'grad_norm': 0.5936764478683472, 'learning_rate': 0.00011896578417711721, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2623/6464 [47:40<1:13:13, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1028, 'grad_norm': 0.6463512778282166, 'learning_rate': 0.00011893481963152191, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2624/6464 [47:41<1:13:50, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2201, 'grad_norm': 0.7315231561660767, 'learning_rate': 0.00011890385508592664, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2625/6464 [47:42<1:14:04, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1365, 'grad_norm': 0.7921847701072693, 'learning_rate': 0.00011887289054033133, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2626/6464 [47:43<1:09:52, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0554, 'grad_norm': 0.6684091687202454, 'learning_rate': 0.00011884192599473603, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2627/6464 [47:44<1:04:07, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1128, 'grad_norm': 0.7685182094573975, 'learning_rate': 0.00011881096144914074, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2628/6464 [47:45<1:02:04, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8995, 'grad_norm': 0.6646100878715515, 'learning_rate': 0.00011877999690354544, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2629/6464 [47:46<1:05:11, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0761, 'grad_norm': 0.5767950415611267, 'learning_rate': 0.00011874903235795017, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2630/6464 [47:47<1:07:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1348, 'grad_norm': 0.7068963646888733, 'learning_rate': 0.00011871806781235486, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2631/6464 [47:48<1:08:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3364, 'grad_norm': 0.745192289352417, 'learning_rate': 0.00011868710326675956, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2632/6464 [47:49<1:10:40, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1668, 'grad_norm': 0.6687730550765991, 'learning_rate': 0.00011865613872116427, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2633/6464 [47:50<1:09:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1381, 'grad_norm': 0.6513742208480835, 'learning_rate': 0.00011862517417556897, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2634/6464 [47:51<1:08:34, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.331, 'grad_norm': 0.9267051219940186, 'learning_rate': 0.0001185942096299737, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2635/6464 [47:52<1:03:54, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9177, 'grad_norm': 0.7057925462722778, 'learning_rate': 0.00011856324508437839, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2636/6464 [47:53<1:05:21, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.041, 'grad_norm': 0.6848708987236023, 'learning_rate': 0.00011853228053878309, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2637/6464 [47:54<1:04:13, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0111, 'grad_norm': 0.6815873980522156, 'learning_rate': 0.00011850131599318782, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2638/6464 [47:55<1:04:39, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2677, 'grad_norm': 0.8273656368255615, 'learning_rate': 0.00011847035144759251, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2639/6464 [47:56<1:05:28, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3618, 'grad_norm': 0.8425807356834412, 'learning_rate': 0.00011843938690199722, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2640/6464 [47:57<1:09:09, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1651, 'grad_norm': 0.7197660803794861, 'learning_rate': 0.00011840842235640192, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2641/6464 [47:59<1:10:25, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3001, 'grad_norm': 0.7063425779342651, 'learning_rate': 0.00011837745781080662, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2642/6464 [48:00<1:17:59, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1138, 'grad_norm': 0.8488981127738953, 'learning_rate': 0.00011834649326521135, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2643/6464 [48:01<1:11:53, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0207, 'grad_norm': 0.7009947896003723, 'learning_rate': 0.00011831552871961604, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2644/6464 [48:02<1:08:15, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8895, 'grad_norm': 0.8185399174690247, 'learning_rate': 0.00011828456417402077, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2645/6464 [48:03<1:05:13, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.045, 'grad_norm': 0.735430896282196, 'learning_rate': 0.00011825359962842547, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2646/6464 [48:04<1:14:09, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1748, 'grad_norm': 0.6123913526535034, 'learning_rate': 0.00011822263508283016, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2647/6464 [48:05<1:13:41, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2159, 'grad_norm': 0.6667314767837524, 'learning_rate': 0.00011819167053723488, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2648/6464 [48:06<1:08:15, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0786, 'grad_norm': 0.8139501214027405, 'learning_rate': 0.00011816070599163957, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2649/6464 [48:07<1:08:36, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4198, 'grad_norm': 0.7319238185882568, 'learning_rate': 0.0001181297414460443, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2650/6464 [48:08<1:07:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1474, 'grad_norm': 0.7066823244094849, 'learning_rate': 0.000118098776900449, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2651/6464 [48:10<1:07:43, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3453, 'grad_norm': 0.6726579070091248, 'learning_rate': 0.0001180678123548537, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2652/6464 [48:10<1:05:14, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0526, 'grad_norm': 0.7040551900863647, 'learning_rate': 0.0001180368478092584, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2653/6464 [48:12<1:05:39, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0663, 'grad_norm': 0.6904028654098511, 'learning_rate': 0.0001180058832636631, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2654/6464 [48:13<1:07:34, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9941, 'grad_norm': 0.6235241293907166, 'learning_rate': 0.00011797491871806783, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2655/6464 [48:14<1:07:12, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0437, 'grad_norm': 0.6638827323913574, 'learning_rate': 0.00011794395417247253, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2656/6464 [48:15<1:06:46, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1005, 'grad_norm': 0.7146404385566711, 'learning_rate': 0.00011791298962687722, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2657/6464 [48:16<1:06:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1195, 'grad_norm': 0.7814654111862183, 'learning_rate': 0.00011788202508128195, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2658/6464 [48:17<1:05:14, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2201, 'grad_norm': 0.7302481532096863, 'learning_rate': 0.00011785106053568665, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2659/6464 [48:18<1:05:39, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3324, 'grad_norm': 0.8094119429588318, 'learning_rate': 0.00011782009599009136, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2660/6464 [48:19<1:04:48, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0291, 'grad_norm': 0.6579031944274902, 'learning_rate': 0.00011778913144449606, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2661/6464 [48:20<1:08:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0857, 'grad_norm': 0.6323326826095581, 'learning_rate': 0.00011775816689890075, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2662/6464 [48:21<1:06:06, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1404, 'grad_norm': 0.7826210856437683, 'learning_rate': 0.00011772720235330548, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2663/6464 [48:22<1:07:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4295, 'grad_norm': 0.6775776743888855, 'learning_rate': 0.00011769623780771018, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2664/6464 [48:23<1:07:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9998, 'grad_norm': 0.666118860244751, 'learning_rate': 0.0001176652732621149, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2665/6464 [48:24<1:07:27, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2842, 'grad_norm': 0.731626033782959, 'learning_rate': 0.0001176343087165196, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆ | 2666/6464 [48:25<1:06:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.167, 'grad_norm': 0.7981396317481995, 'learning_rate': 0.0001176033441709243, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2667/6464 [48:26<1:04:27, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9772, 'grad_norm': 0.7663629651069641, 'learning_rate': 0.00011757237962532901, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2668/6464 [48:27<1:05:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1164, 'grad_norm': 0.65426105260849, 'learning_rate': 0.0001175414150797337, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2669/6464 [48:28<1:05:58, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0454, 'grad_norm': 0.7244325280189514, 'learning_rate': 0.00011751045053413843, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2670/6464 [48:29<1:03:10, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0606, 'grad_norm': 0.7246798276901245, 'learning_rate': 0.00011747948598854313, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2671/6464 [48:30<1:02:14, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1865, 'grad_norm': 0.7604637742042542, 'learning_rate': 0.00011744852144294783, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2672/6464 [48:31<1:00:59, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1292, 'grad_norm': 0.7492474317550659, 'learning_rate': 0.00011741755689735254, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2673/6464 [48:32<1:01:46, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2006, 'grad_norm': 0.7280613780021667, 'learning_rate': 0.00011738659235175723, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2674/6464 [48:33<1:03:27, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0463, 'grad_norm': 0.6034215688705444, 'learning_rate': 0.00011735562780616196, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2675/6464 [48:34<1:03:09, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7796, 'grad_norm': 0.6585028171539307, 'learning_rate': 0.00011732466326056666, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2676/6464 [48:35<1:01:55, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2572, 'grad_norm': 0.8255172371864319, 'learning_rate': 0.00011729369871497136, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2677/6464 [48:36<1:04:24, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.272, 'grad_norm': 0.6692155003547668, 'learning_rate': 0.00011726273416937608, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2678/6464 [48:37<1:08:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2243, 'grad_norm': 0.6087207794189453, 'learning_rate': 0.00011723176962378078, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2679/6464 [48:38<1:06:17, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0179, 'grad_norm': 0.6900701522827148, 'learning_rate': 0.00011720080507818549, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2680/6464 [48:40<1:08:09, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.391, 'grad_norm': 0.7317704558372498, 'learning_rate': 0.00011716984053259019, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2681/6464 [48:41<1:07:12, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1767, 'grad_norm': 0.7733438014984131, 'learning_rate': 0.00011713887598699489, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 41%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2682/6464 [48:42<1:05:01, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0887, 'grad_norm': 0.7454209923744202, 'learning_rate': 0.00011710791144139961, 'epoch': 0.41}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2683/6464 [48:43<1:05:18, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.215, 'grad_norm': 0.6920389533042908, 'learning_rate': 0.00011707694689580431, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2684/6464 [48:44<1:06:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3559, 'grad_norm': 0.7747904658317566, 'learning_rate': 0.00011704598235020903, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2685/6464 [48:45<1:06:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2944, 'grad_norm': 0.7031227946281433, 'learning_rate': 0.00011701501780461373, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2686/6464 [48:46<1:05:11, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.976, 'grad_norm': 0.6513404250144958, 'learning_rate': 0.00011698405325901843, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2687/6464 [48:47<1:08:16, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1867, 'grad_norm': 0.630831241607666, 'learning_rate': 0.00011695308871342314, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2688/6464 [48:48<1:07:16, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3431, 'grad_norm': 0.8123417496681213, 'learning_rate': 0.00011692212416782784, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2689/6464 [48:49<1:08:06, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3029, 'grad_norm': 0.6668825745582581, 'learning_rate': 0.00011689115962223256, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2690/6464 [48:50<1:04:03, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9904, 'grad_norm': 0.7456356287002563, 'learning_rate': 0.00011686019507663726, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2691/6464 [48:51<1:03:11, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1653, 'grad_norm': 0.7459399104118347, 'learning_rate': 0.00011682923053104196, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2692/6464 [48:52<1:02:04, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8587, 'grad_norm': 0.6993618607521057, 'learning_rate': 0.00011679826598544667, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2693/6464 [48:53<1:05:03, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4537, 'grad_norm': 0.6587714552879333, 'learning_rate': 0.00011676730143985137, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2694/6464 [48:54<1:06:42, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2599, 'grad_norm': 0.631373941898346, 'learning_rate': 0.00011673633689425609, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2695/6464 [48:55<1:10:04, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1885, 'grad_norm': 0.572064220905304, 'learning_rate': 0.00011670537234866079, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2696/6464 [48:56<1:09:24, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1101, 'grad_norm': 0.7125418782234192, 'learning_rate': 0.00011667440780306549, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2697/6464 [48:57<1:05:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0793, 'grad_norm': 0.8051580786705017, 'learning_rate': 0.00011664344325747021, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2698/6464 [48:58<1:05:44, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3086, 'grad_norm': 0.8111661076545715, 'learning_rate': 0.00011661247871187491, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2699/6464 [48:59<1:06:00, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.13, 'grad_norm': 0.7220374941825867, 'learning_rate': 0.00011658151416627962, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2700/6464 [49:00<1:01:22, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1189, 'grad_norm': 0.7632446885108948, 'learning_rate': 0.00011655054962068432, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2701/6464 [49:01<59:53, 1.05it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0729, 'grad_norm': 0.6754528284072876, 'learning_rate': 0.00011651958507508902, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2702/6464 [49:02<1:01:46, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0906, 'grad_norm': 0.7739478945732117, 'learning_rate': 0.00011648862052949374, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2703/6464 [49:03<59:31, 1.05it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9088, 'grad_norm': 0.7075280547142029, 'learning_rate': 0.00011645765598389844, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2704/6464 [49:04<1:00:01, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3391, 'grad_norm': 0.7523310780525208, 'learning_rate': 0.00011642669143830316, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2705/6464 [49:05<1:01:11, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3641, 'grad_norm': 0.8266021609306335, 'learning_rate': 0.00011639572689270786, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2706/6464 [49:06<1:03:10, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1049, 'grad_norm': 0.6463066339492798, 'learning_rate': 0.00011636476234711256, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2707/6464 [49:07<1:02:04, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2336, 'grad_norm': 0.8131308555603027, 'learning_rate': 0.00011633379780151727, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2708/6464 [49:08<1:04:18, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3856, 'grad_norm': 0.6881518363952637, 'learning_rate': 0.00011630283325592197, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2709/6464 [49:09<1:03:11, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.962, 'grad_norm': 0.6130647659301758, 'learning_rate': 0.0001162718687103267, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2710/6464 [49:10<1:00:54, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1071, 'grad_norm': 0.794227123260498, 'learning_rate': 0.00011624090416473139, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2711/6464 [49:11<1:05:06, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1767, 'grad_norm': 0.5875658988952637, 'learning_rate': 0.00011620993961913609, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2712/6464 [49:12<1:06:06, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0436, 'grad_norm': 0.6272473335266113, 'learning_rate': 0.0001161789750735408, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2713/6464 [49:13<1:03:09, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.107, 'grad_norm': 0.7078040242195129, 'learning_rate': 0.0001161480105279455, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2714/6464 [49:14<1:02:58, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0881, 'grad_norm': 0.737792432308197, 'learning_rate': 0.00011611704598235022, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2715/6464 [49:15<1:02:34, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.006, 'grad_norm': 0.6581880450248718, 'learning_rate': 0.00011608608143675492, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2716/6464 [49:17<1:09:39, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1286, 'grad_norm': 0.5789807438850403, 'learning_rate': 0.00011605511689115962, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2717/6464 [49:18<1:07:12, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2512, 'grad_norm': 0.6686707139015198, 'learning_rate': 0.00011602415234556434, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2718/6464 [49:19<1:08:27, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1715, 'grad_norm': 0.7223837971687317, 'learning_rate': 0.00011599318779996904, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2719/6464 [49:20<1:09:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1559, 'grad_norm': 0.6622263193130493, 'learning_rate': 0.00011596222325437375, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2720/6464 [49:21<1:09:23, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3559, 'grad_norm': 0.705143392086029, 'learning_rate': 0.00011593125870877845, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2721/6464 [49:22<1:11:03, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4004, 'grad_norm': 0.743507444858551, 'learning_rate': 0.00011590029416318315, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2722/6464 [49:23<1:11:30, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4953, 'grad_norm': 0.727898120880127, 'learning_rate': 0.00011586932961758787, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2723/6464 [49:24<1:09:32, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1238, 'grad_norm': 0.7828543186187744, 'learning_rate': 0.00011583836507199257, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2724/6464 [49:26<1:08:28, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2553, 'grad_norm': 0.7326594591140747, 'learning_rate': 0.0001158074005263973, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2725/6464 [49:27<1:07:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1591, 'grad_norm': 0.7355843782424927, 'learning_rate': 0.000115776435980802, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2726/6464 [49:28<1:04:57, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1418, 'grad_norm': 0.7333186268806458, 'learning_rate': 0.00011574547143520669, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2727/6464 [49:29<1:09:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0849, 'grad_norm': 0.6536771655082703, 'learning_rate': 0.0001157145068896114, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2728/6464 [49:30<1:07:08, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0486, 'grad_norm': 0.6363429427146912, 'learning_rate': 0.0001156835423440161, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2729/6464 [49:31<1:05:15, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1042, 'grad_norm': 0.6847955584526062, 'learning_rate': 0.00011565257779842083, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2730/6464 [49:32<1:03:21, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2573, 'grad_norm': 0.7494703531265259, 'learning_rate': 0.00011562161325282552, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2731/6464 [49:33<1:05:08, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3679, 'grad_norm': 0.66904217004776, 'learning_rate': 0.00011559064870723022, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2732/6464 [49:34<1:01:09, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0151, 'grad_norm': 0.8113884925842285, 'learning_rate': 0.00011555968416163493, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2733/6464 [49:35<1:01:43, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1845, 'grad_norm': 0.6904897689819336, 'learning_rate': 0.00011552871961603963, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2734/6464 [49:36<1:02:02, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0414, 'grad_norm': 0.6410728096961975, 'learning_rate': 0.00011549775507044436, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2735/6464 [49:37<1:03:41, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2528, 'grad_norm': 0.7460752129554749, 'learning_rate': 0.00011546679052484905, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2736/6464 [49:38<1:04:18, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1916, 'grad_norm': 0.7680294513702393, 'learning_rate': 0.00011543582597925375, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2737/6464 [49:39<1:08:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3143, 'grad_norm': 0.668079674243927, 'learning_rate': 0.00011540486143365848, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2738/6464 [49:40<1:10:07, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2194, 'grad_norm': 0.6708976030349731, 'learning_rate': 0.00011537389688806317, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2739/6464 [49:42<1:12:17, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0329, 'grad_norm': 0.6029186844825745, 'learning_rate': 0.00011534293234246787, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2740/6464 [49:43<1:09:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.391, 'grad_norm': 0.7971329092979431, 'learning_rate': 0.00011531196779687258, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2741/6464 [49:44<1:07:06, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2187, 'grad_norm': 0.775699257850647, 'learning_rate': 0.00011528100325127728, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2742/6464 [49:45<1:06:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9874, 'grad_norm': 0.6931353807449341, 'learning_rate': 0.000115250038705682, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2743/6464 [49:46<1:06:33, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.061, 'grad_norm': 0.6484196186065674, 'learning_rate': 0.0001152190741600867, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2744/6464 [49:47<1:06:36, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2124, 'grad_norm': 0.6765077114105225, 'learning_rate': 0.0001151881096144914, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2745/6464 [49:48<1:05:26, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1761, 'grad_norm': 0.7111203074455261, 'learning_rate': 0.00011515714506889613, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2746/6464 [49:49<1:07:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3329, 'grad_norm': 0.6392151713371277, 'learning_rate': 0.00011512618052330083, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 42%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2747/6464 [49:50<1:04:32, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1575, 'grad_norm': 0.7822674512863159, 'learning_rate': 0.00011509521597770554, 'epoch': 0.42}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2748/6464 [49:51<1:02:02, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2697, 'grad_norm': 0.8007005453109741, 'learning_rate': 0.00011506425143211023, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2749/6464 [49:52<1:04:34, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1696, 'grad_norm': 0.6438694000244141, 'learning_rate': 0.00011503328688651493, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2750/6464 [49:53<1:05:50, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2617, 'grad_norm': 0.8204358816146851, 'learning_rate': 0.00011500232234091966, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2751/6464 [49:54<1:06:30, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2151, 'grad_norm': 0.6872907280921936, 'learning_rate': 0.00011497135779532435, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2752/6464 [49:55<1:03:51, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0517, 'grad_norm': 0.7123714089393616, 'learning_rate': 0.00011494039324972907, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2753/6464 [49:56<1:06:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0611, 'grad_norm': 0.61617112159729, 'learning_rate': 0.00011490942870413376, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2754/6464 [49:58<1:12:05, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1559, 'grad_norm': 0.6430280208587646, 'learning_rate': 0.00011487846415853846, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2755/6464 [49:59<1:12:58, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1689, 'grad_norm': 0.6026554107666016, 'learning_rate': 0.00011484749961294319, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2756/6464 [50:00<1:10:33, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2064, 'grad_norm': 0.7820934653282166, 'learning_rate': 0.00011481653506734788, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2757/6464 [50:01<1:11:50, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1406, 'grad_norm': 0.6044891476631165, 'learning_rate': 0.00011478557052175261, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2758/6464 [50:02<1:10:45, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.565, 'grad_norm': 0.7950432896614075, 'learning_rate': 0.00011475460597615731, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2759/6464 [50:03<1:09:40, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3372, 'grad_norm': 0.984717607498169, 'learning_rate': 0.000114723641430562, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2760/6464 [50:04<1:08:20, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2591, 'grad_norm': 0.7346634268760681, 'learning_rate': 0.00011469267688496672, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2761/6464 [50:05<1:07:59, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1353, 'grad_norm': 0.6818830370903015, 'learning_rate': 0.00011466171233937141, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2762/6464 [50:07<1:08:03, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2616, 'grad_norm': 0.7633433938026428, 'learning_rate': 0.00011463074779377614, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2763/6464 [50:08<1:08:16, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9896, 'grad_norm': 0.6875755190849304, 'learning_rate': 0.00011459978324818084, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2764/6464 [50:09<1:10:51, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3501, 'grad_norm': 0.7338444590568542, 'learning_rate': 0.00011456881870258553, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2765/6464 [50:10<1:11:56, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0544, 'grad_norm': 0.6073045134544373, 'learning_rate': 0.00011453785415699026, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2766/6464 [50:11<1:09:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2966, 'grad_norm': 0.7816004753112793, 'learning_rate': 0.00011450688961139496, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2767/6464 [50:13<1:13:58, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3808, 'grad_norm': 0.633249819278717, 'learning_rate': 0.00011447592506579967, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2768/6464 [50:14<1:10:39, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.999, 'grad_norm': 0.6498941779136658, 'learning_rate': 0.00011444496052020437, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2769/6464 [50:15<1:10:55, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2423, 'grad_norm': 0.6793570518493652, 'learning_rate': 0.00011441399597460906, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2770/6464 [50:16<1:14:47, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5379, 'grad_norm': 0.737322986125946, 'learning_rate': 0.00011438303142901379, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2771/6464 [50:17<1:11:21, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9953, 'grad_norm': 0.6522973775863647, 'learning_rate': 0.00011435206688341849, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2772/6464 [50:18<1:13:27, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2301, 'grad_norm': 0.6734658479690552, 'learning_rate': 0.0001143211023378232, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2773/6464 [50:19<1:11:09, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1192, 'grad_norm': 0.7204636335372925, 'learning_rate': 0.0001142901377922279, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2774/6464 [50:20<1:07:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0416, 'grad_norm': 0.7429088354110718, 'learning_rate': 0.0001142591732466326, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2775/6464 [50:21<1:04:48, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.943, 'grad_norm': 0.670533299446106, 'learning_rate': 0.00011422820870103732, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2776/6464 [50:23<1:07:38, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4355, 'grad_norm': 0.758554995059967, 'learning_rate': 0.00011419724415544202, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2777/6464 [50:24<1:10:27, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1496, 'grad_norm': 0.6699452996253967, 'learning_rate': 0.00011416627960984674, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2778/6464 [50:25<1:06:52, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3015, 'grad_norm': 0.8346531391143799, 'learning_rate': 0.00011413531506425144, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2779/6464 [50:26<1:06:11, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3563, 'grad_norm': 0.8187469244003296, 'learning_rate': 0.00011410435051865614, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2780/6464 [50:27<1:10:30, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4604, 'grad_norm': 0.6729464530944824, 'learning_rate': 0.00011407338597306085, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2781/6464 [50:28<1:08:38, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9774, 'grad_norm': 0.78993159532547, 'learning_rate': 0.00011404242142746555, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2782/6464 [50:29<1:10:21, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.298, 'grad_norm': 0.7179825305938721, 'learning_rate': 0.00011401145688187027, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2783/6464 [50:30<1:07:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2063, 'grad_norm': 0.8643933534622192, 'learning_rate': 0.00011398049233627497, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2784/6464 [50:31<1:03:20, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9365, 'grad_norm': 0.8433777093887329, 'learning_rate': 0.00011394952779067967, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2785/6464 [50:32<1:00:16, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9449, 'grad_norm': 0.6491193771362305, 'learning_rate': 0.00011391856324508439, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2786/6464 [50:33<1:06:05, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2165, 'grad_norm': 0.6020338535308838, 'learning_rate': 0.00011388759869948909, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2787/6464 [50:35<1:11:47, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6081, 'grad_norm': 0.7381142973899841, 'learning_rate': 0.0001138566341538938, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2788/6464 [50:36<1:07:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0667, 'grad_norm': 0.7623633742332458, 'learning_rate': 0.0001138256696082985, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2789/6464 [50:37<1:09:14, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3048, 'grad_norm': 0.7721642255783081, 'learning_rate': 0.0001137947050627032, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2790/6464 [50:38<1:08:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0731, 'grad_norm': 0.7269643545150757, 'learning_rate': 0.00011376374051710792, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2791/6464 [50:39<1:05:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1913, 'grad_norm': 0.8139744400978088, 'learning_rate': 0.00011373277597151262, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2792/6464 [50:40<1:04:26, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1214, 'grad_norm': 0.8392419815063477, 'learning_rate': 0.00011370181142591733, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2793/6464 [50:41<1:06:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3519, 'grad_norm': 0.7019805312156677, 'learning_rate': 0.00011367084688032203, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2794/6464 [50:43<1:12:11, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2146, 'grad_norm': 0.7220399975776672, 'learning_rate': 0.00011363988233472673, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2795/6464 [50:44<1:16:03, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2691, 'grad_norm': 0.7183182835578918, 'learning_rate': 0.00011360891778913145, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2796/6464 [50:45<1:14:00, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0978, 'grad_norm': 0.6802627444267273, 'learning_rate': 0.00011357795324353615, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2797/6464 [50:46<1:10:38, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.078, 'grad_norm': 0.7234883904457092, 'learning_rate': 0.00011354698869794087, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2798/6464 [50:48<1:14:44, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2862, 'grad_norm': 0.6270878911018372, 'learning_rate': 0.00011351602415234557, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2799/6464 [50:49<1:13:06, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2663, 'grad_norm': 0.8161284327507019, 'learning_rate': 0.00011348505960675027, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2800/6464 [50:50<1:11:53, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2885, 'grad_norm': 0.805520236492157, 'learning_rate': 0.00011345409506115498, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2801/6464 [50:51<1:10:34, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1078, 'grad_norm': 0.7088527083396912, 'learning_rate': 0.00011342313051555968, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2802/6464 [50:52<1:09:29, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3427, 'grad_norm': 0.6706857085227966, 'learning_rate': 0.0001133921659699644, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2803/6464 [50:53<1:09:30, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2253, 'grad_norm': 0.7990124225616455, 'learning_rate': 0.0001133612014243691, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2804/6464 [50:54<1:07:49, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0687, 'grad_norm': 0.6219303607940674, 'learning_rate': 0.0001133302368787738, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2805/6464 [50:55<1:04:04, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1028, 'grad_norm': 0.730370819568634, 'learning_rate': 0.00011329927233317852, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2806/6464 [50:57<1:13:00, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2881, 'grad_norm': 0.5566056966781616, 'learning_rate': 0.00011326830778758322, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2807/6464 [50:58<1:12:41, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.356, 'grad_norm': 0.7472048997879028, 'learning_rate': 0.00011323734324198793, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2808/6464 [50:59<1:10:21, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0525, 'grad_norm': 0.5952221155166626, 'learning_rate': 0.00011320637869639263, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2809/6464 [51:00<1:08:40, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0817, 'grad_norm': 0.676954448223114, 'learning_rate': 0.00011317541415079733, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2810/6464 [51:01<1:06:58, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0983, 'grad_norm': 0.6575177311897278, 'learning_rate': 0.00011314444960520205, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 43%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2811/6464 [51:02<1:10:39, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0764, 'grad_norm': 0.5870576500892639, 'learning_rate': 0.00011311348505960675, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2812/6464 [51:03<1:06:21, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2004, 'grad_norm': 0.8315773010253906, 'learning_rate': 0.00011308252051401148, 'epoch': 0.43}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2813/6464 [51:04<1:08:11, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1193, 'grad_norm': 0.711269736289978, 'learning_rate': 0.00011305155596841616, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2814/6464 [51:06<1:11:07, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9135, 'grad_norm': 0.5744746923446655, 'learning_rate': 0.00011302059142282086, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2815/6464 [51:07<1:09:53, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1546, 'grad_norm': 0.6518046855926514, 'learning_rate': 0.00011298962687722558, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2816/6464 [51:08<1:12:15, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2943, 'grad_norm': 0.6568603515625, 'learning_rate': 0.00011295866233163028, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2817/6464 [51:09<1:10:03, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2926, 'grad_norm': 0.7658153772354126, 'learning_rate': 0.000112927697786035, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2818/6464 [51:10<1:07:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1546, 'grad_norm': 0.7824543714523315, 'learning_rate': 0.0001128967332404397, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2819/6464 [51:11<1:08:00, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1439, 'grad_norm': 0.6721497774124146, 'learning_rate': 0.0001128657686948444, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2820/6464 [51:12<1:07:27, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4124, 'grad_norm': 0.7328175902366638, 'learning_rate': 0.00011283480414924911, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2821/6464 [51:13<1:04:32, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0568, 'grad_norm': 0.6372442245483398, 'learning_rate': 0.00011280383960365381, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2822/6464 [51:15<1:08:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3355, 'grad_norm': 0.6193578243255615, 'learning_rate': 0.00011277287505805854, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2823/6464 [51:16<1:07:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1445, 'grad_norm': 0.6028206944465637, 'learning_rate': 0.00011274191051246323, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2824/6464 [51:17<1:04:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2543, 'grad_norm': 0.820412278175354, 'learning_rate': 0.00011271094596686793, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2825/6464 [51:18<1:03:42, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1047, 'grad_norm': 0.8106845021247864, 'learning_rate': 0.00011267998142127266, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2826/6464 [51:19<1:04:43, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2423, 'grad_norm': 0.7548901438713074, 'learning_rate': 0.00011264901687567735, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 2827/6464 [51:20<1:05:36, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0395, 'grad_norm': 0.7123066782951355, 'learning_rate': 0.00011261805233008207, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2828/6464 [51:21<1:11:21, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2979, 'grad_norm': 0.6489784121513367, 'learning_rate': 0.00011258708778448676, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2829/6464 [51:22<1:11:50, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3116, 'grad_norm': 0.611358642578125, 'learning_rate': 0.00011255612323889146, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2830/6464 [51:24<1:09:29, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9516, 'grad_norm': 0.6269630193710327, 'learning_rate': 0.00011252515869329619, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2831/6464 [51:24<1:05:42, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1189, 'grad_norm': 0.7188992500305176, 'learning_rate': 0.00011249419414770088, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2832/6464 [51:26<1:09:09, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1215, 'grad_norm': 0.6581507325172424, 'learning_rate': 0.00011246322960210561, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2833/6464 [51:27<1:10:41, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0345, 'grad_norm': 0.697627604007721, 'learning_rate': 0.0001124322650565103, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2834/6464 [51:28<1:09:36, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2481, 'grad_norm': 0.72718745470047, 'learning_rate': 0.000112401300510915, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2835/6464 [51:29<1:06:59, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.471, 'grad_norm': 0.8099291324615479, 'learning_rate': 0.00011237033596531972, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2836/6464 [51:30<1:08:13, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1311, 'grad_norm': 0.633816659450531, 'learning_rate': 0.00011233937141972441, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2837/6464 [51:32<1:12:00, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3627, 'grad_norm': 0.717974841594696, 'learning_rate': 0.00011230840687412914, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2838/6464 [51:32<1:06:15, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9391, 'grad_norm': 0.7299023866653442, 'learning_rate': 0.00011227744232853384, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2839/6464 [51:33<1:03:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1694, 'grad_norm': 0.7653571963310242, 'learning_rate': 0.00011224647778293853, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2840/6464 [51:35<1:05:00, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.295, 'grad_norm': 0.7246621251106262, 'learning_rate': 0.00011221551323734325, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2841/6464 [51:36<1:08:05, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3456, 'grad_norm': 0.7198783755302429, 'learning_rate': 0.00011218454869174794, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2842/6464 [51:37<1:07:34, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1448, 'grad_norm': 0.7174075245857239, 'learning_rate': 0.00011215358414615267, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2843/6464 [51:38<1:10:59, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2263, 'grad_norm': 0.647565484046936, 'learning_rate': 0.00011212261960055737, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2844/6464 [51:39<1:07:29, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3194, 'grad_norm': 0.7673988342285156, 'learning_rate': 0.00011209165505496206, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2845/6464 [51:40<1:04:57, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0984, 'grad_norm': 0.7380334138870239, 'learning_rate': 0.00011206069050936679, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2846/6464 [51:41<1:06:30, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.15, 'grad_norm': 0.7196669578552246, 'learning_rate': 0.00011202972596377149, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2847/6464 [51:42<1:06:35, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1543, 'grad_norm': 0.679435133934021, 'learning_rate': 0.0001119987614181762, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2848/6464 [51:44<1:09:44, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1694, 'grad_norm': 0.7061062455177307, 'learning_rate': 0.0001119677968725809, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2849/6464 [51:45<1:08:22, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2535, 'grad_norm': 0.7546047568321228, 'learning_rate': 0.00011193683232698559, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2850/6464 [51:46<1:05:07, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8881, 'grad_norm': 0.632700502872467, 'learning_rate': 0.00011190586778139032, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2851/6464 [51:47<1:01:07, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0051, 'grad_norm': 0.7013962864875793, 'learning_rate': 0.00011187490323579502, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2852/6464 [51:48<1:02:36, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1977, 'grad_norm': 0.6700460314750671, 'learning_rate': 0.00011184393869019974, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2853/6464 [51:49<1:14:02, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1528, 'grad_norm': 0.5622177720069885, 'learning_rate': 0.00011181297414460444, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2854/6464 [51:50<1:09:34, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2403, 'grad_norm': 0.8276708722114563, 'learning_rate': 0.00011178200959900914, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2855/6464 [51:51<1:06:22, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2171, 'grad_norm': 0.7061797380447388, 'learning_rate': 0.00011175104505341385, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2856/6464 [51:53<1:08:01, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4734, 'grad_norm': 0.6514792442321777, 'learning_rate': 0.00011172008050781855, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2857/6464 [51:54<1:07:49, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0727, 'grad_norm': 0.6401134133338928, 'learning_rate': 0.00011168911596222327, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2858/6464 [51:55<1:06:48, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0163, 'grad_norm': 0.5756939053535461, 'learning_rate': 0.00011165815141662797, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2859/6464 [51:56<1:06:04, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0766, 'grad_norm': 0.7270724773406982, 'learning_rate': 0.00011162718687103267, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2860/6464 [51:57<1:04:34, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1387, 'grad_norm': 0.772668719291687, 'learning_rate': 0.00011159622232543738, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2861/6464 [51:58<1:05:45, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.171, 'grad_norm': 0.6652492880821228, 'learning_rate': 0.00011156525777984208, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2862/6464 [51:59<1:04:57, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.081, 'grad_norm': 0.780714750289917, 'learning_rate': 0.0001115342932342468, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2863/6464 [52:00<1:01:43, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0222, 'grad_norm': 0.7681754231452942, 'learning_rate': 0.0001115033286886515, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2864/6464 [52:01<1:02:37, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2025, 'grad_norm': 0.7836753726005554, 'learning_rate': 0.0001114723641430562, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2865/6464 [52:02<59:55, 1.00it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9901, 'grad_norm': 0.701241135597229, 'learning_rate': 0.00011144139959746092, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2866/6464 [52:03<1:00:13, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0842, 'grad_norm': 0.7567635774612427, 'learning_rate': 0.00011141043505186562, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2867/6464 [52:04<59:24, 1.01it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2754, 'grad_norm': 0.750932514667511, 'learning_rate': 0.00011137947050627033, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2868/6464 [52:05<1:04:29, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.236, 'grad_norm': 0.7337141036987305, 'learning_rate': 0.00011134850596067503, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2869/6464 [52:06<1:04:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0739, 'grad_norm': 0.6943407654762268, 'learning_rate': 0.00011131754141507973, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2870/6464 [52:07<1:06:44, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2019, 'grad_norm': 0.6369333863258362, 'learning_rate': 0.00011128657686948445, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2871/6464 [52:09<1:07:14, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0479, 'grad_norm': 0.6949489116668701, 'learning_rate': 0.00011125561232388915, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2872/6464 [52:10<1:05:19, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1576, 'grad_norm': 0.6870949864387512, 'learning_rate': 0.00011122464777829387, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2873/6464 [52:11<1:07:02, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1274, 'grad_norm': 0.6824086904525757, 'learning_rate': 0.00011119368323269857, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2874/6464 [52:12<1:04:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.995, 'grad_norm': 0.634147047996521, 'learning_rate': 0.00011116271868710327, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2875/6464 [52:13<1:03:04, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1569, 'grad_norm': 0.8255179524421692, 'learning_rate': 0.00011113175414150798, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 44%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2876/6464 [52:14<1:00:49, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0663, 'grad_norm': 0.728916347026825, 'learning_rate': 0.00011110078959591268, 'epoch': 0.44}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2877/6464 [52:15<1:02:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2629, 'grad_norm': 0.6731415390968323, 'learning_rate': 0.0001110698250503174, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2878/6464 [52:16<1:07:45, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3149, 'grad_norm': 0.6062966585159302, 'learning_rate': 0.0001110388605047221, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2879/6464 [52:17<1:03:08, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1678, 'grad_norm': 0.8166847825050354, 'learning_rate': 0.0001110078959591268, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2880/6464 [52:18<1:00:50, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8964, 'grad_norm': 0.7661846876144409, 'learning_rate': 0.00011097693141353151, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2881/6464 [52:19<58:49, 1.02it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0986, 'grad_norm': 0.8779597878456116, 'learning_rate': 0.00011094596686793621, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2882/6464 [52:20<1:01:01, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0618, 'grad_norm': 0.6595751047134399, 'learning_rate': 0.00011091500232234093, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2883/6464 [52:21<1:04:00, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3695, 'grad_norm': 0.7598504424095154, 'learning_rate': 0.00011088403777674563, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2884/6464 [52:22<1:05:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0773, 'grad_norm': 0.667677640914917, 'learning_rate': 0.00011085307323115033, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2885/6464 [52:23<1:02:41, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0458, 'grad_norm': 0.7411330342292786, 'learning_rate': 0.00011082210868555505, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2886/6464 [52:24<58:52, 1.01it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0277, 'grad_norm': 0.764723002910614, 'learning_rate': 0.00011079114413995975, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2887/6464 [52:25<59:02, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.965, 'grad_norm': 0.6145423054695129, 'learning_rate': 0.00011076017959436446, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2888/6464 [52:26<58:26, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0386, 'grad_norm': 0.6429906487464905, 'learning_rate': 0.00011072921504876916, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2889/6464 [52:27<57:47, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.047, 'grad_norm': 0.6778784394264221, 'learning_rate': 0.00011069825050317386, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2890/6464 [52:28<1:01:15, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1768, 'grad_norm': 0.6599152088165283, 'learning_rate': 0.00011066728595757858, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2891/6464 [52:29<1:00:23, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2549, 'grad_norm': 0.7283034324645996, 'learning_rate': 0.00011063632141198328, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2892/6464 [52:30<1:03:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2738, 'grad_norm': 0.7224602103233337, 'learning_rate': 0.000110605356866388, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2893/6464 [52:31<1:04:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0086, 'grad_norm': 0.6783294677734375, 'learning_rate': 0.0001105743923207927, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2894/6464 [52:32<1:01:59, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.23, 'grad_norm': 0.7282753586769104, 'learning_rate': 0.0001105434277751974, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2895/6464 [52:33<1:03:16, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2019, 'grad_norm': 0.6585873961448669, 'learning_rate': 0.00011051246322960211, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2896/6464 [52:35<1:03:11, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2083, 'grad_norm': 0.6839904189109802, 'learning_rate': 0.00011048149868400681, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2897/6464 [52:36<1:04:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1001, 'grad_norm': 0.7040125131607056, 'learning_rate': 0.00011045053413841154, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2898/6464 [52:37<1:08:03, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.323, 'grad_norm': 0.667667031288147, 'learning_rate': 0.00011041956959281623, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2899/6464 [52:38<1:03:12, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0499, 'grad_norm': 0.7566601037979126, 'learning_rate': 0.00011038860504722093, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2900/6464 [52:39<1:03:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.269, 'grad_norm': 0.6423148512840271, 'learning_rate': 0.00011035764050162564, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2901/6464 [52:40<1:06:02, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0396, 'grad_norm': 0.625041127204895, 'learning_rate': 0.00011032667595603034, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2902/6464 [52:41<1:08:06, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2699, 'grad_norm': 0.6362231373786926, 'learning_rate': 0.00011029571141043506, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2903/6464 [52:42<1:06:01, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2131, 'grad_norm': 0.8224936127662659, 'learning_rate': 0.00011026474686483976, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2904/6464 [52:44<1:05:44, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1261, 'grad_norm': 0.6915609240531921, 'learning_rate': 0.00011023378231924446, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2905/6464 [52:45<1:04:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1221, 'grad_norm': 0.6995943188667297, 'learning_rate': 0.00011020281777364919, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2906/6464 [52:46<1:09:05, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.403, 'grad_norm': 0.6387947201728821, 'learning_rate': 0.00011017185322805388, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2907/6464 [52:47<1:05:43, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8481, 'grad_norm': 0.5784368515014648, 'learning_rate': 0.0001101408886824586, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ– | 2908/6464 [52:48<1:04:13, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3146, 'grad_norm': 0.7558552622795105, 'learning_rate': 0.00011010992413686329, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2909/6464 [52:49<1:00:51, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8565, 'grad_norm': 0.7236222624778748, 'learning_rate': 0.00011007895959126799, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2910/6464 [52:50<1:05:34, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1999, 'grad_norm': 0.6511560082435608, 'learning_rate': 0.00011004799504567271, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2911/6464 [52:51<1:05:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1053, 'grad_norm': 0.6652819514274597, 'learning_rate': 0.00011001703050007741, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2912/6464 [52:52<1:07:00, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5137, 'grad_norm': 0.7904580235481262, 'learning_rate': 0.00010998606595448214, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2913/6464 [52:53<1:05:35, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1127, 'grad_norm': 0.7271618247032166, 'learning_rate': 0.00010995510140888684, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2914/6464 [52:55<1:08:32, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1025, 'grad_norm': 0.5945816040039062, 'learning_rate': 0.00010992413686329153, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2915/6464 [52:56<1:07:00, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1592, 'grad_norm': 0.745868444442749, 'learning_rate': 0.00010989317231769624, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2916/6464 [52:57<1:07:49, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3735, 'grad_norm': 0.7423742413520813, 'learning_rate': 0.00010986220777210094, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2917/6464 [52:58<1:05:08, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9702, 'grad_norm': 0.7548853158950806, 'learning_rate': 0.00010983124322650567, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2918/6464 [52:59<1:02:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0499, 'grad_norm': 0.7626228332519531, 'learning_rate': 0.00010980027868091037, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2919/6464 [53:00<1:02:14, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1984, 'grad_norm': 0.6189166903495789, 'learning_rate': 0.00010976931413531506, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2920/6464 [53:01<1:03:28, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2535, 'grad_norm': 0.6491724848747253, 'learning_rate': 0.00010973834958971977, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2921/6464 [53:02<1:06:55, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2895, 'grad_norm': 0.6738871335983276, 'learning_rate': 0.00010970738504412447, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2922/6464 [53:03<1:04:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0246, 'grad_norm': 0.6773674488067627, 'learning_rate': 0.0001096764204985292, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2923/6464 [53:04<1:02:29, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3615, 'grad_norm': 0.7006921172142029, 'learning_rate': 0.0001096454559529339, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2924/6464 [53:06<1:05:23, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1971, 'grad_norm': 0.7184717059135437, 'learning_rate': 0.00010961449140733859, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2925/6464 [53:07<1:06:27, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2303, 'grad_norm': 0.7834857106208801, 'learning_rate': 0.00010958352686174332, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2926/6464 [53:08<1:04:06, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9864, 'grad_norm': 0.758283257484436, 'learning_rate': 0.00010955256231614802, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2927/6464 [53:09<1:06:06, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.965, 'grad_norm': 0.634928822517395, 'learning_rate': 0.00010952159777055273, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2928/6464 [53:10<1:04:06, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2067, 'grad_norm': 0.7457855343818665, 'learning_rate': 0.00010949063322495742, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2929/6464 [53:11<1:05:42, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1004, 'grad_norm': 0.6426076292991638, 'learning_rate': 0.00010945966867936212, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2930/6464 [53:12<1:06:30, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2824, 'grad_norm': 0.6373444199562073, 'learning_rate': 0.00010942870413376685, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2931/6464 [53:13<1:03:08, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0649, 'grad_norm': 0.7782756090164185, 'learning_rate': 0.00010939773958817154, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2932/6464 [53:14<1:02:12, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.881, 'grad_norm': 0.7413214445114136, 'learning_rate': 0.00010936677504257627, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2933/6464 [53:15<1:01:56, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2534, 'grad_norm': 0.7549250721931458, 'learning_rate': 0.00010933581049698097, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2934/6464 [53:16<59:17, 1.01s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1914, 'grad_norm': 0.7712244987487793, 'learning_rate': 0.00010930484595138567, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2935/6464 [53:17<1:01:46, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0893, 'grad_norm': 0.609207034111023, 'learning_rate': 0.00010927388140579038, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2936/6464 [53:18<1:02:20, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2892, 'grad_norm': 0.8307590484619141, 'learning_rate': 0.00010924291686019507, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2937/6464 [53:19<1:01:31, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2343, 'grad_norm': 0.736389696598053, 'learning_rate': 0.0001092119523145998, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2938/6464 [53:21<1:05:49, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1278, 'grad_norm': 0.6517897844314575, 'learning_rate': 0.0001091809877690045, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2939/6464 [53:22<1:08:42, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1378, 'grad_norm': 0.6203503608703613, 'learning_rate': 0.0001091500232234092, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2940/6464 [53:23<1:11:16, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2638, 'grad_norm': 0.6636664867401123, 'learning_rate': 0.0001091190586778139, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 45%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2941/6464 [53:24<1:05:36, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2049, 'grad_norm': 0.8278586864471436, 'learning_rate': 0.0001090880941322186, 'epoch': 0.45}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2942/6464 [53:25<1:04:34, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2948, 'grad_norm': 0.796341598033905, 'learning_rate': 0.00010905712958662333, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2943/6464 [53:26<1:05:14, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2301, 'grad_norm': 0.7047569751739502, 'learning_rate': 0.00010902616504102803, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2944/6464 [53:27<1:03:16, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9946, 'grad_norm': 0.6261560916900635, 'learning_rate': 0.00010899520049543272, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2945/6464 [53:28<1:02:14, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1727, 'grad_norm': 0.8497886657714844, 'learning_rate': 0.00010896423594983745, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2946/6464 [53:30<1:02:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.083, 'grad_norm': 0.70500248670578, 'learning_rate': 0.00010893327140424215, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2947/6464 [53:30<1:00:04, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9749, 'grad_norm': 0.6707228422164917, 'learning_rate': 0.00010890230685864686, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2948/6464 [53:31<58:33, 1.00it/s] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0335, 'grad_norm': 0.7873659133911133, 'learning_rate': 0.00010887134231305156, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2949/6464 [53:32<56:08, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8112, 'grad_norm': 0.7157995700836182, 'learning_rate': 0.00010884037776745625, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2950/6464 [53:33<58:48, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1572, 'grad_norm': 0.8521998524665833, 'learning_rate': 0.00010880941322186098, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2951/6464 [53:34<1:00:32, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3758, 'grad_norm': 0.7587549090385437, 'learning_rate': 0.00010877844867626568, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2952/6464 [53:35<59:02, 1.01s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1268, 'grad_norm': 0.7837046384811401, 'learning_rate': 0.0001087474841306704, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2953/6464 [53:36<59:30, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.211, 'grad_norm': 0.7147911190986633, 'learning_rate': 0.0001087165195850751, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2954/6464 [53:37<59:48, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1002, 'grad_norm': 0.9197097420692444, 'learning_rate': 0.0001086855550394798, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2955/6464 [53:39<1:01:38, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1838, 'grad_norm': 0.7133628129959106, 'learning_rate': 0.00010865459049388451, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2956/6464 [53:40<1:06:37, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.328, 'grad_norm': 0.7148367166519165, 'learning_rate': 0.00010862362594828921, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2957/6464 [53:41<1:07:45, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1161, 'grad_norm': 0.6262744069099426, 'learning_rate': 0.00010859266140269393, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2958/6464 [53:42<1:04:33, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0607, 'grad_norm': 0.6675117015838623, 'learning_rate': 0.00010856169685709863, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2959/6464 [53:43<1:05:12, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3205, 'grad_norm': 0.697573184967041, 'learning_rate': 0.00010853073231150333, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2960/6464 [53:44<1:03:05, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2362, 'grad_norm': 0.7101510167121887, 'learning_rate': 0.00010849976776590804, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2961/6464 [53:45<1:01:56, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0552, 'grad_norm': 0.7415866851806641, 'learning_rate': 0.00010846880322031274, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2962/6464 [53:46<1:00:45, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9533, 'grad_norm': 0.6632810831069946, 'learning_rate': 0.00010843783867471746, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2963/6464 [53:47<1:02:15, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2089, 'grad_norm': 0.7250994443893433, 'learning_rate': 0.00010840687412912216, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2964/6464 [53:48<1:01:42, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2296, 'grad_norm': 0.732718825340271, 'learning_rate': 0.00010837590958352686, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2965/6464 [53:50<1:02:31, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0166, 'grad_norm': 0.6505792737007141, 'learning_rate': 0.00010834494503793158, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2966/6464 [53:51<1:00:46, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9639, 'grad_norm': 0.751316249370575, 'learning_rate': 0.00010831398049233628, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2967/6464 [53:52<1:01:14, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1368, 'grad_norm': 0.7372193336486816, 'learning_rate': 0.00010828301594674099, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2968/6464 [53:53<1:02:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1058, 'grad_norm': 0.6007342338562012, 'learning_rate': 0.00010825205140114569, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2969/6464 [53:54<1:02:16, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1966, 'grad_norm': 0.7222622632980347, 'learning_rate': 0.00010822108685555039, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2970/6464 [53:55<1:04:25, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2677, 'grad_norm': 0.7019522786140442, 'learning_rate': 0.00010819012230995511, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2971/6464 [53:56<1:02:35, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9809, 'grad_norm': 0.6500222086906433, 'learning_rate': 0.00010815915776435981, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2972/6464 [53:57<1:07:50, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2766, 'grad_norm': 0.6235829591751099, 'learning_rate': 0.00010812819321876453, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2973/6464 [53:59<1:07:51, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2308, 'grad_norm': 0.7276217937469482, 'learning_rate': 0.00010809722867316923, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2974/6464 [53:59<1:02:06, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9604, 'grad_norm': 0.7433414459228516, 'learning_rate': 0.00010806626412757393, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2975/6464 [54:00<1:03:09, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.132, 'grad_norm': 0.6208564043045044, 'learning_rate': 0.00010803529958197864, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2976/6464 [54:02<1:02:06, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0476, 'grad_norm': 0.6576781868934631, 'learning_rate': 0.00010800433503638334, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2977/6464 [54:03<1:02:10, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.29, 'grad_norm': 0.8020223379135132, 'learning_rate': 0.00010797337049078806, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2978/6464 [54:03<58:10, 1.00s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1149, 'grad_norm': 0.8118592500686646, 'learning_rate': 0.00010794240594519276, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2979/6464 [54:05<1:03:59, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1117, 'grad_norm': 0.6508319973945618, 'learning_rate': 0.00010791144139959746, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2980/6464 [54:06<1:05:03, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0224, 'grad_norm': 0.6686949133872986, 'learning_rate': 0.00010788047685400217, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2981/6464 [54:07<1:02:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1962, 'grad_norm': 0.7353872060775757, 'learning_rate': 0.00010784951230840687, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2982/6464 [54:08<1:01:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2195, 'grad_norm': 0.6906210780143738, 'learning_rate': 0.0001078185477628116, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2983/6464 [54:09<1:03:21, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0918, 'grad_norm': 0.6384386420249939, 'learning_rate': 0.00010778758321721629, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2984/6464 [54:10<1:00:13, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9409, 'grad_norm': 0.725138247013092, 'learning_rate': 0.00010775661867162099, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2985/6464 [54:11<1:03:06, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2349, 'grad_norm': 0.6756757497787476, 'learning_rate': 0.00010772565412602571, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2986/6464 [54:12<1:03:08, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0516, 'grad_norm': 0.6476103067398071, 'learning_rate': 0.00010769468958043041, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2987/6464 [54:13<1:04:42, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1992, 'grad_norm': 0.7781886458396912, 'learning_rate': 0.00010766372503483512, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2988/6464 [54:15<1:03:25, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1918, 'grad_norm': 0.7320919632911682, 'learning_rate': 0.00010763276048923982, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 2989/6464 [54:16<1:02:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0429, 'grad_norm': 0.6964579820632935, 'learning_rate': 0.00010760179594364452, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2990/6464 [54:17<1:00:05, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2142, 'grad_norm': 0.7355708479881287, 'learning_rate': 0.00010757083139804924, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2991/6464 [54:18<59:59, 1.04s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0115, 'grad_norm': 0.7350790500640869, 'learning_rate': 0.00010753986685245394, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2992/6464 [54:19<1:01:02, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1291, 'grad_norm': 0.645421028137207, 'learning_rate': 0.00010750890230685867, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2993/6464 [54:20<1:00:25, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0424, 'grad_norm': 0.7235060930252075, 'learning_rate': 0.00010747793776126336, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2994/6464 [54:21<1:04:25, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1881, 'grad_norm': 0.6427689790725708, 'learning_rate': 0.00010744697321566806, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2995/6464 [54:22<1:09:49, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4489, 'grad_norm': 0.6510689854621887, 'learning_rate': 0.00010741600867007277, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2996/6464 [54:23<1:05:24, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9754, 'grad_norm': 0.6747689843177795, 'learning_rate': 0.00010738504412447747, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2997/6464 [54:24<1:03:25, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.094, 'grad_norm': 0.7230244278907776, 'learning_rate': 0.0001073540795788822, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2998/6464 [54:25<1:01:53, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.179, 'grad_norm': 0.6692145466804504, 'learning_rate': 0.0001073231150332869, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 2999/6464 [54:27<1:05:41, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1504, 'grad_norm': 0.6145389080047607, 'learning_rate': 0.00010729215048769159, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3000/6464 [54:28<1:02:06, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9689, 'grad_norm': 0.6598514318466187, 'learning_rate': 0.0001072611859420963, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3001/6464 [54:30<1:18:51, 1.37s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3303, 'grad_norm': 0.6324620246887207, 'learning_rate': 0.000107230221396501, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3002/6464 [54:31<1:19:51, 1.38s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3474, 'grad_norm': 0.703727126121521, 'learning_rate': 0.00010719925685090573, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3003/6464 [54:32<1:17:09, 1.34s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3632, 'grad_norm': 0.677924633026123, 'learning_rate': 0.00010716829230531042, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3004/6464 [54:33<1:09:55, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1266, 'grad_norm': 0.7589470744132996, 'learning_rate': 0.00010713732775971512, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 46%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3005/6464 [54:34<1:06:52, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1247, 'grad_norm': 0.7130073308944702, 'learning_rate': 0.00010710636321411985, 'epoch': 0.46}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3006/6464 [54:35<1:02:47, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0233, 'grad_norm': 0.7456527352333069, 'learning_rate': 0.00010707539866852454, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3007/6464 [54:36<1:04:11, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1455, 'grad_norm': 0.6633897423744202, 'learning_rate': 0.00010704443412292926, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3008/6464 [54:38<1:06:57, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.426, 'grad_norm': 0.6939592361450195, 'learning_rate': 0.00010701346957733395, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3009/6464 [54:39<1:05:12, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1093, 'grad_norm': 0.7649304270744324, 'learning_rate': 0.00010698250503173865, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3010/6464 [54:40<1:05:48, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1335, 'grad_norm': 0.7105231285095215, 'learning_rate': 0.00010695154048614338, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3011/6464 [54:41<1:05:09, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2606, 'grad_norm': 0.7470405697822571, 'learning_rate': 0.00010692057594054807, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3012/6464 [54:42<1:02:49, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9375, 'grad_norm': 0.6665686964988708, 'learning_rate': 0.0001068896113949528, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3013/6464 [54:43<59:41, 1.04s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0658, 'grad_norm': 0.8153141736984253, 'learning_rate': 0.0001068586468493575, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3014/6464 [54:44<57:45, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0254, 'grad_norm': 0.755725622177124, 'learning_rate': 0.0001068276823037622, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3015/6464 [54:45<58:39, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3054, 'grad_norm': 0.7569345831871033, 'learning_rate': 0.0001067967177581669, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3016/6464 [54:46<59:29, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.231, 'grad_norm': 0.7679520845413208, 'learning_rate': 0.0001067657532125716, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3017/6464 [54:47<59:46, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0437, 'grad_norm': 0.6731957793235779, 'learning_rate': 0.00010673478866697633, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3018/6464 [54:48<59:24, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2181, 'grad_norm': 0.7922259569168091, 'learning_rate': 0.00010670382412138103, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3019/6464 [54:49<1:05:25, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2174, 'grad_norm': 0.6588689088821411, 'learning_rate': 0.00010667285957578572, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3020/6464 [54:50<1:03:21, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.367, 'grad_norm': 0.742853581905365, 'learning_rate': 0.00010664189503019044, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3021/6464 [54:51<1:03:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.913, 'grad_norm': 0.6084428429603577, 'learning_rate': 0.00010661093048459513, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3022/6464 [54:53<1:03:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2095, 'grad_norm': 0.6051580309867859, 'learning_rate': 0.00010657996593899986, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3023/6464 [54:54<1:05:24, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1744, 'grad_norm': 0.6347887516021729, 'learning_rate': 0.00010654900139340456, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3024/6464 [54:55<1:05:47, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4095, 'grad_norm': 0.6941251754760742, 'learning_rate': 0.00010651803684780925, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3025/6464 [54:56<1:02:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1995, 'grad_norm': 0.7469573616981506, 'learning_rate': 0.00010648707230221398, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3026/6464 [54:57<1:00:18, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9156, 'grad_norm': 0.7239513993263245, 'learning_rate': 0.00010645610775661868, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3027/6464 [54:58<57:48, 1.01s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0093, 'grad_norm': 0.7451785206794739, 'learning_rate': 0.00010642514321102339, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3028/6464 [54:59<59:31, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1917, 'grad_norm': 0.7573050260543823, 'learning_rate': 0.00010639417866542809, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3029/6464 [55:00<58:38, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1467, 'grad_norm': 0.70269376039505, 'learning_rate': 0.00010636321411983278, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3030/6464 [55:01<56:23, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0543, 'grad_norm': 0.852456271648407, 'learning_rate': 0.00010633224957423751, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3031/6464 [55:02<55:04, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.949, 'grad_norm': 0.6096720695495605, 'learning_rate': 0.0001063012850286422, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3032/6464 [55:03<56:12, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1898, 'grad_norm': 0.733015775680542, 'learning_rate': 0.00010627032048304693, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3033/6464 [55:04<56:06, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1891, 'grad_norm': 0.8276207447052002, 'learning_rate': 0.00010623935593745163, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3034/6464 [55:05<53:21, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.963, 'grad_norm': 0.7196498513221741, 'learning_rate': 0.00010620839139185633, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3035/6464 [55:05<52:30, 1.09it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1766, 'grad_norm': 0.7472442388534546, 'learning_rate': 0.00010617742684626104, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3036/6464 [55:06<52:05, 1.10it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7615, 'grad_norm': 0.6336766481399536, 'learning_rate': 0.00010614646230066574, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3037/6464 [55:07<52:41, 1.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1418, 'grad_norm': 0.7261345982551575, 'learning_rate': 0.00010611549775507046, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3038/6464 [55:09<58:36, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3926, 'grad_norm': 0.8321394920349121, 'learning_rate': 0.00010608453320947516, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3039/6464 [55:10<58:38, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2971, 'grad_norm': 0.8020764589309692, 'learning_rate': 0.00010605356866387986, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3040/6464 [55:11<1:00:03, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1408, 'grad_norm': 0.6668566465377808, 'learning_rate': 0.00010602260411828457, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3041/6464 [55:12<1:01:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.018, 'grad_norm': 0.6346712708473206, 'learning_rate': 0.00010599163957268927, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3042/6464 [55:13<58:58, 1.03s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0649, 'grad_norm': 0.7828634977340698, 'learning_rate': 0.00010596067502709399, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3043/6464 [55:14<57:15, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9828, 'grad_norm': 0.7825695872306824, 'learning_rate': 0.00010592971048149869, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3044/6464 [55:15<57:24, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0764, 'grad_norm': 0.6510230302810669, 'learning_rate': 0.00010589874593590339, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3045/6464 [55:16<58:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3096, 'grad_norm': 0.6784271597862244, 'learning_rate': 0.00010586778139030811, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3046/6464 [55:17<1:01:11, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3115, 'grad_norm': 0.635893702507019, 'learning_rate': 0.00010583681684471281, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3047/6464 [55:18<1:00:43, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1797, 'grad_norm': 0.6855732798576355, 'learning_rate': 0.00010580585229911752, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3048/6464 [55:19<59:09, 1.04s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2804, 'grad_norm': 0.9199787974357605, 'learning_rate': 0.00010577488775352222, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3049/6464 [55:20<1:00:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1635, 'grad_norm': 0.7000832557678223, 'learning_rate': 0.00010574392320792692, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3050/6464 [55:21<1:02:14, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0708, 'grad_norm': 0.6350958347320557, 'learning_rate': 0.00010571295866233164, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3051/6464 [55:22<1:02:42, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9333, 'grad_norm': 0.6678605675697327, 'learning_rate': 0.00010568199411673634, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3052/6464 [55:23<1:00:57, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9661, 'grad_norm': 0.6438960433006287, 'learning_rate': 0.00010565102957114106, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3053/6464 [55:24<59:37, 1.05s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0169, 'grad_norm': 0.6637356281280518, 'learning_rate': 0.00010562006502554576, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3054/6464 [55:25<59:19, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.107, 'grad_norm': 0.6315485835075378, 'learning_rate': 0.00010558910047995046, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3055/6464 [55:26<57:34, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1012, 'grad_norm': 0.786039412021637, 'learning_rate': 0.00010555813593435517, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3056/6464 [55:27<54:49, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1086, 'grad_norm': 0.7566514015197754, 'learning_rate': 0.00010552717138875987, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3057/6464 [55:28<58:12, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4814, 'grad_norm': 0.7245268225669861, 'learning_rate': 0.00010549620684316459, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3058/6464 [55:30<1:00:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3682, 'grad_norm': 0.7154173254966736, 'learning_rate': 0.00010546524229756929, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3059/6464 [55:31<1:01:03, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3409, 'grad_norm': 0.7444722652435303, 'learning_rate': 0.00010543427775197399, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3060/6464 [55:32<1:03:37, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2721, 'grad_norm': 0.6897439360618591, 'learning_rate': 0.0001054033132063787, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3061/6464 [55:33<1:04:35, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1691, 'grad_norm': 0.6195662617683411, 'learning_rate': 0.0001053723486607834, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3062/6464 [55:34<1:02:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1235, 'grad_norm': 0.7961133122444153, 'learning_rate': 0.00010534138411518812, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3063/6464 [55:35<1:02:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1739, 'grad_norm': 0.6705684661865234, 'learning_rate': 0.00010531041956959282, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3064/6464 [55:36<58:52, 1.04s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.931, 'grad_norm': 0.6927082538604736, 'learning_rate': 0.00010527945502399752, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3065/6464 [55:37<58:43, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0635, 'grad_norm': 0.6168277263641357, 'learning_rate': 0.00010524849047840224, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3066/6464 [55:38<59:01, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1322, 'grad_norm': 0.7155029773712158, 'learning_rate': 0.00010521752593280694, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3067/6464 [55:39<56:17, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0827, 'grad_norm': 0.73166823387146, 'learning_rate': 0.00010518656138721165, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3068/6464 [55:40<1:01:35, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2754, 'grad_norm': 0.6559041142463684, 'learning_rate': 0.00010515559684161635, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3069/6464 [55:41<1:01:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2859, 'grad_norm': 0.6985926032066345, 'learning_rate': 0.00010512463229602105, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 47%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3070/6464 [55:43<1:04:19, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1671, 'grad_norm': 0.6459254026412964, 'learning_rate': 0.00010509366775042577, 'epoch': 0.47}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3071/6464 [55:44<1:01:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0825, 'grad_norm': 0.7068207859992981, 'learning_rate': 0.00010506270320483047, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3072/6464 [55:45<1:00:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1737, 'grad_norm': 0.8459106087684631, 'learning_rate': 0.0001050317386592352, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3073/6464 [55:46<1:03:06, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1831, 'grad_norm': 0.7086950540542603, 'learning_rate': 0.0001050007741136399, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3074/6464 [55:47<1:02:35, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1955, 'grad_norm': 0.7814739942550659, 'learning_rate': 0.00010496980956804459, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3075/6464 [55:48<1:05:17, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2028, 'grad_norm': 0.6884282231330872, 'learning_rate': 0.0001049388450224493, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3076/6464 [55:49<1:02:33, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2419, 'grad_norm': 0.775531530380249, 'learning_rate': 0.000104907880476854, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3077/6464 [55:50<59:01, 1.05s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3467, 'grad_norm': 0.7696186304092407, 'learning_rate': 0.00010487691593125873, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3078/6464 [55:51<55:56, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1934, 'grad_norm': 0.8165212869644165, 'learning_rate': 0.00010484595138566342, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3079/6464 [55:52<57:10, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.055, 'grad_norm': 0.6742199063301086, 'learning_rate': 0.00010481498684006812, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3080/6464 [55:54<1:05:06, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2713, 'grad_norm': 0.6188685297966003, 'learning_rate': 0.00010478402229447283, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3081/6464 [55:55<1:03:02, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.129, 'grad_norm': 0.7407559752464294, 'learning_rate': 0.00010475305774887753, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3082/6464 [55:56<1:05:00, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4539, 'grad_norm': 0.6816537380218506, 'learning_rate': 0.00010472209320328225, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3083/6464 [55:57<1:03:36, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1807, 'grad_norm': 0.7180051803588867, 'learning_rate': 0.00010469112865768695, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3084/6464 [55:58<1:03:20, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.052, 'grad_norm': 0.7517749667167664, 'learning_rate': 0.00010466016411209165, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3085/6464 [55:59<1:03:31, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2609, 'grad_norm': 0.6932225823402405, 'learning_rate': 0.00010462919956649638, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3086/6464 [56:00<1:02:20, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1374, 'grad_norm': 0.7558743357658386, 'learning_rate': 0.00010459823502090107, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3087/6464 [56:01<1:04:09, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.007, 'grad_norm': 0.709803581237793, 'learning_rate': 0.00010456727047530578, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3088/6464 [56:02<1:02:19, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1086, 'grad_norm': 0.6641387939453125, 'learning_rate': 0.00010453630592971048, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3089/6464 [56:04<1:04:15, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2641, 'grad_norm': 0.6335834264755249, 'learning_rate': 0.00010450534138411518, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3090/6464 [56:05<1:03:54, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3222, 'grad_norm': 0.6223177313804626, 'learning_rate': 0.0001044743768385199, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3091/6464 [56:06<58:21, 1.04s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0193, 'grad_norm': 0.894860029220581, 'learning_rate': 0.0001044434122929246, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3092/6464 [56:07<58:07, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1137, 'grad_norm': 0.6918960809707642, 'learning_rate': 0.00010441244774732933, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3093/6464 [56:08<59:13, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0002, 'grad_norm': 0.5737457871437073, 'learning_rate': 0.00010438148320173403, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3094/6464 [56:09<1:01:48, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2405, 'grad_norm': 0.6774078607559204, 'learning_rate': 0.00010435051865613872, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3095/6464 [56:10<1:07:19, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9735, 'grad_norm': 0.6151197552680969, 'learning_rate': 0.00010431955411054343, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3096/6464 [56:11<1:02:31, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.038, 'grad_norm': 0.8281764388084412, 'learning_rate': 0.00010428858956494813, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3097/6464 [56:13<1:08:30, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4166, 'grad_norm': 0.7081498503684998, 'learning_rate': 0.00010425762501935286, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3098/6464 [56:14<1:08:16, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0859, 'grad_norm': 0.6765462160110474, 'learning_rate': 0.00010422666047375756, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3099/6464 [56:15<1:08:07, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2462, 'grad_norm': 0.6485470533370972, 'learning_rate': 0.00010419569592816225, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3100/6464 [56:16<1:06:41, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.123, 'grad_norm': 0.6704171895980835, 'learning_rate': 0.00010416473138256698, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3101/6464 [56:17<1:02:21, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3741, 'grad_norm': 0.8110705018043518, 'learning_rate': 0.00010413376683697168, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3102/6464 [56:18<1:03:00, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3037, 'grad_norm': 0.7148106694221497, 'learning_rate': 0.00010410280229137639, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3103/6464 [56:19<1:01:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1449, 'grad_norm': 0.7019634246826172, 'learning_rate': 0.00010407183774578108, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3104/6464 [56:20<1:00:31, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2271, 'grad_norm': 0.936373770236969, 'learning_rate': 0.00010404087320018578, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3105/6464 [56:21<58:13, 1.04s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0048, 'grad_norm': 0.771247148513794, 'learning_rate': 0.00010400990865459051, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3106/6464 [56:22<57:18, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0193, 'grad_norm': 0.7102173566818237, 'learning_rate': 0.0001039789441089952, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3107/6464 [56:23<57:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1895, 'grad_norm': 0.7291304469108582, 'learning_rate': 0.00010394797956339992, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3108/6464 [56:24<55:47, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1546, 'grad_norm': 0.8637694120407104, 'learning_rate': 0.00010391701501780461, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3109/6464 [56:25<58:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2262, 'grad_norm': 0.7452818155288696, 'learning_rate': 0.00010388605047220931, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3110/6464 [56:27<59:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0512, 'grad_norm': 0.6348410844802856, 'learning_rate': 0.00010385508592661404, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3111/6464 [56:28<58:39, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.291, 'grad_norm': 0.7799288630485535, 'learning_rate': 0.00010382412138101874, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3112/6464 [56:29<58:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0426, 'grad_norm': 0.7305728793144226, 'learning_rate': 0.00010379315683542346, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3113/6464 [56:30<1:00:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1212, 'grad_norm': 0.6418569684028625, 'learning_rate': 0.00010376219228982816, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3114/6464 [56:31<1:02:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2471, 'grad_norm': 0.7256413102149963, 'learning_rate': 0.00010373122774423286, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3115/6464 [56:32<1:02:44, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3347, 'grad_norm': 0.711250901222229, 'learning_rate': 0.00010370026319863757, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3116/6464 [56:33<59:47, 1.07s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0569, 'grad_norm': 0.7133957147598267, 'learning_rate': 0.00010366929865304226, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3117/6464 [56:35<1:05:13, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3573, 'grad_norm': 0.6665650606155396, 'learning_rate': 0.00010363833410744699, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3118/6464 [56:36<1:03:47, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2013, 'grad_norm': 0.6998268365859985, 'learning_rate': 0.00010360736956185169, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3119/6464 [56:37<1:02:06, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1481, 'grad_norm': 0.6871828436851501, 'learning_rate': 0.00010357640501625639, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3120/6464 [56:38<1:00:47, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1655, 'grad_norm': 0.7223494648933411, 'learning_rate': 0.00010354544047066111, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3121/6464 [56:39<58:23, 1.05s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1039, 'grad_norm': 0.7289866209030151, 'learning_rate': 0.00010351447592506581, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3122/6464 [56:40<56:01, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9795, 'grad_norm': 0.7083942294120789, 'learning_rate': 0.00010348351137947052, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3123/6464 [56:41<58:31, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2037, 'grad_norm': 0.7044758796691895, 'learning_rate': 0.00010345254683387522, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3124/6464 [56:42<57:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0844, 'grad_norm': 0.8319677114486694, 'learning_rate': 0.00010342158228827991, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3125/6464 [56:43<59:35, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0325, 'grad_norm': 0.6815873980522156, 'learning_rate': 0.00010339061774268464, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3126/6464 [56:44<59:59, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2641, 'grad_norm': 0.757937490940094, 'learning_rate': 0.00010335965319708934, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3127/6464 [56:45<1:03:21, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2529, 'grad_norm': 0.7391537427902222, 'learning_rate': 0.00010332868865149405, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3128/6464 [56:46<1:01:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1567, 'grad_norm': 0.7264445424079895, 'learning_rate': 0.00010329772410589875, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3129/6464 [56:47<1:02:50, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1477, 'grad_norm': 0.6005263328552246, 'learning_rate': 0.00010326675956030344, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3130/6464 [56:48<58:19, 1.05s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0618, 'grad_norm': 0.894415020942688, 'learning_rate': 0.00010323579501470817, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3131/6464 [56:49<56:36, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.134, 'grad_norm': 0.8125756978988647, 'learning_rate': 0.00010320483046911287, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3132/6464 [56:50<54:16, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9234, 'grad_norm': 0.6873106956481934, 'learning_rate': 0.00010317386592351759, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3133/6464 [56:51<57:05, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1994, 'grad_norm': 0.7294086813926697, 'learning_rate': 0.00010314290137792229, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3134/6464 [56:53<1:00:39, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4539, 'grad_norm': 0.7192226052284241, 'learning_rate': 0.00010311193683232699, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 48%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3135/6464 [56:53<57:43, 1.04s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2793, 'grad_norm': 0.7780285477638245, 'learning_rate': 0.0001030809722867317, 'epoch': 0.48}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3136/6464 [56:54<57:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0389, 'grad_norm': 0.7150225043296814, 'learning_rate': 0.0001030500077411364, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3137/6464 [56:56<59:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1239, 'grad_norm': 0.6242230534553528, 'learning_rate': 0.00010301904319554112, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3138/6464 [56:57<1:01:39, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3121, 'grad_norm': 0.66839998960495, 'learning_rate': 0.00010298807864994582, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3139/6464 [56:58<1:00:10, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.6742, 'grad_norm': 0.7016100287437439, 'learning_rate': 0.00010295711410435052, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3140/6464 [56:59<58:12, 1.05s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0896, 'grad_norm': 0.7729629278182983, 'learning_rate': 0.00010292614955875524, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3141/6464 [57:00<57:51, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0247, 'grad_norm': 0.7053247690200806, 'learning_rate': 0.00010289518501315994, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3142/6464 [57:01<58:57, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9863, 'grad_norm': 0.6127387881278992, 'learning_rate': 0.00010286422046756465, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3143/6464 [57:02<57:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0944, 'grad_norm': 0.8010727763175964, 'learning_rate': 0.00010283325592196935, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3144/6464 [57:03<59:43, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1111, 'grad_norm': 0.681635320186615, 'learning_rate': 0.00010280229137637405, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3145/6464 [57:04<58:49, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1412, 'grad_norm': 1.003235936164856, 'learning_rate': 0.00010277132683077877, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3146/6464 [57:05<57:11, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9782, 'grad_norm': 0.6768850088119507, 'learning_rate': 0.00010274036228518347, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3147/6464 [57:06<55:25, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1216, 'grad_norm': 0.7181738018989563, 'learning_rate': 0.00010270939773958818, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3148/6464 [57:07<57:57, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3097, 'grad_norm': 0.6854041814804077, 'learning_rate': 0.00010267843319399288, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3149/6464 [57:08<59:42, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3824, 'grad_norm': 0.762513279914856, 'learning_rate': 0.00010264746864839758, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3150/6464 [57:10<1:00:42, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3126, 'grad_norm': 0.706695556640625, 'learning_rate': 0.0001026165041028023, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3151/6464 [57:11<59:27, 1.08s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3933, 'grad_norm': 0.7195688486099243, 'learning_rate': 0.000102585539557207, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3152/6464 [57:12<59:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2362, 'grad_norm': 0.7951079607009888, 'learning_rate': 0.00010255457501161172, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3153/6464 [57:13<59:37, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1428, 'grad_norm': 0.758743941783905, 'learning_rate': 0.00010252361046601642, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3154/6464 [57:14<59:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4012, 'grad_norm': 0.7832359075546265, 'learning_rate': 0.00010249264592042112, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3155/6464 [57:15<1:00:53, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1656, 'grad_norm': 0.6689127683639526, 'learning_rate': 0.00010246168137482583, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3156/6464 [57:16<58:27, 1.06s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1062, 'grad_norm': 0.8133999705314636, 'learning_rate': 0.00010243071682923053, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3157/6464 [57:17<57:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0985, 'grad_norm': 0.7205655574798584, 'learning_rate': 0.00010239975228363525, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3158/6464 [57:18<56:56, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.092, 'grad_norm': 0.7145042419433594, 'learning_rate': 0.00010236878773803995, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3159/6464 [57:19<56:33, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9276, 'grad_norm': 0.6163198351860046, 'learning_rate': 0.00010233782319244465, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3160/6464 [57:20<56:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1806, 'grad_norm': 0.7635159492492676, 'learning_rate': 0.00010230685864684937, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3161/6464 [57:21<55:29, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0221, 'grad_norm': 0.7301788330078125, 'learning_rate': 0.00010227589410125407, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3162/6464 [57:22<54:41, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1228, 'grad_norm': 0.6894705295562744, 'learning_rate': 0.00010224492955565878, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3163/6464 [57:23<53:51, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9377, 'grad_norm': 0.6987563371658325, 'learning_rate': 0.00010221396501006348, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3164/6464 [57:24<53:23, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2525, 'grad_norm': 0.7969488501548767, 'learning_rate': 0.00010218300046446818, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3165/6464 [57:25<56:22, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1039, 'grad_norm': 0.6426795721054077, 'learning_rate': 0.0001021520359188729, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3166/6464 [57:26<57:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9987, 'grad_norm': 0.6713166236877441, 'learning_rate': 0.0001021210713732776, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3167/6464 [57:27<57:01, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0914, 'grad_norm': 0.70639568567276, 'learning_rate': 0.00010209010682768231, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3168/6464 [57:28<1:00:45, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0299, 'grad_norm': 0.697307288646698, 'learning_rate': 0.00010205914228208701, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3169/6464 [57:30<1:04:50, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3215, 'grad_norm': 0.6091349124908447, 'learning_rate': 0.00010202817773649171, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3170/6464 [57:31<1:04:38, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2942, 'grad_norm': 0.8158774375915527, 'learning_rate': 0.00010199721319089643, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3171/6464 [57:32<1:02:56, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1389, 'grad_norm': 0.7056903839111328, 'learning_rate': 0.00010196624864530113, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3172/6464 [57:33<1:02:58, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2737, 'grad_norm': 0.7812362313270569, 'learning_rate': 0.00010193528409970586, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3173/6464 [57:34<1:01:19, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3034, 'grad_norm': 0.7990267276763916, 'learning_rate': 0.00010190431955411055, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3174/6464 [57:35<58:01, 1.06s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0968, 'grad_norm': 0.789103627204895, 'learning_rate': 0.00010187335500851525, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3175/6464 [57:36<57:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1896, 'grad_norm': 1.2351292371749878, 'learning_rate': 0.00010184239046291996, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3176/6464 [57:37<1:02:49, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.26, 'grad_norm': 0.7605124115943909, 'learning_rate': 0.00010181142591732466, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3177/6464 [57:39<1:06:12, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2514, 'grad_norm': 0.7740278840065002, 'learning_rate': 0.00010178046137172939, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3178/6464 [57:40<1:03:32, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3001, 'grad_norm': 0.7266420125961304, 'learning_rate': 0.00010174949682613408, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3179/6464 [57:41<1:01:07, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9322, 'grad_norm': 0.6592952609062195, 'learning_rate': 0.00010171853228053878, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3180/6464 [57:42<59:11, 1.08s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1474, 'grad_norm': 0.7230293154716492, 'learning_rate': 0.00010168756773494351, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3181/6464 [57:43<59:32, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1686, 'grad_norm': 0.7729673981666565, 'learning_rate': 0.0001016566031893482, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3182/6464 [57:44<1:02:37, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1725, 'grad_norm': 0.6474832892417908, 'learning_rate': 0.00010162563864375292, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3183/6464 [57:45<1:01:21, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2423, 'grad_norm': 0.6391403079032898, 'learning_rate': 0.00010159467409815761, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3184/6464 [57:46<1:00:06, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2802, 'grad_norm': 0.7228279709815979, 'learning_rate': 0.00010156370955256231, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3185/6464 [57:47<58:33, 1.07s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0412, 'grad_norm': 0.8170189261436462, 'learning_rate': 0.00010153274500696704, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3186/6464 [57:48<55:49, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0932, 'grad_norm': 0.8654074668884277, 'learning_rate': 0.00010150178046137173, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3187/6464 [57:49<57:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4385, 'grad_norm': 0.7025020718574524, 'learning_rate': 0.00010147081591577645, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3188/6464 [57:51<1:02:00, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0771, 'grad_norm': 0.6340311169624329, 'learning_rate': 0.00010143985137018114, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3189/6464 [57:52<59:18, 1.09s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9634, 'grad_norm': 0.7435087561607361, 'learning_rate': 0.00010140888682458584, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3190/6464 [57:53<1:01:50, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2589, 'grad_norm': 0.6294488906860352, 'learning_rate': 0.00010137792227899057, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3191/6464 [57:54<1:00:29, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1683, 'grad_norm': 0.6896986365318298, 'learning_rate': 0.00010134695773339526, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3192/6464 [57:55<1:00:27, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3239, 'grad_norm': 0.6851683855056763, 'learning_rate': 0.00010131599318779999, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3193/6464 [57:56<1:01:07, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2065, 'grad_norm': 0.7504954934120178, 'learning_rate': 0.00010128502864220469, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3194/6464 [57:57<59:19, 1.09s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1582, 'grad_norm': 0.7399176359176636, 'learning_rate': 0.00010125406409660938, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3195/6464 [57:58<55:15, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8586, 'grad_norm': 0.673385500907898, 'learning_rate': 0.0001012230995510141, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3196/6464 [57:59<59:58, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1517, 'grad_norm': 0.6252413392066956, 'learning_rate': 0.0001011921350054188, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3197/6464 [58:01<1:01:06, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0408, 'grad_norm': 0.5814692974090576, 'learning_rate': 0.00010116117045982352, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3198/6464 [58:01<57:22, 1.05s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1278, 'grad_norm': 0.8624325394630432, 'learning_rate': 0.00010113020591422822, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 49%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3199/6464 [58:02<57:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2794, 'grad_norm': 0.7642514109611511, 'learning_rate': 0.00010109924136863291, 'epoch': 0.49}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3200/6464 [58:04<1:00:19, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2912, 'grad_norm': 0.8428159356117249, 'learning_rate': 0.00010106827682303764, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3201/6464 [58:05<1:00:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3324, 'grad_norm': 0.6837854385375977, 'learning_rate': 0.00010103731227744234, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3202/6464 [58:06<59:45, 1.10s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2061, 'grad_norm': 0.6811189651489258, 'learning_rate': 0.00010100634773184705, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3203/6464 [58:07<57:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0314, 'grad_norm': 0.7535247802734375, 'learning_rate': 0.00010097538318625175, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3204/6464 [58:08<57:48, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.035, 'grad_norm': 0.8901789784431458, 'learning_rate': 0.00010094441864065644, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3205/6464 [58:09<57:55, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2796, 'grad_norm': 0.7358971238136292, 'learning_rate': 0.00010091345409506117, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3206/6464 [58:10<57:48, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1459, 'grad_norm': 0.7951127290725708, 'learning_rate': 0.00010088248954946587, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3207/6464 [58:11<57:21, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2117, 'grad_norm': 0.6836631894111633, 'learning_rate': 0.00010085152500387058, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3208/6464 [58:12<58:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1232, 'grad_norm': 0.6430730223655701, 'learning_rate': 0.00010082056045827528, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3209/6464 [58:13<1:01:04, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3047, 'grad_norm': 0.6493038535118103, 'learning_rate': 0.00010078959591267997, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3210/6464 [58:15<59:27, 1.10s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3679, 'grad_norm': 0.7966850399971008, 'learning_rate': 0.0001007586313670847, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3211/6464 [58:16<57:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1809, 'grad_norm': 0.7660133242607117, 'learning_rate': 0.0001007276668214894, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3212/6464 [58:16<55:29, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0371, 'grad_norm': 0.7207558155059814, 'learning_rate': 0.00010069670227589412, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3213/6464 [58:18<56:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1664, 'grad_norm': 0.6670817136764526, 'learning_rate': 0.00010066573773029882, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3214/6464 [58:18<55:05, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9447, 'grad_norm': 0.7529245615005493, 'learning_rate': 0.00010063477318470352, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3215/6464 [58:20<55:26, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1082, 'grad_norm': 0.7024210691452026, 'learning_rate': 0.00010060380863910823, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3216/6464 [58:21<56:57, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0691, 'grad_norm': 0.6345977783203125, 'learning_rate': 0.00010057284409351293, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3217/6464 [58:22<57:43, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2475, 'grad_norm': 0.7448643445968628, 'learning_rate': 0.00010054187954791765, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3218/6464 [58:23<55:17, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0432, 'grad_norm': 0.7837299108505249, 'learning_rate': 0.00010051091500232235, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3219/6464 [58:24<56:46, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2487, 'grad_norm': 0.7988907098770142, 'learning_rate': 0.00010047995045672705, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3220/6464 [58:25<55:55, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8754, 'grad_norm': 0.6051980257034302, 'learning_rate': 0.00010044898591113177, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3221/6464 [58:26<54:31, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9064, 'grad_norm': 0.616479218006134, 'learning_rate': 0.00010041802136553647, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3222/6464 [58:27<54:11, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0034, 'grad_norm': 0.6517351269721985, 'learning_rate': 0.00010038705681994118, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3223/6464 [58:28<55:14, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2012, 'grad_norm': 0.7839587926864624, 'learning_rate': 0.00010035609227434588, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3224/6464 [58:29<54:06, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1411, 'grad_norm': 0.7394124269485474, 'learning_rate': 0.00010032512772875058, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3225/6464 [58:30<1:02:13, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9787, 'grad_norm': 0.6547293066978455, 'learning_rate': 0.0001002941631831553, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3226/6464 [58:31<1:01:41, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2016, 'grad_norm': 0.8160549402236938, 'learning_rate': 0.00010026319863756, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3227/6464 [58:32<59:30, 1.10s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9624, 'grad_norm': 0.6541344523429871, 'learning_rate': 0.00010023223409196471, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3228/6464 [58:33<56:48, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1425, 'grad_norm': 0.724117636680603, 'learning_rate': 0.00010020126954636941, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3229/6464 [58:34<55:07, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9861, 'grad_norm': 0.6957983374595642, 'learning_rate': 0.0001001703050007741, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3230/6464 [58:35<55:36, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0381, 'grad_norm': 0.6670031547546387, 'learning_rate': 0.00010013934045517883, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3231/6464 [58:36<54:55, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0928, 'grad_norm': 0.7345811724662781, 'learning_rate': 0.00010010837590958353, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3232/6464 [58:37<53:34, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1323, 'grad_norm': 0.703827977180481, 'learning_rate': 0.00010007741136398825, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3233/6464 [58:38<54:43, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2087, 'grad_norm': 0.7106440663337708, 'learning_rate': 0.00010004644681839295, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3234/6464 [58:39<54:06, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9249, 'grad_norm': 0.6700929999351501, 'learning_rate': 0.00010001548227279765, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3235/6464 [58:40<54:47, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8918, 'grad_norm': 0.6224570870399475, 'learning_rate': 9.998451772720235e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3236/6464 [58:41<54:34, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.086, 'grad_norm': 0.6712702512741089, 'learning_rate': 9.995355318160706e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3237/6464 [58:42<55:08, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1972, 'grad_norm': 0.7236195802688599, 'learning_rate': 9.992258863601177e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3238/6464 [58:44<58:02, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2308, 'grad_norm': 0.7368266582489014, 'learning_rate': 9.989162409041648e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3239/6464 [58:45<59:45, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1475, 'grad_norm': 0.6367499232292175, 'learning_rate': 9.986065954482119e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3240/6464 [58:46<1:00:34, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0956, 'grad_norm': 0.7787549495697021, 'learning_rate': 9.982969499922589e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3241/6464 [58:47<1:00:55, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0542, 'grad_norm': 0.6884787678718567, 'learning_rate': 9.97987304536306e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3242/6464 [58:48<1:01:06, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2249, 'grad_norm': 0.723548948764801, 'learning_rate': 9.97677659080353e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3243/6464 [58:49<1:00:37, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1571, 'grad_norm': 0.7878345251083374, 'learning_rate': 9.973680136244001e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3244/6464 [58:51<1:03:02, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0914, 'grad_norm': 0.6323760151863098, 'learning_rate': 9.970583681684472e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3245/6464 [58:52<58:11, 1.08s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0559, 'grad_norm': 0.7582228183746338, 'learning_rate': 9.967487227124942e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3246/6464 [58:52<56:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1222, 'grad_norm': 0.7895947694778442, 'learning_rate': 9.964390772565413e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3247/6464 [58:54<57:34, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0961, 'grad_norm': 0.6989558935165405, 'learning_rate': 9.961294318005884e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3248/6464 [58:55<1:02:05, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3317, 'grad_norm': 0.7097575068473816, 'learning_rate': 9.958197863446354e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3249/6464 [58:56<1:01:05, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.254, 'grad_norm': 0.7335568070411682, 'learning_rate': 9.955101408886825e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3250/6464 [58:57<1:01:53, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0966, 'grad_norm': 0.6801158785820007, 'learning_rate': 9.952004954327295e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3251/6464 [58:58<59:58, 1.12s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9833, 'grad_norm': 0.6653759479522705, 'learning_rate': 9.948908499767766e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3252/6464 [58:59<59:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2009, 'grad_norm': 0.7031757831573486, 'learning_rate': 9.945812045208237e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3253/6464 [59:00<57:01, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1131, 'grad_norm': 0.6899146437644958, 'learning_rate': 9.942715590648708e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3254/6464 [59:02<1:04:12, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4548, 'grad_norm': 0.6237587332725525, 'learning_rate': 9.93961913608918e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3255/6464 [59:03<1:02:00, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2647, 'grad_norm': 0.8282029628753662, 'learning_rate': 9.936522681529649e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3256/6464 [59:04<1:01:27, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2461, 'grad_norm': 0.6687648296356201, 'learning_rate': 9.933426226970119e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3257/6464 [59:05<1:04:43, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3105, 'grad_norm': 0.6317130923271179, 'learning_rate': 9.93032977241059e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3258/6464 [59:06<1:00:12, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0016, 'grad_norm': 0.7114570736885071, 'learning_rate': 9.927233317851061e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3259/6464 [59:07<59:17, 1.11s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4619, 'grad_norm': 0.8746512532234192, 'learning_rate': 9.924136863291532e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3260/6464 [59:08<57:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2499, 'grad_norm': 0.6983189582824707, 'learning_rate': 9.921040408732002e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3261/6464 [59:09<56:34, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0213, 'grad_norm': 0.7400715351104736, 'learning_rate': 9.917943954172473e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3262/6464 [59:11<1:04:22, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2665, 'grad_norm': 0.6094582676887512, 'learning_rate': 9.914847499612943e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3263/6464 [59:12<1:01:33, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1885, 'grad_norm': 0.6998968124389648, 'learning_rate': 9.911751045053414e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 50%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3264/6464 [59:13<59:06, 1.11s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.243, 'grad_norm': 0.7518514394760132, 'learning_rate': 9.908654590493885e-05, 'epoch': 0.5}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3265/6464 [59:14<56:59, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1748, 'grad_norm': 0.7188268303871155, 'learning_rate': 9.905558135934355e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3266/6464 [59:15<56:06, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0958, 'grad_norm': 0.7417429089546204, 'learning_rate': 9.902461681374826e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3267/6464 [59:16<1:00:33, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2665, 'grad_norm': 0.6791783571243286, 'learning_rate': 9.899365226815297e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3268/6464 [59:17<58:07, 1.09s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1599, 'grad_norm': 0.7045944929122925, 'learning_rate': 9.896268772255767e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3269/6464 [59:18<57:56, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0567, 'grad_norm': 0.6850743889808655, 'learning_rate': 9.893172317696238e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3270/6464 [59:19<55:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1372, 'grad_norm': 0.7747779488563538, 'learning_rate': 9.890075863136708e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3271/6464 [59:20<57:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0986, 'grad_norm': 0.6832787394523621, 'learning_rate': 9.886979408577179e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3272/6464 [59:21<54:53, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1191, 'grad_norm': 0.7315893173217773, 'learning_rate': 9.88388295401765e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3273/6464 [59:22<53:25, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0829, 'grad_norm': 0.6971367597579956, 'learning_rate': 9.880786499458122e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3274/6464 [59:24<57:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1557, 'grad_norm': 0.5916168689727783, 'learning_rate': 9.877690044898593e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3275/6464 [59:25<1:01:23, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0564, 'grad_norm': 0.6899307370185852, 'learning_rate': 9.874593590339062e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3276/6464 [59:26<58:38, 1.10s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0479, 'grad_norm': 0.7738549709320068, 'learning_rate': 9.871497135779532e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3277/6464 [59:27<58:27, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1019, 'grad_norm': 0.6787852048873901, 'learning_rate': 9.868400681220003e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3278/6464 [59:28<1:02:12, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3852, 'grad_norm': 0.637864887714386, 'learning_rate': 9.865304226660475e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3279/6464 [59:29<58:57, 1.11s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0779, 'grad_norm': 0.7013478875160217, 'learning_rate': 9.862207772100946e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3280/6464 [59:30<57:23, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2177, 'grad_norm': 0.6686927676200867, 'learning_rate': 9.859111317541415e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3281/6464 [59:31<56:22, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2406, 'grad_norm': 0.8312034010887146, 'learning_rate': 9.856014862981887e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3282/6464 [59:32<57:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2692, 'grad_norm': 0.7286423444747925, 'learning_rate': 9.852918408422356e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3283/6464 [59:34<57:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0983, 'grad_norm': 0.7194595336914062, 'learning_rate': 9.849821953862828e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3284/6464 [59:35<55:16, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8961, 'grad_norm': 0.6193161010742188, 'learning_rate': 9.846725499303299e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3285/6464 [59:36<54:34, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1204, 'grad_norm': 0.7510019540786743, 'learning_rate': 9.843629044743768e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3286/6464 [59:36<50:48, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8445, 'grad_norm': 0.6942819356918335, 'learning_rate': 9.84053259018424e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3287/6464 [59:38<55:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1502, 'grad_norm': 0.681209146976471, 'learning_rate': 9.837436135624711e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3288/6464 [59:39<54:59, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1309, 'grad_norm': 0.7967934608459473, 'learning_rate': 9.83433968106518e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3289/6464 [59:40<56:57, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1561, 'grad_norm': 0.7057139277458191, 'learning_rate': 9.831243226505652e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3290/6464 [59:41<55:19, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1131, 'grad_norm': 0.8387269377708435, 'learning_rate': 9.828146771946121e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3291/6464 [59:42<52:48, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.042, 'grad_norm': 0.7988048791885376, 'learning_rate': 9.825050317386593e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3292/6464 [59:43<52:42, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0209, 'grad_norm': 0.7038412094116211, 'learning_rate': 9.821953862827064e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3293/6464 [59:44<53:39, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1718, 'grad_norm': 0.683494508266449, 'learning_rate': 9.818857408267535e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3294/6464 [59:45<54:35, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2894, 'grad_norm': 0.7585805058479309, 'learning_rate': 9.815760953708006e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3295/6464 [59:46<55:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1343, 'grad_norm': 0.7351830005645752, 'learning_rate': 9.812664499148476e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3296/6464 [59:47<56:10, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1794, 'grad_norm': 0.7651079893112183, 'learning_rate': 9.809568044588946e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3297/6464 [59:48<55:46, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.106, 'grad_norm': 0.6865591406822205, 'learning_rate': 9.806471590029417e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3298/6464 [59:49<55:07, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9597, 'grad_norm': 0.6743031740188599, 'learning_rate': 9.803375135469888e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3299/6464 [59:50<54:16, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3194, 'grad_norm': 0.8444713950157166, 'learning_rate': 9.800278680910359e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3300/6464 [59:51<54:31, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9649, 'grad_norm': 0.645368754863739, 'learning_rate': 9.797182226350829e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3301/6464 [59:52<53:46, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.129, 'grad_norm': 0.7239351868629456, 'learning_rate': 9.7940857717913e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3302/6464 [59:53<54:14, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1885, 'grad_norm': 0.7167401909828186, 'learning_rate': 9.79098931723177e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3303/6464 [59:54<54:38, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0958, 'grad_norm': 0.6871540546417236, 'learning_rate': 9.787892862672241e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3304/6464 [59:55<56:53, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0777, 'grad_norm': 0.6905775666236877, 'learning_rate': 9.784796408112712e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3305/6464 [59:56<56:18, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3484, 'grad_norm': 0.8537756204605103, 'learning_rate': 9.781699953553182e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3306/6464 [59:57<56:40, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3441, 'grad_norm': 0.7868550419807434, 'learning_rate': 9.778603498993653e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3307/6464 [59:58<54:41, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0711, 'grad_norm': 0.8187411427497864, 'learning_rate': 9.775507044434124e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3308/6464 [59:59<54:42, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0249, 'grad_norm': 0.705920398235321, 'learning_rate': 9.772410589874594e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3309/6464 [1:00:01<55:45, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1622, 'grad_norm': 0.7419707775115967, 'learning_rate': 9.769314135315065e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3310/6464 [1:00:02<57:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1927, 'grad_norm': 0.643608570098877, 'learning_rate': 9.766217680755535e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3311/6464 [1:00:03<58:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4019, 'grad_norm': 0.6894448399543762, 'learning_rate': 9.763121226196006e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3312/6464 [1:00:04<57:17, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1606, 'grad_norm': 0.6465157270431519, 'learning_rate': 9.760024771636477e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3313/6464 [1:00:05<54:46, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0551, 'grad_norm': 0.7288931608200073, 'learning_rate': 9.756928317076948e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3314/6464 [1:00:06<54:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2072, 'grad_norm': 0.8222574591636658, 'learning_rate': 9.753831862517419e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3315/6464 [1:00:07<52:47, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2125, 'grad_norm': 0.743850588798523, 'learning_rate': 9.750735407957889e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3316/6464 [1:00:08<52:17, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0242, 'grad_norm': 0.6711092591285706, 'learning_rate': 9.747638953398359e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3317/6464 [1:00:09<52:59, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2054, 'grad_norm': 0.7840684056282043, 'learning_rate': 9.74454249883883e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3318/6464 [1:00:10<52:41, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2686, 'grad_norm': 0.8409227728843689, 'learning_rate': 9.741446044279301e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3319/6464 [1:00:11<54:02, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.35, 'grad_norm': 0.6968954205513, 'learning_rate': 9.738349589719772e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3320/6464 [1:00:12<52:09, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2229, 'grad_norm': 0.83707195520401, 'learning_rate': 9.735253135160242e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3321/6464 [1:00:13<51:55, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0928, 'grad_norm': 0.7469006180763245, 'learning_rate': 9.732156680600713e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3322/6464 [1:00:14<53:24, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0737, 'grad_norm': 0.6682207584381104, 'learning_rate': 9.729060226041183e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3323/6464 [1:00:15<56:06, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.106, 'grad_norm': 0.7924038171768188, 'learning_rate': 9.725963771481654e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3324/6464 [1:00:16<59:16, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1335, 'grad_norm': 0.6144444346427917, 'learning_rate': 9.722867316922125e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3325/6464 [1:00:17<56:35, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.116, 'grad_norm': 0.7606815695762634, 'learning_rate': 9.719770862362595e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3326/6464 [1:00:18<56:44, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.285, 'grad_norm': 0.7827135324478149, 'learning_rate': 9.716674407803066e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3327/6464 [1:00:20<57:53, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0166, 'grad_norm': 0.6302602291107178, 'learning_rate': 9.713577953243537e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 51%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3328/6464 [1:00:21<57:39, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.233, 'grad_norm': 0.6904124021530151, 'learning_rate': 9.710481498684007e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3329/6464 [1:00:22<54:28, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1362, 'grad_norm': 0.7736949920654297, 'learning_rate': 9.707385044124478e-05, 'epoch': 0.51}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3330/6464 [1:00:23<54:54, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1122, 'grad_norm': 0.725007951259613, 'learning_rate': 9.704288589564948e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3331/6464 [1:00:24<1:00:33, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2672, 'grad_norm': 0.6004565358161926, 'learning_rate': 9.701192135005419e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3332/6464 [1:00:26<1:05:37, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9919, 'grad_norm': 0.6567763686180115, 'learning_rate': 9.69809568044589e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3333/6464 [1:00:27<1:05:29, 1.25s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1963, 'grad_norm': 0.6112838387489319, 'learning_rate': 9.694999225886361e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3334/6464 [1:00:28<1:04:34, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3045, 'grad_norm': 0.7256873846054077, 'learning_rate': 9.691902771326832e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3335/6464 [1:00:29<1:03:53, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1947, 'grad_norm': 0.7364195585250854, 'learning_rate': 9.688806316767302e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3336/6464 [1:00:30<1:03:31, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1725, 'grad_norm': 0.6461330652236938, 'learning_rate': 9.685709862207772e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3337/6464 [1:00:31<1:01:39, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0294, 'grad_norm': 0.6686522364616394, 'learning_rate': 9.682613407648243e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3338/6464 [1:00:33<1:02:01, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1709, 'grad_norm': 0.5729420185089111, 'learning_rate': 9.679516953088714e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3339/6464 [1:00:34<59:09, 1.14s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2814, 'grad_norm': 0.7896955013275146, 'learning_rate': 9.676420498529185e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3340/6464 [1:00:35<1:02:07, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.212, 'grad_norm': 0.6892940402030945, 'learning_rate': 9.673324043969655e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3341/6464 [1:00:36<1:00:46, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2126, 'grad_norm': 0.7169594764709473, 'learning_rate': 9.670227589410126e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3342/6464 [1:00:37<1:01:08, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.296, 'grad_norm': 0.8617371916770935, 'learning_rate': 9.667131134850596e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3343/6464 [1:00:39<1:06:03, 1.27s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3491, 'grad_norm': 0.6801720857620239, 'learning_rate': 9.664034680291067e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3344/6464 [1:00:40<1:02:20, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9754, 'grad_norm': 0.8111810088157654, 'learning_rate': 9.660938225731538e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3345/6464 [1:00:41<59:13, 1.14s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2253, 'grad_norm': 0.7872037887573242, 'learning_rate': 9.657841771172008e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3346/6464 [1:00:42<54:18, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9861, 'grad_norm': 0.7853187918663025, 'learning_rate': 9.654745316612479e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3347/6464 [1:00:43<52:47, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1202, 'grad_norm': 0.7602483630180359, 'learning_rate': 9.65164886205295e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3348/6464 [1:00:44<56:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3128, 'grad_norm': 0.7309510111808777, 'learning_rate': 9.64855240749342e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3349/6464 [1:00:45<56:37, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2553, 'grad_norm': 0.7075642347335815, 'learning_rate': 9.645455952933891e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3350/6464 [1:00:46<54:14, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0931, 'grad_norm': 0.7753921151161194, 'learning_rate': 9.642359498374361e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3351/6464 [1:00:47<55:51, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2796, 'grad_norm': 0.7598620057106018, 'learning_rate': 9.639263043814832e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3352/6464 [1:00:48<1:00:35, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2566, 'grad_norm': 0.6468256711959839, 'learning_rate': 9.636166589255303e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3353/6464 [1:00:50<1:00:05, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3603, 'grad_norm': 0.7932442426681519, 'learning_rate': 9.633070134695774e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3354/6464 [1:00:51<56:40, 1.09s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0643, 'grad_norm': 0.7628620862960815, 'learning_rate': 9.629973680136246e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3355/6464 [1:00:52<56:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4139, 'grad_norm': 0.8174670934677124, 'learning_rate': 9.626877225576715e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3356/6464 [1:00:53<56:58, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1809, 'grad_norm': 0.660335123538971, 'learning_rate': 9.623780771017185e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3357/6464 [1:00:54<55:08, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1491, 'grad_norm': 0.7534894943237305, 'learning_rate': 9.620684316457656e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3358/6464 [1:00:55<56:58, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3785, 'grad_norm': 0.7095792293548584, 'learning_rate': 9.617587861898127e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3359/6464 [1:00:56<59:41, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3793, 'grad_norm': 0.7234548926353455, 'learning_rate': 9.614491407338597e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3360/6464 [1:00:57<58:57, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.185, 'grad_norm': 0.7072494029998779, 'learning_rate': 9.611394952779068e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3361/6464 [1:00:58<58:38, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2344, 'grad_norm': 0.6948502063751221, 'learning_rate': 9.60829849821954e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3362/6464 [1:00:59<57:46, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5367, 'grad_norm': 0.7105806469917297, 'learning_rate': 9.605202043660009e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3363/6464 [1:01:01<58:46, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0483, 'grad_norm': 0.6444006562232971, 'learning_rate': 9.60210558910048e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3364/6464 [1:01:02<55:45, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1722, 'grad_norm': 0.9523526430130005, 'learning_rate': 9.59900913454095e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3365/6464 [1:01:03<1:00:45, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0971, 'grad_norm': 0.6308795213699341, 'learning_rate': 9.595912679981421e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3366/6464 [1:01:04<56:37, 1.10s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9819, 'grad_norm': 0.6396747827529907, 'learning_rate': 9.592816225421892e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3367/6464 [1:01:05<56:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.296, 'grad_norm': 0.7840079665184021, 'learning_rate': 9.589719770862364e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3368/6464 [1:01:06<58:24, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2792, 'grad_norm': 0.7196952700614929, 'learning_rate': 9.586623316302833e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3369/6464 [1:01:07<58:41, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2694, 'grad_norm': 0.7240561842918396, 'learning_rate': 9.583526861743303e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3370/6464 [1:01:08<53:19, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9131, 'grad_norm': 0.918724000453949, 'learning_rate': 9.580430407183774e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3371/6464 [1:01:09<55:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2308, 'grad_norm': 0.6677970290184021, 'learning_rate': 9.577333952624245e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3372/6464 [1:01:11<1:02:30, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3023, 'grad_norm': 0.7287883758544922, 'learning_rate': 9.574237498064717e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3373/6464 [1:01:12<58:19, 1.13s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1907, 'grad_norm': 0.7859495282173157, 'learning_rate': 9.571141043505188e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3374/6464 [1:01:13<57:32, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0814, 'grad_norm': 0.6778578162193298, 'learning_rate': 9.568044588945657e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3375/6464 [1:01:14<55:23, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1385, 'grad_norm': 0.7369911670684814, 'learning_rate': 9.564948134386129e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3376/6464 [1:01:15<54:25, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0137, 'grad_norm': 0.6574245095252991, 'learning_rate': 9.561851679826598e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3377/6464 [1:01:16<53:40, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.166, 'grad_norm': 0.7294420003890991, 'learning_rate': 9.55875522526707e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3378/6464 [1:01:17<59:24, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.289, 'grad_norm': 0.6553261876106262, 'learning_rate': 9.55565877070754e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3379/6464 [1:01:18<57:53, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1434, 'grad_norm': 0.7324413061141968, 'learning_rate': 9.55256231614801e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3380/6464 [1:01:20<57:48, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1352, 'grad_norm': 0.6578732132911682, 'learning_rate': 9.549465861588482e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3381/6464 [1:01:21<58:42, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1329, 'grad_norm': 0.7523483633995056, 'learning_rate': 9.546369407028953e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3382/6464 [1:01:22<56:01, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2469, 'grad_norm': 0.6945065259933472, 'learning_rate': 9.543272952469423e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3383/6464 [1:01:23<57:31, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9704, 'grad_norm': 0.5931921601295471, 'learning_rate': 9.540176497909894e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3384/6464 [1:01:24<56:10, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9233, 'grad_norm': 0.6170344948768616, 'learning_rate': 9.537080043350363e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3385/6464 [1:01:25<55:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0256, 'grad_norm': 0.6600267291069031, 'learning_rate': 9.533983588790835e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3386/6464 [1:01:26<55:51, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9985, 'grad_norm': 0.6264317631721497, 'learning_rate': 9.530887134231306e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3387/6464 [1:01:27<53:58, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1855, 'grad_norm': 0.7627092003822327, 'learning_rate': 9.527790679671777e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3388/6464 [1:01:28<53:40, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9811, 'grad_norm': 0.6204071044921875, 'learning_rate': 9.524694225112248e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3389/6464 [1:01:29<55:34, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2901, 'grad_norm': 0.7151501774787903, 'learning_rate': 9.521597770552718e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3390/6464 [1:01:30<58:18, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2615, 'grad_norm': 0.7487080693244934, 'learning_rate': 9.518501315993188e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3391/6464 [1:01:32<57:00, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4355, 'grad_norm': 0.7762094736099243, 'learning_rate': 9.515404861433659e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3392/6464 [1:01:33<55:53, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1903, 'grad_norm': 0.8087586164474487, 'learning_rate': 9.51230840687413e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 52%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3393/6464 [1:01:34<55:57, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1944, 'grad_norm': 0.7023297548294067, 'learning_rate': 9.509211952314601e-05, 'epoch': 0.52}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3394/6464 [1:01:35<54:39, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1578, 'grad_norm': 0.6683512926101685, 'learning_rate': 9.506115497755071e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3395/6464 [1:01:36<50:57, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7941, 'grad_norm': 0.7818554043769836, 'learning_rate': 9.503019043195542e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3396/6464 [1:01:37<54:20, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2202, 'grad_norm': 0.6488218903541565, 'learning_rate': 9.499922588636012e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3397/6464 [1:01:38<55:32, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1087, 'grad_norm': 0.6602820158004761, 'learning_rate': 9.496826134076483e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3398/6464 [1:01:39<57:12, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.232, 'grad_norm': 0.7266827821731567, 'learning_rate': 9.493729679516954e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3399/6464 [1:01:40<56:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2529, 'grad_norm': 0.7694076895713806, 'learning_rate': 9.490633224957424e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3400/6464 [1:01:41<59:54, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3654, 'grad_norm': 0.6390635371208191, 'learning_rate': 9.487536770397895e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3401/6464 [1:01:43<58:08, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9867, 'grad_norm': 0.6165002584457397, 'learning_rate': 9.484440315838366e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3402/6464 [1:01:43<53:24, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9147, 'grad_norm': 0.749625027179718, 'learning_rate': 9.481343861278836e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3403/6464 [1:01:44<51:45, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9036, 'grad_norm': 0.7135515213012695, 'learning_rate': 9.478247406719307e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3404/6464 [1:01:45<53:54, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2491, 'grad_norm': 0.6536581516265869, 'learning_rate': 9.475150952159777e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3405/6464 [1:01:46<53:05, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1752, 'grad_norm': 0.8040589690208435, 'learning_rate': 9.472054497600248e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3406/6464 [1:01:48<53:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9824, 'grad_norm': 0.6725102663040161, 'learning_rate': 9.468958043040719e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3407/6464 [1:01:49<54:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0373, 'grad_norm': 0.6330937147140503, 'learning_rate': 9.46586158848119e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3408/6464 [1:01:50<52:12, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.067, 'grad_norm': 0.7317911386489868, 'learning_rate': 9.462765133921661e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3409/6464 [1:01:51<51:11, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1306, 'grad_norm': 0.76807701587677, 'learning_rate': 9.459668679362131e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3410/6464 [1:01:52<54:18, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0981, 'grad_norm': 0.5848752856254578, 'learning_rate': 9.456572224802601e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3411/6464 [1:01:53<53:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1338, 'grad_norm': 0.7582083344459534, 'learning_rate': 9.453475770243072e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3412/6464 [1:01:54<52:02, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1125, 'grad_norm': 0.747076690196991, 'learning_rate': 9.450379315683543e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3413/6464 [1:01:55<50:51, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0883, 'grad_norm': 0.8059597015380859, 'learning_rate': 9.447282861124014e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3414/6464 [1:01:56<51:07, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.157, 'grad_norm': 0.7296229004859924, 'learning_rate': 9.444186406564484e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3415/6464 [1:01:57<51:07, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2161, 'grad_norm': 0.679343581199646, 'learning_rate': 9.441089952004955e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3416/6464 [1:01:58<51:42, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0281, 'grad_norm': 0.6583395004272461, 'learning_rate': 9.437993497445425e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3417/6464 [1:01:59<52:00, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1181, 'grad_norm': 0.6381545066833496, 'learning_rate': 9.434897042885896e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3418/6464 [1:02:00<53:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1359, 'grad_norm': 0.7706635594367981, 'learning_rate': 9.431800588326367e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3419/6464 [1:02:01<56:53, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2493, 'grad_norm': 0.6490930318832397, 'learning_rate': 9.428704133766837e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3420/6464 [1:02:02<55:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0567, 'grad_norm': 0.7036570906639099, 'learning_rate': 9.425607679207308e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3421/6464 [1:02:03<56:25, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1533, 'grad_norm': 0.6230341792106628, 'learning_rate': 9.422511224647779e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3422/6464 [1:02:04<55:50, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1119, 'grad_norm': 0.6646100878715515, 'learning_rate': 9.419414770088249e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3423/6464 [1:02:06<56:01, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3118, 'grad_norm': 0.7118664383888245, 'learning_rate': 9.41631831552872e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3424/6464 [1:02:07<54:27, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2534, 'grad_norm': 0.6915967464447021, 'learning_rate': 9.41322186096919e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3425/6464 [1:02:08<53:30, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3516, 'grad_norm': 0.7789388298988342, 'learning_rate': 9.410125406409661e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3426/6464 [1:02:08<51:59, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9858, 'grad_norm': 0.6966773271560669, 'learning_rate': 9.407028951850132e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3427/6464 [1:02:10<52:31, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.213, 'grad_norm': 0.7403092384338379, 'learning_rate': 9.403932497290603e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3428/6464 [1:02:10<50:58, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0802, 'grad_norm': 0.6785216927528381, 'learning_rate': 9.400836042731074e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3429/6464 [1:02:12<53:22, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2921, 'grad_norm': 0.710392415523529, 'learning_rate': 9.397739588171544e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3430/6464 [1:02:13<55:27, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2942, 'grad_norm': 0.6488112807273865, 'learning_rate': 9.394643133612014e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3431/6464 [1:02:14<54:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0318, 'grad_norm': 0.6202141642570496, 'learning_rate': 9.391546679052485e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3432/6464 [1:02:15<55:23, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2952, 'grad_norm': 0.7223911285400391, 'learning_rate': 9.388450224492956e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3433/6464 [1:02:16<55:45, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3604, 'grad_norm': 0.7062069773674011, 'learning_rate': 9.385353769933427e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3434/6464 [1:02:17<55:25, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1516, 'grad_norm': 0.792137861251831, 'learning_rate': 9.382257315373897e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3435/6464 [1:02:18<53:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0516, 'grad_norm': 0.8271661400794983, 'learning_rate': 9.379160860814368e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3436/6464 [1:02:19<54:58, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3273, 'grad_norm': 0.6971884965896606, 'learning_rate': 9.376064406254838e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3437/6464 [1:02:20<52:00, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8607, 'grad_norm': 0.7641291618347168, 'learning_rate': 9.372967951695309e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3438/6464 [1:02:21<54:53, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1709, 'grad_norm': 0.7325499057769775, 'learning_rate': 9.36987149713578e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3439/6464 [1:02:22<52:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9051, 'grad_norm': 0.7237386107444763, 'learning_rate': 9.36677504257625e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3440/6464 [1:02:23<50:22, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9544, 'grad_norm': 0.7691993713378906, 'learning_rate': 9.363678588016721e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3441/6464 [1:02:25<53:41, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2013, 'grad_norm': 0.6830746531486511, 'learning_rate': 9.360582133457192e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3442/6464 [1:02:26<53:31, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0863, 'grad_norm': 0.7437257766723633, 'learning_rate': 9.357485678897662e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3443/6464 [1:02:27<54:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1773, 'grad_norm': 0.822901725769043, 'learning_rate': 9.354389224338133e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3444/6464 [1:02:28<56:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1523, 'grad_norm': 0.6660405993461609, 'learning_rate': 9.351292769778603e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3445/6464 [1:02:29<56:42, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0292, 'grad_norm': 0.599610447883606, 'learning_rate': 9.348196315219074e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3446/6464 [1:02:30<53:06, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0021, 'grad_norm': 0.7200444936752319, 'learning_rate': 9.345099860659545e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3447/6464 [1:02:31<51:20, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8634, 'grad_norm': 0.6694163680076599, 'learning_rate': 9.342003406100016e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3448/6464 [1:02:32<51:45, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1354, 'grad_norm': 0.7293340563774109, 'learning_rate': 9.338906951540488e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3449/6464 [1:02:33<50:24, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9886, 'grad_norm': 0.7061713337898254, 'learning_rate': 9.335810496980957e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3450/6464 [1:02:34<48:16, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9068, 'grad_norm': 0.6568235158920288, 'learning_rate': 9.332714042421427e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3451/6464 [1:02:35<49:10, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9409, 'grad_norm': 0.6967766284942627, 'learning_rate': 9.329617587861898e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3452/6464 [1:02:36<49:20, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9914, 'grad_norm': 0.7414677143096924, 'learning_rate': 9.32652113330237e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3453/6464 [1:02:37<51:00, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0404, 'grad_norm': 0.6814359426498413, 'learning_rate': 9.32342467874284e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3454/6464 [1:02:38<51:44, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2232, 'grad_norm': 0.718216061592102, 'learning_rate': 9.32032822418331e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3455/6464 [1:02:39<51:54, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1625, 'grad_norm': 0.703373372554779, 'learning_rate': 9.317231769623782e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3456/6464 [1:02:40<54:14, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2835, 'grad_norm': 0.6666248440742493, 'learning_rate': 9.314135315064251e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3457/6464 [1:02:41<53:06, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1905, 'grad_norm': 0.7197088599205017, 'learning_rate': 9.311038860504722e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 53%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3458/6464 [1:02:42<53:33, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2115, 'grad_norm': 0.7396706938743591, 'learning_rate': 9.307942405945194e-05, 'epoch': 0.53}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3459/6464 [1:02:43<52:11, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.074, 'grad_norm': 0.7934402823448181, 'learning_rate': 9.304845951385663e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3460/6464 [1:02:44<51:24, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.205, 'grad_norm': 0.7557416558265686, 'learning_rate': 9.301749496826134e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3461/6464 [1:02:45<51:31, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1153, 'grad_norm': 0.6478404998779297, 'learning_rate': 9.298653042266606e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3462/6464 [1:02:46<50:56, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0956, 'grad_norm': 0.6758819818496704, 'learning_rate': 9.295556587707075e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3463/6464 [1:02:47<52:37, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0704, 'grad_norm': 0.7353169918060303, 'learning_rate': 9.292460133147547e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3464/6464 [1:02:48<51:16, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2444, 'grad_norm': 0.7766902446746826, 'learning_rate': 9.289363678588016e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3465/6464 [1:02:49<52:07, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9689, 'grad_norm': 0.6818294525146484, 'learning_rate': 9.286267224028487e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3466/6464 [1:02:51<53:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9221, 'grad_norm': 0.5963568687438965, 'learning_rate': 9.283170769468959e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3467/6464 [1:02:52<53:06, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1196, 'grad_norm': 0.6808436512947083, 'learning_rate': 9.28007431490943e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3468/6464 [1:02:53<56:52, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5278, 'grad_norm': 0.7228144407272339, 'learning_rate': 9.276977860349901e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3469/6464 [1:02:54<55:35, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1994, 'grad_norm': 1.0239611864089966, 'learning_rate': 9.27388140579037e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3470/6464 [1:02:55<54:37, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0237, 'grad_norm': 0.6388654112815857, 'learning_rate': 9.27078495123084e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3471/6464 [1:02:56<53:03, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.97, 'grad_norm': 0.7968785762786865, 'learning_rate': 9.267688496671312e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3472/6464 [1:02:57<50:23, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9993, 'grad_norm': 0.744579017162323, 'learning_rate': 9.264592042111783e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3473/6464 [1:02:58<52:56, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1133, 'grad_norm': 0.7480915188789368, 'learning_rate': 9.261495587552254e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 3474/6464 [1:02:59<53:56, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0884, 'grad_norm': 0.6710368990898132, 'learning_rate': 9.258399132992724e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3475/6464 [1:03:00<54:52, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0539, 'grad_norm': 0.7130952477455139, 'learning_rate': 9.255302678433195e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3476/6464 [1:03:01<54:14, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1059, 'grad_norm': 0.6374394297599792, 'learning_rate': 9.252206223873665e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3477/6464 [1:03:02<51:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9595, 'grad_norm': 0.7695314884185791, 'learning_rate': 9.249109769314136e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3478/6464 [1:03:03<49:28, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0979, 'grad_norm': 0.7660771608352661, 'learning_rate': 9.246013314754607e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3479/6464 [1:03:04<51:56, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2409, 'grad_norm': 0.6802374124526978, 'learning_rate': 9.242916860195077e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3480/6464 [1:03:05<52:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.348, 'grad_norm': 0.7785443663597107, 'learning_rate': 9.239820405635548e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3481/6464 [1:03:06<51:50, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0636, 'grad_norm': 0.7073243856430054, 'learning_rate': 9.236723951076019e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3482/6464 [1:03:08<52:25, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.295, 'grad_norm': 0.745126485824585, 'learning_rate': 9.233627496516489e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3483/6464 [1:03:09<53:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1928, 'grad_norm': 0.6999270915985107, 'learning_rate': 9.23053104195696e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3484/6464 [1:03:10<50:52, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1869, 'grad_norm': 0.7750419974327087, 'learning_rate': 9.22743458739743e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3485/6464 [1:03:11<50:32, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0497, 'grad_norm': 0.6924733519554138, 'learning_rate': 9.2243381328379e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3486/6464 [1:03:12<53:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2251, 'grad_norm': 0.6873366832733154, 'learning_rate': 9.221241678278372e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3487/6464 [1:03:13<53:15, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0205, 'grad_norm': 0.6103419065475464, 'learning_rate': 9.218145223718843e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3488/6464 [1:03:14<1:00:05, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2538, 'grad_norm': 0.5733306407928467, 'learning_rate': 9.215048769159314e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3489/6464 [1:03:16<1:00:04, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1366, 'grad_norm': 0.6601300835609436, 'learning_rate': 9.211952314599784e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3490/6464 [1:03:17<55:59, 1.13s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8644, 'grad_norm': 0.6391849517822266, 'learning_rate': 9.208855860040254e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3491/6464 [1:03:17<52:29, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0764, 'grad_norm': 0.7837465405464172, 'learning_rate': 9.205759405480725e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3492/6464 [1:03:18<49:40, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8952, 'grad_norm': 0.7931115627288818, 'learning_rate': 9.202662950921196e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3493/6464 [1:03:19<51:07, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1851, 'grad_norm': 0.7599238157272339, 'learning_rate': 9.199566496361667e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3494/6464 [1:03:21<51:37, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0288, 'grad_norm': 0.698878288269043, 'learning_rate': 9.196470041802137e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3495/6464 [1:03:22<1:00:06, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2403, 'grad_norm': 0.6042650938034058, 'learning_rate': 9.193373587242608e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3496/6464 [1:03:23<59:20, 1.20s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2475, 'grad_norm': 0.6577930450439453, 'learning_rate': 9.190277132683078e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3497/6464 [1:03:24<58:12, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2304, 'grad_norm': 0.7554277181625366, 'learning_rate': 9.187180678123549e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3498/6464 [1:03:26<58:56, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2401, 'grad_norm': 0.6814929842948914, 'learning_rate': 9.18408422356402e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3499/6464 [1:03:27<1:01:56, 1.25s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9595, 'grad_norm': 0.6169039607048035, 'learning_rate': 9.18098776900449e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3500/6464 [1:03:28<56:19, 1.14s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8894, 'grad_norm': 0.7635680437088013, 'learning_rate': 9.177891314444961e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/other.py:619: UserWarning: Unable to fetch remote file due to the following error (ReadTimeoutError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)\"), '(Request ID: 316d2fce-8b42-4d46-b6f0-625721309911)') - silently ignoring the lookup for the file config.json in Magpie-Align/MagpieLM-4B-Chat-v0.1.\n", " warnings.warn(\n", "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/save_and_load.py:218: UserWarning: Could not find a config file in Magpie-Align/MagpieLM-4B-Chat-v0.1 - will assume that the vocabulary was not modified.\n", " warnings.warn(\n", " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3501/6464 [1:03:39<3:27:55, 4.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2868, 'grad_norm': 0.7265945672988892, 'learning_rate': 9.174794859885432e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3502/6464 [1:03:40<2:40:57, 3.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.056, 'grad_norm': 0.7713377475738525, 'learning_rate': 9.171698405325902e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3503/6464 [1:03:41<2:07:49, 2.59s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1495, 'grad_norm': 0.7067415714263916, 'learning_rate': 9.168601950766373e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3504/6464 [1:03:42<1:44:49, 2.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.079, 'grad_norm': 0.6131211519241333, 'learning_rate': 9.165505496206843e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3505/6464 [1:03:44<1:30:15, 1.83s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.329, 'grad_norm': 0.7512075304985046, 'learning_rate': 9.162409041647314e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3506/6464 [1:03:45<1:18:22, 1.59s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.109, 'grad_norm': 0.7113748788833618, 'learning_rate': 9.159312587087785e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3507/6464 [1:03:46<1:10:57, 1.44s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2714, 'grad_norm': 0.6804924011230469, 'learning_rate': 9.156216132528256e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3508/6464 [1:03:47<1:04:52, 1.32s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2611, 'grad_norm': 0.7267914414405823, 'learning_rate': 9.153119677968727e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3509/6464 [1:03:47<56:54, 1.16s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8696, 'grad_norm': 0.6999794840812683, 'learning_rate': 9.150023223409197e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3510/6464 [1:03:49<55:49, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2011, 'grad_norm': 0.7355808615684509, 'learning_rate': 9.146926768849667e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3511/6464 [1:03:50<53:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2446, 'grad_norm': 0.721234142780304, 'learning_rate': 9.143830314290138e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3512/6464 [1:03:51<54:57, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3338, 'grad_norm': 0.6892656683921814, 'learning_rate': 9.140733859730609e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3513/6464 [1:03:52<51:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0251, 'grad_norm': 0.6822878122329712, 'learning_rate': 9.13763740517108e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3514/6464 [1:03:53<50:32, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9721, 'grad_norm': 0.6715260148048401, 'learning_rate': 9.13454095061155e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3515/6464 [1:03:54<49:08, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7914, 'grad_norm': 0.7067328691482544, 'learning_rate': 9.131444496052021e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3516/6464 [1:03:55<55:08, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0387, 'grad_norm': 0.5864906907081604, 'learning_rate': 9.128348041492491e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3517/6464 [1:03:56<53:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2284, 'grad_norm': 0.7772772908210754, 'learning_rate': 9.125251586932962e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3518/6464 [1:03:57<51:46, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.138, 'grad_norm': 0.8449162244796753, 'learning_rate': 9.122155132373433e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3519/6464 [1:03:58<48:31, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9238, 'grad_norm': 0.8909621238708496, 'learning_rate': 9.119058677813903e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3520/6464 [1:03:59<47:40, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1914, 'grad_norm': 0.7867956757545471, 'learning_rate': 9.115962223254374e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3521/6464 [1:04:00<49:42, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0855, 'grad_norm': 0.654793918132782, 'learning_rate': 9.112865768694845e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 54%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3522/6464 [1:04:01<53:20, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3476, 'grad_norm': 0.7405469417572021, 'learning_rate': 9.109769314135316e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3523/6464 [1:04:02<53:59, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1358, 'grad_norm': 0.7044516801834106, 'learning_rate': 9.106672859575786e-05, 'epoch': 0.54}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3524/6464 [1:04:03<54:20, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1965, 'grad_norm': 0.7324852347373962, 'learning_rate': 9.103576405016256e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3525/6464 [1:04:04<53:52, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3142, 'grad_norm': 0.702139675617218, 'learning_rate': 9.100479950456727e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3526/6464 [1:04:05<53:27, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2117, 'grad_norm': 0.6761022806167603, 'learning_rate': 9.097383495897198e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3527/6464 [1:04:06<52:15, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1703, 'grad_norm': 0.7963728904724121, 'learning_rate': 9.09428704133767e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3528/6464 [1:04:07<49:32, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2369, 'grad_norm': 0.8268749117851257, 'learning_rate': 9.09119058677814e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3529/6464 [1:04:08<49:12, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0723, 'grad_norm': 0.8301143646240234, 'learning_rate': 9.08809413221861e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3530/6464 [1:04:09<50:13, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1784, 'grad_norm': 0.8071090579032898, 'learning_rate': 9.08499767765908e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3531/6464 [1:04:10<49:52, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2068, 'grad_norm': 0.7316404581069946, 'learning_rate': 9.081901223099551e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3532/6464 [1:04:12<54:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3551, 'grad_norm': 0.6227662563323975, 'learning_rate': 9.078804768540022e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3533/6464 [1:04:13<51:34, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0367, 'grad_norm': 0.7612451314926147, 'learning_rate': 9.075708313980493e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3534/6464 [1:04:14<52:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9605, 'grad_norm': 0.6273985505104065, 'learning_rate': 9.072611859420963e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3535/6464 [1:04:15<52:00, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2177, 'grad_norm': 0.7531867623329163, 'learning_rate': 9.069515404861434e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3536/6464 [1:04:16<50:19, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0262, 'grad_norm': 0.7256660461425781, 'learning_rate': 9.066418950301904e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3537/6464 [1:04:17<49:20, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1188, 'grad_norm': 0.7328090071678162, 'learning_rate': 9.063322495742375e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3538/6464 [1:04:18<51:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0933, 'grad_norm': 0.6212531328201294, 'learning_rate': 9.060226041182846e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3539/6464 [1:04:19<51:21, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0562, 'grad_norm': 0.6917474269866943, 'learning_rate': 9.057129586623316e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3540/6464 [1:04:20<51:50, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0726, 'grad_norm': 0.6339970231056213, 'learning_rate': 9.054033132063787e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3541/6464 [1:04:21<57:14, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.13, 'grad_norm': 0.5771842002868652, 'learning_rate': 9.050936677504259e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3542/6464 [1:04:23<55:08, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0025, 'grad_norm': 0.6490893363952637, 'learning_rate': 9.04784022294473e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3543/6464 [1:04:24<56:03, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0619, 'grad_norm': 0.6877392530441284, 'learning_rate': 9.0447437683852e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3544/6464 [1:04:25<54:58, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4366, 'grad_norm': 0.7502363324165344, 'learning_rate': 9.041647313825669e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3545/6464 [1:04:26<56:24, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3535, 'grad_norm': 0.6849304437637329, 'learning_rate': 9.03855085926614e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3546/6464 [1:04:27<51:25, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9417, 'grad_norm': 0.7554724216461182, 'learning_rate': 9.035454404706611e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3547/6464 [1:04:28<52:00, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1078, 'grad_norm': 0.6549021601676941, 'learning_rate': 9.032357950147083e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3548/6464 [1:04:29<50:42, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9574, 'grad_norm': 0.6340201497077942, 'learning_rate': 9.029261495587554e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3549/6464 [1:04:30<50:00, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1486, 'grad_norm': 0.7233894467353821, 'learning_rate': 9.026165041028024e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3550/6464 [1:04:31<48:37, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1008, 'grad_norm': 0.7528835535049438, 'learning_rate': 9.023068586468493e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3551/6464 [1:04:32<50:18, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0699, 'grad_norm': 0.6201964616775513, 'learning_rate': 9.019972131908964e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3552/6464 [1:04:33<49:54, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2236, 'grad_norm': 0.7260141372680664, 'learning_rate': 9.016875677349436e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3553/6464 [1:04:34<48:45, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9988, 'grad_norm': 0.7428381443023682, 'learning_rate': 9.013779222789907e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3554/6464 [1:04:35<47:24, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0208, 'grad_norm': 0.7166744470596313, 'learning_rate': 9.010682768230377e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3555/6464 [1:04:36<47:42, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2199, 'grad_norm': 0.7374040484428406, 'learning_rate': 9.007586313670848e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3556/6464 [1:04:37<49:02, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0811, 'grad_norm': 0.7117849588394165, 'learning_rate': 9.004489859111317e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3557/6464 [1:04:38<51:14, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0931, 'grad_norm': 0.6671662926673889, 'learning_rate': 9.001393404551789e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3558/6464 [1:04:39<48:40, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8938, 'grad_norm': 0.6689518094062805, 'learning_rate': 8.99829694999226e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3559/6464 [1:04:40<46:43, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0133, 'grad_norm': 0.7750495672225952, 'learning_rate': 8.99520049543273e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3560/6464 [1:04:41<51:09, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2866, 'grad_norm': 0.6587863564491272, 'learning_rate': 8.9921040408732e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3561/6464 [1:04:42<51:46, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2963, 'grad_norm': 0.7036490440368652, 'learning_rate': 8.989007586313672e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3562/6464 [1:04:43<53:06, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9705, 'grad_norm': 0.7385064363479614, 'learning_rate': 8.985911131754143e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3563/6464 [1:04:44<53:04, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0086, 'grad_norm': 0.7174471616744995, 'learning_rate': 8.982814677194613e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3564/6464 [1:04:46<52:55, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2313, 'grad_norm': 0.7923966646194458, 'learning_rate': 8.979718222635082e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3565/6464 [1:04:47<50:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1174, 'grad_norm': 0.7618926167488098, 'learning_rate': 8.976621768075554e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3566/6464 [1:04:48<52:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2726, 'grad_norm': 0.7308061718940735, 'learning_rate': 8.973525313516025e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3567/6464 [1:04:49<49:22, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1153, 'grad_norm': 0.7615929245948792, 'learning_rate': 8.970428858956496e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3568/6464 [1:04:50<55:02, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1316, 'grad_norm': 0.6470713019371033, 'learning_rate': 8.967332404396967e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3569/6464 [1:04:51<52:50, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9329, 'grad_norm': 0.7747337818145752, 'learning_rate': 8.964235949837437e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3570/6464 [1:04:52<56:11, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1968, 'grad_norm': 0.6914283633232117, 'learning_rate': 8.961139495277907e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3571/6464 [1:04:53<54:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0832, 'grad_norm': 0.7188951373100281, 'learning_rate': 8.958043040718378e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3572/6464 [1:04:54<54:24, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1406, 'grad_norm': 0.6883817315101624, 'learning_rate': 8.954946586158849e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3573/6464 [1:04:56<54:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1376, 'grad_norm': 0.6464614272117615, 'learning_rate': 8.95185013159932e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3574/6464 [1:04:57<52:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0861, 'grad_norm': 0.7710934281349182, 'learning_rate': 8.94875367703979e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3575/6464 [1:04:58<52:12, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.936, 'grad_norm': 0.6695473790168762, 'learning_rate': 8.945657222480261e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3576/6464 [1:04:59<53:52, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3119, 'grad_norm': 0.6590299606323242, 'learning_rate': 8.94256076792073e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3577/6464 [1:05:00<51:17, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0215, 'grad_norm': 0.7978531718254089, 'learning_rate': 8.939464313361202e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3578/6464 [1:05:01<51:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1288, 'grad_norm': 0.6140835285186768, 'learning_rate': 8.936367858801673e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3579/6464 [1:05:02<50:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3554, 'grad_norm': 0.7318812012672424, 'learning_rate': 8.933271404242143e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3580/6464 [1:05:03<50:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0159, 'grad_norm': 0.7678360939025879, 'learning_rate': 8.930174949682614e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3581/6464 [1:05:04<49:09, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8453, 'grad_norm': 0.68569016456604, 'learning_rate': 8.927078495123085e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3582/6464 [1:05:05<52:14, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2076, 'grad_norm': 0.7402073740959167, 'learning_rate': 8.923982040563556e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3583/6464 [1:05:06<54:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9677, 'grad_norm': 0.662373960018158, 'learning_rate': 8.920885586004026e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3584/6464 [1:05:07<53:21, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2883, 'grad_norm': 0.728296160697937, 'learning_rate': 8.917789131444496e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3585/6464 [1:05:09<54:35, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3685, 'grad_norm': 0.8753759860992432, 'learning_rate': 8.914692676884967e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3586/6464 [1:05:10<53:58, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2232, 'grad_norm': 0.7300748825073242, 'learning_rate': 8.911596222325438e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 55%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3587/6464 [1:05:11<54:00, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1013, 'grad_norm': 0.6907355189323425, 'learning_rate': 8.908499767765909e-05, 'epoch': 0.55}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3588/6464 [1:05:12<52:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9115, 'grad_norm': 0.6724751591682434, 'learning_rate': 8.90540331320638e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3589/6464 [1:05:13<51:55, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2444, 'grad_norm': 0.8247934579849243, 'learning_rate': 8.90230685864685e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3590/6464 [1:05:14<50:25, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9655, 'grad_norm': 0.7051319479942322, 'learning_rate': 8.89921040408732e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3591/6464 [1:05:15<52:01, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0344, 'grad_norm': 0.5840914845466614, 'learning_rate': 8.896113949527791e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3592/6464 [1:05:16<50:33, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1105, 'grad_norm': 0.7407903671264648, 'learning_rate': 8.893017494968262e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3593/6464 [1:05:17<51:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1784, 'grad_norm': 0.7482672929763794, 'learning_rate': 8.889921040408733e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3594/6464 [1:05:18<52:17, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2238, 'grad_norm': 0.6507181525230408, 'learning_rate': 8.886824585849203e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3595/6464 [1:05:19<51:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.192, 'grad_norm': 0.6911022067070007, 'learning_rate': 8.883728131289674e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3596/6464 [1:05:20<51:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1532, 'grad_norm': 0.7548086047172546, 'learning_rate': 8.880631676730144e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3597/6464 [1:05:21<48:09, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0047, 'grad_norm': 0.7567763328552246, 'learning_rate': 8.877535222170615e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3598/6464 [1:05:22<50:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2943, 'grad_norm': 0.7082774639129639, 'learning_rate': 8.874438767611086e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3599/6464 [1:05:24<50:13, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0854, 'grad_norm': 0.6680474877357483, 'learning_rate': 8.871342313051556e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3600/6464 [1:05:25<51:42, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1273, 'grad_norm': 0.5629940629005432, 'learning_rate': 8.868245858492027e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3601/6464 [1:05:26<51:47, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0722, 'grad_norm': 0.6813255548477173, 'learning_rate': 8.865149403932498e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3602/6464 [1:05:27<52:39, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1527, 'grad_norm': 0.6739360094070435, 'learning_rate': 8.86205294937297e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3603/6464 [1:05:28<51:40, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1971, 'grad_norm': 0.8574093580245972, 'learning_rate': 8.858956494813439e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3604/6464 [1:05:29<55:30, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0145, 'grad_norm': 0.6181943416595459, 'learning_rate': 8.855860040253909e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3605/6464 [1:05:30<54:14, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1778, 'grad_norm': 0.6891123652458191, 'learning_rate': 8.85276358569438e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3606/6464 [1:05:31<51:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2258, 'grad_norm': 0.8014299869537354, 'learning_rate': 8.849667131134851e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3607/6464 [1:05:32<51:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0494, 'grad_norm': 0.6628351211547852, 'learning_rate': 8.846570676575322e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3608/6464 [1:05:34<54:25, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2902, 'grad_norm': 0.6582803130149841, 'learning_rate': 8.843474222015792e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3609/6464 [1:05:35<56:51, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2178, 'grad_norm': 0.7205149531364441, 'learning_rate': 8.840377767456263e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3610/6464 [1:05:36<55:38, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1187, 'grad_norm': 0.6162004470825195, 'learning_rate': 8.837281312896733e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3611/6464 [1:05:37<54:56, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2721, 'grad_norm': 0.7151957154273987, 'learning_rate': 8.834184858337204e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3612/6464 [1:05:38<53:20, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0434, 'grad_norm': 0.72674959897995, 'learning_rate': 8.831088403777675e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3613/6464 [1:05:39<53:17, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0867, 'grad_norm': 0.6908661723136902, 'learning_rate': 8.827991949218145e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3614/6464 [1:05:41<56:39, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.343, 'grad_norm': 0.6127553582191467, 'learning_rate': 8.824895494658616e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3615/6464 [1:05:42<53:08, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8143, 'grad_norm': 0.6342631578445435, 'learning_rate': 8.821799040099087e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3616/6464 [1:05:43<52:28, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0715, 'grad_norm': 0.7479022741317749, 'learning_rate': 8.818702585539557e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3617/6464 [1:05:44<51:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1604, 'grad_norm': 0.7484930157661438, 'learning_rate': 8.815606130980028e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3618/6464 [1:05:45<51:50, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3087, 'grad_norm': 0.7314602732658386, 'learning_rate': 8.812509676420498e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3619/6464 [1:05:46<49:01, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.954, 'grad_norm': 0.7581772208213806, 'learning_rate': 8.809413221860969e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3620/6464 [1:05:47<49:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0394, 'grad_norm': 0.6503791809082031, 'learning_rate': 8.80631676730144e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3621/6464 [1:05:48<49:51, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0963, 'grad_norm': 0.6915751695632935, 'learning_rate': 8.803220312741911e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3622/6464 [1:05:49<48:58, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9542, 'grad_norm': 0.6458215117454529, 'learning_rate': 8.800123858182383e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3623/6464 [1:05:50<48:16, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1854, 'grad_norm': 0.769808828830719, 'learning_rate': 8.797027403622852e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3624/6464 [1:05:51<48:10, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2428, 'grad_norm': 0.7938652634620667, 'learning_rate': 8.793930949063322e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3625/6464 [1:05:52<48:36, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3085, 'grad_norm': 0.9071465730667114, 'learning_rate': 8.790834494503793e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3626/6464 [1:05:53<45:26, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0501, 'grad_norm': 0.9219439625740051, 'learning_rate': 8.787738039944264e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3627/6464 [1:05:54<50:08, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0319, 'grad_norm': 0.6213436722755432, 'learning_rate': 8.784641585384736e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3628/6464 [1:05:55<50:42, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2324, 'grad_norm': 0.7333652973175049, 'learning_rate': 8.781545130825205e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3629/6464 [1:05:56<50:23, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2681, 'grad_norm': 0.7212120294570923, 'learning_rate': 8.778448676265676e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3630/6464 [1:05:57<48:53, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9626, 'grad_norm': 0.7448555827140808, 'learning_rate': 8.775352221706146e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3631/6464 [1:05:58<49:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9164, 'grad_norm': 0.703831672668457, 'learning_rate': 8.772255767146617e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3632/6464 [1:05:59<48:30, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0106, 'grad_norm': 0.7214223742485046, 'learning_rate': 8.769159312587088e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3633/6464 [1:06:00<48:07, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2844, 'grad_norm': 0.733542263507843, 'learning_rate': 8.766062858027558e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3634/6464 [1:06:01<47:52, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9073, 'grad_norm': 0.7740241885185242, 'learning_rate': 8.76296640346803e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 3635/6464 [1:06:03<51:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1716, 'grad_norm': 0.5969112515449524, 'learning_rate': 8.7598699489085e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3636/6464 [1:06:04<50:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0167, 'grad_norm': 0.6860421299934387, 'learning_rate': 8.75677349434897e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3637/6464 [1:06:05<50:53, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2304, 'grad_norm': 0.6620141863822937, 'learning_rate': 8.753677039789441e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3638/6464 [1:06:06<48:56, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9669, 'grad_norm': 0.7267414927482605, 'learning_rate': 8.750580585229911e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3639/6464 [1:06:07<48:36, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0645, 'grad_norm': 0.732874870300293, 'learning_rate': 8.747484130670382e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3640/6464 [1:06:08<48:30, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1795, 'grad_norm': 0.7285025119781494, 'learning_rate': 8.744387676110854e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3641/6464 [1:06:09<51:34, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1452, 'grad_norm': 0.6075055003166199, 'learning_rate': 8.741291221551325e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3642/6464 [1:06:10<48:01, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9571, 'grad_norm': 0.7897107005119324, 'learning_rate': 8.738194766991796e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3643/6464 [1:06:11<47:33, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.104, 'grad_norm': 0.8107982873916626, 'learning_rate': 8.735098312432266e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3644/6464 [1:06:12<48:07, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1998, 'grad_norm': 0.738025426864624, 'learning_rate': 8.732001857872735e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3645/6464 [1:06:13<56:59, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2234, 'grad_norm': 0.6797761917114258, 'learning_rate': 8.728905403313206e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3646/6464 [1:06:14<53:59, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1087, 'grad_norm': 0.7502395510673523, 'learning_rate': 8.725808948753678e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3647/6464 [1:06:15<51:14, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1564, 'grad_norm': 0.7399501800537109, 'learning_rate': 8.722712494194149e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3648/6464 [1:06:16<50:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1601, 'grad_norm': 0.6949213743209839, 'learning_rate': 8.719616039634619e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3649/6464 [1:06:18<51:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1869, 'grad_norm': 0.7388185858726501, 'learning_rate': 8.71651958507509e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3650/6464 [1:06:19<50:06, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3052, 'grad_norm': 0.8352744579315186, 'learning_rate': 8.71342313051556e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3651/6464 [1:06:20<52:30, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3181, 'grad_norm': 0.7162275314331055, 'learning_rate': 8.71032667595603e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 56%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3652/6464 [1:06:21<50:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0295, 'grad_norm': 0.7154219150543213, 'learning_rate': 8.707230221396502e-05, 'epoch': 0.56}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3653/6464 [1:06:22<49:47, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.094, 'grad_norm': 0.6727548837661743, 'learning_rate': 8.704133766836971e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3654/6464 [1:06:23<50:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2108, 'grad_norm': 0.7090625762939453, 'learning_rate': 8.701037312277443e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3655/6464 [1:06:24<50:39, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1897, 'grad_norm': 0.7119866609573364, 'learning_rate': 8.697940857717914e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3656/6464 [1:06:25<50:51, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.158, 'grad_norm': 0.6990227103233337, 'learning_rate': 8.694844403158385e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3657/6464 [1:06:26<49:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0452, 'grad_norm': 0.7485036849975586, 'learning_rate': 8.691747948598855e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3658/6464 [1:06:27<51:37, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3926, 'grad_norm': 0.7709220051765442, 'learning_rate': 8.688651494039324e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3659/6464 [1:06:28<51:16, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9735, 'grad_norm': 0.6774082183837891, 'learning_rate': 8.685555039479796e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3660/6464 [1:06:30<51:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2739, 'grad_norm': 0.7991147637367249, 'learning_rate': 8.682458584920267e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3661/6464 [1:06:31<51:19, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2345, 'grad_norm': 0.7355266213417053, 'learning_rate': 8.679362130360738e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3662/6464 [1:06:32<50:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3227, 'grad_norm': 0.8800910711288452, 'learning_rate': 8.676265675801209e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3663/6464 [1:06:33<53:43, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.078, 'grad_norm': 0.6201590895652771, 'learning_rate': 8.673169221241679e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3664/6464 [1:06:34<54:14, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.052, 'grad_norm': 0.6556967496871948, 'learning_rate': 8.670072766682149e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3665/6464 [1:06:35<54:26, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0069, 'grad_norm': 0.6586683392524719, 'learning_rate': 8.66697631212262e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3666/6464 [1:06:36<51:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2213, 'grad_norm': 0.763790488243103, 'learning_rate': 8.663879857563091e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3667/6464 [1:06:37<50:41, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.173, 'grad_norm': 0.7305902242660522, 'learning_rate': 8.660783403003562e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3668/6464 [1:06:38<49:26, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1125, 'grad_norm': 0.7470771074295044, 'learning_rate': 8.657686948444032e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3669/6464 [1:06:40<52:21, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2962, 'grad_norm': 0.7405757308006287, 'learning_rate': 8.654590493884503e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3670/6464 [1:06:41<57:19, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4946, 'grad_norm': 0.6105810403823853, 'learning_rate': 8.651494039324973e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3671/6464 [1:06:42<53:25, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3686, 'grad_norm': 0.8854507803916931, 'learning_rate': 8.648397584765444e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3672/6464 [1:06:43<51:49, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9633, 'grad_norm': 0.7075481414794922, 'learning_rate': 8.645301130205915e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3673/6464 [1:06:44<52:26, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3359, 'grad_norm': 0.7530025839805603, 'learning_rate': 8.642204675646385e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3674/6464 [1:06:45<49:41, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1015, 'grad_norm': 0.7649775743484497, 'learning_rate': 8.639108221086856e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3675/6464 [1:06:46<49:25, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3896, 'grad_norm': 0.7615112662315369, 'learning_rate': 8.636011766527327e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3676/6464 [1:06:47<49:18, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0, 'grad_norm': 0.6467560529708862, 'learning_rate': 8.632915311967798e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3677/6464 [1:06:48<48:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0664, 'grad_norm': 0.7475308179855347, 'learning_rate': 8.629818857408268e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3678/6464 [1:06:49<47:04, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2049, 'grad_norm': 0.7938953638076782, 'learning_rate': 8.626722402848738e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3679/6464 [1:06:50<49:42, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1983, 'grad_norm': 0.6657782196998596, 'learning_rate': 8.623625948289209e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3680/6464 [1:06:52<54:47, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2011, 'grad_norm': 0.536281406879425, 'learning_rate': 8.62052949372968e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3681/6464 [1:06:53<51:15, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.963, 'grad_norm': 0.7003145217895508, 'learning_rate': 8.617433039170151e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3682/6464 [1:06:54<48:51, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0563, 'grad_norm': 0.7386812567710876, 'learning_rate': 8.614336584610622e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3683/6464 [1:06:55<49:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2524, 'grad_norm': 0.7003431916236877, 'learning_rate': 8.611240130051092e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3684/6464 [1:06:56<54:17, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0622, 'grad_norm': 0.6840843558311462, 'learning_rate': 8.608143675491562e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3685/6464 [1:06:57<51:55, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1089, 'grad_norm': 0.7321513891220093, 'learning_rate': 8.605047220932033e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3686/6464 [1:06:58<51:33, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3924, 'grad_norm': 0.8004996180534363, 'learning_rate': 8.601950766372504e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3687/6464 [1:06:59<49:21, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1573, 'grad_norm': 0.6987186670303345, 'learning_rate': 8.598854311812975e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3688/6464 [1:07:01<53:40, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2261, 'grad_norm': 0.7382933497428894, 'learning_rate': 8.595757857253445e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3689/6464 [1:07:02<52:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1916, 'grad_norm': 0.6794157028198242, 'learning_rate': 8.592661402693916e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3690/6464 [1:07:03<50:06, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0878, 'grad_norm': 0.7816522717475891, 'learning_rate': 8.589564948134386e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3691/6464 [1:07:04<49:31, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0528, 'grad_norm': 0.6919770240783691, 'learning_rate': 8.586468493574857e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3692/6464 [1:07:05<52:29, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1703, 'grad_norm': 0.6349959373474121, 'learning_rate': 8.583372039015328e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3693/6464 [1:07:06<51:07, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1934, 'grad_norm': 0.697731614112854, 'learning_rate': 8.580275584455798e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3694/6464 [1:07:07<52:06, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3697, 'grad_norm': 0.8469661474227905, 'learning_rate': 8.577179129896269e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3695/6464 [1:07:08<49:37, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0928, 'grad_norm': 0.8030256628990173, 'learning_rate': 8.57408267533674e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3696/6464 [1:07:09<50:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.07, 'grad_norm': 0.6531639695167542, 'learning_rate': 8.570986220777211e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3697/6464 [1:07:10<48:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0518, 'grad_norm': 0.7406216859817505, 'learning_rate': 8.567889766217681e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3698/6464 [1:07:11<49:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3593, 'grad_norm': 0.7154614925384521, 'learning_rate': 8.564793311658151e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3699/6464 [1:07:12<47:51, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1048, 'grad_norm': 0.8162233233451843, 'learning_rate': 8.561696857098622e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3700/6464 [1:07:14<49:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1418, 'grad_norm': 0.6750676035881042, 'learning_rate': 8.558600402539093e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3701/6464 [1:07:15<51:26, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2987, 'grad_norm': 0.6687110066413879, 'learning_rate': 8.555503947979564e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3702/6464 [1:07:16<51:02, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3509, 'grad_norm': 0.6970193386077881, 'learning_rate': 8.552407493420035e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3703/6464 [1:07:17<50:22, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2561, 'grad_norm': 0.8579740524291992, 'learning_rate': 8.549311038860505e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3704/6464 [1:07:18<50:14, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2295, 'grad_norm': 0.6891055703163147, 'learning_rate': 8.546214584300975e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3705/6464 [1:07:19<51:51, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9962, 'grad_norm': 0.647193431854248, 'learning_rate': 8.543118129741446e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3706/6464 [1:07:21<54:29, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2597, 'grad_norm': 0.6903799176216125, 'learning_rate': 8.540021675181917e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3707/6464 [1:07:21<49:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1268, 'grad_norm': 0.7392781376838684, 'learning_rate': 8.536925220622388e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3708/6464 [1:07:23<50:15, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4253, 'grad_norm': 0.7629299759864807, 'learning_rate': 8.533828766062858e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3709/6464 [1:07:23<48:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2122, 'grad_norm': 0.7881782650947571, 'learning_rate': 8.53073231150333e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3710/6464 [1:07:25<49:40, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1952, 'grad_norm': 0.7025527954101562, 'learning_rate': 8.527635856943799e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3711/6464 [1:07:26<49:10, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.064, 'grad_norm': 0.7083892822265625, 'learning_rate': 8.52453940238427e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3712/6464 [1:07:27<51:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2928, 'grad_norm': 0.6583844423294067, 'learning_rate': 8.521442947824741e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3713/6464 [1:07:28<51:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.379, 'grad_norm': 0.8093469738960266, 'learning_rate': 8.518346493265211e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3714/6464 [1:07:29<49:29, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1747, 'grad_norm': 0.7580199837684631, 'learning_rate': 8.515250038705682e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3715/6464 [1:07:30<45:55, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9571, 'grad_norm': 0.702542245388031, 'learning_rate': 8.512153584146153e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 57%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 3716/6464 [1:07:31<49:53, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2073, 'grad_norm': 0.6225403547286987, 'learning_rate': 8.509057129586625e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3717/6464 [1:07:32<48:54, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0559, 'grad_norm': 0.6562278270721436, 'learning_rate': 8.505960675027094e-05, 'epoch': 0.57}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3718/6464 [1:07:33<45:55, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9465, 'grad_norm': 0.7761552333831787, 'learning_rate': 8.502864220467564e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3719/6464 [1:07:34<49:01, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1941, 'grad_norm': 0.6729675531387329, 'learning_rate': 8.499767765908035e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3720/6464 [1:07:35<48:11, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9984, 'grad_norm': 0.7553339600563049, 'learning_rate': 8.496671311348506e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3721/6464 [1:07:36<50:15, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2171, 'grad_norm': 0.6999169588088989, 'learning_rate': 8.493574856788978e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3722/6464 [1:07:38<50:55, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0927, 'grad_norm': 1.1940162181854248, 'learning_rate': 8.490478402229449e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3723/6464 [1:07:39<52:39, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2378, 'grad_norm': 0.6828974485397339, 'learning_rate': 8.487381947669918e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3724/6464 [1:07:40<50:01, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1497, 'grad_norm': 0.7622852921485901, 'learning_rate': 8.484285493110388e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3725/6464 [1:07:41<51:19, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0915, 'grad_norm': 0.7633162140846252, 'learning_rate': 8.48118903855086e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3726/6464 [1:07:42<50:39, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2357, 'grad_norm': 0.801354706287384, 'learning_rate': 8.47809258399133e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3727/6464 [1:07:43<48:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9515, 'grad_norm': 0.7152717709541321, 'learning_rate': 8.474996129431802e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3728/6464 [1:07:44<47:54, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1211, 'grad_norm': 0.6910290122032166, 'learning_rate': 8.471899674872271e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3729/6464 [1:07:45<48:39, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2325, 'grad_norm': 0.7700919508934021, 'learning_rate': 8.468803220312743e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3730/6464 [1:07:46<49:18, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3072, 'grad_norm': 0.7331124544143677, 'learning_rate': 8.465706765753212e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3731/6464 [1:07:47<45:42, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7483, 'grad_norm': 0.747765302658081, 'learning_rate': 8.462610311193683e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3732/6464 [1:07:48<46:33, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0626, 'grad_norm': 0.6878067255020142, 'learning_rate': 8.459513856634155e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3733/6464 [1:07:49<44:55, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7076, 'grad_norm': 0.5830221772193909, 'learning_rate': 8.456417402074624e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3734/6464 [1:07:50<48:04, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3832, 'grad_norm': 0.7792268395423889, 'learning_rate': 8.453320947515096e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3735/6464 [1:07:51<48:17, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3298, 'grad_norm': 0.7940976023674011, 'learning_rate': 8.450224492955567e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3736/6464 [1:07:52<45:49, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.94, 'grad_norm': 0.734015703201294, 'learning_rate': 8.447128038396038e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3737/6464 [1:07:53<45:10, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1715, 'grad_norm': 0.7299582362174988, 'learning_rate': 8.444031583836508e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3738/6464 [1:07:54<45:53, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0864, 'grad_norm': 0.7070662975311279, 'learning_rate': 8.440935129276977e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3739/6464 [1:07:55<45:35, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0411, 'grad_norm': 0.8370069861412048, 'learning_rate': 8.437838674717448e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3740/6464 [1:07:56<47:40, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1621, 'grad_norm': 0.7019349336624146, 'learning_rate': 8.43474222015792e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3741/6464 [1:07:57<46:26, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1201, 'grad_norm': 0.7780343890190125, 'learning_rate': 8.431645765598391e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3742/6464 [1:07:58<46:21, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0971, 'grad_norm': 0.7737667560577393, 'learning_rate': 8.428549311038862e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3743/6464 [1:08:00<48:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2024, 'grad_norm': 0.7374290227890015, 'learning_rate': 8.425452856479332e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3744/6464 [1:08:01<46:54, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9931, 'grad_norm': 1.0725871324539185, 'learning_rate': 8.422356401919801e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3745/6464 [1:08:02<47:59, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.186, 'grad_norm': 0.742398738861084, 'learning_rate': 8.419259947360273e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3746/6464 [1:08:03<48:56, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3522, 'grad_norm': 0.7687533497810364, 'learning_rate': 8.416163492800744e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3747/6464 [1:08:04<48:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0213, 'grad_norm': 0.7268160581588745, 'learning_rate': 8.413067038241215e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3748/6464 [1:08:05<46:33, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1809, 'grad_norm': 0.7128475904464722, 'learning_rate': 8.409970583681685e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3749/6464 [1:08:06<47:14, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1638, 'grad_norm': 0.6937981247901917, 'learning_rate': 8.406874129122156e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3750/6464 [1:08:07<48:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9665, 'grad_norm': 0.7283748984336853, 'learning_rate': 8.403777674562626e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3751/6464 [1:08:08<51:30, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3918, 'grad_norm': 0.6317559480667114, 'learning_rate': 8.400681220003097e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3752/6464 [1:08:09<48:07, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9633, 'grad_norm': 0.8693466186523438, 'learning_rate': 8.397584765443568e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3753/6464 [1:08:10<49:18, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2902, 'grad_norm': 0.731665849685669, 'learning_rate': 8.394488310884038e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3754/6464 [1:08:11<49:40, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1441, 'grad_norm': 0.7449830770492554, 'learning_rate': 8.391391856324509e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3755/6464 [1:08:12<47:39, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0241, 'grad_norm': 0.6639432311058044, 'learning_rate': 8.38829540176498e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3756/6464 [1:08:13<46:47, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9925, 'grad_norm': 0.6650799512863159, 'learning_rate': 8.385198947205451e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3757/6464 [1:08:14<45:37, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1363, 'grad_norm': 0.7466337084770203, 'learning_rate': 8.382102492645921e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3758/6464 [1:08:16<48:55, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3557, 'grad_norm': 0.6839070320129395, 'learning_rate': 8.37900603808639e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3759/6464 [1:08:17<48:31, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9783, 'grad_norm': 0.6728963851928711, 'learning_rate': 8.375909583526862e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3760/6464 [1:08:18<46:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8432, 'grad_norm': 0.6405428647994995, 'learning_rate': 8.372813128967333e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3761/6464 [1:08:19<49:31, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9964, 'grad_norm': 0.5716251730918884, 'learning_rate': 8.369716674407804e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3762/6464 [1:08:20<47:13, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8503, 'grad_norm': 0.7325611114501953, 'learning_rate': 8.366620219848275e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3763/6464 [1:08:21<47:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9637, 'grad_norm': 0.6219493746757507, 'learning_rate': 8.363523765288745e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3764/6464 [1:08:22<45:52, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1595, 'grad_norm': 0.8046317100524902, 'learning_rate': 8.360427310729215e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3765/6464 [1:08:23<48:20, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2942, 'grad_norm': 0.6280192732810974, 'learning_rate': 8.357330856169686e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3766/6464 [1:08:24<49:25, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3762, 'grad_norm': 0.7414938807487488, 'learning_rate': 8.354234401610157e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3767/6464 [1:08:25<48:45, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0889, 'grad_norm': 0.6899862885475159, 'learning_rate': 8.351137947050628e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3768/6464 [1:08:26<49:03, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2127, 'grad_norm': 0.7835765480995178, 'learning_rate': 8.348041492491098e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3769/6464 [1:08:27<49:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2412, 'grad_norm': 0.8723012804985046, 'learning_rate': 8.344945037931569e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3770/6464 [1:08:29<51:06, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2708, 'grad_norm': 0.6885085105895996, 'learning_rate': 8.341848583372039e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3771/6464 [1:08:30<48:23, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2143, 'grad_norm': 0.7629822492599487, 'learning_rate': 8.33875212881251e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3772/6464 [1:08:31<48:11, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1962, 'grad_norm': 0.7268120050430298, 'learning_rate': 8.335655674252981e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3773/6464 [1:08:32<52:40, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4033, 'grad_norm': 0.6447420716285706, 'learning_rate': 8.332559219693451e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3774/6464 [1:08:33<51:44, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0431, 'grad_norm': 0.702824592590332, 'learning_rate': 8.329462765133922e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3775/6464 [1:08:35<54:26, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1171, 'grad_norm': 0.641548752784729, 'learning_rate': 8.326366310574393e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3776/6464 [1:08:35<50:54, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1282, 'grad_norm': 0.7182679176330566, 'learning_rate': 8.323269856014864e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3777/6464 [1:08:36<49:12, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1703, 'grad_norm': 0.7595745921134949, 'learning_rate': 8.320173401455334e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3778/6464 [1:08:38<48:54, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2165, 'grad_norm': 0.6900023818016052, 'learning_rate': 8.317076946895804e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3779/6464 [1:08:39<47:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1301, 'grad_norm': 0.6892773509025574, 'learning_rate': 8.313980492336275e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3780/6464 [1:08:40<46:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1666, 'grad_norm': 0.691441535949707, 'learning_rate': 8.310884037776746e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 58%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3781/6464 [1:08:41<46:23, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1307, 'grad_norm': 0.6934064030647278, 'learning_rate': 8.307787583217217e-05, 'epoch': 0.58}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3782/6464 [1:08:42<46:46, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9153, 'grad_norm': 0.6117011904716492, 'learning_rate': 8.304691128657688e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3783/6464 [1:08:43<45:00, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1626, 'grad_norm': 0.7534593939781189, 'learning_rate': 8.301594674098158e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3784/6464 [1:08:44<46:20, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2658, 'grad_norm': 0.686380922794342, 'learning_rate': 8.298498219538628e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3785/6464 [1:08:45<44:49, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2338, 'grad_norm': 0.7619589567184448, 'learning_rate': 8.295401764979099e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3786/6464 [1:08:46<43:35, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0951, 'grad_norm': 0.7573220729827881, 'learning_rate': 8.29230531041957e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3787/6464 [1:08:46<43:12, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9765, 'grad_norm': 0.7130177617073059, 'learning_rate': 8.289208855860041e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3788/6464 [1:08:48<45:00, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0665, 'grad_norm': 0.6477271318435669, 'learning_rate': 8.286112401300511e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3789/6464 [1:08:49<46:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0188, 'grad_norm': 0.6831598281860352, 'learning_rate': 8.283015946740982e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3790/6464 [1:08:50<44:04, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0131, 'grad_norm': 0.8193672299385071, 'learning_rate': 8.279919492181452e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3791/6464 [1:08:51<44:08, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3128, 'grad_norm': 0.8240098357200623, 'learning_rate': 8.276823037621923e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3792/6464 [1:08:52<44:09, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0046, 'grad_norm': 0.7173638343811035, 'learning_rate': 8.273726583062394e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3793/6464 [1:08:53<47:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2363, 'grad_norm': 0.619961678981781, 'learning_rate': 8.270630128502864e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3794/6464 [1:08:54<50:36, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0773, 'grad_norm': 0.6683215498924255, 'learning_rate': 8.267533673943335e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3795/6464 [1:08:55<49:58, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0463, 'grad_norm': 0.7416099309921265, 'learning_rate': 8.264437219383806e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3796/6464 [1:08:56<49:12, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2323, 'grad_norm': 0.742050290107727, 'learning_rate': 8.261340764824277e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 3797/6464 [1:08:57<50:54, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9706, 'grad_norm': 0.6124987006187439, 'learning_rate': 8.258244310264747e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3798/6464 [1:08:59<51:39, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1743, 'grad_norm': 0.7069000601768494, 'learning_rate': 8.255147855705217e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3799/6464 [1:09:00<51:26, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2965, 'grad_norm': 0.8120179772377014, 'learning_rate': 8.252051401145688e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3800/6464 [1:09:01<48:30, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0227, 'grad_norm': 0.7498440742492676, 'learning_rate': 8.248954946586159e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3801/6464 [1:09:02<46:58, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0634, 'grad_norm': 0.7831100225448608, 'learning_rate': 8.24585849202663e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3802/6464 [1:09:03<46:06, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1049, 'grad_norm': 0.79131680727005, 'learning_rate': 8.242762037467102e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3803/6464 [1:09:04<47:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.177, 'grad_norm': 0.7217733263969421, 'learning_rate': 8.239665582907571e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3804/6464 [1:09:05<47:22, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0697, 'grad_norm': 0.6823676824569702, 'learning_rate': 8.236569128348041e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3805/6464 [1:09:06<46:58, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1042, 'grad_norm': 0.6870402097702026, 'learning_rate': 8.233472673788512e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3806/6464 [1:09:07<46:06, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2913, 'grad_norm': 0.8407962918281555, 'learning_rate': 8.230376219228983e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3807/6464 [1:09:08<46:14, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2608, 'grad_norm': 0.7309186458587646, 'learning_rate': 8.227279764669455e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3808/6464 [1:09:09<43:54, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8555, 'grad_norm': 0.6776286363601685, 'learning_rate': 8.224183310109924e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3809/6464 [1:09:10<48:41, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5353, 'grad_norm': 0.7053353190422058, 'learning_rate': 8.221086855550395e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3810/6464 [1:09:11<46:46, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0064, 'grad_norm': 0.754503607749939, 'learning_rate': 8.217990400990867e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3811/6464 [1:09:12<46:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2775, 'grad_norm': 0.8033375144004822, 'learning_rate': 8.214893946431336e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3812/6464 [1:09:13<48:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.894, 'grad_norm': 0.6072925329208374, 'learning_rate': 8.211797491871808e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3813/6464 [1:09:15<50:24, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1624, 'grad_norm': 0.6461167931556702, 'learning_rate': 8.208701037312277e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3814/6464 [1:09:16<51:07, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1435, 'grad_norm': 0.636202871799469, 'learning_rate': 8.205604582752748e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3815/6464 [1:09:17<50:23, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0855, 'grad_norm': 0.6936859488487244, 'learning_rate': 8.20250812819322e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3816/6464 [1:09:18<47:49, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.915, 'grad_norm': 0.7321484088897705, 'learning_rate': 8.199411673633691e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3817/6464 [1:09:19<48:25, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.118, 'grad_norm': 0.6853529214859009, 'learning_rate': 8.19631521907416e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3818/6464 [1:09:20<46:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0765, 'grad_norm': 0.7634280920028687, 'learning_rate': 8.19321876451463e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3819/6464 [1:09:21<47:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2734, 'grad_norm': 0.7886274456977844, 'learning_rate': 8.190122309955101e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3820/6464 [1:09:22<45:42, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1589, 'grad_norm': 0.8321817517280579, 'learning_rate': 8.187025855395573e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3821/6464 [1:09:23<44:54, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9862, 'grad_norm': 0.6626142859458923, 'learning_rate': 8.183929400836044e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3822/6464 [1:09:24<46:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2683, 'grad_norm': 0.7333030700683594, 'learning_rate': 8.180832946276515e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3823/6464 [1:09:25<49:11, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1262, 'grad_norm': 0.7209640741348267, 'learning_rate': 8.177736491716985e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3824/6464 [1:09:27<49:28, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2858, 'grad_norm': 0.7118117809295654, 'learning_rate': 8.174640037157454e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3825/6464 [1:09:28<48:15, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2706, 'grad_norm': 0.724485456943512, 'learning_rate': 8.171543582597925e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3826/6464 [1:09:29<47:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9924, 'grad_norm': 0.6926181316375732, 'learning_rate': 8.168447128038397e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3827/6464 [1:09:30<48:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3063, 'grad_norm': 0.7288075089454651, 'learning_rate': 8.165350673478868e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3828/6464 [1:09:31<49:12, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1938, 'grad_norm': 0.7222301363945007, 'learning_rate': 8.162254218919338e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3829/6464 [1:09:32<50:21, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1863, 'grad_norm': 0.689700186252594, 'learning_rate': 8.159157764359809e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3830/6464 [1:09:33<46:16, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0684, 'grad_norm': 0.8317527770996094, 'learning_rate': 8.15606130980028e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3831/6464 [1:09:34<45:21, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.974, 'grad_norm': 0.7246521711349487, 'learning_rate': 8.15296485524075e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3832/6464 [1:09:35<43:43, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9269, 'grad_norm': 0.8271531462669373, 'learning_rate': 8.149868400681221e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3833/6464 [1:09:36<45:39, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9788, 'grad_norm': 0.7053002715110779, 'learning_rate': 8.14677194612169e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3834/6464 [1:09:37<44:06, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0469, 'grad_norm': 0.7965081334114075, 'learning_rate': 8.143675491562162e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3835/6464 [1:09:38<44:10, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0228, 'grad_norm': 0.629427969455719, 'learning_rate': 8.140579037002633e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3836/6464 [1:09:39<44:26, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0682, 'grad_norm': 0.9101265072822571, 'learning_rate': 8.137482582443104e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3837/6464 [1:09:40<44:06, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0558, 'grad_norm': 0.699321448802948, 'learning_rate': 8.134386127883574e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3838/6464 [1:09:42<50:25, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2637, 'grad_norm': 0.5795989632606506, 'learning_rate': 8.131289673324043e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3839/6464 [1:09:43<48:22, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0499, 'grad_norm': 0.7259416580200195, 'learning_rate': 8.128193218764515e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3840/6464 [1:09:44<47:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1644, 'grad_norm': 0.6569643616676331, 'learning_rate': 8.125096764204986e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3841/6464 [1:09:45<48:07, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0172, 'grad_norm': 0.6221407055854797, 'learning_rate': 8.122000309645457e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3842/6464 [1:09:46<51:10, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5169, 'grad_norm': 0.6515331864356995, 'learning_rate': 8.118903855085928e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3843/6464 [1:09:47<48:18, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0134, 'grad_norm': 0.7522486448287964, 'learning_rate': 8.115807400526398e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3844/6464 [1:09:48<48:27, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9726, 'grad_norm': 0.699120283126831, 'learning_rate': 8.112710945966868e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3845/6464 [1:09:49<50:07, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3786, 'grad_norm': 0.751243531703949, 'learning_rate': 8.109614491407339e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 59%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3846/6464 [1:09:50<46:58, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0288, 'grad_norm': 0.7080649733543396, 'learning_rate': 8.10651803684781e-05, 'epoch': 0.59}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3847/6464 [1:09:52<48:48, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0533, 'grad_norm': 0.59842848777771, 'learning_rate': 8.103421582288281e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3848/6464 [1:09:52<46:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1619, 'grad_norm': 0.7836025953292847, 'learning_rate': 8.100325127728751e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3849/6464 [1:09:54<48:14, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0792, 'grad_norm': 0.74847012758255, 'learning_rate': 8.097228673169222e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3850/6464 [1:09:55<46:23, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0109, 'grad_norm': 0.7437190413475037, 'learning_rate': 8.094132218609693e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3851/6464 [1:09:56<45:44, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9398, 'grad_norm': 0.6208214163780212, 'learning_rate': 8.091035764050163e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3852/6464 [1:09:57<45:26, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9171, 'grad_norm': 0.6831782460212708, 'learning_rate': 8.087939309490634e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3853/6464 [1:09:58<46:27, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0809, 'grad_norm': 0.6891117691993713, 'learning_rate': 8.084842854931104e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3854/6464 [1:09:59<46:17, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1034, 'grad_norm': 0.6650381684303284, 'learning_rate': 8.081746400371575e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3855/6464 [1:10:00<44:32, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0806, 'grad_norm': 0.7929040789604187, 'learning_rate': 8.078649945812046e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3856/6464 [1:10:01<43:35, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9698, 'grad_norm': 0.6795617938041687, 'learning_rate': 8.075553491252517e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3857/6464 [1:10:02<44:19, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1449, 'grad_norm': 0.6883378624916077, 'learning_rate': 8.072457036692987e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3858/6464 [1:10:03<43:20, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9813, 'grad_norm': 0.7260294556617737, 'learning_rate': 8.069360582133457e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3859/6464 [1:10:04<43:02, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8633, 'grad_norm': 0.8241310119628906, 'learning_rate': 8.066264127573928e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3860/6464 [1:10:05<44:01, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0354, 'grad_norm': 0.6628619432449341, 'learning_rate': 8.063167673014399e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3861/6464 [1:10:06<47:23, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.291, 'grad_norm': 0.5823901295661926, 'learning_rate': 8.06007121845487e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3862/6464 [1:10:07<46:43, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1422, 'grad_norm': 0.7493652105331421, 'learning_rate': 8.05697476389534e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3863/6464 [1:10:08<46:55, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0553, 'grad_norm': 0.7790986895561218, 'learning_rate': 8.053878309335811e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3864/6464 [1:10:09<47:58, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0329, 'grad_norm': 0.6504828333854675, 'learning_rate': 8.050781854776281e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3865/6464 [1:10:10<47:13, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3069, 'grad_norm': 0.7605764269828796, 'learning_rate': 8.047685400216752e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3866/6464 [1:10:11<46:51, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3315, 'grad_norm': 0.6998220682144165, 'learning_rate': 8.044588945657223e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3867/6464 [1:10:12<45:15, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1027, 'grad_norm': 0.7679982781410217, 'learning_rate': 8.041492491097693e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3868/6464 [1:10:13<44:38, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8946, 'grad_norm': 0.7068946957588196, 'learning_rate': 8.038396036538164e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3869/6464 [1:10:15<46:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.033, 'grad_norm': 0.6723169684410095, 'learning_rate': 8.035299581978635e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3870/6464 [1:10:16<44:30, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8587, 'grad_norm': 0.6854056119918823, 'learning_rate': 8.032203127419106e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3871/6464 [1:10:16<42:27, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0042, 'grad_norm': 0.8678562641143799, 'learning_rate': 8.029106672859576e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3872/6464 [1:10:18<45:04, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1763, 'grad_norm': 0.6433007717132568, 'learning_rate': 8.026010218300046e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3873/6464 [1:10:19<44:29, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9606, 'grad_norm': 0.7484356760978699, 'learning_rate': 8.022913763740517e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3874/6464 [1:10:20<44:38, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3357, 'grad_norm': 0.7925796508789062, 'learning_rate': 8.019817309180988e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3875/6464 [1:10:21<46:04, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3075, 'grad_norm': 0.699346125125885, 'learning_rate': 8.016720854621459e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3876/6464 [1:10:22<45:12, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1431, 'grad_norm': 0.7329269647598267, 'learning_rate': 8.01362440006193e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3877/6464 [1:10:23<44:49, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1989, 'grad_norm': 0.7750178575515747, 'learning_rate': 8.0105279455024e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 3878/6464 [1:10:24<46:31, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2038, 'grad_norm': 0.7546907067298889, 'learning_rate': 8.00743149094287e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3879/6464 [1:10:25<46:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2203, 'grad_norm': 0.6562875509262085, 'learning_rate': 8.004335036383341e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3880/6464 [1:10:26<45:17, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0564, 'grad_norm': 0.7904752492904663, 'learning_rate': 8.001238581823812e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3881/6464 [1:10:27<46:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9694, 'grad_norm': 0.5987658500671387, 'learning_rate': 7.998142127264283e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3882/6464 [1:10:28<45:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0652, 'grad_norm': 0.8637184500694275, 'learning_rate': 7.995045672704753e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3883/6464 [1:10:29<43:03, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0468, 'grad_norm': 0.8212466835975647, 'learning_rate': 7.991949218145224e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3884/6464 [1:10:30<46:26, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1992, 'grad_norm': 0.5578668117523193, 'learning_rate': 7.988852763585694e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3885/6464 [1:10:31<46:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2949, 'grad_norm': 0.8443903923034668, 'learning_rate': 7.985756309026165e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3886/6464 [1:10:33<46:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2041, 'grad_norm': 0.691563069820404, 'learning_rate': 7.982659854466636e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3887/6464 [1:10:34<48:40, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.148, 'grad_norm': 0.6192102432250977, 'learning_rate': 7.979563399907106e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3888/6464 [1:10:35<47:33, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4144, 'grad_norm': 0.7553074359893799, 'learning_rate': 7.976466945347577e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3889/6464 [1:10:36<48:11, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2586, 'grad_norm': 0.7156023383140564, 'learning_rate': 7.973370490788048e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3890/6464 [1:10:37<48:58, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1828, 'grad_norm': 0.6260786652565002, 'learning_rate': 7.97027403622852e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3891/6464 [1:10:38<48:23, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1711, 'grad_norm': 0.651823878288269, 'learning_rate': 7.967177581668989e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3892/6464 [1:10:39<47:07, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1338, 'grad_norm': 0.7907018065452576, 'learning_rate': 7.964081127109459e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3893/6464 [1:10:41<49:01, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1196, 'grad_norm': 0.6128340363502502, 'learning_rate': 7.96098467254993e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3894/6464 [1:10:42<50:30, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.357, 'grad_norm': 0.6534599661827087, 'learning_rate': 7.957888217990401e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3895/6464 [1:10:43<49:39, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9759, 'grad_norm': 0.6991252899169922, 'learning_rate': 7.954791763430872e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3896/6464 [1:10:44<49:02, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1885, 'grad_norm': 0.6824760437011719, 'learning_rate': 7.951695308871344e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3897/6464 [1:10:45<48:57, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1116, 'grad_norm': 0.811313807964325, 'learning_rate': 7.948598854311813e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3898/6464 [1:10:46<47:56, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2307, 'grad_norm': 0.6842753291130066, 'learning_rate': 7.945502399752283e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3899/6464 [1:10:47<46:37, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0895, 'grad_norm': 0.6360596418380737, 'learning_rate': 7.942405945192754e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3900/6464 [1:10:48<46:28, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.321, 'grad_norm': 0.7420857548713684, 'learning_rate': 7.939309490633225e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3901/6464 [1:10:49<44:18, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0391, 'grad_norm': 0.7376522421836853, 'learning_rate': 7.936213036073697e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3902/6464 [1:10:51<51:51, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4788, 'grad_norm': 0.7147917747497559, 'learning_rate': 7.933116581514166e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3903/6464 [1:10:52<51:59, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1149, 'grad_norm': 0.7128926515579224, 'learning_rate': 7.930020126954637e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3904/6464 [1:10:53<52:35, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.264, 'grad_norm': 0.6182186603546143, 'learning_rate': 7.926923672395107e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3905/6464 [1:10:54<50:51, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2454, 'grad_norm': 0.6769317984580994, 'learning_rate': 7.923827217835578e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3906/6464 [1:10:55<48:10, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2082, 'grad_norm': 0.7717778086662292, 'learning_rate': 7.92073076327605e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3907/6464 [1:10:56<46:01, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1762, 'grad_norm': 0.7282838225364685, 'learning_rate': 7.917634308716519e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3908/6464 [1:10:57<45:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2311, 'grad_norm': 0.7335312366485596, 'learning_rate': 7.91453785415699e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3909/6464 [1:10:58<43:01, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8955, 'grad_norm': 0.7778207063674927, 'learning_rate': 7.911441399597462e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 60%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3910/6464 [1:11:00<47:33, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1337, 'grad_norm': 0.6734480261802673, 'learning_rate': 7.908344945037933e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3911/6464 [1:11:01<48:14, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3151, 'grad_norm': 0.8029921650886536, 'learning_rate': 7.905248490478402e-05, 'epoch': 0.6}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3912/6464 [1:11:02<46:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0367, 'grad_norm': 0.7405518293380737, 'learning_rate': 7.902152035918872e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3913/6464 [1:11:03<48:01, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4824, 'grad_norm': 0.7238118052482605, 'learning_rate': 7.899055581359343e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3914/6464 [1:11:04<46:12, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0985, 'grad_norm': 0.8307960629463196, 'learning_rate': 7.895959126799815e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3915/6464 [1:11:05<47:27, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1632, 'grad_norm': 0.6825952529907227, 'learning_rate': 7.892862672240286e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3916/6464 [1:11:06<45:06, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0353, 'grad_norm': 0.7386375069618225, 'learning_rate': 7.889766217680757e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3917/6464 [1:11:07<44:53, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2041, 'grad_norm': 0.7219359874725342, 'learning_rate': 7.886669763121227e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3918/6464 [1:11:08<44:45, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3317, 'grad_norm': 0.7765136361122131, 'learning_rate': 7.883573308561696e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3919/6464 [1:11:09<43:39, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0973, 'grad_norm': 0.7856290340423584, 'learning_rate': 7.880476854002168e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3920/6464 [1:11:10<41:32, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0389, 'grad_norm': 0.7099674940109253, 'learning_rate': 7.877380399442639e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3921/6464 [1:11:11<41:37, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2938, 'grad_norm': 0.8240426182746887, 'learning_rate': 7.87428394488311e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3922/6464 [1:11:12<43:20, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2736, 'grad_norm': 0.6456952095031738, 'learning_rate': 7.87118749032358e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3923/6464 [1:11:13<45:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3384, 'grad_norm': 0.8021661043167114, 'learning_rate': 7.868091035764051e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3924/6464 [1:11:14<44:07, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0797, 'grad_norm': 0.6953278183937073, 'learning_rate': 7.86499458120452e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3925/6464 [1:11:16<45:58, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2283, 'grad_norm': 0.6680376529693604, 'learning_rate': 7.861898126644992e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3926/6464 [1:11:17<44:54, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0442, 'grad_norm': 0.7512810230255127, 'learning_rate': 7.858801672085463e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3927/6464 [1:11:18<43:39, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9824, 'grad_norm': 0.6358737945556641, 'learning_rate': 7.855705217525933e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3928/6464 [1:11:19<44:09, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2727, 'grad_norm': 0.7089139819145203, 'learning_rate': 7.852608762966404e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3929/6464 [1:11:20<44:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9419, 'grad_norm': 0.7229714393615723, 'learning_rate': 7.849512308406875e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3930/6464 [1:11:21<44:54, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.209, 'grad_norm': 0.7862012982368469, 'learning_rate': 7.846415853847346e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3931/6464 [1:11:22<46:45, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.234, 'grad_norm': 0.6778627038002014, 'learning_rate': 7.843319399287816e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3932/6464 [1:11:23<43:46, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8256, 'grad_norm': 0.8652362823486328, 'learning_rate': 7.840222944728285e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3933/6464 [1:11:24<45:11, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2079, 'grad_norm': 0.6189591884613037, 'learning_rate': 7.837126490168757e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3934/6464 [1:11:25<46:21, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.241, 'grad_norm': 0.6648401021957397, 'learning_rate': 7.834030035609228e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3935/6464 [1:11:26<46:49, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3409, 'grad_norm': 0.7055699825286865, 'learning_rate': 7.830933581049699e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3936/6464 [1:11:27<45:23, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0225, 'grad_norm': 0.6616045236587524, 'learning_rate': 7.82783712649017e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3937/6464 [1:11:28<43:50, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1332, 'grad_norm': 0.7259976863861084, 'learning_rate': 7.82474067193064e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3938/6464 [1:11:30<47:58, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1926, 'grad_norm': 0.7053974270820618, 'learning_rate': 7.82164421737111e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3939/6464 [1:11:31<48:15, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1293, 'grad_norm': 0.6468254327774048, 'learning_rate': 7.818547762811581e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3940/6464 [1:11:32<47:31, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2191, 'grad_norm': 0.7845959663391113, 'learning_rate': 7.815451308252052e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3941/6464 [1:11:33<51:45, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3426, 'grad_norm': 0.6745830178260803, 'learning_rate': 7.812354853692523e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3942/6464 [1:11:35<53:00, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1178, 'grad_norm': 0.6621095538139343, 'learning_rate': 7.809258399132993e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3943/6464 [1:11:36<49:00, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9885, 'grad_norm': 0.8937168121337891, 'learning_rate': 7.806161944573464e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3944/6464 [1:11:37<47:05, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1507, 'grad_norm': 0.7604997158050537, 'learning_rate': 7.803065490013935e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3945/6464 [1:11:38<46:18, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1314, 'grad_norm': 0.7722072601318359, 'learning_rate': 7.799969035454405e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3946/6464 [1:11:39<47:06, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9595, 'grad_norm': 0.6090834140777588, 'learning_rate': 7.796872580894876e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3947/6464 [1:11:40<48:37, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3997, 'grad_norm': 0.7596893906593323, 'learning_rate': 7.793776126335346e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3948/6464 [1:11:41<48:26, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3471, 'grad_norm': 0.7169070243835449, 'learning_rate': 7.790679671775817e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3949/6464 [1:11:42<47:45, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.286, 'grad_norm': 0.8222824335098267, 'learning_rate': 7.787583217216288e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3950/6464 [1:11:43<46:08, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1187, 'grad_norm': 0.7570275068283081, 'learning_rate': 7.784486762656759e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3951/6464 [1:11:44<46:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0946, 'grad_norm': 0.6602940559387207, 'learning_rate': 7.781390308097229e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3952/6464 [1:11:45<44:26, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9442, 'grad_norm': 0.715310275554657, 'learning_rate': 7.778293853537699e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3953/6464 [1:11:46<41:35, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0635, 'grad_norm': 0.8944796919822693, 'learning_rate': 7.77519739897817e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3954/6464 [1:11:47<40:48, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0342, 'grad_norm': 0.742997944355011, 'learning_rate': 7.772100944418641e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3955/6464 [1:11:48<40:04, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1858, 'grad_norm': 0.8558354377746582, 'learning_rate': 7.769004489859112e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3956/6464 [1:11:49<40:00, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1263, 'grad_norm': 0.7133302092552185, 'learning_rate': 7.765908035299583e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3957/6464 [1:11:50<41:39, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0293, 'grad_norm': 0.7275105714797974, 'learning_rate': 7.762811580740053e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3958/6464 [1:11:51<41:33, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9398, 'grad_norm': 0.6531925797462463, 'learning_rate': 7.759715126180523e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 3959/6464 [1:11:52<42:35, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0925, 'grad_norm': 0.7427082657814026, 'learning_rate': 7.756618671620994e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3960/6464 [1:11:53<40:50, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0702, 'grad_norm': 0.740216076374054, 'learning_rate': 7.753522217061465e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3961/6464 [1:11:54<42:45, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2846, 'grad_norm': 0.7829392552375793, 'learning_rate': 7.750425762501936e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3962/6464 [1:11:55<42:25, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0572, 'grad_norm': 0.6452977061271667, 'learning_rate': 7.747329307942406e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3963/6464 [1:11:56<43:30, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.275, 'grad_norm': 0.7334591746330261, 'learning_rate': 7.744232853382877e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3964/6464 [1:11:57<43:54, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0367, 'grad_norm': 0.7278541922569275, 'learning_rate': 7.741136398823348e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3965/6464 [1:11:59<44:26, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3442, 'grad_norm': 0.8196899890899658, 'learning_rate': 7.738039944263818e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3966/6464 [1:12:00<44:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2687, 'grad_norm': 0.7103814482688904, 'learning_rate': 7.734943489704289e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3967/6464 [1:12:01<45:22, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3678, 'grad_norm': 0.7672987580299377, 'learning_rate': 7.731847035144759e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3968/6464 [1:12:02<44:01, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1145, 'grad_norm': 0.7430527210235596, 'learning_rate': 7.72875058058523e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3969/6464 [1:12:03<47:49, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3099, 'grad_norm': 0.6124125719070435, 'learning_rate': 7.725654126025701e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3970/6464 [1:12:04<45:38, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0747, 'grad_norm': 0.7290236353874207, 'learning_rate': 7.722557671466172e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3971/6464 [1:12:05<45:38, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2424, 'grad_norm': 0.725970447063446, 'learning_rate': 7.719461216906642e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3972/6464 [1:12:06<44:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2129, 'grad_norm': 0.7752495408058167, 'learning_rate': 7.716364762347112e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3973/6464 [1:12:07<42:18, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9787, 'grad_norm': 0.6972155570983887, 'learning_rate': 7.713268307787583e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3974/6464 [1:12:08<46:39, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1871, 'grad_norm': 0.6784738898277283, 'learning_rate': 7.710171853228054e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 61%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3975/6464 [1:12:10<49:03, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3024, 'grad_norm': 0.6480562686920166, 'learning_rate': 7.707075398668525e-05, 'epoch': 0.61}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3976/6464 [1:12:12<56:58, 1.37s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1807, 'grad_norm': 0.5609480142593384, 'learning_rate': 7.703978944108996e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3977/6464 [1:12:13<52:11, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1152, 'grad_norm': 0.7400022149085999, 'learning_rate': 7.700882489549466e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3978/6464 [1:12:13<47:44, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9971, 'grad_norm': 0.7515943050384521, 'learning_rate': 7.697786034989936e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3979/6464 [1:12:15<48:31, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.137, 'grad_norm': 0.6502391695976257, 'learning_rate': 7.694689580430407e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3980/6464 [1:12:16<48:14, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3023, 'grad_norm': 0.7080438733100891, 'learning_rate': 7.691593125870878e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3981/6464 [1:12:17<45:19, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8123, 'grad_norm': 0.6647676825523376, 'learning_rate': 7.68849667131135e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3982/6464 [1:12:18<42:14, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9797, 'grad_norm': 0.8115183711051941, 'learning_rate': 7.685400216751819e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3983/6464 [1:12:18<39:47, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0974, 'grad_norm': 0.9842884540557861, 'learning_rate': 7.68230376219229e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3984/6464 [1:12:19<40:16, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9644, 'grad_norm': 0.7064806222915649, 'learning_rate': 7.679207307632762e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3985/6464 [1:12:21<42:45, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0877, 'grad_norm': 0.6526682376861572, 'learning_rate': 7.676110853073231e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3986/6464 [1:12:22<40:46, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0358, 'grad_norm': 0.7971833348274231, 'learning_rate': 7.673014398513702e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3987/6464 [1:12:23<41:06, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0813, 'grad_norm': 0.6390599012374878, 'learning_rate': 7.669917943954172e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3988/6464 [1:12:24<41:26, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2664, 'grad_norm': 0.8331169486045837, 'learning_rate': 7.666821489394643e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3989/6464 [1:12:24<39:59, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.935, 'grad_norm': 0.6776153445243835, 'learning_rate': 7.663725034835114e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3990/6464 [1:12:26<43:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9573, 'grad_norm': 0.6787194609642029, 'learning_rate': 7.660628580275586e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3991/6464 [1:12:27<44:29, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2812, 'grad_norm': 0.7025103569030762, 'learning_rate': 7.657532125716055e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3992/6464 [1:12:28<45:11, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.164, 'grad_norm': 0.8276124596595764, 'learning_rate': 7.654435671156525e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3993/6464 [1:12:29<43:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9741, 'grad_norm': 0.6852372288703918, 'learning_rate': 7.651339216596996e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3994/6464 [1:12:30<44:26, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1442, 'grad_norm': 0.7344316840171814, 'learning_rate': 7.648242762037467e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3995/6464 [1:12:31<46:35, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0086, 'grad_norm': 0.5799545645713806, 'learning_rate': 7.645146307477939e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3996/6464 [1:12:32<46:09, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1943, 'grad_norm': 0.6967185139656067, 'learning_rate': 7.64204985291841e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3997/6464 [1:12:34<47:33, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.079, 'grad_norm': 0.6270527839660645, 'learning_rate': 7.63895339835888e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3998/6464 [1:12:35<46:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1862, 'grad_norm': 0.7238949537277222, 'learning_rate': 7.635856943799349e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 3999/6464 [1:12:36<45:51, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.278, 'grad_norm': 0.7087214589118958, 'learning_rate': 7.63276048923982e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4000/6464 [1:12:37<46:27, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0346, 'grad_norm': 0.6098752021789551, 'learning_rate': 7.629664034680292e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4001/6464 [1:12:39<54:36, 1.33s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0434, 'grad_norm': 0.6973881721496582, 'learning_rate': 7.626567580120763e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4002/6464 [1:12:40<54:36, 1.33s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3481, 'grad_norm': 0.7009469270706177, 'learning_rate': 7.623471125561232e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4003/6464 [1:12:41<49:44, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0191, 'grad_norm': 0.7295575737953186, 'learning_rate': 7.620374671001704e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4004/6464 [1:12:42<49:12, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1357, 'grad_norm': 0.656267523765564, 'learning_rate': 7.617278216442175e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4005/6464 [1:12:44<50:45, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2249, 'grad_norm': 0.6184156537055969, 'learning_rate': 7.614181761882645e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4006/6464 [1:12:45<47:51, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0055, 'grad_norm': 0.8319051265716553, 'learning_rate': 7.611085307323116e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4007/6464 [1:12:45<44:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8514, 'grad_norm': 0.7018612027168274, 'learning_rate': 7.607988852763585e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4008/6464 [1:12:47<46:11, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3467, 'grad_norm': 0.651258647441864, 'learning_rate': 7.604892398204057e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4009/6464 [1:12:48<42:39, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7771, 'grad_norm': 0.6627812385559082, 'learning_rate': 7.601795943644528e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4010/6464 [1:12:49<43:36, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0666, 'grad_norm': 0.6617425680160522, 'learning_rate': 7.598699489084999e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4011/6464 [1:12:50<42:19, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1665, 'grad_norm': 0.7219825983047485, 'learning_rate': 7.595603034525469e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4012/6464 [1:12:51<43:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.317, 'grad_norm': 0.846156895160675, 'learning_rate': 7.592506579965938e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4013/6464 [1:12:52<42:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1063, 'grad_norm': 0.7199399471282959, 'learning_rate': 7.58941012540641e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4014/6464 [1:12:53<40:47, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0349, 'grad_norm': 0.6984779834747314, 'learning_rate': 7.58631367084688e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4015/6464 [1:12:54<40:28, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9823, 'grad_norm': 0.6829039454460144, 'learning_rate': 7.583217216287352e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4016/6464 [1:12:55<42:23, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2839, 'grad_norm': 0.7282581925392151, 'learning_rate': 7.580120761727823e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4017/6464 [1:12:56<42:16, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0949, 'grad_norm': 0.7855759859085083, 'learning_rate': 7.577024307168293e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4018/6464 [1:12:57<42:51, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1661, 'grad_norm': 0.8115835785865784, 'learning_rate': 7.573927852608763e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4019/6464 [1:12:58<44:14, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0851, 'grad_norm': 0.6833449006080627, 'learning_rate': 7.570831398049234e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4020/6464 [1:12:59<45:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.277, 'grad_norm': 0.7029368877410889, 'learning_rate': 7.567734943489705e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4021/6464 [1:13:00<44:42, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9434, 'grad_norm': 0.6540825366973877, 'learning_rate': 7.564638488930176e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4022/6464 [1:13:01<44:47, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0539, 'grad_norm': 0.6600427627563477, 'learning_rate': 7.561542034370646e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4023/6464 [1:13:02<44:02, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2579, 'grad_norm': 0.7647965550422668, 'learning_rate': 7.558445579811117e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4024/6464 [1:13:03<43:34, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2553, 'grad_norm': 0.7372454404830933, 'learning_rate': 7.555349125251588e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4025/6464 [1:13:04<42:11, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8485, 'grad_norm': 0.6533075571060181, 'learning_rate': 7.552252670692058e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4026/6464 [1:13:06<47:28, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4699, 'grad_norm': 0.7128673791885376, 'learning_rate': 7.549156216132529e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4027/6464 [1:13:07<45:34, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2421, 'grad_norm': 0.7722182869911194, 'learning_rate': 7.546059761572999e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4028/6464 [1:13:08<44:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.118, 'grad_norm': 0.6844126582145691, 'learning_rate': 7.54296330701347e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4029/6464 [1:13:09<44:59, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1742, 'grad_norm': 0.6869356036186218, 'learning_rate': 7.539866852453941e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4030/6464 [1:13:10<44:45, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0485, 'grad_norm': 0.6328253746032715, 'learning_rate': 7.536770397894412e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4031/6464 [1:13:11<45:22, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4493, 'grad_norm': 0.7032119035720825, 'learning_rate': 7.533673943334882e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4032/6464 [1:13:13<45:57, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1539, 'grad_norm': 0.7129087448120117, 'learning_rate': 7.530577488775352e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4033/6464 [1:13:13<43:46, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9376, 'grad_norm': 0.6241949200630188, 'learning_rate': 7.527481034215823e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4034/6464 [1:13:14<41:27, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1288, 'grad_norm': 0.7705684304237366, 'learning_rate': 7.524384579656294e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4035/6464 [1:13:15<40:37, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9934, 'grad_norm': 0.7909083366394043, 'learning_rate': 7.521288125096765e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4036/6464 [1:13:17<44:12, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4566, 'grad_norm': 0.6553704142570496, 'learning_rate': 7.518191670537236e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4037/6464 [1:13:18<43:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2272, 'grad_norm': 0.7751986980438232, 'learning_rate': 7.515095215977706e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4038/6464 [1:13:19<44:59, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.342, 'grad_norm': 0.6771507859230042, 'learning_rate': 7.511998761418176e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4039/6464 [1:13:20<43:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0782, 'grad_norm': 0.8551464676856995, 'learning_rate': 7.508902306858647e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 62%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4040/6464 [1:13:21<43:32, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2522, 'grad_norm': 0.8153089880943298, 'learning_rate': 7.505805852299118e-05, 'epoch': 0.62}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4041/6464 [1:13:22<43:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0123, 'grad_norm': 0.7019527554512024, 'learning_rate': 7.502709397739589e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4042/6464 [1:13:23<42:13, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9793, 'grad_norm': 0.7601521611213684, 'learning_rate': 7.499612943180059e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4043/6464 [1:13:24<40:37, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.987, 'grad_norm': 0.7826533317565918, 'learning_rate': 7.49651648862053e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4044/6464 [1:13:25<42:07, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.005, 'grad_norm': 0.6151511669158936, 'learning_rate': 7.493420034061001e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4045/6464 [1:13:26<43:00, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1568, 'grad_norm': 0.6932163238525391, 'learning_rate': 7.490323579501471e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4046/6464 [1:13:27<43:44, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3401, 'grad_norm': 0.7612322568893433, 'learning_rate': 7.487227124941942e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4047/6464 [1:13:28<43:30, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2118, 'grad_norm': 0.7541132569313049, 'learning_rate': 7.484130670382412e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4048/6464 [1:13:29<43:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1326, 'grad_norm': 0.6433945298194885, 'learning_rate': 7.481034215822883e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4049/6464 [1:13:31<44:39, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.044, 'grad_norm': 0.6519919633865356, 'learning_rate': 7.477937761263354e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4050/6464 [1:13:32<44:22, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4213, 'grad_norm': 0.7782464623451233, 'learning_rate': 7.474841306703825e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4051/6464 [1:13:33<44:10, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0145, 'grad_norm': 0.6114625930786133, 'learning_rate': 7.471744852144295e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4052/6464 [1:13:34<47:58, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8937, 'grad_norm': 0.6401013135910034, 'learning_rate': 7.468648397584765e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4053/6464 [1:13:35<46:43, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1846, 'grad_norm': 0.7694926261901855, 'learning_rate': 7.465551943025236e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4054/6464 [1:13:36<46:24, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2707, 'grad_norm': 0.6969970464706421, 'learning_rate': 7.462455488465707e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4055/6464 [1:13:37<44:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0809, 'grad_norm': 0.8276433944702148, 'learning_rate': 7.459359033906178e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4056/6464 [1:13:38<42:22, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0733, 'grad_norm': 0.69651859998703, 'learning_rate': 7.45626257934665e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4057/6464 [1:13:40<43:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2963, 'grad_norm': 0.7626796960830688, 'learning_rate': 7.453166124787119e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4058/6464 [1:13:41<44:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2555, 'grad_norm': 0.7201288342475891, 'learning_rate': 7.450069670227589e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4059/6464 [1:13:42<44:15, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9615, 'grad_norm': 0.6621582508087158, 'learning_rate': 7.44697321566806e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4060/6464 [1:13:43<45:58, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.012, 'grad_norm': 0.596086323261261, 'learning_rate': 7.443876761108531e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4061/6464 [1:13:44<44:08, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2206, 'grad_norm': 0.7724570035934448, 'learning_rate': 7.440780306549002e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4062/6464 [1:13:45<45:11, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3361, 'grad_norm': 0.7095595002174377, 'learning_rate': 7.437683851989472e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4063/6464 [1:13:46<43:53, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0228, 'grad_norm': 0.7292963266372681, 'learning_rate': 7.434587397429943e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4064/6464 [1:13:47<44:22, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2153, 'grad_norm': 0.652165949344635, 'learning_rate': 7.431490942870414e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4065/6464 [1:13:48<43:46, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3334, 'grad_norm': 0.8329493403434753, 'learning_rate': 7.428394488310884e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4066/6464 [1:13:49<43:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1628, 'grad_norm': 0.6560533046722412, 'learning_rate': 7.425298033751355e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4067/6464 [1:13:50<40:03, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9791, 'grad_norm': 0.7873805165290833, 'learning_rate': 7.422201579191825e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4068/6464 [1:13:51<39:50, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2434, 'grad_norm': 0.9003393054008484, 'learning_rate': 7.419105124632296e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4069/6464 [1:13:52<40:56, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2232, 'grad_norm': 0.7179169654846191, 'learning_rate': 7.416008670072767e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4070/6464 [1:13:53<40:02, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3555, 'grad_norm': 0.8121237754821777, 'learning_rate': 7.412912215513239e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4071/6464 [1:13:55<44:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3374, 'grad_norm': 0.7430124878883362, 'learning_rate': 7.409815760953708e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4072/6464 [1:13:56<43:18, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8619, 'grad_norm': 0.6627099514007568, 'learning_rate': 7.406719306394178e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4073/6464 [1:13:57<42:35, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0341, 'grad_norm': 0.7240769267082214, 'learning_rate': 7.403622851834649e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4074/6464 [1:13:58<44:24, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3279, 'grad_norm': 0.7517186403274536, 'learning_rate': 7.40052639727512e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4075/6464 [1:13:59<42:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0481, 'grad_norm': 0.718978762626648, 'learning_rate': 7.397429942715591e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4076/6464 [1:14:00<40:10, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8185, 'grad_norm': 0.6232830286026001, 'learning_rate': 7.394333488156063e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4077/6464 [1:14:01<41:11, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3118, 'grad_norm': 0.7026289701461792, 'learning_rate': 7.391237033596532e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4078/6464 [1:14:02<39:30, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9203, 'grad_norm': 0.7080640196800232, 'learning_rate': 7.388140579037002e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4079/6464 [1:14:03<38:47, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0392, 'grad_norm': 0.7633166313171387, 'learning_rate': 7.385044124477473e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4080/6464 [1:14:04<41:04, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0981, 'grad_norm': 0.5976954698562622, 'learning_rate': 7.381947669917944e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4081/6464 [1:14:05<40:21, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1761, 'grad_norm': 0.6788223385810852, 'learning_rate': 7.378851215358416e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4082/6464 [1:14:06<43:18, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2445, 'grad_norm': 0.6773651838302612, 'learning_rate': 7.375754760798885e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4083/6464 [1:14:07<43:12, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0839, 'grad_norm': 0.7416108846664429, 'learning_rate': 7.372658306239356e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4084/6464 [1:14:08<42:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0587, 'grad_norm': 0.6453609466552734, 'learning_rate': 7.369561851679828e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4085/6464 [1:14:09<41:15, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9829, 'grad_norm': 0.7558475136756897, 'learning_rate': 7.366465397120297e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4086/6464 [1:14:11<44:07, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3342, 'grad_norm': 0.6688844561576843, 'learning_rate': 7.363368942560769e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4087/6464 [1:14:12<44:03, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2149, 'grad_norm': 0.6645103693008423, 'learning_rate': 7.360272488001238e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4088/6464 [1:14:13<42:27, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0445, 'grad_norm': 0.6644585728645325, 'learning_rate': 7.35717603344171e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4089/6464 [1:14:14<44:57, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3205, 'grad_norm': 0.6586511731147766, 'learning_rate': 7.35407957888218e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4090/6464 [1:14:15<45:36, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2605, 'grad_norm': 0.7238021492958069, 'learning_rate': 7.350983124322652e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4091/6464 [1:14:16<43:19, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1637, 'grad_norm': 0.7431023120880127, 'learning_rate': 7.347886669763122e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4092/6464 [1:14:17<44:21, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4842, 'grad_norm': 0.7129800915718079, 'learning_rate': 7.344790215203591e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4093/6464 [1:14:19<48:09, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1741, 'grad_norm': 0.6566137075424194, 'learning_rate': 7.341693760644062e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4094/6464 [1:14:20<46:31, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2973, 'grad_norm': 0.685107409954071, 'learning_rate': 7.338597306084534e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4095/6464 [1:14:21<44:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0325, 'grad_norm': 0.7672891020774841, 'learning_rate': 7.335500851525005e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4096/6464 [1:14:22<42:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0931, 'grad_norm': 0.799769937992096, 'learning_rate': 7.332404396965476e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4097/6464 [1:14:23<42:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2832, 'grad_norm': 0.835211992263794, 'learning_rate': 7.329307942405946e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4098/6464 [1:14:24<43:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1061, 'grad_norm': 0.779220700263977, 'learning_rate': 7.326211487846417e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4099/6464 [1:14:25<44:30, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4056, 'grad_norm': 0.73162442445755, 'learning_rate': 7.323115033286887e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4100/6464 [1:14:26<44:03, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0052, 'grad_norm': 0.5922946333885193, 'learning_rate': 7.320018578727358e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4101/6464 [1:14:27<43:46, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1201, 'grad_norm': 0.7488093376159668, 'learning_rate': 7.316922124167829e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4102/6464 [1:14:28<42:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0846, 'grad_norm': 0.8617249727249146, 'learning_rate': 7.313825669608299e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4103/6464 [1:14:29<43:19, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0383, 'grad_norm': 0.6347746849060059, 'learning_rate': 7.31072921504877e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 63%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4104/6464 [1:14:31<45:37, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2794, 'grad_norm': 0.6535363793373108, 'learning_rate': 7.307632760489241e-05, 'epoch': 0.63}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4105/6464 [1:14:32<43:29, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9698, 'grad_norm': 0.6925555467605591, 'learning_rate': 7.30453630592971e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4106/6464 [1:14:33<43:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1867, 'grad_norm': 0.7235968112945557, 'learning_rate': 7.30143985137018e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4107/6464 [1:14:34<42:38, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0005, 'grad_norm': 0.6954891085624695, 'learning_rate': 7.298343396810652e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4108/6464 [1:14:35<44:20, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0686, 'grad_norm': 0.6538370251655579, 'learning_rate': 7.295246942251123e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4109/6464 [1:14:36<42:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0876, 'grad_norm': 0.7435376644134521, 'learning_rate': 7.292150487691594e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4110/6464 [1:14:37<42:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1029, 'grad_norm': 0.6550591588020325, 'learning_rate': 7.289054033132065e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4111/6464 [1:14:38<42:26, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0725, 'grad_norm': 0.6471295356750488, 'learning_rate': 7.285957578572535e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4112/6464 [1:14:39<41:23, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1916, 'grad_norm': 0.8000396490097046, 'learning_rate': 7.282861124013005e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4113/6464 [1:14:40<41:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3052, 'grad_norm': 0.7080878615379333, 'learning_rate': 7.279764669453476e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4114/6464 [1:14:41<39:46, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9483, 'grad_norm': 0.738440215587616, 'learning_rate': 7.276668214893947e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4115/6464 [1:14:43<43:39, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0041, 'grad_norm': 0.5728024244308472, 'learning_rate': 7.273571760334418e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4116/6464 [1:14:44<42:08, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0808, 'grad_norm': 0.789738118648529, 'learning_rate': 7.270475305774888e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4117/6464 [1:14:45<40:37, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9854, 'grad_norm': 0.7013458609580994, 'learning_rate': 7.267378851215359e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4118/6464 [1:14:46<49:38, 1.27s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.014, 'grad_norm': 0.5642267465591431, 'learning_rate': 7.26428239665583e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4119/6464 [1:14:47<46:59, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2716, 'grad_norm': 0.7109073996543884, 'learning_rate': 7.2611859420963e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4120/6464 [1:14:48<45:36, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.068, 'grad_norm': 0.7602007389068604, 'learning_rate': 7.258089487536771e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4121/6464 [1:14:50<44:45, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0558, 'grad_norm': 0.6799014210700989, 'learning_rate': 7.25499303297724e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4122/6464 [1:14:51<44:07, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0884, 'grad_norm': 0.7258784174919128, 'learning_rate': 7.251896578417712e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4123/6464 [1:14:52<42:39, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.196, 'grad_norm': 0.7827544808387756, 'learning_rate': 7.248800123858183e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4124/6464 [1:14:53<40:20, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1849, 'grad_norm': 0.8247532844543457, 'learning_rate': 7.245703669298654e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4125/6464 [1:14:54<39:58, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1392, 'grad_norm': 0.686212956905365, 'learning_rate': 7.242607214739124e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4126/6464 [1:14:55<40:19, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1599, 'grad_norm': 0.6736361980438232, 'learning_rate': 7.239510760179594e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4127/6464 [1:14:56<40:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1826, 'grad_norm': 0.7953144907951355, 'learning_rate': 7.236414305620065e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4128/6464 [1:14:57<40:59, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3285, 'grad_norm': 0.7576838135719299, 'learning_rate': 7.233317851060536e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4129/6464 [1:14:58<38:05, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0023, 'grad_norm': 0.7798058986663818, 'learning_rate': 7.230221396501007e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4130/6464 [1:14:59<40:17, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3031, 'grad_norm': 0.7409866452217102, 'learning_rate': 7.227124941941478e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4131/6464 [1:15:00<40:41, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1223, 'grad_norm': 0.7072409391403198, 'learning_rate': 7.224028487381948e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4132/6464 [1:15:01<41:34, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2836, 'grad_norm': 0.7477790713310242, 'learning_rate': 7.220932032822418e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4133/6464 [1:15:02<45:29, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3269, 'grad_norm': 0.6229836940765381, 'learning_rate': 7.217835578262889e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4134/6464 [1:15:03<45:13, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4064, 'grad_norm': 0.76017826795578, 'learning_rate': 7.21473912370336e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4135/6464 [1:15:04<42:38, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1918, 'grad_norm': 0.7431468367576599, 'learning_rate': 7.211642669143831e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4136/6464 [1:15:05<40:32, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0363, 'grad_norm': 0.8143817186355591, 'learning_rate': 7.208546214584301e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4137/6464 [1:15:06<38:44, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9748, 'grad_norm': 0.7053079605102539, 'learning_rate': 7.205449760024772e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4138/6464 [1:15:07<38:35, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0475, 'grad_norm': 0.7373899221420288, 'learning_rate': 7.202353305465243e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4139/6464 [1:15:08<39:07, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9795, 'grad_norm': 0.6758824586868286, 'learning_rate': 7.199256850905713e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4140/6464 [1:15:09<40:03, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3529, 'grad_norm': 0.823291540145874, 'learning_rate': 7.196160396346184e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4141/6464 [1:15:10<39:29, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8728, 'grad_norm': 0.6363077759742737, 'learning_rate': 7.193063941786654e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4142/6464 [1:15:12<41:59, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1351, 'grad_norm': 0.687035322189331, 'learning_rate': 7.189967487227125e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4143/6464 [1:15:12<39:44, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1852, 'grad_norm': 0.7704706192016602, 'learning_rate': 7.186871032667596e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4144/6464 [1:15:14<40:29, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2107, 'grad_norm': 0.7156047821044922, 'learning_rate': 7.183774578108067e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4145/6464 [1:15:15<44:06, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4559, 'grad_norm': 0.8417956233024597, 'learning_rate': 7.180678123548537e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4146/6464 [1:15:16<43:56, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2334, 'grad_norm': 0.7381181716918945, 'learning_rate': 7.177581668989007e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4147/6464 [1:15:17<42:56, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1849, 'grad_norm': 0.8882766962051392, 'learning_rate': 7.174485214429478e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4148/6464 [1:15:19<46:33, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.086, 'grad_norm': 0.6188558340072632, 'learning_rate': 7.171388759869949e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4149/6464 [1:15:19<43:23, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1219, 'grad_norm': 0.8627830743789673, 'learning_rate': 7.16829230531042e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4150/6464 [1:15:21<43:11, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0368, 'grad_norm': 0.6307201981544495, 'learning_rate': 7.165195850750891e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4151/6464 [1:15:21<39:57, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8589, 'grad_norm': 0.6777607202529907, 'learning_rate': 7.162099396191361e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4152/6464 [1:15:23<42:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0844, 'grad_norm': 0.6863059997558594, 'learning_rate': 7.159002941631831e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4153/6464 [1:15:24<42:29, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2543, 'grad_norm': 0.7458471655845642, 'learning_rate': 7.155906487072302e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4154/6464 [1:15:25<42:38, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1828, 'grad_norm': 0.6702739596366882, 'learning_rate': 7.152810032512773e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4155/6464 [1:15:26<45:19, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2725, 'grad_norm': 0.6773114204406738, 'learning_rate': 7.149713577953244e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4156/6464 [1:15:27<44:05, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.039, 'grad_norm': 0.7755146622657776, 'learning_rate': 7.146617123393714e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4157/6464 [1:15:29<45:17, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1385, 'grad_norm': 0.626419723033905, 'learning_rate': 7.143520668834185e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4158/6464 [1:15:30<46:07, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1899, 'grad_norm': 0.6513949036598206, 'learning_rate': 7.140424214274656e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4159/6464 [1:15:31<42:33, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0283, 'grad_norm': 0.8528664708137512, 'learning_rate': 7.137327759715126e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4160/6464 [1:15:32<42:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9526, 'grad_norm': 0.6538311243057251, 'learning_rate': 7.134231305155597e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4161/6464 [1:15:33<41:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0347, 'grad_norm': 0.6556314826011658, 'learning_rate': 7.131134850596067e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4162/6464 [1:15:34<40:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0164, 'grad_norm': 0.7463818788528442, 'learning_rate': 7.128038396036538e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4163/6464 [1:15:35<40:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0815, 'grad_norm': 0.7854152917861938, 'learning_rate': 7.12494194147701e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4164/6464 [1:15:36<41:25, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3366, 'grad_norm': 0.7099725008010864, 'learning_rate': 7.12184548691748e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4165/6464 [1:15:37<39:54, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0682, 'grad_norm': 0.748643696308136, 'learning_rate': 7.11874903235795e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4166/6464 [1:15:38<41:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1096, 'grad_norm': 0.7610786557197571, 'learning_rate': 7.11565257779842e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4167/6464 [1:15:39<40:34, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0245, 'grad_norm': 0.7177780270576477, 'learning_rate': 7.112556123238891e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4168/6464 [1:15:40<40:03, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9252, 'grad_norm': 0.6610248684883118, 'learning_rate': 7.109459668679362e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 64%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4169/6464 [1:15:41<40:13, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9425, 'grad_norm': 0.6716437935829163, 'learning_rate': 7.106363214119833e-05, 'epoch': 0.64}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4170/6464 [1:15:42<41:54, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2818, 'grad_norm': 0.6946514248847961, 'learning_rate': 7.103266759560305e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4171/6464 [1:15:43<41:26, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1327, 'grad_norm': 0.7281277179718018, 'learning_rate': 7.100170305000774e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4172/6464 [1:15:45<42:47, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3324, 'grad_norm': 0.6127322316169739, 'learning_rate': 7.097073850441244e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4173/6464 [1:15:46<42:29, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2382, 'grad_norm': 0.8218291997909546, 'learning_rate': 7.093977395881715e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4174/6464 [1:15:47<40:39, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0123, 'grad_norm': 0.7596524357795715, 'learning_rate': 7.090880941322186e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4175/6464 [1:15:48<38:10, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8937, 'grad_norm': 0.80315762758255, 'learning_rate': 7.087784486762658e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4176/6464 [1:15:49<40:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1161, 'grad_norm': 0.6727328896522522, 'learning_rate': 7.084688032203127e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4177/6464 [1:15:50<38:40, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1652, 'grad_norm': 0.8017406463623047, 'learning_rate': 7.081591577643599e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4178/6464 [1:15:51<37:44, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2059, 'grad_norm': 0.8126961588859558, 'learning_rate': 7.07849512308407e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4179/6464 [1:15:52<37:52, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7918, 'grad_norm': 0.6277068853378296, 'learning_rate': 7.07539866852454e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4180/6464 [1:15:53<40:10, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1585, 'grad_norm': 0.6881459951400757, 'learning_rate': 7.07230221396501e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4181/6464 [1:15:54<40:46, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3348, 'grad_norm': 0.6821048855781555, 'learning_rate': 7.06920575940548e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4182/6464 [1:15:55<39:22, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9279, 'grad_norm': 0.6890075206756592, 'learning_rate': 7.066109304845951e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4183/6464 [1:15:56<42:15, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0108, 'grad_norm': 0.6446011662483215, 'learning_rate': 7.063012850286423e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4184/6464 [1:15:57<42:50, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1087, 'grad_norm': 0.6909227967262268, 'learning_rate': 7.059916395726894e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4185/6464 [1:15:59<43:47, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3915, 'grad_norm': 0.7647101879119873, 'learning_rate': 7.056819941167364e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4186/6464 [1:16:00<43:33, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3439, 'grad_norm': 0.7369214296340942, 'learning_rate': 7.053723486607833e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4187/6464 [1:16:01<47:25, 1.25s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1257, 'grad_norm': 0.5875725746154785, 'learning_rate': 7.050627032048304e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4188/6464 [1:16:02<43:49, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2328, 'grad_norm': 0.8943522572517395, 'learning_rate': 7.047530577488776e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4189/6464 [1:16:03<43:10, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2751, 'grad_norm': 0.7672247886657715, 'learning_rate': 7.044434122929247e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4190/6464 [1:16:04<40:07, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.202, 'grad_norm': 0.7982307076454163, 'learning_rate': 7.041337668369718e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4191/6464 [1:16:05<41:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1177, 'grad_norm': 0.6654344201087952, 'learning_rate': 7.038241213810188e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4192/6464 [1:16:07<44:25, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1707, 'grad_norm': 0.6178596615791321, 'learning_rate': 7.035144759250657e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4193/6464 [1:16:08<42:21, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0679, 'grad_norm': 0.7799270153045654, 'learning_rate': 7.032048304691129e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4194/6464 [1:16:09<42:42, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0279, 'grad_norm': 0.6307783722877502, 'learning_rate': 7.0289518501316e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4195/6464 [1:16:10<40:48, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2049, 'grad_norm': 0.8088442087173462, 'learning_rate': 7.025855395572071e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4196/6464 [1:16:11<40:07, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0804, 'grad_norm': 0.6664960384368896, 'learning_rate': 7.02275894101254e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4197/6464 [1:16:12<39:06, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0305, 'grad_norm': 0.6952125430107117, 'learning_rate': 7.019662486453012e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4198/6464 [1:16:13<38:36, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0044, 'grad_norm': 0.6756427884101868, 'learning_rate': 7.016566031893483e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4199/6464 [1:16:14<41:08, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1296, 'grad_norm': 0.6187507510185242, 'learning_rate': 7.013469577333953e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4200/6464 [1:16:15<39:31, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9941, 'grad_norm': 0.7501615285873413, 'learning_rate': 7.010373122774424e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4201/6464 [1:16:16<37:53, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9368, 'grad_norm': 0.7392058968544006, 'learning_rate': 7.007276668214894e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4202/6464 [1:16:17<37:51, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0828, 'grad_norm': 0.6541820764541626, 'learning_rate': 7.004180213655365e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4203/6464 [1:16:18<38:25, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1406, 'grad_norm': 0.8199993968009949, 'learning_rate': 7.001083759095836e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4204/6464 [1:16:19<38:22, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1666, 'grad_norm': 0.8940931558609009, 'learning_rate': 6.997987304536307e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4205/6464 [1:16:20<36:58, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9117, 'grad_norm': 0.8906611204147339, 'learning_rate': 6.994890849976777e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4206/6464 [1:16:21<37:31, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0202, 'grad_norm': 0.6929125785827637, 'learning_rate': 6.991794395417247e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4207/6464 [1:16:22<37:52, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2225, 'grad_norm': 0.7437548041343689, 'learning_rate': 6.988697940857718e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4208/6464 [1:16:23<38:01, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0924, 'grad_norm': 0.7154822945594788, 'learning_rate': 6.985601486298189e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4209/6464 [1:16:24<38:18, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9818, 'grad_norm': 0.6519919037818909, 'learning_rate': 6.98250503173866e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4210/6464 [1:16:25<39:45, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2407, 'grad_norm': 0.6884635090827942, 'learning_rate': 6.979408577179131e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4211/6464 [1:16:26<38:08, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9471, 'grad_norm': 0.7076215147972107, 'learning_rate': 6.976312122619601e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4212/6464 [1:16:27<42:57, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4461, 'grad_norm': 0.754294753074646, 'learning_rate': 6.97321566806007e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4213/6464 [1:16:29<44:31, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1847, 'grad_norm': 0.6493632793426514, 'learning_rate': 6.970119213500542e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4214/6464 [1:16:30<43:09, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0631, 'grad_norm': 0.7014197707176208, 'learning_rate': 6.967022758941013e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4215/6464 [1:16:31<43:19, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1147, 'grad_norm': 0.6557389497756958, 'learning_rate': 6.963926304381484e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4216/6464 [1:16:32<43:56, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3317, 'grad_norm': 0.7482554912567139, 'learning_rate': 6.960829849821954e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4217/6464 [1:16:33<42:04, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0471, 'grad_norm': 0.6824792623519897, 'learning_rate': 6.957733395262425e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4218/6464 [1:16:34<42:36, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0815, 'grad_norm': 0.6875655055046082, 'learning_rate': 6.954636940702896e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4219/6464 [1:16:36<43:33, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8561, 'grad_norm': 0.6433541178703308, 'learning_rate': 6.951540486143366e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4220/6464 [1:16:37<42:27, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0535, 'grad_norm': 0.639238178730011, 'learning_rate': 6.948444031583837e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4221/6464 [1:16:38<41:51, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9008, 'grad_norm': 0.60859215259552, 'learning_rate': 6.945347577024307e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4222/6464 [1:16:39<39:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1178, 'grad_norm': 0.7580442428588867, 'learning_rate': 6.942251122464778e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4223/6464 [1:16:40<41:38, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2758, 'grad_norm': 0.7388088703155518, 'learning_rate': 6.939154667905249e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4224/6464 [1:16:41<40:47, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.029, 'grad_norm': 0.718018114566803, 'learning_rate': 6.93605821334572e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4225/6464 [1:16:42<40:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3457, 'grad_norm': 0.7788134813308716, 'learning_rate': 6.93296175878619e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4226/6464 [1:16:43<39:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0426, 'grad_norm': 0.7602942585945129, 'learning_rate': 6.92986530422666e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4227/6464 [1:16:44<39:20, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1872, 'grad_norm': 0.649501621723175, 'learning_rate': 6.926768849667131e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4228/6464 [1:16:45<41:37, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1042, 'grad_norm': 0.6596218347549438, 'learning_rate': 6.923672395107602e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4229/6464 [1:16:46<40:51, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0466, 'grad_norm': 0.712467610836029, 'learning_rate': 6.920575940548073e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4230/6464 [1:16:47<38:47, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9497, 'grad_norm': 0.6765840649604797, 'learning_rate': 6.917479485988544e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4231/6464 [1:16:48<38:09, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0747, 'grad_norm': 0.8207722306251526, 'learning_rate': 6.914383031429014e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4232/6464 [1:16:49<40:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.172, 'grad_norm': 0.6796014308929443, 'learning_rate': 6.911286576869485e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 65%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4233/6464 [1:16:50<38:41, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0912, 'grad_norm': 0.7563062310218811, 'learning_rate': 6.908190122309955e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4234/6464 [1:16:51<38:49, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0712, 'grad_norm': 0.6764575242996216, 'learning_rate': 6.905093667750426e-05, 'epoch': 0.65}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4235/6464 [1:16:52<38:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1225, 'grad_norm': 0.713962197303772, 'learning_rate': 6.901997213190897e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4236/6464 [1:16:54<40:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0917, 'grad_norm': 0.6126153469085693, 'learning_rate': 6.898900758631367e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4237/6464 [1:16:55<39:22, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0997, 'grad_norm': 0.71993488073349, 'learning_rate': 6.895804304071838e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4238/6464 [1:16:56<38:16, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9131, 'grad_norm': 0.71257084608078, 'learning_rate': 6.89270784951231e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4239/6464 [1:16:57<39:36, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0418, 'grad_norm': 0.7076902985572815, 'learning_rate': 6.889611394952779e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4240/6464 [1:16:58<41:19, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2009, 'grad_norm': 0.6344174742698669, 'learning_rate': 6.88651494039325e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4241/6464 [1:16:59<40:11, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9976, 'grad_norm': 0.7539723515510559, 'learning_rate': 6.88341848583372e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4242/6464 [1:17:00<38:03, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0008, 'grad_norm': 0.7091045379638672, 'learning_rate': 6.880322031274191e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4243/6464 [1:17:01<37:10, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1822, 'grad_norm': 0.7588027119636536, 'learning_rate': 6.877225576714662e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4244/6464 [1:17:02<40:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3409, 'grad_norm': 0.629292368888855, 'learning_rate': 6.874129122155133e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4245/6464 [1:17:04<43:09, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0562, 'grad_norm': 0.6330046057701111, 'learning_rate': 6.871032667595603e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4246/6464 [1:17:05<42:24, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2247, 'grad_norm': 0.7114194631576538, 'learning_rate': 6.867936213036073e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4247/6464 [1:17:06<44:18, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3172, 'grad_norm': 0.6551552414894104, 'learning_rate': 6.864839758476544e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4248/6464 [1:17:07<44:38, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.105, 'grad_norm': 0.687811017036438, 'learning_rate': 6.861743303917015e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4249/6464 [1:17:08<44:10, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2187, 'grad_norm': 0.7892341613769531, 'learning_rate': 6.858646849357486e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4250/6464 [1:17:09<42:35, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9875, 'grad_norm': 0.6900079250335693, 'learning_rate': 6.855550394797958e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4251/6464 [1:17:11<44:10, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3349, 'grad_norm': 0.7468897104263306, 'learning_rate': 6.852453940238427e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4252/6464 [1:17:12<43:25, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0713, 'grad_norm': 0.652729332447052, 'learning_rate': 6.849357485678898e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4253/6464 [1:17:13<46:41, 1.27s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2013, 'grad_norm': 0.5907890796661377, 'learning_rate': 6.846261031119368e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4254/6464 [1:17:14<43:50, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0972, 'grad_norm': 0.6961835622787476, 'learning_rate': 6.84316457655984e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4255/6464 [1:17:15<40:45, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9586, 'grad_norm': 0.7760233283042908, 'learning_rate': 6.84006812200031e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4256/6464 [1:17:16<40:30, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0393, 'grad_norm': 0.681530237197876, 'learning_rate': 6.83697166744078e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4257/6464 [1:17:17<41:07, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2245, 'grad_norm': 0.680797278881073, 'learning_rate': 6.833875212881251e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4258/6464 [1:17:19<45:24, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2637, 'grad_norm': 0.694915771484375, 'learning_rate': 6.830778758321723e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4259/6464 [1:17:20<43:36, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0743, 'grad_norm': 0.678496241569519, 'learning_rate': 6.827682303762192e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4260/6464 [1:17:21<42:44, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1554, 'grad_norm': 0.8749170303344727, 'learning_rate': 6.824585849202663e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4261/6464 [1:17:22<41:06, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2696, 'grad_norm': 0.7820364832878113, 'learning_rate': 6.821489394643133e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4262/6464 [1:17:23<40:21, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0228, 'grad_norm': 0.7524094581604004, 'learning_rate': 6.818392940083604e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4263/6464 [1:17:24<39:43, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3071, 'grad_norm': 0.8737521171569824, 'learning_rate': 6.815296485524076e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4264/6464 [1:17:25<38:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9722, 'grad_norm': 0.8106585741043091, 'learning_rate': 6.812200030964547e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4265/6464 [1:17:26<39:49, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2478, 'grad_norm': 0.65628981590271, 'learning_rate': 6.809103576405016e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4266/6464 [1:17:28<41:54, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.301, 'grad_norm': 0.6911219358444214, 'learning_rate': 6.806007121845486e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4267/6464 [1:17:29<41:26, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3155, 'grad_norm': 0.7540926337242126, 'learning_rate': 6.802910667285957e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4268/6464 [1:17:30<41:01, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1625, 'grad_norm': 0.7211562991142273, 'learning_rate': 6.799814212726428e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4269/6464 [1:17:31<40:37, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9918, 'grad_norm': 0.8227139711380005, 'learning_rate': 6.7967177581669e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4270/6464 [1:17:32<41:28, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2934, 'grad_norm': 0.651165783405304, 'learning_rate': 6.793621303607371e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4271/6464 [1:17:33<43:18, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4299, 'grad_norm': 0.7075299620628357, 'learning_rate': 6.79052484904784e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4272/6464 [1:17:35<44:05, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1924, 'grad_norm': 0.7600015997886658, 'learning_rate': 6.787428394488312e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4273/6464 [1:17:36<43:38, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1662, 'grad_norm': 0.8242434859275818, 'learning_rate': 6.784331939928781e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4274/6464 [1:17:37<42:33, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0015, 'grad_norm': 0.7250365018844604, 'learning_rate': 6.781235485369253e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4275/6464 [1:17:38<42:27, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.026, 'grad_norm': 0.630683422088623, 'learning_rate': 6.778139030809724e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4276/6464 [1:17:39<40:29, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1043, 'grad_norm': 0.7348296642303467, 'learning_rate': 6.775042576250194e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4277/6464 [1:17:40<41:29, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1589, 'grad_norm': 0.7388158440589905, 'learning_rate': 6.771946121690665e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4278/6464 [1:17:41<40:57, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0202, 'grad_norm': 0.6422834992408752, 'learning_rate': 6.768849667131136e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4279/6464 [1:17:43<40:52, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1773, 'grad_norm': 0.7590185403823853, 'learning_rate': 6.765753212571606e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4280/6464 [1:17:44<42:10, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1133, 'grad_norm': 0.7137663960456848, 'learning_rate': 6.762656758012077e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4281/6464 [1:17:45<40:14, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1409, 'grad_norm': 0.7716296911239624, 'learning_rate': 6.759560303452546e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4282/6464 [1:17:46<43:05, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3108, 'grad_norm': 0.8036195635795593, 'learning_rate': 6.756463848893018e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4283/6464 [1:17:47<41:26, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9997, 'grad_norm': 0.6839732527732849, 'learning_rate': 6.753367394333489e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4284/6464 [1:17:48<40:25, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1984, 'grad_norm': 0.7535660266876221, 'learning_rate': 6.75027093977396e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4285/6464 [1:17:49<40:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.219, 'grad_norm': 0.7417524456977844, 'learning_rate': 6.74717448521443e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4286/6464 [1:17:50<38:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2105, 'grad_norm': 0.7861788272857666, 'learning_rate': 6.7440780306549e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4287/6464 [1:17:51<37:49, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.062, 'grad_norm': 0.7664511203765869, 'learning_rate': 6.74098157609537e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4288/6464 [1:17:52<38:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.286, 'grad_norm': 0.7933645844459534, 'learning_rate': 6.737885121535842e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4289/6464 [1:17:54<38:47, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0267, 'grad_norm': 0.6787015199661255, 'learning_rate': 6.734788666976313e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4290/6464 [1:17:55<38:57, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0964, 'grad_norm': 0.6847261786460876, 'learning_rate': 6.731692212416784e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4291/6464 [1:17:56<38:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0812, 'grad_norm': 0.699498176574707, 'learning_rate': 6.728595757857254e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4292/6464 [1:17:57<39:04, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1089, 'grad_norm': 0.7192448377609253, 'learning_rate': 6.725499303297725e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4293/6464 [1:17:58<41:19, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2006, 'grad_norm': 0.6678399443626404, 'learning_rate': 6.722402848738195e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4294/6464 [1:17:59<41:03, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2672, 'grad_norm': 0.6646881699562073, 'learning_rate': 6.719306394178666e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4295/6464 [1:18:00<38:31, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1329, 'grad_norm': 0.7779536247253418, 'learning_rate': 6.716209939619137e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4296/6464 [1:18:01<38:18, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1874, 'grad_norm': 0.7278906106948853, 'learning_rate': 6.713113485059607e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4297/6464 [1:18:02<39:22, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2389, 'grad_norm': 0.6664914488792419, 'learning_rate': 6.710017030500078e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 66%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4298/6464 [1:18:04<42:17, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0991, 'grad_norm': 0.6687950491905212, 'learning_rate': 6.706920575940549e-05, 'epoch': 0.66}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4299/6464 [1:18:05<40:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2936, 'grad_norm': 0.8135910034179688, 'learning_rate': 6.703824121381019e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4300/6464 [1:18:06<40:45, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1273, 'grad_norm': 0.6480403542518616, 'learning_rate': 6.70072766682149e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4301/6464 [1:18:07<38:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8935, 'grad_norm': 0.775567889213562, 'learning_rate': 6.69763121226196e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4302/6464 [1:18:08<37:19, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2297, 'grad_norm': 0.764617383480072, 'learning_rate': 6.694534757702431e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4303/6464 [1:18:09<38:54, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1427, 'grad_norm': 0.6850810647010803, 'learning_rate': 6.691438303142902e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4304/6464 [1:18:10<36:46, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3191, 'grad_norm': 0.8384097218513489, 'learning_rate': 6.688341848583373e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4305/6464 [1:18:11<35:45, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.971, 'grad_norm': 0.6396950483322144, 'learning_rate': 6.685245394023843e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4306/6464 [1:18:12<36:18, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0546, 'grad_norm': 0.8183842897415161, 'learning_rate': 6.682148939464313e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4307/6464 [1:18:13<37:11, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2644, 'grad_norm': 0.7383540868759155, 'learning_rate': 6.679052484904784e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4308/6464 [1:18:14<35:24, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1421, 'grad_norm': 0.8335418105125427, 'learning_rate': 6.675956030345255e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4309/6464 [1:18:15<38:21, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2919, 'grad_norm': 0.8536993861198425, 'learning_rate': 6.672859575785726e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4310/6464 [1:18:16<40:20, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3571, 'grad_norm': 0.7727183699607849, 'learning_rate': 6.669763121226197e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4311/6464 [1:18:17<39:58, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1092, 'grad_norm': 0.6408883333206177, 'learning_rate': 6.666666666666667e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4312/6464 [1:18:18<39:10, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2733, 'grad_norm': 0.7267473340034485, 'learning_rate': 6.663570212107138e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4313/6464 [1:18:19<39:12, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0934, 'grad_norm': 0.6775677800178528, 'learning_rate': 6.660473757547608e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4314/6464 [1:18:21<40:01, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3813, 'grad_norm': 0.6582032442092896, 'learning_rate': 6.657377302988079e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4315/6464 [1:18:22<39:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.309, 'grad_norm': 0.7230265140533447, 'learning_rate': 6.65428084842855e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4316/6464 [1:18:23<39:10, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1047, 'grad_norm': 0.7974644303321838, 'learning_rate': 6.65118439386902e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4317/6464 [1:18:24<39:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9659, 'grad_norm': 0.6170049905776978, 'learning_rate': 6.648087939309491e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4318/6464 [1:18:25<38:06, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1651, 'grad_norm': 0.6754791140556335, 'learning_rate': 6.644991484749962e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4319/6464 [1:18:26<39:21, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2558, 'grad_norm': 0.6941376328468323, 'learning_rate': 6.641895030190432e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4320/6464 [1:18:27<36:33, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0771, 'grad_norm': 0.7889374494552612, 'learning_rate': 6.638798575630903e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4321/6464 [1:18:28<38:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0807, 'grad_norm': 0.5971819162368774, 'learning_rate': 6.635702121071373e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4322/6464 [1:18:29<40:18, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9729, 'grad_norm': 0.6212323307991028, 'learning_rate': 6.632605666511844e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4323/6464 [1:18:31<42:08, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.087, 'grad_norm': 0.5796799063682556, 'learning_rate': 6.629509211952315e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4324/6464 [1:18:32<40:09, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0031, 'grad_norm': 0.7218320369720459, 'learning_rate': 6.626412757392786e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4325/6464 [1:18:33<40:37, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1006, 'grad_norm': 0.7299014329910278, 'learning_rate': 6.623316302833256e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4326/6464 [1:18:34<39:55, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1243, 'grad_norm': 0.7165592908859253, 'learning_rate': 6.620219848273726e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4327/6464 [1:18:35<39:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2178, 'grad_norm': 0.7895726561546326, 'learning_rate': 6.617123393714197e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4328/6464 [1:18:36<36:18, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9755, 'grad_norm': 0.8223104476928711, 'learning_rate': 6.614026939154668e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4329/6464 [1:18:37<36:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0966, 'grad_norm': 0.6612535715103149, 'learning_rate': 6.610930484595139e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4330/6464 [1:18:38<37:43, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0269, 'grad_norm': 0.657299280166626, 'learning_rate': 6.60783403003561e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4331/6464 [1:18:39<38:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1236, 'grad_norm': 0.6094316840171814, 'learning_rate': 6.60473757547608e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4332/6464 [1:18:40<38:01, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2009, 'grad_norm': 0.6972855925559998, 'learning_rate': 6.601641120916551e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4333/6464 [1:18:41<38:22, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.222, 'grad_norm': 0.7623215913772583, 'learning_rate': 6.598544666357021e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4334/6464 [1:18:42<37:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3728, 'grad_norm': 0.8146920800209045, 'learning_rate': 6.595448211797492e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4335/6464 [1:18:43<36:24, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1705, 'grad_norm': 0.7648140788078308, 'learning_rate': 6.592351757237963e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4336/6464 [1:18:44<36:58, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9271, 'grad_norm': 0.6175537109375, 'learning_rate': 6.589255302678433e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4337/6464 [1:18:45<38:44, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1241, 'grad_norm': 0.5691086649894714, 'learning_rate': 6.586158848118904e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4338/6464 [1:18:47<39:33, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1428, 'grad_norm': 0.617836058139801, 'learning_rate': 6.583062393559375e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4339/6464 [1:18:48<39:38, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1497, 'grad_norm': 0.7076998949050903, 'learning_rate': 6.579965938999845e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4340/6464 [1:18:49<37:47, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0694, 'grad_norm': 0.8391029238700867, 'learning_rate': 6.576869484440316e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4341/6464 [1:18:50<36:56, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.961, 'grad_norm': 0.6736079454421997, 'learning_rate': 6.573773029880786e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4342/6464 [1:18:51<36:57, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1767, 'grad_norm': 0.683914840221405, 'learning_rate': 6.570676575321257e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4343/6464 [1:18:52<37:00, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1101, 'grad_norm': 0.6875234246253967, 'learning_rate': 6.567580120761728e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4344/6464 [1:18:53<36:24, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9863, 'grad_norm': 0.7337433695793152, 'learning_rate': 6.5644836662022e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4345/6464 [1:18:54<36:57, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2372, 'grad_norm': 0.7069835662841797, 'learning_rate': 6.56138721164267e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4346/6464 [1:18:55<36:42, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3427, 'grad_norm': 0.8010176420211792, 'learning_rate': 6.558290757083139e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4347/6464 [1:18:56<36:12, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1638, 'grad_norm': 0.7556045651435852, 'learning_rate': 6.55519430252361e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4348/6464 [1:18:57<35:26, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1639, 'grad_norm': 0.7912912368774414, 'learning_rate': 6.552097847964081e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4349/6464 [1:18:58<38:25, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2797, 'grad_norm': 0.7046239972114563, 'learning_rate': 6.549001393404553e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4350/6464 [1:18:59<39:18, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1562, 'grad_norm': 0.8107563257217407, 'learning_rate': 6.545904938845024e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4351/6464 [1:19:00<37:39, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0256, 'grad_norm': 0.7323083281517029, 'learning_rate': 6.542808484285493e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4352/6464 [1:19:01<34:58, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9548, 'grad_norm': 0.7305433750152588, 'learning_rate': 6.539712029725965e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4353/6464 [1:19:02<35:58, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2083, 'grad_norm': 0.7297461628913879, 'learning_rate': 6.536615575166434e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4354/6464 [1:19:03<38:10, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2373, 'grad_norm': 0.6815012693405151, 'learning_rate': 6.533519120606905e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4355/6464 [1:19:05<40:11, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1993, 'grad_norm': 0.6542995572090149, 'learning_rate': 6.530422666047375e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4356/6464 [1:19:06<38:36, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1383, 'grad_norm': 0.7782258987426758, 'learning_rate': 6.527326211487846e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4357/6464 [1:19:07<39:00, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1673, 'grad_norm': 0.688734233379364, 'learning_rate': 6.524229756928318e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4358/6464 [1:19:08<40:33, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3874, 'grad_norm': 0.7628201246261597, 'learning_rate': 6.521133302368789e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4359/6464 [1:19:09<40:13, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2429, 'grad_norm': 0.7373244762420654, 'learning_rate': 6.518036847809258e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4360/6464 [1:19:10<37:24, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9874, 'grad_norm': 0.8282722234725952, 'learning_rate': 6.514940393249728e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4361/6464 [1:19:11<35:59, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9838, 'grad_norm': 0.741828441619873, 'learning_rate': 6.5118439386902e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4362/6464 [1:19:12<36:03, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9447, 'grad_norm': 0.7484219670295715, 'learning_rate': 6.50874748413067e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 67%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4363/6464 [1:19:13<35:13, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0207, 'grad_norm': 0.7716714143753052, 'learning_rate': 6.505651029571142e-05, 'epoch': 0.67}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4364/6464 [1:19:14<33:56, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2169, 'grad_norm': 0.816622793674469, 'learning_rate': 6.502554575011613e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4365/6464 [1:19:15<37:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1708, 'grad_norm': 0.6000677347183228, 'learning_rate': 6.499458120452083e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4366/6464 [1:19:16<38:30, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0974, 'grad_norm': 0.6625084280967712, 'learning_rate': 6.496361665892554e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4367/6464 [1:19:18<39:24, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1467, 'grad_norm': 0.7546884417533875, 'learning_rate': 6.493265211333023e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4368/6464 [1:19:19<40:23, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1937, 'grad_norm': 0.768175482749939, 'learning_rate': 6.490168756773495e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4369/6464 [1:19:20<40:20, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2412, 'grad_norm': 0.7286818027496338, 'learning_rate': 6.487072302213966e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4370/6464 [1:19:21<39:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1136, 'grad_norm': 0.6198294162750244, 'learning_rate': 6.483975847654436e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4371/6464 [1:19:22<37:57, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0476, 'grad_norm': 0.7015122175216675, 'learning_rate': 6.480879393094907e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4372/6464 [1:19:23<38:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4557, 'grad_norm': 0.7904645204544067, 'learning_rate': 6.477782938535378e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4373/6464 [1:19:24<37:29, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1027, 'grad_norm': 0.6238661408424377, 'learning_rate': 6.474686483975848e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4374/6464 [1:19:25<37:13, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1026, 'grad_norm': 0.7413727045059204, 'learning_rate': 6.471590029416319e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4375/6464 [1:19:26<36:22, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1423, 'grad_norm': 0.7917835712432861, 'learning_rate': 6.468493574856788e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4376/6464 [1:19:27<38:10, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2543, 'grad_norm': 0.6198388338088989, 'learning_rate': 6.46539712029726e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4377/6464 [1:19:28<38:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0807, 'grad_norm': 0.7005829811096191, 'learning_rate': 6.462300665737731e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4378/6464 [1:19:29<35:30, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8037, 'grad_norm': 0.752258837223053, 'learning_rate': 6.459204211178202e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4379/6464 [1:19:30<34:43, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9722, 'grad_norm': 0.7590040564537048, 'learning_rate': 6.456107756618672e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4380/6464 [1:19:32<37:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.222, 'grad_norm': 0.692823052406311, 'learning_rate': 6.453011302059141e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4381/6464 [1:19:32<35:21, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0599, 'grad_norm': 0.7146597504615784, 'learning_rate': 6.449914847499613e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4382/6464 [1:19:34<36:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.26, 'grad_norm': 0.7107942700386047, 'learning_rate': 6.446818392940084e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4383/6464 [1:19:35<36:33, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3081, 'grad_norm': 0.8244787454605103, 'learning_rate': 6.443721938380555e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4384/6464 [1:19:36<38:09, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1161, 'grad_norm': 0.6862761974334717, 'learning_rate': 6.440625483821026e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4385/6464 [1:19:37<39:57, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1205, 'grad_norm': 0.5719406604766846, 'learning_rate': 6.437529029261496e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4386/6464 [1:19:38<40:12, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1391, 'grad_norm': 0.6930919885635376, 'learning_rate': 6.434432574701967e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4387/6464 [1:19:39<37:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9874, 'grad_norm': 0.7774243950843811, 'learning_rate': 6.431336120142437e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4388/6464 [1:19:40<39:36, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2776, 'grad_norm': 0.7844297289848328, 'learning_rate': 6.428239665582908e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4389/6464 [1:19:41<37:08, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.075, 'grad_norm': 0.8004273176193237, 'learning_rate': 6.425143211023379e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4390/6464 [1:19:42<37:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3398, 'grad_norm': 0.7968336939811707, 'learning_rate': 6.422046756463849e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4391/6464 [1:19:44<37:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2481, 'grad_norm': 0.7043865919113159, 'learning_rate': 6.41895030190432e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4392/6464 [1:19:45<38:18, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0178, 'grad_norm': 0.6214712262153625, 'learning_rate': 6.415853847344791e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4393/6464 [1:19:46<38:20, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0677, 'grad_norm': 0.6385329961776733, 'learning_rate': 6.412757392785261e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4394/6464 [1:19:47<37:09, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0418, 'grad_norm': 0.7146806120872498, 'learning_rate': 6.409660938225732e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4395/6464 [1:19:48<36:01, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9694, 'grad_norm': 0.674005925655365, 'learning_rate': 6.406564483666202e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4396/6464 [1:19:49<37:59, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1812, 'grad_norm': 0.6523763537406921, 'learning_rate': 6.403468029106673e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4397/6464 [1:19:50<36:47, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9719, 'grad_norm': 0.7920523285865784, 'learning_rate': 6.400371574547144e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4398/6464 [1:19:51<38:32, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2856, 'grad_norm': 0.6828958988189697, 'learning_rate': 6.397275119987615e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4399/6464 [1:19:52<39:01, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3089, 'grad_norm': 0.7290734052658081, 'learning_rate': 6.394178665428085e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4400/6464 [1:19:53<36:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9916, 'grad_norm': 0.7146720290184021, 'learning_rate': 6.391082210868555e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4401/6464 [1:19:55<39:11, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.008, 'grad_norm': 0.6976248025894165, 'learning_rate': 6.387985756309026e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4402/6464 [1:19:56<39:28, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1208, 'grad_norm': 0.6722436547279358, 'learning_rate': 6.384889301749497e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4403/6464 [1:19:57<38:52, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9494, 'grad_norm': 0.5987739562988281, 'learning_rate': 6.381792847189968e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4404/6464 [1:19:58<40:20, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.164, 'grad_norm': 0.6307098865509033, 'learning_rate': 6.378696392630439e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4405/6464 [1:20:00<42:34, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2385, 'grad_norm': 0.7024446129798889, 'learning_rate': 6.375599938070909e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4406/6464 [1:20:00<38:59, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8177, 'grad_norm': 0.7000069618225098, 'learning_rate': 6.37250348351138e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4407/6464 [1:20:01<36:41, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9968, 'grad_norm': 0.752901017665863, 'learning_rate': 6.36940702895185e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4408/6464 [1:20:02<36:56, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1158, 'grad_norm': 0.6716203689575195, 'learning_rate': 6.366310574392321e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4409/6464 [1:20:03<34:58, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.004, 'grad_norm': 0.722735583782196, 'learning_rate': 6.363214119832792e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4410/6464 [1:20:04<35:48, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0323, 'grad_norm': 0.6302947402000427, 'learning_rate': 6.360117665273262e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4411/6464 [1:20:06<39:11, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3604, 'grad_norm': 0.6397945284843445, 'learning_rate': 6.357021210713733e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4412/6464 [1:20:07<36:42, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0041, 'grad_norm': 0.7175886034965515, 'learning_rate': 6.353924756154204e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4413/6464 [1:20:08<35:40, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0904, 'grad_norm': 0.8864008188247681, 'learning_rate': 6.350828301594674e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4414/6464 [1:20:09<37:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2697, 'grad_norm': 0.6434213519096375, 'learning_rate': 6.347731847035145e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4415/6464 [1:20:10<38:01, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0319, 'grad_norm': 0.6088763475418091, 'learning_rate': 6.344635392475615e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4416/6464 [1:20:11<38:54, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3679, 'grad_norm': 0.8473566770553589, 'learning_rate': 6.341538937916086e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4417/6464 [1:20:12<37:31, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8894, 'grad_norm': 0.637702465057373, 'learning_rate': 6.338442483356557e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4418/6464 [1:20:13<36:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2781, 'grad_norm': 0.9372014403343201, 'learning_rate': 6.335346028797028e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4419/6464 [1:20:14<35:44, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9819, 'grad_norm': 0.7370145916938782, 'learning_rate': 6.332249574237498e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4420/6464 [1:20:15<35:48, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0121, 'grad_norm': 0.704261302947998, 'learning_rate': 6.329153119677968e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4421/6464 [1:20:16<36:12, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0275, 'grad_norm': 0.665095329284668, 'learning_rate': 6.326056665118439e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4422/6464 [1:20:18<36:11, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2796, 'grad_norm': 0.7451876401901245, 'learning_rate': 6.32296021055891e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4423/6464 [1:20:19<40:29, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1706, 'grad_norm': 0.719307005405426, 'learning_rate': 6.319863755999381e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4424/6464 [1:20:20<40:38, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.241, 'grad_norm': 0.7131220102310181, 'learning_rate': 6.316767301439852e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4425/6464 [1:20:21<40:20, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0016, 'grad_norm': 0.7253925204277039, 'learning_rate': 6.313670846880322e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4426/6464 [1:20:22<39:26, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8967, 'grad_norm': 0.6047251224517822, 'learning_rate': 6.310574392320793e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 68%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4427/6464 [1:20:24<40:29, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1903, 'grad_norm': 0.6345059275627136, 'learning_rate': 6.307477937761263e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4428/6464 [1:20:25<37:56, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0709, 'grad_norm': 0.8402281999588013, 'learning_rate': 6.304381483201734e-05, 'epoch': 0.68}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4429/6464 [1:20:26<36:37, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.991, 'grad_norm': 0.6935880184173584, 'learning_rate': 6.301285028642205e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4430/6464 [1:20:27<38:18, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3992, 'grad_norm': 0.7950253486633301, 'learning_rate': 6.298188574082675e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4431/6464 [1:20:28<37:09, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2491, 'grad_norm': 0.9029342532157898, 'learning_rate': 6.295092119523146e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4432/6464 [1:20:29<36:39, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1028, 'grad_norm': 0.6590219140052795, 'learning_rate': 6.291995664963617e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4433/6464 [1:20:30<36:08, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.111, 'grad_norm': 0.7131263613700867, 'learning_rate': 6.288899210404087e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4434/6464 [1:20:31<37:41, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.007, 'grad_norm': 0.5728005766868591, 'learning_rate': 6.285802755844558e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4435/6464 [1:20:32<36:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0871, 'grad_norm': 0.6955826282501221, 'learning_rate': 6.282706301285028e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4436/6464 [1:20:33<38:11, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9635, 'grad_norm': 0.606924295425415, 'learning_rate': 6.279609846725499e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4437/6464 [1:20:35<37:41, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1993, 'grad_norm': 0.7362135052680969, 'learning_rate': 6.27651339216597e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4438/6464 [1:20:36<36:21, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1445, 'grad_norm': 0.672035813331604, 'learning_rate': 6.273416937606442e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4439/6464 [1:20:37<37:57, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.144, 'grad_norm': 0.663261353969574, 'learning_rate': 6.270320483046911e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4440/6464 [1:20:38<35:43, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9801, 'grad_norm': 0.7508540153503418, 'learning_rate': 6.267224028487381e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4441/6464 [1:20:39<36:31, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2771, 'grad_norm': 0.7718571424484253, 'learning_rate': 6.264127573927852e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4442/6464 [1:20:40<37:07, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2197, 'grad_norm': 0.6946338415145874, 'learning_rate': 6.261031119368323e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 4443/6464 [1:20:41<36:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1203, 'grad_norm': 0.7772273421287537, 'learning_rate': 6.257934664808795e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4444/6464 [1:20:42<36:58, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0691, 'grad_norm': 0.6170323491096497, 'learning_rate': 6.254838210249266e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4445/6464 [1:20:43<36:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.956, 'grad_norm': 0.6494638323783875, 'learning_rate': 6.251741755689735e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4446/6464 [1:20:44<35:07, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.065, 'grad_norm': 0.6826521754264832, 'learning_rate': 6.248645301130207e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4447/6464 [1:20:45<34:54, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3927, 'grad_norm': 0.8269832730293274, 'learning_rate': 6.245548846570676e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4448/6464 [1:20:46<34:59, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3181, 'grad_norm': 0.7338500618934631, 'learning_rate': 6.242452392011148e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4449/6464 [1:20:47<34:16, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1475, 'grad_norm': 0.7984404563903809, 'learning_rate': 6.239355937451619e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4450/6464 [1:20:48<34:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0623, 'grad_norm': 0.7145828008651733, 'learning_rate': 6.236259482892088e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4451/6464 [1:20:49<33:29, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9364, 'grad_norm': 0.708124041557312, 'learning_rate': 6.23316302833256e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4452/6464 [1:20:50<32:26, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0126, 'grad_norm': 0.7272071242332458, 'learning_rate': 6.230066573773031e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4453/6464 [1:20:51<31:54, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2562, 'grad_norm': 0.8432551026344299, 'learning_rate': 6.2269701192135e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4454/6464 [1:20:52<32:45, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.34, 'grad_norm': 0.723008930683136, 'learning_rate': 6.223873664653972e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4455/6464 [1:20:53<35:31, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0938, 'grad_norm': 0.5677486658096313, 'learning_rate': 6.220777210094441e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4456/6464 [1:20:54<35:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.232, 'grad_norm': 0.6979559659957886, 'learning_rate': 6.217680755534913e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4457/6464 [1:20:56<37:42, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1019, 'grad_norm': 0.632128119468689, 'learning_rate': 6.214584300975384e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4458/6464 [1:20:57<37:09, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0583, 'grad_norm': 0.7276101112365723, 'learning_rate': 6.211487846415855e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4459/6464 [1:20:58<37:30, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1862, 'grad_norm': 0.709690272808075, 'learning_rate': 6.208391391856325e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4460/6464 [1:20:59<39:24, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0906, 'grad_norm': 0.6550247073173523, 'learning_rate': 6.205294937296794e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4461/6464 [1:21:00<40:08, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2158, 'grad_norm': 0.66325443983078, 'learning_rate': 6.202198482737265e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4462/6464 [1:21:01<37:31, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9683, 'grad_norm': 0.7321664690971375, 'learning_rate': 6.199102028177737e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4463/6464 [1:21:02<36:05, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0872, 'grad_norm': 0.8189502358436584, 'learning_rate': 6.196005573618208e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4464/6464 [1:21:04<37:32, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2072, 'grad_norm': 0.6942266225814819, 'learning_rate': 6.192909119058679e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4465/6464 [1:21:05<37:42, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2855, 'grad_norm': 0.7278610467910767, 'learning_rate': 6.189812664499149e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4466/6464 [1:21:06<35:51, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2408, 'grad_norm': 0.7758334279060364, 'learning_rate': 6.18671620993962e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4467/6464 [1:21:07<39:14, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4219, 'grad_norm': 0.6598085165023804, 'learning_rate': 6.18361975538009e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4468/6464 [1:21:08<37:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2665, 'grad_norm': 0.7626409530639648, 'learning_rate': 6.180523300820561e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4469/6464 [1:21:09<37:41, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3299, 'grad_norm': 0.7794030904769897, 'learning_rate': 6.177426846261032e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4470/6464 [1:21:11<39:05, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.176, 'grad_norm': 0.7137304544448853, 'learning_rate': 6.174330391701502e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4471/6464 [1:21:12<38:08, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9759, 'grad_norm': 0.6544321775436401, 'learning_rate': 6.171233937141973e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4472/6464 [1:21:13<37:31, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9715, 'grad_norm': 0.6837494969367981, 'learning_rate': 6.168137482582444e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4473/6464 [1:21:14<35:58, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9526, 'grad_norm': 0.737534761428833, 'learning_rate': 6.165041028022914e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4474/6464 [1:21:15<35:11, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2254, 'grad_norm': 0.7997993230819702, 'learning_rate': 6.161944573463385e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4475/6464 [1:21:16<34:18, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0334, 'grad_norm': 0.8160169720649719, 'learning_rate': 6.158848118903855e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4476/6464 [1:21:17<33:59, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1394, 'grad_norm': 0.7378355860710144, 'learning_rate': 6.155751664344326e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4477/6464 [1:21:18<34:21, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2662, 'grad_norm': 0.8025252819061279, 'learning_rate': 6.152655209784797e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4478/6464 [1:21:19<35:22, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9928, 'grad_norm': 0.6678715944290161, 'learning_rate': 6.149558755225268e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4479/6464 [1:21:20<34:47, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2021, 'grad_norm': 0.7432523369789124, 'learning_rate': 6.146462300665738e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4480/6464 [1:21:21<35:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9162, 'grad_norm': 0.6353894472122192, 'learning_rate': 6.143365846106208e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4481/6464 [1:21:22<36:34, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2173, 'grad_norm': 0.6818574666976929, 'learning_rate': 6.140269391546679e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4482/6464 [1:21:23<36:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3355, 'grad_norm': 0.8067302703857422, 'learning_rate': 6.13717293698715e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4483/6464 [1:21:24<37:04, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.098, 'grad_norm': 0.6276475191116333, 'learning_rate': 6.134076482427621e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4484/6464 [1:21:25<35:35, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1904, 'grad_norm': 0.9274476766586304, 'learning_rate': 6.130980027868092e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4485/6464 [1:21:26<35:37, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1066, 'grad_norm': 0.7136247158050537, 'learning_rate': 6.127883573308562e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4486/6464 [1:21:28<35:54, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1634, 'grad_norm': 0.7143463492393494, 'learning_rate': 6.124787118749033e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4487/6464 [1:21:29<34:54, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1655, 'grad_norm': 0.7025122046470642, 'learning_rate': 6.121690664189503e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4488/6464 [1:21:30<35:47, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0695, 'grad_norm': 0.7007858157157898, 'learning_rate': 6.118594209629974e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4489/6464 [1:21:31<37:56, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2695, 'grad_norm': 0.6786547303199768, 'learning_rate': 6.115497755070445e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4490/6464 [1:21:32<36:53, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1832, 'grad_norm': 0.7367172241210938, 'learning_rate': 6.112401300510915e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4491/6464 [1:21:33<38:33, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1002, 'grad_norm': 0.6263959407806396, 'learning_rate': 6.109304845951386e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 69%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4492/6464 [1:21:34<37:47, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0679, 'grad_norm': 0.7101587653160095, 'learning_rate': 6.106208391391857e-05, 'epoch': 0.69}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4493/6464 [1:21:35<36:17, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1044, 'grad_norm': 0.7032427191734314, 'learning_rate': 6.1031119368323276e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4494/6464 [1:21:36<35:00, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.046, 'grad_norm': 0.7011876702308655, 'learning_rate': 6.100015482272799e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4495/6464 [1:21:38<37:12, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2607, 'grad_norm': 0.6861882209777832, 'learning_rate': 6.096919027713268e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4496/6464 [1:21:39<36:48, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2068, 'grad_norm': 0.6932650804519653, 'learning_rate': 6.093822573153739e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4497/6464 [1:21:40<36:43, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1613, 'grad_norm': 0.714250385761261, 'learning_rate': 6.09072611859421e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4498/6464 [1:21:41<36:44, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0236, 'grad_norm': 0.7228854298591614, 'learning_rate': 6.0876296640346806e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4499/6464 [1:21:42<35:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0176, 'grad_norm': 0.7683702707290649, 'learning_rate': 6.084533209475152e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4500/6464 [1:21:43<33:59, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1501, 'grad_norm': 0.843254566192627, 'learning_rate': 6.0814367549156215e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/other.py:619: UserWarning: Unable to fetch remote file due to the following error (ReadTimeoutError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)\"), '(Request ID: 2ff9e460-184b-41c9-85e3-908c146835a4)') - silently ignoring the lookup for the file config.json in Magpie-Align/MagpieLM-4B-Chat-v0.1.\n", " warnings.warn(\n", "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/save_and_load.py:218: UserWarning: Could not find a config file in Magpie-Align/MagpieLM-4B-Chat-v0.1 - will assume that the vocabulary was not modified.\n", " warnings.warn(\n", " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4501/6464 [1:21:54<2:15:47, 4.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2507, 'grad_norm': 0.7712644338607788, 'learning_rate': 6.0783403003560926e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4502/6464 [1:21:55<1:43:32, 3.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.966, 'grad_norm': 0.8041490316390991, 'learning_rate': 6.075243845796563e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4503/6464 [1:21:56<1:23:37, 2.56s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.957, 'grad_norm': 0.7054910659790039, 'learning_rate': 6.072147391237034e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4504/6464 [1:21:57<1:08:01, 2.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2016, 'grad_norm': 0.9477333426475525, 'learning_rate': 6.0690509366775053e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4505/6464 [1:21:58<58:11, 1.78s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0564, 'grad_norm': 0.7196264266967773, 'learning_rate': 6.065954482117975e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4506/6464 [1:22:00<53:35, 1.64s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1866, 'grad_norm': 0.6317177414894104, 'learning_rate': 6.0628580275584456e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4507/6464 [1:22:01<47:30, 1.46s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.884, 'grad_norm': 0.6449068784713745, 'learning_rate': 6.059761572998917e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4508/6464 [1:22:02<44:45, 1.37s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1122, 'grad_norm': 0.6240707039833069, 'learning_rate': 6.056665118439387e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4509/6464 [1:22:03<42:51, 1.32s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3986, 'grad_norm': 0.7169924974441528, 'learning_rate': 6.053568663879858e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4510/6464 [1:22:04<38:01, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8449, 'grad_norm': 0.7088481783866882, 'learning_rate': 6.050472209320328e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4511/6464 [1:22:05<34:41, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.148, 'grad_norm': 0.9067846536636353, 'learning_rate': 6.047375754760799e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4512/6464 [1:22:06<34:22, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2196, 'grad_norm': 0.7703447937965393, 'learning_rate': 6.04427930020127e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4513/6464 [1:22:07<36:17, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2725, 'grad_norm': 0.7303062081336975, 'learning_rate': 6.041182845641741e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4514/6464 [1:22:08<34:31, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0827, 'grad_norm': 0.8436765074729919, 'learning_rate': 6.038086391082212e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4515/6464 [1:22:09<35:52, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3432, 'grad_norm': 0.6802632808685303, 'learning_rate': 6.034989936522682e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4516/6464 [1:22:10<33:43, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9677, 'grad_norm': 0.6883114576339722, 'learning_rate': 6.031893481963152e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4517/6464 [1:22:11<36:01, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1828, 'grad_norm': 0.6370490789413452, 'learning_rate': 6.028797027403623e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4518/6464 [1:22:12<33:13, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9534, 'grad_norm': 0.8082057237625122, 'learning_rate': 6.025700572844094e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4519/6464 [1:22:13<33:21, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2311, 'grad_norm': 0.7626603841781616, 'learning_rate': 6.022604118284565e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4520/6464 [1:22:14<33:41, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2053, 'grad_norm': 0.761734664440155, 'learning_rate': 6.019507663725035e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4521/6464 [1:22:15<34:03, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1397, 'grad_norm': 0.6843803524971008, 'learning_rate': 6.016411209165506e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4522/6464 [1:22:16<33:20, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1387, 'grad_norm': 0.7988113164901733, 'learning_rate': 6.013314754605976e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4523/6464 [1:22:18<35:05, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1338, 'grad_norm': 0.7506789565086365, 'learning_rate': 6.0102183000464474e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 4524/6464 [1:22:19<35:19, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2924, 'grad_norm': 0.7559390664100647, 'learning_rate': 6.0071218454869186e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4525/6464 [1:22:20<33:13, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1056, 'grad_norm': 0.7869114875793457, 'learning_rate': 6.0040253909273884e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4526/6464 [1:22:21<36:41, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2414, 'grad_norm': 0.644767165184021, 'learning_rate': 6.000928936367859e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4527/6464 [1:22:22<35:47, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0046, 'grad_norm': 0.682144045829773, 'learning_rate': 5.99783248180833e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4528/6464 [1:22:23<33:56, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7684, 'grad_norm': 0.6663230061531067, 'learning_rate': 5.9947360272488004e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4529/6464 [1:22:24<32:18, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9419, 'grad_norm': 0.6711874008178711, 'learning_rate': 5.9916395726892715e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4530/6464 [1:22:25<32:53, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0375, 'grad_norm': 0.6436053514480591, 'learning_rate': 5.988543118129741e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4531/6464 [1:22:26<31:55, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1483, 'grad_norm': 0.7706899046897888, 'learning_rate': 5.9854466635702125e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4532/6464 [1:22:27<32:56, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1445, 'grad_norm': 0.7496808767318726, 'learning_rate': 5.982350209010683e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4533/6464 [1:22:28<36:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9812, 'grad_norm': 0.5464591383934021, 'learning_rate': 5.979253754451154e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4534/6464 [1:22:29<35:43, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2451, 'grad_norm': 0.797547459602356, 'learning_rate': 5.976157299891625e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4535/6464 [1:22:30<34:15, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0512, 'grad_norm': 0.7139543294906616, 'learning_rate': 5.973060845332095e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4536/6464 [1:22:31<33:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0722, 'grad_norm': 0.7200537919998169, 'learning_rate': 5.9699643907725654e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4537/6464 [1:22:32<34:04, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.176, 'grad_norm': 0.6854909062385559, 'learning_rate': 5.9668679362130366e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4538/6464 [1:22:34<34:38, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0659, 'grad_norm': 0.737964391708374, 'learning_rate': 5.963771481653507e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4539/6464 [1:22:35<33:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.061, 'grad_norm': 0.7237285375595093, 'learning_rate': 5.960675027093978e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4540/6464 [1:22:36<33:39, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9441, 'grad_norm': 0.6511138677597046, 'learning_rate': 5.957578572534448e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4541/6464 [1:22:37<34:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1665, 'grad_norm': 0.7484695911407471, 'learning_rate': 5.954482117974919e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4542/6464 [1:22:38<34:50, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.191, 'grad_norm': 0.7349349856376648, 'learning_rate': 5.9513856634153895e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4543/6464 [1:22:39<34:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2161, 'grad_norm': 0.6830019950866699, 'learning_rate': 5.948289208855861e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4544/6464 [1:22:40<34:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3506, 'grad_norm': 0.7525566816329956, 'learning_rate': 5.945192754296332e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4545/6464 [1:22:41<37:28, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0843, 'grad_norm': 0.7155686616897583, 'learning_rate': 5.9420962997368016e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4546/6464 [1:22:43<38:31, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2224, 'grad_norm': 0.6426213383674622, 'learning_rate': 5.938999845177272e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4547/6464 [1:22:44<40:10, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.926, 'grad_norm': 0.614393413066864, 'learning_rate': 5.935903390617743e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4548/6464 [1:22:45<40:16, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2503, 'grad_norm': 0.6364418864250183, 'learning_rate': 5.9328069360582136e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4549/6464 [1:22:46<38:36, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1839, 'grad_norm': 0.690284788608551, 'learning_rate': 5.929710481498685e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4550/6464 [1:22:47<37:02, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1612, 'grad_norm': 0.7580654621124268, 'learning_rate': 5.9266140269391545e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4551/6464 [1:22:48<35:11, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1051, 'grad_norm': 0.8566319346427917, 'learning_rate': 5.923517572379626e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4552/6464 [1:22:49<34:42, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1947, 'grad_norm': 0.7548568844795227, 'learning_rate': 5.920421117820096e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4553/6464 [1:22:50<33:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9227, 'grad_norm': 0.7571226358413696, 'learning_rate': 5.917324663260567e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4554/6464 [1:22:51<32:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2099, 'grad_norm': 0.7375727295875549, 'learning_rate': 5.9142282087010384e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4555/6464 [1:22:53<34:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2432, 'grad_norm': 0.7440115213394165, 'learning_rate': 5.911131754141508e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4556/6464 [1:22:54<33:03, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9659, 'grad_norm': 0.77470463514328, 'learning_rate': 5.9080352995819786e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 70%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4557/6464 [1:22:55<34:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4716, 'grad_norm': 0.8413599133491516, 'learning_rate': 5.90493884502245e-05, 'epoch': 0.7}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4558/6464 [1:22:56<38:21, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4859, 'grad_norm': 0.704659640789032, 'learning_rate': 5.90184239046292e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4559/6464 [1:22:57<38:16, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1046, 'grad_norm': 0.8055444359779358, 'learning_rate': 5.8987459359033914e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4560/6464 [1:22:58<36:24, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1774, 'grad_norm': 0.7644432187080383, 'learning_rate': 5.895649481343861e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4561/6464 [1:22:59<35:04, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2192, 'grad_norm': 0.8238391876220703, 'learning_rate': 5.892553026784332e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4562/6464 [1:23:00<34:07, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1689, 'grad_norm': 0.753848671913147, 'learning_rate': 5.889456572224803e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4563/6464 [1:23:02<34:59, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1708, 'grad_norm': 0.6969931125640869, 'learning_rate': 5.886360117665274e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4564/6464 [1:23:03<34:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2138, 'grad_norm': 0.6309646368026733, 'learning_rate': 5.883263663105745e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4565/6464 [1:23:04<32:50, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0063, 'grad_norm': 0.7660656571388245, 'learning_rate': 5.880167208546215e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4566/6464 [1:23:05<33:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9524, 'grad_norm': 0.6264710426330566, 'learning_rate': 5.877070753986685e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4567/6464 [1:23:06<36:52, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3342, 'grad_norm': 0.6779049038887024, 'learning_rate': 5.8739742994271564e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4568/6464 [1:23:07<36:39, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1432, 'grad_norm': 0.6686618328094482, 'learning_rate': 5.870877844867627e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4569/6464 [1:23:08<36:42, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1028, 'grad_norm': 0.6993030309677124, 'learning_rate': 5.867781390308098e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4570/6464 [1:23:10<36:57, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8438, 'grad_norm': 0.5791705250740051, 'learning_rate': 5.864684935748568e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4571/6464 [1:23:11<36:39, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0323, 'grad_norm': 0.6645909547805786, 'learning_rate': 5.861588481189039e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4572/6464 [1:23:12<35:53, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0399, 'grad_norm': 0.7041729688644409, 'learning_rate': 5.8584920266295094e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4573/6464 [1:23:13<35:41, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1169, 'grad_norm': 0.7035876512527466, 'learning_rate': 5.8553955720699805e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4574/6464 [1:23:14<34:25, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0715, 'grad_norm': 0.8979038596153259, 'learning_rate': 5.8522991175104516e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4575/6464 [1:23:15<34:49, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1918, 'grad_norm': 0.8248112797737122, 'learning_rate': 5.8492026629509214e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4576/6464 [1:23:16<35:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0259, 'grad_norm': 0.6466636657714844, 'learning_rate': 5.846106208391392e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4577/6464 [1:23:17<33:08, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1215, 'grad_norm': 0.7965354919433594, 'learning_rate': 5.843009753831863e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4578/6464 [1:23:18<34:07, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0948, 'grad_norm': 0.6727802753448486, 'learning_rate': 5.8399132992723335e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4579/6464 [1:23:20<35:49, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1611, 'grad_norm': 0.6265578269958496, 'learning_rate': 5.8368168447128046e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4580/6464 [1:23:21<34:59, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0582, 'grad_norm': 0.8081852197647095, 'learning_rate': 5.8337203901532744e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4581/6464 [1:23:22<35:17, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0785, 'grad_norm': 0.8619365096092224, 'learning_rate': 5.8306239355937455e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4582/6464 [1:23:23<34:36, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1768, 'grad_norm': 0.719028890132904, 'learning_rate': 5.827527481034216e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4583/6464 [1:23:24<36:17, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9492, 'grad_norm': 0.6032950282096863, 'learning_rate': 5.824431026474687e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4584/6464 [1:23:25<34:45, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0585, 'grad_norm': 0.7275246977806091, 'learning_rate': 5.821334571915158e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4585/6464 [1:23:26<35:36, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0122, 'grad_norm': 0.7260849475860596, 'learning_rate': 5.818238117355628e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4586/6464 [1:23:28<36:57, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2423, 'grad_norm': 0.7464172840118408, 'learning_rate': 5.8151416627960985e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4587/6464 [1:23:29<33:36, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.903, 'grad_norm': 0.883543074131012, 'learning_rate': 5.8120452082365696e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4588/6464 [1:23:29<32:46, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1481, 'grad_norm': 0.6916913390159607, 'learning_rate': 5.80894875367704e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4589/6464 [1:23:31<33:34, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0486, 'grad_norm': 0.6309731006622314, 'learning_rate': 5.805852299117511e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4590/6464 [1:23:32<32:40, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0327, 'grad_norm': 0.7344405651092529, 'learning_rate': 5.802755844557981e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4591/6464 [1:23:32<30:36, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8214, 'grad_norm': 0.6744582056999207, 'learning_rate': 5.799659389998452e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4592/6464 [1:23:33<30:34, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0283, 'grad_norm': 0.71243816614151, 'learning_rate': 5.7965629354389226e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4593/6464 [1:23:35<35:15, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3793, 'grad_norm': 0.6606463193893433, 'learning_rate': 5.793466480879394e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4594/6464 [1:23:36<32:53, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2041, 'grad_norm': 0.8382558226585388, 'learning_rate': 5.790370026319865e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4595/6464 [1:23:37<35:54, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2886, 'grad_norm': 0.7098792195320129, 'learning_rate': 5.7872735717603346e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4596/6464 [1:23:38<34:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9419, 'grad_norm': 0.7023968696594238, 'learning_rate': 5.784177117200805e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4597/6464 [1:23:39<34:25, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1783, 'grad_norm': 0.6337980628013611, 'learning_rate': 5.781080662641276e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4598/6464 [1:23:41<36:42, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.095, 'grad_norm': 0.6090385913848877, 'learning_rate': 5.777984208081747e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4599/6464 [1:23:42<34:50, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.885, 'grad_norm': 0.7186486721038818, 'learning_rate': 5.774887753522218e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4600/6464 [1:23:42<32:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9593, 'grad_norm': 0.797261118888855, 'learning_rate': 5.7717912989626876e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4601/6464 [1:23:44<33:50, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2069, 'grad_norm': 0.6371098756790161, 'learning_rate': 5.768694844403159e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4602/6464 [1:23:45<32:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0457, 'grad_norm': 0.668947696685791, 'learning_rate': 5.765598389843629e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4603/6464 [1:23:46<32:52, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1392, 'grad_norm': 0.7172403931617737, 'learning_rate': 5.7625019352841e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4604/6464 [1:23:47<31:23, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1126, 'grad_norm': 0.8759083151817322, 'learning_rate': 5.75940548072457e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 4605/6464 [1:23:48<34:19, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1276, 'grad_norm': 0.6634164452552795, 'learning_rate': 5.756309026165041e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4606/6464 [1:23:49<35:02, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2478, 'grad_norm': 0.7921195030212402, 'learning_rate': 5.753212571605512e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4607/6464 [1:23:50<35:12, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1153, 'grad_norm': 0.6593407988548279, 'learning_rate': 5.750116117045983e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4608/6464 [1:23:51<35:20, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4048, 'grad_norm': 0.7234311699867249, 'learning_rate': 5.747019662486453e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4609/6464 [1:23:53<36:16, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4621, 'grad_norm': 0.7558901906013489, 'learning_rate': 5.743923207926923e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4610/6464 [1:23:54<36:45, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1861, 'grad_norm': 0.6332911252975464, 'learning_rate': 5.740826753367394e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4611/6464 [1:23:55<33:26, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9258, 'grad_norm': 0.7439612150192261, 'learning_rate': 5.7377302988078654e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4612/6464 [1:23:56<32:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1145, 'grad_norm': 0.802627444267273, 'learning_rate': 5.734633844248336e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4613/6464 [1:23:57<33:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9137, 'grad_norm': 0.6633151173591614, 'learning_rate': 5.731537389688807e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4614/6464 [1:23:58<32:07, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1419, 'grad_norm': 0.9263350963592529, 'learning_rate': 5.728440935129277e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4615/6464 [1:23:59<32:24, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.142, 'grad_norm': 0.6790632009506226, 'learning_rate': 5.725344480569748e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4616/6464 [1:24:00<32:09, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1175, 'grad_norm': 0.7007392644882202, 'learning_rate': 5.722248026010218e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4617/6464 [1:24:01<33:52, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.513, 'grad_norm': 0.7869411110877991, 'learning_rate': 5.7191515714506895e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4618/6464 [1:24:02<32:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1805, 'grad_norm': 0.7443923950195312, 'learning_rate': 5.71605511689116e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4619/6464 [1:24:03<30:51, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9302, 'grad_norm': 0.711764931678772, 'learning_rate': 5.71295866233163e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4620/6464 [1:24:04<32:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3864, 'grad_norm': 0.7203113436698914, 'learning_rate': 5.709862207772101e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 71%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4621/6464 [1:24:05<31:58, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1878, 'grad_norm': 0.9981034398078918, 'learning_rate': 5.706765753212572e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4622/6464 [1:24:06<31:54, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2599, 'grad_norm': 0.7233709096908569, 'learning_rate': 5.7036692986530424e-05, 'epoch': 0.71}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4623/6464 [1:24:07<32:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0558, 'grad_norm': 0.663873553276062, 'learning_rate': 5.7005728440935136e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4624/6464 [1:24:09<35:47, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2222, 'grad_norm': 0.6069968342781067, 'learning_rate': 5.6974763895339833e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4625/6464 [1:24:10<33:41, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9889, 'grad_norm': 0.9736827611923218, 'learning_rate': 5.6943799349744545e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4626/6464 [1:24:11<35:29, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.15, 'grad_norm': 0.6450456380844116, 'learning_rate': 5.691283480414925e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4627/6464 [1:24:12<34:05, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0528, 'grad_norm': 0.7843915224075317, 'learning_rate': 5.688187025855396e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4628/6464 [1:24:13<32:05, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2853, 'grad_norm': 1.0121536254882812, 'learning_rate': 5.6850905712958665e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4629/6464 [1:24:14<31:51, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2055, 'grad_norm': 0.754989743232727, 'learning_rate': 5.681994116736336e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4630/6464 [1:24:15<30:53, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.014, 'grad_norm': 0.6654069423675537, 'learning_rate': 5.6788976621768074e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4631/6464 [1:24:16<31:26, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0524, 'grad_norm': 0.6681168675422668, 'learning_rate': 5.6758012076172786e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4632/6464 [1:24:17<30:31, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1483, 'grad_norm': 0.7483282089233398, 'learning_rate': 5.672704753057749e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4633/6464 [1:24:18<29:07, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.036, 'grad_norm': 0.7724868655204773, 'learning_rate': 5.66960829849822e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4634/6464 [1:24:19<29:03, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1245, 'grad_norm': 0.7806848287582397, 'learning_rate': 5.66651184393869e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4635/6464 [1:24:20<30:19, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9722, 'grad_norm': 0.651648759841919, 'learning_rate': 5.663415389379161e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4636/6464 [1:24:21<31:19, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2922, 'grad_norm': 0.6901082396507263, 'learning_rate': 5.6603189348196315e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4637/6464 [1:24:22<32:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3645, 'grad_norm': 0.7861316204071045, 'learning_rate': 5.657222480260103e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4638/6464 [1:24:23<33:15, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2779, 'grad_norm': 0.7586246132850647, 'learning_rate': 5.654126025700574e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4639/6464 [1:24:24<33:10, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0944, 'grad_norm': 0.6652129292488098, 'learning_rate': 5.651029571141043e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4640/6464 [1:24:25<32:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1663, 'grad_norm': 0.884606659412384, 'learning_rate': 5.647933116581514e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4641/6464 [1:24:26<33:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2586, 'grad_norm': 0.7430076599121094, 'learning_rate': 5.644836662021985e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4642/6464 [1:24:27<32:51, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0308, 'grad_norm': 0.6737122535705566, 'learning_rate': 5.6417402074624556e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4643/6464 [1:24:28<31:11, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8404, 'grad_norm': 0.6552342772483826, 'learning_rate': 5.638643752902927e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4644/6464 [1:24:30<35:33, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1285, 'grad_norm': 0.7362737059593201, 'learning_rate': 5.6355472983433966e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4645/6464 [1:24:31<34:26, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9768, 'grad_norm': 0.7007060050964355, 'learning_rate': 5.632450843783868e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4646/6464 [1:24:32<34:35, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.041, 'grad_norm': 0.6763813495635986, 'learning_rate': 5.629354389224338e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4647/6464 [1:24:33<35:19, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9464, 'grad_norm': 0.7061051726341248, 'learning_rate': 5.626257934664809e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4648/6464 [1:24:34<33:34, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9641, 'grad_norm': 0.7998954057693481, 'learning_rate': 5.6231614801052804e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4649/6464 [1:24:35<32:12, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9766, 'grad_norm': 0.6887756586074829, 'learning_rate': 5.62006502554575e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4650/6464 [1:24:36<32:07, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.254, 'grad_norm': 0.7775264382362366, 'learning_rate': 5.616968570986221e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4651/6464 [1:24:37<31:56, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8627, 'grad_norm': 0.67307049036026, 'learning_rate': 5.613872116426692e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4652/6464 [1:24:39<34:00, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0631, 'grad_norm': 0.6413224935531616, 'learning_rate': 5.610775661867162e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4653/6464 [1:24:40<33:57, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2129, 'grad_norm': 0.7777941823005676, 'learning_rate': 5.6076792073076334e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4654/6464 [1:24:41<35:19, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3143, 'grad_norm': 0.6975314021110535, 'learning_rate': 5.604582752748103e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4655/6464 [1:24:42<33:29, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0587, 'grad_norm': 0.7638260722160339, 'learning_rate': 5.601486298188574e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4656/6464 [1:24:43<34:22, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2637, 'grad_norm': 0.7215933203697205, 'learning_rate': 5.598389843629045e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4657/6464 [1:24:44<33:03, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1581, 'grad_norm': 0.7899294495582581, 'learning_rate': 5.595293389069516e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4658/6464 [1:24:45<34:28, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2636, 'grad_norm': 0.6909703612327576, 'learning_rate': 5.592196934509987e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4659/6464 [1:24:47<34:40, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9078, 'grad_norm': 0.6496864557266235, 'learning_rate': 5.589100479950457e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4660/6464 [1:24:48<34:22, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1918, 'grad_norm': 0.6659600734710693, 'learning_rate': 5.586004025390927e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4661/6464 [1:24:49<33:47, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9271, 'grad_norm': 0.6040012836456299, 'learning_rate': 5.5829075708313984e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4662/6464 [1:24:50<32:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0778, 'grad_norm': 0.7161785364151001, 'learning_rate': 5.579811116271869e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4663/6464 [1:24:51<34:34, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2924, 'grad_norm': 0.6207610368728638, 'learning_rate': 5.57671466171234e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4664/6464 [1:24:52<33:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1191, 'grad_norm': 0.6835342645645142, 'learning_rate': 5.57361820715281e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4665/6464 [1:24:53<33:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0748, 'grad_norm': 0.6975047588348389, 'learning_rate': 5.570521752593281e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4666/6464 [1:24:54<32:36, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2469, 'grad_norm': 0.8522367477416992, 'learning_rate': 5.5674252980337514e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4667/6464 [1:24:55<32:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0652, 'grad_norm': 0.6705458164215088, 'learning_rate': 5.5643288434742225e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4668/6464 [1:24:56<31:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9928, 'grad_norm': 0.722038745880127, 'learning_rate': 5.5612323889146937e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4669/6464 [1:24:58<32:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1849, 'grad_norm': 0.6557197570800781, 'learning_rate': 5.5581359343551634e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4670/6464 [1:24:59<34:00, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.352, 'grad_norm': 0.7834091186523438, 'learning_rate': 5.555039479795634e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4671/6464 [1:25:00<33:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1952, 'grad_norm': 0.6658226251602173, 'learning_rate': 5.551943025236105e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4672/6464 [1:25:01<33:04, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0099, 'grad_norm': 0.6683207154273987, 'learning_rate': 5.5488465706765755e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4673/6464 [1:25:02<33:05, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.043, 'grad_norm': 0.7469727993011475, 'learning_rate': 5.5457501161170466e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4674/6464 [1:25:03<32:23, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1072, 'grad_norm': 0.7396644353866577, 'learning_rate': 5.5426536615575164e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4675/6464 [1:25:04<34:33, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1289, 'grad_norm': 0.6758278012275696, 'learning_rate': 5.5395572069979875e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4676/6464 [1:25:05<33:21, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0224, 'grad_norm': 0.7040532827377319, 'learning_rate': 5.536460752438458e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4677/6464 [1:25:07<32:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2662, 'grad_norm': 0.7377063035964966, 'learning_rate': 5.533364297878929e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4678/6464 [1:25:08<32:22, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0957, 'grad_norm': 0.7617249488830566, 'learning_rate': 5.5302678433194e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4679/6464 [1:25:09<32:12, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8625, 'grad_norm': 0.5694766044616699, 'learning_rate': 5.52717138875987e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4680/6464 [1:25:10<31:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3767, 'grad_norm': 0.7527027130126953, 'learning_rate': 5.5240749342003405e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4681/6464 [1:25:11<31:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1772, 'grad_norm': 0.6694894433021545, 'learning_rate': 5.5209784796408116e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4682/6464 [1:25:12<31:31, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.991, 'grad_norm': 0.7188608050346375, 'learning_rate': 5.517882025081282e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4683/6464 [1:25:13<30:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.976, 'grad_norm': 0.7422308325767517, 'learning_rate': 5.514785570521753e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4684/6464 [1:25:14<29:38, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9111, 'grad_norm': 0.713187038898468, 'learning_rate': 5.511689115962223e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4685/6464 [1:25:15<31:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.187, 'grad_norm': 0.6017635464668274, 'learning_rate': 5.508592661402694e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 72%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4686/6464 [1:25:16<30:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2205, 'grad_norm': 0.7604982256889343, 'learning_rate': 5.5054962068431646e-05, 'epoch': 0.72}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4687/6464 [1:25:17<30:56, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2308, 'grad_norm': 0.8262903094291687, 'learning_rate': 5.502399752283636e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4688/6464 [1:25:18<30:45, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0898, 'grad_norm': 0.7346556782722473, 'learning_rate': 5.499303297724107e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4689/6464 [1:25:19<31:19, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0109, 'grad_norm': 0.7169568538665771, 'learning_rate': 5.4962068431645767e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4690/6464 [1:25:20<30:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0699, 'grad_norm': 0.761961817741394, 'learning_rate': 5.493110388605047e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4691/6464 [1:25:21<31:43, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.213, 'grad_norm': 0.7450792193412781, 'learning_rate': 5.490013934045518e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4692/6464 [1:25:22<31:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2282, 'grad_norm': 0.6898144483566284, 'learning_rate': 5.486917479485989e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4693/6464 [1:25:24<33:00, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1886, 'grad_norm': 0.7064281702041626, 'learning_rate': 5.48382102492646e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4694/6464 [1:25:25<34:05, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4365, 'grad_norm': 0.6685075759887695, 'learning_rate': 5.4807245703669296e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4695/6464 [1:25:26<32:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0693, 'grad_norm': 0.7894620895385742, 'learning_rate': 5.477628115807401e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4696/6464 [1:25:27<31:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2131, 'grad_norm': 0.7146642208099365, 'learning_rate': 5.474531661247871e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4697/6464 [1:25:28<32:37, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3119, 'grad_norm': 0.8426439166069031, 'learning_rate': 5.4714352066883424e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4698/6464 [1:25:29<33:13, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3102, 'grad_norm': 0.6975240111351013, 'learning_rate': 5.4683387521288135e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4699/6464 [1:25:30<33:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2601, 'grad_norm': 0.7751463055610657, 'learning_rate': 5.465242297569283e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4700/6464 [1:25:31<31:57, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1134, 'grad_norm': 0.8023326992988586, 'learning_rate': 5.462145843009754e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4701/6464 [1:25:32<31:40, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0995, 'grad_norm': 0.7751771211624146, 'learning_rate': 5.459049388450225e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4702/6464 [1:25:34<33:41, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3282, 'grad_norm': 0.7414863705635071, 'learning_rate': 5.455952933890695e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4703/6464 [1:25:35<31:49, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9418, 'grad_norm': 0.7231734991073608, 'learning_rate': 5.4528564793311665e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4704/6464 [1:25:36<32:41, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.215, 'grad_norm': 0.7344517111778259, 'learning_rate': 5.449760024771636e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4705/6464 [1:25:37<32:38, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2774, 'grad_norm': 0.8064543008804321, 'learning_rate': 5.4466635702121074e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4706/6464 [1:25:38<31:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2037, 'grad_norm': 0.7367177605628967, 'learning_rate': 5.443567115652578e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4707/6464 [1:25:39<32:28, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0984, 'grad_norm': 0.6327908635139465, 'learning_rate': 5.440470661093049e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4708/6464 [1:25:40<32:41, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1976, 'grad_norm': 0.770755410194397, 'learning_rate': 5.43737420653352e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4709/6464 [1:25:41<31:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2094, 'grad_norm': 0.7883673906326294, 'learning_rate': 5.43427775197399e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4710/6464 [1:25:42<30:45, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9926, 'grad_norm': 0.6886524558067322, 'learning_rate': 5.4311812974144603e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4711/6464 [1:25:43<30:28, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1497, 'grad_norm': 0.7581207752227783, 'learning_rate': 5.4280848428549315e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4712/6464 [1:25:44<30:47, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2869, 'grad_norm': 0.759979784488678, 'learning_rate': 5.424988388295402e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4713/6464 [1:25:45<30:19, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1543, 'grad_norm': 0.7179548144340515, 'learning_rate': 5.421891933735873e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4714/6464 [1:25:46<30:56, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2995, 'grad_norm': 0.77264404296875, 'learning_rate': 5.418795479176343e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4715/6464 [1:25:47<31:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1867, 'grad_norm': 0.7356762290000916, 'learning_rate': 5.415699024616814e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4716/6464 [1:25:48<31:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2602, 'grad_norm': 0.7877657413482666, 'learning_rate': 5.4126025700572844e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4717/6464 [1:25:50<32:36, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2601, 'grad_norm': 0.6481779217720032, 'learning_rate': 5.4095061154977556e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4718/6464 [1:25:51<33:16, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1358, 'grad_norm': 0.6637870669364929, 'learning_rate': 5.406409660938227e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4719/6464 [1:25:52<33:11, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0772, 'grad_norm': 0.6764946579933167, 'learning_rate': 5.4033132063786965e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4720/6464 [1:25:53<31:51, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0102, 'grad_norm': 0.7379547953605652, 'learning_rate': 5.400216751819167e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4721/6464 [1:25:54<32:13, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1126, 'grad_norm': 0.6081525087356567, 'learning_rate': 5.397120297259638e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4722/6464 [1:25:55<33:35, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2079, 'grad_norm': 0.6592970490455627, 'learning_rate': 5.3940238427001085e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4723/6464 [1:25:56<31:22, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9215, 'grad_norm': 0.765049934387207, 'learning_rate': 5.39092738814058e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4724/6464 [1:25:58<32:30, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3708, 'grad_norm': 0.7946868538856506, 'learning_rate': 5.3878309335810495e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4725/6464 [1:25:59<32:44, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0601, 'grad_norm': 0.760603129863739, 'learning_rate': 5.3847344790215206e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4726/6464 [1:26:00<31:17, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.128, 'grad_norm': 0.7473224401473999, 'learning_rate': 5.381638024461991e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4727/6464 [1:26:01<30:28, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1097, 'grad_norm': 0.7456815838813782, 'learning_rate': 5.378541569902462e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4728/6464 [1:26:02<31:45, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3422, 'grad_norm': 0.7135179042816162, 'learning_rate': 5.375445115342933e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4729/6464 [1:26:03<31:39, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0918, 'grad_norm': 0.6751893162727356, 'learning_rate': 5.372348660783403e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4730/6464 [1:26:04<31:24, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.965, 'grad_norm': 0.6448222994804382, 'learning_rate': 5.3692522062238736e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4731/6464 [1:26:05<32:36, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1268, 'grad_norm': 0.6329165697097778, 'learning_rate': 5.366155751664345e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4732/6464 [1:26:06<33:05, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0497, 'grad_norm': 0.6606413722038269, 'learning_rate': 5.363059297104815e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4733/6464 [1:26:08<32:16, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1259, 'grad_norm': 0.6815508604049683, 'learning_rate': 5.359962842545286e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4734/6464 [1:26:09<31:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1504, 'grad_norm': 0.6610227227210999, 'learning_rate': 5.356866387985756e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4735/6464 [1:26:10<32:07, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2722, 'grad_norm': 0.7584040760993958, 'learning_rate': 5.353769933426227e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4736/6464 [1:26:11<31:47, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2005, 'grad_norm': 0.7128901481628418, 'learning_rate': 5.350673478866698e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4737/6464 [1:26:12<31:14, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2678, 'grad_norm': 0.7775260806083679, 'learning_rate': 5.347577024307169e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4738/6464 [1:26:13<30:46, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1189, 'grad_norm': 0.6720705628395081, 'learning_rate': 5.34448056974764e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4739/6464 [1:26:14<29:43, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1416, 'grad_norm': 0.7733607292175293, 'learning_rate': 5.34138411518811e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4740/6464 [1:26:15<29:42, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0427, 'grad_norm': 0.7347729802131653, 'learning_rate': 5.33828766062858e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4741/6464 [1:26:16<28:32, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1512, 'grad_norm': 0.7831151485443115, 'learning_rate': 5.335191206069051e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4742/6464 [1:26:17<28:19, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1171, 'grad_norm': 0.6680643558502197, 'learning_rate': 5.332094751509522e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4743/6464 [1:26:18<27:22, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8966, 'grad_norm': 0.783366322517395, 'learning_rate': 5.328998296949993e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4744/6464 [1:26:19<27:23, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1381, 'grad_norm': 0.7515032291412354, 'learning_rate': 5.325901842390463e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4745/6464 [1:26:20<28:38, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2854, 'grad_norm': 0.7591909766197205, 'learning_rate': 5.322805387830934e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4746/6464 [1:26:21<27:11, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0246, 'grad_norm': 0.7662358283996582, 'learning_rate': 5.319708933271404e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4747/6464 [1:26:21<26:35, 1.08it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9009, 'grad_norm': 0.7107680439949036, 'learning_rate': 5.3166124787118754e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4748/6464 [1:26:22<27:47, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9813, 'grad_norm': 0.6625438928604126, 'learning_rate': 5.3135160241523466e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4749/6464 [1:26:23<27:11, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0497, 'grad_norm': 0.8563435673713684, 'learning_rate': 5.310419569592816e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4750/6464 [1:26:24<26:43, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0276, 'grad_norm': 0.6793005466461182, 'learning_rate': 5.307323115033287e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 73%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4751/6464 [1:26:26<29:32, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0356, 'grad_norm': 0.5895026922225952, 'learning_rate': 5.304226660473758e-05, 'epoch': 0.73}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4752/6464 [1:26:27<29:09, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0377, 'grad_norm': 0.6867825984954834, 'learning_rate': 5.3011302059142284e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4753/6464 [1:26:28<30:24, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2379, 'grad_norm': 0.7496277093887329, 'learning_rate': 5.2980337513546995e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4754/6464 [1:26:29<28:54, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0905, 'grad_norm': 0.752338171005249, 'learning_rate': 5.294937296795169e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4755/6464 [1:26:30<28:39, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9029, 'grad_norm': 0.7057291269302368, 'learning_rate': 5.2918408422356404e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4756/6464 [1:26:31<29:06, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0089, 'grad_norm': 0.6736724376678467, 'learning_rate': 5.288744387676111e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4757/6464 [1:26:32<28:54, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2789, 'grad_norm': 0.7691332697868347, 'learning_rate': 5.285647933116582e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4758/6464 [1:26:33<28:42, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1633, 'grad_norm': 0.6944006085395813, 'learning_rate': 5.282551478557053e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4759/6464 [1:26:34<29:58, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1643, 'grad_norm': 0.7581868171691895, 'learning_rate': 5.279455023997523e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4760/6464 [1:26:35<31:10, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8652, 'grad_norm': 0.7870458364486694, 'learning_rate': 5.2763585694379934e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4761/6464 [1:26:36<29:51, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.202, 'grad_norm': 0.7851507663726807, 'learning_rate': 5.2732621148784645e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4762/6464 [1:26:37<31:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1768, 'grad_norm': 0.6175621747970581, 'learning_rate': 5.270165660318935e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4763/6464 [1:26:38<30:20, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0908, 'grad_norm': 0.7452825903892517, 'learning_rate': 5.267069205759406e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4764/6464 [1:26:39<31:12, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1934, 'grad_norm': 0.744608461856842, 'learning_rate': 5.263972751199876e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4765/6464 [1:26:40<31:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0333, 'grad_norm': 0.6211766600608826, 'learning_rate': 5.260876296640347e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4766/6464 [1:26:41<30:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1821, 'grad_norm': 0.8420303463935852, 'learning_rate': 5.2577798420808175e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 4767/6464 [1:26:42<29:39, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.093, 'grad_norm': 0.7500060200691223, 'learning_rate': 5.2546833875212886e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4768/6464 [1:26:44<29:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.288, 'grad_norm': 0.7418107390403748, 'learning_rate': 5.25158693296176e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4769/6464 [1:26:45<32:10, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3987, 'grad_norm': 0.7102522253990173, 'learning_rate': 5.2484904784022296e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4770/6464 [1:26:46<31:07, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2308, 'grad_norm': 0.7604983448982239, 'learning_rate': 5.2453940238427e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4771/6464 [1:26:47<29:50, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9739, 'grad_norm': 0.711254358291626, 'learning_rate': 5.242297569283171e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4772/6464 [1:26:48<30:02, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1047, 'grad_norm': 0.6618621945381165, 'learning_rate': 5.2392011147236416e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4773/6464 [1:26:49<29:29, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1272, 'grad_norm': 0.6665415167808533, 'learning_rate': 5.236104660164113e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4774/6464 [1:26:50<32:28, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0342, 'grad_norm': 0.6038230657577515, 'learning_rate': 5.2330082056045825e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4775/6464 [1:26:51<30:47, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9713, 'grad_norm': 0.706825852394104, 'learning_rate': 5.2299117510450537e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4776/6464 [1:26:52<31:13, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3808, 'grad_norm': 0.7101029753684998, 'learning_rate': 5.226815296485524e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4777/6464 [1:26:54<31:54, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3036, 'grad_norm': 0.69828200340271, 'learning_rate': 5.223718841925995e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4778/6464 [1:26:55<30:01, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8177, 'grad_norm': 0.6105227470397949, 'learning_rate': 5.2206223873664664e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4779/6464 [1:26:56<31:26, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2748, 'grad_norm': 0.7437697649002075, 'learning_rate': 5.217525932806936e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4780/6464 [1:26:57<29:34, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0813, 'grad_norm': 0.8633968830108643, 'learning_rate': 5.2144294782474066e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4781/6464 [1:26:58<30:21, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1329, 'grad_norm': 0.7021505832672119, 'learning_rate': 5.211333023687878e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4782/6464 [1:26:59<29:56, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2781, 'grad_norm': 0.8278903365135193, 'learning_rate': 5.208236569128349e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4783/6464 [1:27:00<32:16, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.155, 'grad_norm': 0.6240748763084412, 'learning_rate': 5.2051401145688194e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4784/6464 [1:27:01<33:02, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1386, 'grad_norm': 0.6532653570175171, 'learning_rate': 5.202043660009289e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4785/6464 [1:27:02<31:40, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1128, 'grad_norm': 0.7767907977104187, 'learning_rate': 5.19894720544976e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4786/6464 [1:27:04<31:02, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0426, 'grad_norm': 0.6987881064414978, 'learning_rate': 5.195850750890231e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4787/6464 [1:27:05<30:53, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1136, 'grad_norm': 0.6773674488067627, 'learning_rate': 5.192754296330702e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4788/6464 [1:27:06<32:14, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1729, 'grad_norm': 0.7165580987930298, 'learning_rate': 5.189657841771173e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4789/6464 [1:27:07<30:42, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.233, 'grad_norm': 0.743762731552124, 'learning_rate': 5.186561387211643e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4790/6464 [1:27:08<29:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0321, 'grad_norm': 0.8156610727310181, 'learning_rate': 5.183464932652113e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4791/6464 [1:27:09<30:12, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.055, 'grad_norm': 0.6768800020217896, 'learning_rate': 5.1803684780925844e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4792/6464 [1:27:10<29:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0951, 'grad_norm': 0.688077449798584, 'learning_rate': 5.1772720235330555e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4793/6464 [1:27:11<28:22, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7913, 'grad_norm': 0.650033712387085, 'learning_rate': 5.174175568973526e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4794/6464 [1:27:12<29:58, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1385, 'grad_norm': 0.6899732351303101, 'learning_rate': 5.171079114413996e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4795/6464 [1:27:13<29:18, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8484, 'grad_norm': 0.6210699677467346, 'learning_rate': 5.167982659854467e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4796/6464 [1:27:14<31:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1934, 'grad_norm': 0.6528501510620117, 'learning_rate': 5.1648862052949373e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4797/6464 [1:27:15<31:01, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9947, 'grad_norm': 0.6456750631332397, 'learning_rate': 5.1617897507354085e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4798/6464 [1:27:16<29:04, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9073, 'grad_norm': 0.715909481048584, 'learning_rate': 5.1586932961758796e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4799/6464 [1:27:17<28:20, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3094, 'grad_norm': 0.8845717310905457, 'learning_rate': 5.1555968416163494e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4800/6464 [1:27:18<28:12, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1368, 'grad_norm': 0.721311092376709, 'learning_rate': 5.15250038705682e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4801/6464 [1:27:20<30:53, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0552, 'grad_norm': 0.6441429853439331, 'learning_rate': 5.149403932497291e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4802/6464 [1:27:21<31:02, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9647, 'grad_norm': 0.6133729815483093, 'learning_rate': 5.146307477937762e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4803/6464 [1:27:22<29:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0634, 'grad_norm': 0.7610182762145996, 'learning_rate': 5.1432110233782326e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4804/6464 [1:27:23<28:58, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.299, 'grad_norm': 0.7033716440200806, 'learning_rate': 5.1401145688187024e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4805/6464 [1:27:24<30:28, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0904, 'grad_norm': 0.7038089632987976, 'learning_rate': 5.1370181142591735e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4806/6464 [1:27:25<29:46, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1487, 'grad_norm': 0.7423219680786133, 'learning_rate': 5.133921659699644e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4807/6464 [1:27:26<32:21, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1472, 'grad_norm': 0.6110439896583557, 'learning_rate': 5.130825205140115e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4808/6464 [1:27:27<31:05, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9194, 'grad_norm': 0.6637778878211975, 'learning_rate': 5.127728750580586e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4809/6464 [1:27:29<32:15, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0976, 'grad_norm': 0.6122108101844788, 'learning_rate': 5.124632296021056e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4810/6464 [1:27:30<33:14, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2627, 'grad_norm': 0.637346088886261, 'learning_rate': 5.1215358414615265e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4811/6464 [1:27:31<33:48, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1303, 'grad_norm': 0.6277636885643005, 'learning_rate': 5.1184393869019976e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4812/6464 [1:27:33<34:35, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2525, 'grad_norm': 0.6530590653419495, 'learning_rate': 5.115342932342469e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4813/6464 [1:27:34<32:49, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0486, 'grad_norm': 0.8831096887588501, 'learning_rate': 5.112246477782939e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4814/6464 [1:27:35<31:34, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0132, 'grad_norm': 0.7471219897270203, 'learning_rate': 5.109150023223409e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 74%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4815/6464 [1:27:36<29:51, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9942, 'grad_norm': 0.672392725944519, 'learning_rate': 5.10605356866388e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4816/6464 [1:27:37<28:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9154, 'grad_norm': 0.7527177333831787, 'learning_rate': 5.1029571141043506e-05, 'epoch': 0.74}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4817/6464 [1:27:38<28:23, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9864, 'grad_norm': 0.7412013411521912, 'learning_rate': 5.099860659544822e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4818/6464 [1:27:39<30:39, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2018, 'grad_norm': 0.7053313255310059, 'learning_rate': 5.096764204985293e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4819/6464 [1:27:40<29:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2487, 'grad_norm': 0.7830803990364075, 'learning_rate': 5.0936677504257626e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4820/6464 [1:27:41<29:04, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0772, 'grad_norm': 0.6691920161247253, 'learning_rate': 5.090571295866233e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4821/6464 [1:27:42<29:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0738, 'grad_norm': 0.6420508027076721, 'learning_rate': 5.087474841306704e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4822/6464 [1:27:43<28:52, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9443, 'grad_norm': 0.6433242559432983, 'learning_rate': 5.0843783867471753e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4823/6464 [1:27:44<29:54, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3199, 'grad_norm': 0.732311487197876, 'learning_rate': 5.081281932187646e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4824/6464 [1:27:45<28:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0464, 'grad_norm': 0.755000114440918, 'learning_rate': 5.0781854776281156e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4825/6464 [1:27:46<30:39, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3154, 'grad_norm': 0.6367655992507935, 'learning_rate': 5.075089023068587e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4826/6464 [1:27:47<30:01, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0431, 'grad_norm': 0.8731465935707092, 'learning_rate': 5.071992568509057e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4827/6464 [1:27:49<30:31, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.078, 'grad_norm': 0.6835136413574219, 'learning_rate': 5.068896113949528e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4828/6464 [1:27:50<31:37, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9923, 'grad_norm': 0.655491292476654, 'learning_rate': 5.0657996593899995e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4829/6464 [1:27:51<30:20, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1964, 'grad_norm': 0.7624641060829163, 'learning_rate': 5.062703204830469e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4830/6464 [1:27:52<29:47, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3277, 'grad_norm': 0.7613755464553833, 'learning_rate': 5.05960675027094e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4831/6464 [1:27:53<31:39, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0853, 'grad_norm': 0.7561673521995544, 'learning_rate': 5.056510295711411e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4832/6464 [1:27:54<30:58, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1268, 'grad_norm': 0.7319955825805664, 'learning_rate': 5.053413841151882e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4833/6464 [1:27:56<31:45, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.948, 'grad_norm': 0.6902710795402527, 'learning_rate': 5.0503173865923524e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4834/6464 [1:27:57<30:18, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0445, 'grad_norm': 0.7678455114364624, 'learning_rate': 5.047220932032822e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4835/6464 [1:27:58<31:35, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1543, 'grad_norm': 0.6309283375740051, 'learning_rate': 5.044124477473293e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4836/6464 [1:27:59<30:54, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2704, 'grad_norm': 0.7339949607849121, 'learning_rate': 5.041028022913764e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4837/6464 [1:28:00<29:16, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2161, 'grad_norm': 0.8457925319671631, 'learning_rate': 5.037931568354235e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4838/6464 [1:28:01<29:13, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1861, 'grad_norm': 0.7863290905952454, 'learning_rate': 5.034835113794706e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4839/6464 [1:28:02<28:28, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4317, 'grad_norm': 0.7772417068481445, 'learning_rate': 5.031738659235176e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4840/6464 [1:28:03<29:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2781, 'grad_norm': 0.6763849258422852, 'learning_rate': 5.028642204675646e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4841/6464 [1:28:04<29:29, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0627, 'grad_norm': 0.7354190945625305, 'learning_rate': 5.0255457501161174e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4842/6464 [1:28:05<28:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3288, 'grad_norm': 0.7832745313644409, 'learning_rate': 5.0224492955565886e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4843/6464 [1:28:06<28:29, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9517, 'grad_norm': 0.7390761971473694, 'learning_rate': 5.019352840997059e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4844/6464 [1:28:07<28:41, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1156, 'grad_norm': 0.7025797963142395, 'learning_rate': 5.016256386437529e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4845/6464 [1:28:08<28:09, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2126, 'grad_norm': 0.7575348019599915, 'learning_rate': 5.013159931878e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4846/6464 [1:28:09<27:50, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2342, 'grad_norm': 0.7901651859283447, 'learning_rate': 5.0100634773184704e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 4847/6464 [1:28:10<27:47, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2144, 'grad_norm': 0.799903929233551, 'learning_rate': 5.0069670227589415e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4848/6464 [1:28:11<28:51, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2613, 'grad_norm': 0.7809821367263794, 'learning_rate': 5.003870568199413e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4849/6464 [1:28:12<27:43, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2468, 'grad_norm': 0.9712319374084473, 'learning_rate': 5.0007741136398825e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4850/6464 [1:28:13<27:42, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2651, 'grad_norm': 0.7444798946380615, 'learning_rate': 4.997677659080353e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4851/6464 [1:28:15<28:40, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4192, 'grad_norm': 0.7034334540367126, 'learning_rate': 4.994581204520824e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4852/6464 [1:28:16<29:20, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2032, 'grad_norm': 0.6621910929679871, 'learning_rate': 4.9914847499612945e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4853/6464 [1:28:17<29:55, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0651, 'grad_norm': 0.6352224946022034, 'learning_rate': 4.988388295401765e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4854/6464 [1:28:18<30:37, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0339, 'grad_norm': 0.6425437331199646, 'learning_rate': 4.985291840842236e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4855/6464 [1:28:19<29:02, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0508, 'grad_norm': 0.7465651035308838, 'learning_rate': 4.9821953862827066e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4856/6464 [1:28:20<28:24, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0778, 'grad_norm': 0.6873833537101746, 'learning_rate': 4.979098931723177e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4857/6464 [1:28:21<28:55, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1454, 'grad_norm': 0.705941379070282, 'learning_rate': 4.9760024771636475e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4858/6464 [1:28:22<27:21, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1556, 'grad_norm': 0.767865002155304, 'learning_rate': 4.9729060226041186e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4859/6464 [1:28:23<26:30, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0294, 'grad_norm': 0.7341631054878235, 'learning_rate': 4.96980956804459e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4860/6464 [1:28:24<29:34, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0071, 'grad_norm': 0.6251024007797241, 'learning_rate': 4.9667131134850595e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4861/6464 [1:28:25<27:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0483, 'grad_norm': 0.7004901766777039, 'learning_rate': 4.963616658925531e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4862/6464 [1:28:26<27:20, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9661, 'grad_norm': 0.6404118537902832, 'learning_rate': 4.960520204366001e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4863/6464 [1:28:27<29:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2255, 'grad_norm': 0.6522313356399536, 'learning_rate': 4.9574237498064716e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4864/6464 [1:28:29<30:56, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1712, 'grad_norm': 0.6761360168457031, 'learning_rate': 4.954327295246943e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4865/6464 [1:28:30<27:51, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9234, 'grad_norm': 0.8316510319709778, 'learning_rate': 4.951230840687413e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4866/6464 [1:28:31<26:54, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.157, 'grad_norm': 0.857561469078064, 'learning_rate': 4.9481343861278836e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4867/6464 [1:28:32<27:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0561, 'grad_norm': 0.644746720790863, 'learning_rate': 4.945037931568354e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4868/6464 [1:28:33<28:03, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.913, 'grad_norm': 0.6359400153160095, 'learning_rate': 4.941941477008825e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4869/6464 [1:28:34<27:53, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1149, 'grad_norm': 0.7549417018890381, 'learning_rate': 4.9388450224492964e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4870/6464 [1:28:35<27:25, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.23, 'grad_norm': 0.7340048551559448, 'learning_rate': 4.935748567889766e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4871/6464 [1:28:36<29:48, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1266, 'grad_norm': 0.6252660155296326, 'learning_rate': 4.932652113330237e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4872/6464 [1:28:37<29:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2636, 'grad_norm': 0.7609065771102905, 'learning_rate': 4.929555658770708e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4873/6464 [1:28:38<29:08, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9666, 'grad_norm': 0.6354473233222961, 'learning_rate': 4.926459204211178e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4874/6464 [1:28:39<27:45, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1628, 'grad_norm': 0.8542897701263428, 'learning_rate': 4.923362749651649e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4875/6464 [1:28:40<25:58, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9295, 'grad_norm': 0.7987384796142578, 'learning_rate': 4.92026629509212e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4876/6464 [1:28:41<25:38, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0852, 'grad_norm': 0.8398440480232239, 'learning_rate': 4.91716984053259e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4877/6464 [1:28:42<26:35, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0542, 'grad_norm': 0.7017294764518738, 'learning_rate': 4.914073385973061e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4878/6464 [1:28:43<26:00, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9649, 'grad_norm': 0.8120512366294861, 'learning_rate': 4.910976931413532e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4879/6464 [1:28:44<26:54, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1771, 'grad_norm': 0.680293619632721, 'learning_rate': 4.907880476854003e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 75%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4880/6464 [1:28:45<26:43, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1607, 'grad_norm': 0.7077568769454956, 'learning_rate': 4.904784022294473e-05, 'epoch': 0.75}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4881/6464 [1:28:46<26:55, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0505, 'grad_norm': 0.7082364559173584, 'learning_rate': 4.901687567734944e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4882/6464 [1:28:47<27:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1344, 'grad_norm': 0.8442254662513733, 'learning_rate': 4.8985911131754143e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4883/6464 [1:28:48<28:31, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1874, 'grad_norm': 0.7387908101081848, 'learning_rate': 4.895494658615885e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4884/6464 [1:28:50<29:19, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0596, 'grad_norm': 0.6347994804382324, 'learning_rate': 4.892398204056356e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4885/6464 [1:28:51<28:47, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4343, 'grad_norm': 0.8097483515739441, 'learning_rate': 4.8893017494968264e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4886/6464 [1:28:52<27:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9989, 'grad_norm': 0.7617628574371338, 'learning_rate': 4.886205294937297e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4887/6464 [1:28:53<27:12, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0759, 'grad_norm': 0.7222906351089478, 'learning_rate': 4.883108840377767e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4888/6464 [1:28:54<26:31, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0087, 'grad_norm': 0.6828162670135498, 'learning_rate': 4.8800123858182384e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4889/6464 [1:28:55<27:05, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0042, 'grad_norm': 0.6576183438301086, 'learning_rate': 4.8769159312587096e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4890/6464 [1:28:56<26:30, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.06, 'grad_norm': 0.7958294749259949, 'learning_rate': 4.8738194766991794e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4891/6464 [1:28:57<26:02, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1016, 'grad_norm': 0.739057719707489, 'learning_rate': 4.8707230221396505e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4892/6464 [1:28:58<27:18, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3277, 'grad_norm': 0.7206666469573975, 'learning_rate': 4.867626567580121e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4893/6464 [1:28:59<25:45, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9814, 'grad_norm': 0.778990626335144, 'learning_rate': 4.8645301130205914e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4894/6464 [1:28:59<25:31, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9635, 'grad_norm': 0.7540352940559387, 'learning_rate': 4.8614336584610625e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4895/6464 [1:29:01<27:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1714, 'grad_norm': 0.6681907176971436, 'learning_rate': 4.858337203901533e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4896/6464 [1:29:02<29:19, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1527, 'grad_norm': 0.6436074376106262, 'learning_rate': 4.8552407493420035e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4897/6464 [1:29:03<28:48, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4297, 'grad_norm': 0.7833553552627563, 'learning_rate': 4.852144294782474e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4898/6464 [1:29:04<29:26, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4766, 'grad_norm': 0.7361643314361572, 'learning_rate': 4.849047840222945e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4899/6464 [1:29:05<29:35, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2619, 'grad_norm': 0.7277644276618958, 'learning_rate': 4.845951385663416e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4900/6464 [1:29:06<28:26, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0555, 'grad_norm': 0.8052895665168762, 'learning_rate': 4.842854931103886e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4901/6464 [1:29:08<30:31, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1234, 'grad_norm': 0.7204083204269409, 'learning_rate': 4.839758476544357e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4902/6464 [1:29:09<29:39, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1135, 'grad_norm': 0.7677419781684875, 'learning_rate': 4.8366620219848276e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4903/6464 [1:29:10<29:47, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9665, 'grad_norm': 0.6932964324951172, 'learning_rate': 4.833565567425298e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4904/6464 [1:29:11<29:32, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3915, 'grad_norm': 0.7789382338523865, 'learning_rate': 4.830469112865769e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4905/6464 [1:29:12<30:06, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8317, 'grad_norm': 0.5574125051498413, 'learning_rate': 4.8273726583062396e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4906/6464 [1:29:13<28:45, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.107, 'grad_norm': 0.7545962333679199, 'learning_rate': 4.82427620374671e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4907/6464 [1:29:14<27:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9473, 'grad_norm': 0.6932040452957153, 'learning_rate': 4.8211797491871805e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4908/6464 [1:29:15<25:46, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9604, 'grad_norm': 0.7027300596237183, 'learning_rate': 4.818083294627652e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4909/6464 [1:29:16<26:35, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1856, 'grad_norm': 0.7420331239700317, 'learning_rate': 4.814986840068123e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4910/6464 [1:29:17<27:14, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.201, 'grad_norm': 0.7035732865333557, 'learning_rate': 4.8118903855085926e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4911/6464 [1:29:19<28:35, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3232, 'grad_norm': 0.6135176420211792, 'learning_rate': 4.808793930949064e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4912/6464 [1:29:20<29:10, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1038, 'grad_norm': 0.6743601560592651, 'learning_rate': 4.805697476389534e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4913/6464 [1:29:21<28:12, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0418, 'grad_norm': 0.7442734837532043, 'learning_rate': 4.8026010218300046e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4914/6464 [1:29:22<27:12, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9733, 'grad_norm': 0.697516679763794, 'learning_rate': 4.799504567270475e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4915/6464 [1:29:23<26:52, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2898, 'grad_norm': 0.7656651735305786, 'learning_rate': 4.796408112710946e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4916/6464 [1:29:24<26:02, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0411, 'grad_norm': 0.7527588605880737, 'learning_rate': 4.793311658151417e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4917/6464 [1:29:25<25:44, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1263, 'grad_norm': 0.7736700773239136, 'learning_rate': 4.790215203591887e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4918/6464 [1:29:26<25:43, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.062, 'grad_norm': 0.746203601360321, 'learning_rate': 4.787118749032358e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4919/6464 [1:29:27<26:22, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2005, 'grad_norm': 0.7802284359931946, 'learning_rate': 4.784022294472829e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4920/6464 [1:29:28<27:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1651, 'grad_norm': 0.7103692889213562, 'learning_rate': 4.780925839913299e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4921/6464 [1:29:29<28:53, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2241, 'grad_norm': 0.8152265548706055, 'learning_rate': 4.77782938535377e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4922/6464 [1:29:30<27:54, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.054, 'grad_norm': 0.7970976233482361, 'learning_rate': 4.774732930794241e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4923/6464 [1:29:31<28:45, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1337, 'grad_norm': 0.6924349665641785, 'learning_rate': 4.771636476234711e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4924/6464 [1:29:32<28:16, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1028, 'grad_norm': 0.795832097530365, 'learning_rate': 4.768540021675182e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4925/6464 [1:29:34<30:01, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1329, 'grad_norm': 0.9692795872688293, 'learning_rate': 4.765443567115653e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4926/6464 [1:29:35<34:01, 1.33s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.402, 'grad_norm': 0.625615656375885, 'learning_rate': 4.762347112556124e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4927/6464 [1:29:36<31:06, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1408, 'grad_norm': 0.8890194296836853, 'learning_rate': 4.759250657996594e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 4928/6464 [1:29:38<31:02, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1453, 'grad_norm': 0.6893147230148315, 'learning_rate': 4.756154203437065e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4929/6464 [1:29:39<30:00, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0072, 'grad_norm': 0.6700403094291687, 'learning_rate': 4.7530577488775354e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4930/6464 [1:29:40<28:35, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3136, 'grad_norm': 0.7947472333908081, 'learning_rate': 4.749961294318006e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4931/6464 [1:29:41<27:31, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1374, 'grad_norm': 0.7227409482002258, 'learning_rate': 4.746864839758477e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4932/6464 [1:29:42<27:58, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.132, 'grad_norm': 0.6981375813484192, 'learning_rate': 4.7437683851989474e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4933/6464 [1:29:43<26:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1676, 'grad_norm': 0.761918306350708, 'learning_rate': 4.740671930639418e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4934/6464 [1:29:44<27:11, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2655, 'grad_norm': 0.7030431032180786, 'learning_rate': 4.737575476079888e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4935/6464 [1:29:45<27:44, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2152, 'grad_norm': 0.6843249201774597, 'learning_rate': 4.7344790215203595e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4936/6464 [1:29:46<29:44, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3247, 'grad_norm': 0.7020733952522278, 'learning_rate': 4.7313825669608306e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4937/6464 [1:29:47<27:23, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0427, 'grad_norm': 0.740009605884552, 'learning_rate': 4.7282861124013004e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4938/6464 [1:29:48<26:40, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9617, 'grad_norm': 0.7658040523529053, 'learning_rate': 4.7251896578417715e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4939/6464 [1:29:49<27:02, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0735, 'grad_norm': 0.6823824644088745, 'learning_rate': 4.722093203282242e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4940/6464 [1:29:50<28:34, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2382, 'grad_norm': 0.7243872880935669, 'learning_rate': 4.7189967487227124e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4941/6464 [1:29:51<26:25, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7911, 'grad_norm': 0.6712195873260498, 'learning_rate': 4.7159002941631836e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4942/6464 [1:29:52<26:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0865, 'grad_norm': 0.7409871220588684, 'learning_rate': 4.712803839603654e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4943/6464 [1:29:53<26:37, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.044, 'grad_norm': 0.7224487066268921, 'learning_rate': 4.7097073850441245e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 76%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4944/6464 [1:29:54<26:08, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.036, 'grad_norm': 0.6649503707885742, 'learning_rate': 4.706610930484595e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4945/6464 [1:29:55<25:34, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9598, 'grad_norm': 0.808769702911377, 'learning_rate': 4.703514475925066e-05, 'epoch': 0.76}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4946/6464 [1:29:56<25:09, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9912, 'grad_norm': 0.6887364983558655, 'learning_rate': 4.700418021365537e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4947/6464 [1:29:57<25:57, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4305, 'grad_norm': 0.8125840425491333, 'learning_rate': 4.697321566806007e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4948/6464 [1:29:59<26:11, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0326, 'grad_norm': 0.7449729442596436, 'learning_rate': 4.694225112246478e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4949/6464 [1:30:00<28:26, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5204, 'grad_norm': 0.6950849890708923, 'learning_rate': 4.6911286576869486e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4950/6464 [1:30:01<28:22, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1595, 'grad_norm': 0.6503576636314392, 'learning_rate': 4.688032203127419e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4951/6464 [1:30:02<26:59, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9857, 'grad_norm': 0.6546930074691772, 'learning_rate': 4.68493574856789e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4952/6464 [1:30:03<25:30, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9865, 'grad_norm': 0.6842195987701416, 'learning_rate': 4.6818392940083606e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4953/6464 [1:30:04<26:10, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1068, 'grad_norm': 0.6722804307937622, 'learning_rate': 4.678742839448831e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4954/6464 [1:30:05<26:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0749, 'grad_norm': 0.7378582954406738, 'learning_rate': 4.6756463848893015e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4955/6464 [1:30:06<26:32, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0774, 'grad_norm': 0.7525771260261536, 'learning_rate': 4.672549930329773e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4956/6464 [1:30:07<26:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1204, 'grad_norm': 0.7776263952255249, 'learning_rate': 4.669453475770244e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4957/6464 [1:30:08<28:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1358, 'grad_norm': 0.6516056656837463, 'learning_rate': 4.6663570212107136e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4958/6464 [1:30:09<26:59, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9745, 'grad_norm': 0.7895199060440063, 'learning_rate': 4.663260566651185e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4959/6464 [1:30:11<28:01, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2136, 'grad_norm': 0.6585428714752197, 'learning_rate': 4.660164112091655e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4960/6464 [1:30:12<26:34, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1514, 'grad_norm': 0.7987938523292542, 'learning_rate': 4.6570676575321256e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4961/6464 [1:30:13<29:40, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2201, 'grad_norm': 0.6494492888450623, 'learning_rate': 4.653971202972597e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4962/6464 [1:30:14<28:35, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2516, 'grad_norm': 0.66990065574646, 'learning_rate': 4.650874748413067e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4963/6464 [1:30:15<29:04, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2765, 'grad_norm': 0.701926052570343, 'learning_rate': 4.647778293853538e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4964/6464 [1:30:16<28:26, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.065, 'grad_norm': 0.6698476076126099, 'learning_rate': 4.644681839294008e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4965/6464 [1:30:17<27:02, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7987, 'grad_norm': 0.6461029052734375, 'learning_rate': 4.641585384734479e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4966/6464 [1:30:19<28:12, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0596, 'grad_norm': 0.6155992150306702, 'learning_rate': 4.6384889301749504e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4967/6464 [1:30:20<27:45, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1363, 'grad_norm': 0.7225522398948669, 'learning_rate': 4.63539247561542e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4968/6464 [1:30:20<25:23, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8607, 'grad_norm': 0.7624781131744385, 'learning_rate': 4.6322960210558913e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4969/6464 [1:30:22<26:34, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.11, 'grad_norm': 0.6378152370452881, 'learning_rate': 4.629199566496362e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4970/6464 [1:30:23<28:24, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.16, 'grad_norm': 0.6517473459243774, 'learning_rate': 4.626103111936832e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4971/6464 [1:30:24<28:39, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2487, 'grad_norm': 0.6760709285736084, 'learning_rate': 4.6230066573773034e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4972/6464 [1:30:25<29:09, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1733, 'grad_norm': 0.7606580853462219, 'learning_rate': 4.619910202817774e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4973/6464 [1:30:26<28:13, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2882, 'grad_norm': 0.7354738116264343, 'learning_rate': 4.616813748258244e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4974/6464 [1:30:28<29:24, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1979, 'grad_norm': 0.7835573554039001, 'learning_rate': 4.613717293698715e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4975/6464 [1:30:29<28:24, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0631, 'grad_norm': 0.6871913075447083, 'learning_rate': 4.610620839139186e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4976/6464 [1:30:30<28:38, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2159, 'grad_norm': 0.7316229939460754, 'learning_rate': 4.607524384579657e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4977/6464 [1:30:31<27:57, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9558, 'grad_norm': 0.7288895845413208, 'learning_rate': 4.604427930020127e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4978/6464 [1:30:32<27:49, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2572, 'grad_norm': 0.6915421485900879, 'learning_rate': 4.601331475460598e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4979/6464 [1:30:33<27:46, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0623, 'grad_norm': 0.7308092713356018, 'learning_rate': 4.5982350209010684e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4980/6464 [1:30:34<26:55, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0582, 'grad_norm': 0.707048237323761, 'learning_rate': 4.595138566341539e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4981/6464 [1:30:35<25:57, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9398, 'grad_norm': 0.6672091484069824, 'learning_rate': 4.59204211178201e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4982/6464 [1:30:36<26:44, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2577, 'grad_norm': 0.7640326023101807, 'learning_rate': 4.5889456572224805e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4983/6464 [1:30:37<26:36, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9375, 'grad_norm': 0.7366898059844971, 'learning_rate': 4.585849202662951e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4984/6464 [1:30:38<26:17, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0852, 'grad_norm': 0.6812565922737122, 'learning_rate': 4.5827527481034214e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4985/6464 [1:30:39<26:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1115, 'grad_norm': 0.7725276350975037, 'learning_rate': 4.5796562935438925e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4986/6464 [1:30:41<27:13, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2696, 'grad_norm': 0.756718099117279, 'learning_rate': 4.5765598389843637e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4987/6464 [1:30:42<28:03, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0437, 'grad_norm': 0.711574912071228, 'learning_rate': 4.5734633844248334e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4988/6464 [1:30:43<27:49, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1911, 'grad_norm': 0.7356794476509094, 'learning_rate': 4.5703669298653046e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4989/6464 [1:30:44<28:13, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8726, 'grad_norm': 0.6698586344718933, 'learning_rate': 4.567270475305775e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4990/6464 [1:30:45<26:25, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9403, 'grad_norm': 0.7871982455253601, 'learning_rate': 4.5641740207462455e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4991/6464 [1:30:46<25:58, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2103, 'grad_norm': 0.7743613123893738, 'learning_rate': 4.5610775661867166e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4992/6464 [1:30:47<25:04, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9605, 'grad_norm': 0.6808050870895386, 'learning_rate': 4.557981111627187e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4993/6464 [1:30:48<24:24, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9819, 'grad_norm': 0.7174550294876099, 'learning_rate': 4.554884657067658e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4994/6464 [1:30:49<23:43, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9081, 'grad_norm': 0.7720298767089844, 'learning_rate': 4.551788202508128e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4995/6464 [1:30:50<23:42, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1106, 'grad_norm': 0.7523762583732605, 'learning_rate': 4.548691747948599e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4996/6464 [1:30:51<23:30, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1088, 'grad_norm': 0.8082641959190369, 'learning_rate': 4.54559529338907e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4997/6464 [1:30:52<23:48, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2878, 'grad_norm': 0.7744448781013489, 'learning_rate': 4.54249883882954e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4998/6464 [1:30:53<24:36, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0841, 'grad_norm': 0.6658675074577332, 'learning_rate': 4.539402384270011e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 4999/6464 [1:30:54<26:13, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0362, 'grad_norm': 0.6016831398010254, 'learning_rate': 4.5363059297104816e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5000/6464 [1:30:55<24:37, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.936, 'grad_norm': 0.6865227222442627, 'learning_rate': 4.533209475150952e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5001/6464 [1:30:57<30:14, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8693, 'grad_norm': 0.6262425780296326, 'learning_rate': 4.530113020591423e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5002/6464 [1:30:58<30:18, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2005, 'grad_norm': 0.7294527888298035, 'learning_rate': 4.527016566031894e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5003/6464 [1:30:59<29:22, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0847, 'grad_norm': 1.0478713512420654, 'learning_rate': 4.523920111472365e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5004/6464 [1:31:00<27:59, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9643, 'grad_norm': 0.6363033652305603, 'learning_rate': 4.5208236569128346e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5005/6464 [1:31:01<25:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0235, 'grad_norm': 0.9368097186088562, 'learning_rate': 4.517727202353306e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5006/6464 [1:31:02<26:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1775, 'grad_norm': 0.7873470187187195, 'learning_rate': 4.514630747793777e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5007/6464 [1:31:03<25:14, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1939, 'grad_norm': 0.8827716708183289, 'learning_rate': 4.5115342932342467e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5008/6464 [1:31:04<25:59, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1197, 'grad_norm': 0.6491172909736633, 'learning_rate': 4.508437838674718e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 77%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5009/6464 [1:31:05<25:41, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1535, 'grad_norm': 0.7076922059059143, 'learning_rate': 4.505341384115188e-05, 'epoch': 0.77}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5010/6464 [1:31:06<24:36, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0271, 'grad_norm': 0.7260867953300476, 'learning_rate': 4.502244929555659e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5011/6464 [1:31:07<23:44, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9703, 'grad_norm': 0.8946263790130615, 'learning_rate': 4.49914847499613e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5012/6464 [1:31:08<24:12, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9915, 'grad_norm': 0.7551883459091187, 'learning_rate': 4.4960520204366e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5013/6464 [1:31:09<25:15, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1024, 'grad_norm': 0.6925632357597351, 'learning_rate': 4.4929555658770714e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5014/6464 [1:31:10<24:37, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1323, 'grad_norm': 0.7871990203857422, 'learning_rate': 4.489859111317541e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5015/6464 [1:31:11<25:32, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3756, 'grad_norm': 0.8001610040664673, 'learning_rate': 4.4867626567580124e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5016/6464 [1:31:12<24:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.016, 'grad_norm': 0.7298597097396851, 'learning_rate': 4.4836662021984835e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5017/6464 [1:31:13<25:31, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2679, 'grad_norm': 0.6724193096160889, 'learning_rate': 4.480569747638953e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5018/6464 [1:31:14<25:31, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.107, 'grad_norm': 0.6651992201805115, 'learning_rate': 4.4774732930794244e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5019/6464 [1:31:16<26:35, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1431, 'grad_norm': 0.7033929824829102, 'learning_rate': 4.474376838519895e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5020/6464 [1:31:17<25:48, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1538, 'grad_norm': 0.8251495361328125, 'learning_rate': 4.471280383960365e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5021/6464 [1:31:18<25:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9377, 'grad_norm': 0.6005298495292664, 'learning_rate': 4.4681839294008365e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5022/6464 [1:31:19<25:11, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3196, 'grad_norm': 0.8038443326950073, 'learning_rate': 4.465087474841307e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5023/6464 [1:31:20<24:47, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1148, 'grad_norm': 0.7728932499885559, 'learning_rate': 4.461991020281778e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5024/6464 [1:31:21<24:10, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9325, 'grad_norm': 0.6808651685714722, 'learning_rate': 4.458894565722248e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5025/6464 [1:31:22<24:26, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0981, 'grad_norm': 0.7129772305488586, 'learning_rate': 4.455798111162719e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5026/6464 [1:31:23<24:16, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1826, 'grad_norm': 0.7289573550224304, 'learning_rate': 4.45270165660319e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5027/6464 [1:31:24<24:25, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0482, 'grad_norm': 0.7641929984092712, 'learning_rate': 4.44960520204366e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5028/6464 [1:31:25<24:02, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2135, 'grad_norm': 0.7653201222419739, 'learning_rate': 4.446508747484131e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5029/6464 [1:31:26<24:11, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1501, 'grad_norm': 0.8215135335922241, 'learning_rate': 4.4434122929246015e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5030/6464 [1:31:27<24:25, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9765, 'grad_norm': 0.6395566463470459, 'learning_rate': 4.440315838365072e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5031/6464 [1:31:28<24:26, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1208, 'grad_norm': 0.7049397826194763, 'learning_rate': 4.437219383805543e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5032/6464 [1:31:29<24:41, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1132, 'grad_norm': 0.7106220126152039, 'learning_rate': 4.4341229292460135e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5033/6464 [1:31:30<24:08, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1893, 'grad_norm': 0.6921643018722534, 'learning_rate': 4.431026474686485e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5034/6464 [1:31:31<25:57, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0891, 'grad_norm': 0.6917211413383484, 'learning_rate': 4.4279300201269544e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5035/6464 [1:31:32<25:23, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4145, 'grad_norm': 0.8273484706878662, 'learning_rate': 4.4248335655674256e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5036/6464 [1:31:34<28:05, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2077, 'grad_norm': 0.6992924213409424, 'learning_rate': 4.421737111007896e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5037/6464 [1:31:35<31:03, 1.31s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2173, 'grad_norm': 0.6168091893196106, 'learning_rate': 4.4186406564483665e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5038/6464 [1:31:36<29:04, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9762, 'grad_norm': 0.6888445019721985, 'learning_rate': 4.4155442018888376e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5039/6464 [1:31:37<27:31, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0513, 'grad_norm': 0.8046414852142334, 'learning_rate': 4.412447747329308e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5040/6464 [1:31:38<27:03, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1682, 'grad_norm': 0.6979271173477173, 'learning_rate': 4.4093512927697785e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5041/6464 [1:31:40<27:48, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1267, 'grad_norm': 0.6433187127113342, 'learning_rate': 4.406254838210249e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5042/6464 [1:31:41<26:32, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0556, 'grad_norm': 0.7604207396507263, 'learning_rate': 4.40315838365072e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5043/6464 [1:31:41<24:39, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8857, 'grad_norm': 0.8040187358856201, 'learning_rate': 4.400061929091191e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5044/6464 [1:31:43<25:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3573, 'grad_norm': 0.7143696546554565, 'learning_rate': 4.396965474531661e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5045/6464 [1:31:44<26:03, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0804, 'grad_norm': 0.6515457630157471, 'learning_rate': 4.393869019972132e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5046/6464 [1:31:45<25:16, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9492, 'grad_norm': 0.6683624982833862, 'learning_rate': 4.3907725654126026e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5047/6464 [1:31:46<24:38, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0602, 'grad_norm': 0.7730402946472168, 'learning_rate': 4.387676110853073e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5048/6464 [1:31:47<24:38, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1364, 'grad_norm': 0.6872150301933289, 'learning_rate': 4.384579656293544e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5049/6464 [1:31:48<25:22, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3816, 'grad_norm': 0.7117639183998108, 'learning_rate': 4.381483201734015e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5050/6464 [1:31:49<24:10, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.974, 'grad_norm': 0.7752033472061157, 'learning_rate': 4.378386747174485e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5051/6464 [1:31:50<25:12, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9148, 'grad_norm': 0.7550376057624817, 'learning_rate': 4.3752902926149556e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5052/6464 [1:31:51<26:06, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2444, 'grad_norm': 0.7209469079971313, 'learning_rate': 4.372193838055427e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5053/6464 [1:31:53<27:53, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0661, 'grad_norm': 0.5999053120613098, 'learning_rate': 4.369097383495898e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5054/6464 [1:31:54<28:06, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2075, 'grad_norm': 0.6843312978744507, 'learning_rate': 4.366000928936368e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5055/6464 [1:31:55<27:24, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.147, 'grad_norm': 0.7042438387870789, 'learning_rate': 4.362904474376839e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5056/6464 [1:31:56<25:49, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2811, 'grad_norm': 0.7967637181282043, 'learning_rate': 4.359808019817309e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5057/6464 [1:31:57<25:52, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0489, 'grad_norm': 0.7742617130279541, 'learning_rate': 4.35671156525778e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5058/6464 [1:31:58<28:03, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4441, 'grad_norm': 0.6256285309791565, 'learning_rate': 4.353615110698251e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5059/6464 [1:32:00<28:33, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1209, 'grad_norm': 0.6422078013420105, 'learning_rate': 4.350518656138721e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5060/6464 [1:32:01<27:19, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0231, 'grad_norm': 0.7270478010177612, 'learning_rate': 4.3474222015791924e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5061/6464 [1:32:02<26:40, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9366, 'grad_norm': 0.6596150398254395, 'learning_rate': 4.344325747019662e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5062/6464 [1:32:03<25:52, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1757, 'grad_norm': 0.7438196539878845, 'learning_rate': 4.3412292924601334e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5063/6464 [1:32:04<25:25, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.365, 'grad_norm': 0.7400426864624023, 'learning_rate': 4.3381328379006045e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5064/6464 [1:32:05<25:31, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1321, 'grad_norm': 0.6679978966712952, 'learning_rate': 4.335036383341074e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5065/6464 [1:32:06<24:55, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0293, 'grad_norm': 0.6963971257209778, 'learning_rate': 4.3319399287815454e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5066/6464 [1:32:07<24:34, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0676, 'grad_norm': 0.682007908821106, 'learning_rate': 4.328843474222016e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5067/6464 [1:32:08<25:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1857, 'grad_norm': 0.7506971955299377, 'learning_rate': 4.325747019662486e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5068/6464 [1:32:09<24:59, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9693, 'grad_norm': 0.7151678800582886, 'learning_rate': 4.3226505651029575e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5069/6464 [1:32:10<26:34, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3941, 'grad_norm': 0.682385265827179, 'learning_rate': 4.319554110543428e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5070/6464 [1:32:12<26:50, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2677, 'grad_norm': 0.7732306122779846, 'learning_rate': 4.316457655983899e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5071/6464 [1:32:13<27:54, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9937, 'grad_norm': 0.6071125864982605, 'learning_rate': 4.313361201424369e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5072/6464 [1:32:15<30:41, 1.32s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2993, 'grad_norm': 0.6328137516975403, 'learning_rate': 4.31026474686484e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5073/6464 [1:32:16<30:01, 1.30s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2804, 'grad_norm': 0.6459688544273376, 'learning_rate': 4.307168292305311e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 78%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5074/6464 [1:32:17<27:43, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.02, 'grad_norm': 0.7166447043418884, 'learning_rate': 4.304071837745781e-05, 'epoch': 0.78}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5075/6464 [1:32:18<28:01, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0529, 'grad_norm': 0.6347339153289795, 'learning_rate': 4.300975383186252e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5076/6464 [1:32:19<27:56, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1945, 'grad_norm': 0.6326282620429993, 'learning_rate': 4.2978789286267225e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5077/6464 [1:32:20<28:16, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4237, 'grad_norm': 0.6803028583526611, 'learning_rate': 4.294782474067193e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5078/6464 [1:32:22<30:48, 1.33s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1529, 'grad_norm': 0.5965775847434998, 'learning_rate': 4.291686019507664e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5079/6464 [1:32:23<29:10, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2669, 'grad_norm': 0.7938952445983887, 'learning_rate': 4.2885895649481345e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5080/6464 [1:32:24<27:24, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1696, 'grad_norm': 0.8237273097038269, 'learning_rate': 4.285493110388606e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5081/6464 [1:32:25<26:04, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.336, 'grad_norm': 0.7870559096336365, 'learning_rate': 4.2823966558290755e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5082/6464 [1:32:26<25:23, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.084, 'grad_norm': 0.7088160514831543, 'learning_rate': 4.2793002012695466e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5083/6464 [1:32:27<25:09, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9307, 'grad_norm': 0.5924956798553467, 'learning_rate': 4.276203746710018e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5084/6464 [1:32:29<26:51, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.144, 'grad_norm': 0.6912433505058289, 'learning_rate': 4.2731072921504875e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5085/6464 [1:32:30<27:16, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4077, 'grad_norm': 0.7185222506523132, 'learning_rate': 4.2700108375909586e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5086/6464 [1:32:31<27:51, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1169, 'grad_norm': 0.6515185832977295, 'learning_rate': 4.266914383031429e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5087/6464 [1:32:32<25:22, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0536, 'grad_norm': 0.8360210657119751, 'learning_rate': 4.2638179284718996e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5088/6464 [1:32:33<24:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.088, 'grad_norm': 0.7315107583999634, 'learning_rate': 4.260721473912371e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5089/6464 [1:32:34<23:33, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8669, 'grad_norm': 0.674961507320404, 'learning_rate': 4.257625019352841e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5090/6464 [1:32:35<22:32, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0048, 'grad_norm': 0.7963590025901794, 'learning_rate': 4.254528564793312e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5091/6464 [1:32:36<25:01, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0589, 'grad_norm': 0.5761837959289551, 'learning_rate': 4.251432110233782e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5092/6464 [1:32:37<23:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0289, 'grad_norm': 0.7023857235908508, 'learning_rate': 4.248335655674253e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5093/6464 [1:32:38<22:22, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8055, 'grad_norm': 0.7173283696174622, 'learning_rate': 4.245239201114724e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5094/6464 [1:32:39<22:31, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.263, 'grad_norm': 0.6761393547058105, 'learning_rate': 4.242142746555194e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5095/6464 [1:32:40<23:16, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0426, 'grad_norm': 0.6122133731842041, 'learning_rate': 4.239046291995665e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5096/6464 [1:32:41<22:05, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0584, 'grad_norm': 0.8491267561912537, 'learning_rate': 4.235949837436136e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5097/6464 [1:32:42<22:11, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9702, 'grad_norm': 0.7776833176612854, 'learning_rate': 4.232853382876606e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5098/6464 [1:32:43<24:21, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1286, 'grad_norm': 0.6371245980262756, 'learning_rate': 4.229756928317077e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5099/6464 [1:32:44<24:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9392, 'grad_norm': 0.7145446538925171, 'learning_rate': 4.226660473757548e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5100/6464 [1:32:45<23:49, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0768, 'grad_norm': 0.7235157489776611, 'learning_rate': 4.223564019198019e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5101/6464 [1:32:46<23:30, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1568, 'grad_norm': 0.8075705170631409, 'learning_rate': 4.220467564638489e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5102/6464 [1:32:47<23:36, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8857, 'grad_norm': 0.895529568195343, 'learning_rate': 4.21737111007896e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5103/6464 [1:32:48<22:57, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0139, 'grad_norm': 0.8024253249168396, 'learning_rate': 4.214274655519431e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5104/6464 [1:32:50<25:05, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1084, 'grad_norm': 0.563563883304596, 'learning_rate': 4.211178200959901e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5105/6464 [1:32:50<23:58, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1179, 'grad_norm': 0.7044262886047363, 'learning_rate': 4.208081746400372e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5106/6464 [1:32:52<25:33, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.452, 'grad_norm': 0.7626616358757019, 'learning_rate': 4.204985291840842e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5107/6464 [1:32:53<26:37, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9523, 'grad_norm': 0.6032058596611023, 'learning_rate': 4.201888837281313e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5108/6464 [1:32:54<26:03, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1572, 'grad_norm': 0.6426862478256226, 'learning_rate': 4.198792382721784e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5109/6464 [1:32:55<26:09, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3816, 'grad_norm': 0.7683783173561096, 'learning_rate': 4.1956959281622544e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5110/6464 [1:32:56<25:51, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0813, 'grad_norm': 0.6747589111328125, 'learning_rate': 4.1925994736027255e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5111/6464 [1:32:57<24:44, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9878, 'grad_norm': 0.7491303086280823, 'learning_rate': 4.189503019043195e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5112/6464 [1:32:59<25:03, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1085, 'grad_norm': 0.6640791893005371, 'learning_rate': 4.1864065644836664e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5113/6464 [1:33:00<25:50, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3153, 'grad_norm': 0.7253525853157043, 'learning_rate': 4.1833101099241376e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5114/6464 [1:33:01<25:39, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3242, 'grad_norm': 0.8000211715698242, 'learning_rate': 4.1802136553646073e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5115/6464 [1:33:02<24:19, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1239, 'grad_norm': 0.99039226770401, 'learning_rate': 4.1771172008050785e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5116/6464 [1:33:03<24:05, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8912, 'grad_norm': 0.6459591388702393, 'learning_rate': 4.174020746245549e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5117/6464 [1:33:04<23:09, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2296, 'grad_norm': 0.8717030882835388, 'learning_rate': 4.1709242916860194e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5118/6464 [1:33:05<24:45, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1805, 'grad_norm': 0.6384283304214478, 'learning_rate': 4.1678278371264905e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5119/6464 [1:33:07<26:44, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4396, 'grad_norm': 0.7358367443084717, 'learning_rate': 4.164731382566961e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5120/6464 [1:33:08<26:03, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4179, 'grad_norm': 0.8447756767272949, 'learning_rate': 4.161634928007432e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5121/6464 [1:33:09<26:07, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1261, 'grad_norm': 0.6622317433357239, 'learning_rate': 4.158538473447902e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5122/6464 [1:33:10<25:58, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0981, 'grad_norm': 0.6432759165763855, 'learning_rate': 4.155442018888373e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5123/6464 [1:33:11<25:09, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.23, 'grad_norm': 0.8962159156799316, 'learning_rate': 4.152345564328844e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5124/6464 [1:33:12<25:43, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3133, 'grad_norm': 0.7086086273193359, 'learning_rate': 4.149249109769314e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5125/6464 [1:33:13<25:25, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0156, 'grad_norm': 0.7273638248443604, 'learning_rate': 4.146152655209785e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5126/6464 [1:33:14<24:35, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9638, 'grad_norm': 0.779056191444397, 'learning_rate': 4.1430562006502555e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5127/6464 [1:33:15<24:31, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1202, 'grad_norm': 0.7060213685035706, 'learning_rate': 4.139959746090726e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5128/6464 [1:33:16<24:05, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9343, 'grad_norm': 0.6478337645530701, 'learning_rate': 4.136863291531197e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5129/6464 [1:33:18<24:38, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9935, 'grad_norm': 0.5940291285514832, 'learning_rate': 4.1337668369716676e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5130/6464 [1:33:19<24:42, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0123, 'grad_norm': 0.6474856734275818, 'learning_rate': 4.130670382412139e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5131/6464 [1:33:20<23:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9158, 'grad_norm': 0.6511790752410889, 'learning_rate': 4.1275739278526085e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5132/6464 [1:33:21<23:26, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3117, 'grad_norm': 0.7629575133323669, 'learning_rate': 4.1244774732930797e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5133/6464 [1:33:22<25:29, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1101, 'grad_norm': 0.609978437423706, 'learning_rate': 4.121381018733551e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5134/6464 [1:33:23<25:05, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9813, 'grad_norm': 0.6718799471855164, 'learning_rate': 4.1182845641740206e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5135/6464 [1:33:24<24:15, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0681, 'grad_norm': 0.7875359654426575, 'learning_rate': 4.115188109614492e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5136/6464 [1:33:25<23:14, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0619, 'grad_norm': 0.7705553770065308, 'learning_rate': 4.112091655054962e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5137/6464 [1:33:26<23:58, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.174, 'grad_norm': 0.7177802920341492, 'learning_rate': 4.108995200495433e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 79%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5138/6464 [1:33:27<23:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1484, 'grad_norm': 0.6991090178489685, 'learning_rate': 4.105898745935904e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5139/6464 [1:33:28<23:30, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1496, 'grad_norm': 0.7358909845352173, 'learning_rate': 4.102802291376374e-05, 'epoch': 0.79}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5140/6464 [1:33:29<23:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2496, 'grad_norm': 0.6639956831932068, 'learning_rate': 4.0997058368168453e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5141/6464 [1:33:31<24:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1627, 'grad_norm': 0.7254418134689331, 'learning_rate': 4.096609382257315e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5142/6464 [1:33:32<23:34, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2072, 'grad_norm': 0.8093604445457458, 'learning_rate': 4.093512927697786e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5143/6464 [1:33:33<22:20, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8748, 'grad_norm': 0.709628164768219, 'learning_rate': 4.0904164731382574e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5144/6464 [1:33:33<21:45, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1422, 'grad_norm': 0.771115243434906, 'learning_rate': 4.087320018578727e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5145/6464 [1:33:35<22:09, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1142, 'grad_norm': 0.7351731657981873, 'learning_rate': 4.084223564019198e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5146/6464 [1:33:35<21:25, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.943, 'grad_norm': 0.7342020273208618, 'learning_rate': 4.081127109459669e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5147/6464 [1:33:36<21:29, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9959, 'grad_norm': 0.6817193627357483, 'learning_rate': 4.07803065490014e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5148/6464 [1:33:38<22:54, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2237, 'grad_norm': 0.750903844833374, 'learning_rate': 4.0749342003406104e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5149/6464 [1:33:39<22:00, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.161, 'grad_norm': 0.7772724628448486, 'learning_rate': 4.071837745781081e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5150/6464 [1:33:40<22:28, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3075, 'grad_norm': 0.8379826545715332, 'learning_rate': 4.068741291221552e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5151/6464 [1:33:41<23:14, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1676, 'grad_norm': 0.7901589274406433, 'learning_rate': 4.065644836662022e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5152/6464 [1:33:42<23:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.247, 'grad_norm': 0.6775223612785339, 'learning_rate': 4.062548382102493e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5153/6464 [1:33:43<22:57, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1141, 'grad_norm': 0.7376784086227417, 'learning_rate': 4.059451927542964e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5154/6464 [1:33:44<22:09, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.822, 'grad_norm': 0.6721224784851074, 'learning_rate': 4.056355472983434e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5155/6464 [1:33:45<22:05, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0779, 'grad_norm': 0.7154517769813538, 'learning_rate': 4.053259018423905e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5156/6464 [1:33:46<21:56, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0137, 'grad_norm': 0.6625959277153015, 'learning_rate': 4.0501625638643754e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5157/6464 [1:33:47<22:12, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.071, 'grad_norm': 0.7971206903457642, 'learning_rate': 4.0470661093048465e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5158/6464 [1:33:48<23:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1987, 'grad_norm': 0.7282736301422119, 'learning_rate': 4.043969654745317e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5159/6464 [1:33:49<23:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.303, 'grad_norm': 0.7339154481887817, 'learning_rate': 4.0408732001857874e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5160/6464 [1:33:50<23:13, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1929, 'grad_norm': 0.7711108326911926, 'learning_rate': 4.0377767456262586e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5161/6464 [1:33:51<22:42, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9971, 'grad_norm': 0.7396089434623718, 'learning_rate': 4.0346802910667284e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5162/6464 [1:33:52<22:27, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0107, 'grad_norm': 0.7098840475082397, 'learning_rate': 4.0315838365071995e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5163/6464 [1:33:53<23:26, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1383, 'grad_norm': 0.711150050163269, 'learning_rate': 4.02848738194767e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5164/6464 [1:33:55<23:58, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1705, 'grad_norm': 0.6889194846153259, 'learning_rate': 4.0253909273881404e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5165/6464 [1:33:56<23:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1781, 'grad_norm': 0.7019180059432983, 'learning_rate': 4.0222944728286115e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5166/6464 [1:33:57<24:17, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1647, 'grad_norm': 0.6985650658607483, 'learning_rate': 4.019198018269082e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5167/6464 [1:33:58<23:36, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9536, 'grad_norm': 0.7099125981330872, 'learning_rate': 4.016101563709553e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5168/6464 [1:33:59<22:59, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9557, 'grad_norm': 0.7620473504066467, 'learning_rate': 4.013005109150023e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5169/6464 [1:34:00<22:38, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0407, 'grad_norm': 0.763464629650116, 'learning_rate': 4.009908654590494e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5170/6464 [1:34:01<22:45, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1325, 'grad_norm': 0.641603946685791, 'learning_rate': 4.006812200030965e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5171/6464 [1:34:02<22:18, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1551, 'grad_norm': 0.683490514755249, 'learning_rate': 4.003715745471435e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5172/6464 [1:34:03<22:19, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2141, 'grad_norm': 0.8618229627609253, 'learning_rate': 4.000619290911906e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5173/6464 [1:34:04<22:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1603, 'grad_norm': 0.6587375998497009, 'learning_rate': 3.9975228363523766e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5174/6464 [1:34:05<22:01, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2174, 'grad_norm': 0.8440096378326416, 'learning_rate': 3.994426381792847e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5175/6464 [1:34:06<22:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2667, 'grad_norm': 0.686026930809021, 'learning_rate': 3.991329927233318e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5176/6464 [1:34:07<22:03, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8219, 'grad_norm': 0.7687340378761292, 'learning_rate': 3.9882334726737886e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5177/6464 [1:34:08<22:39, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2865, 'grad_norm': 0.7969653606414795, 'learning_rate': 3.98513701811426e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5178/6464 [1:34:09<22:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1411, 'grad_norm': 0.754730224609375, 'learning_rate': 3.9820405635547295e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5179/6464 [1:34:10<22:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1104, 'grad_norm': 0.6740475296974182, 'learning_rate': 3.9789441089952007e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5180/6464 [1:34:11<22:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0498, 'grad_norm': 0.7092124819755554, 'learning_rate': 3.975847654435672e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5181/6464 [1:34:12<22:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0301, 'grad_norm': 0.6936230659484863, 'learning_rate': 3.9727511998761416e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5182/6464 [1:34:14<24:18, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0566, 'grad_norm': 0.6239697933197021, 'learning_rate': 3.969654745316613e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5183/6464 [1:34:15<23:38, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3518, 'grad_norm': 0.8887990713119507, 'learning_rate': 3.966558290757083e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5184/6464 [1:34:16<23:13, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0637, 'grad_norm': 0.7119863033294678, 'learning_rate': 3.9634618361975536e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5185/6464 [1:34:17<23:38, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0572, 'grad_norm': 0.8022072911262512, 'learning_rate': 3.960365381638025e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5186/6464 [1:34:18<22:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.976, 'grad_norm': 0.7191420197486877, 'learning_rate': 3.957268927078495e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5187/6464 [1:34:19<23:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2283, 'grad_norm': 0.7648558616638184, 'learning_rate': 3.9541724725189664e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5188/6464 [1:34:20<23:11, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1299, 'grad_norm': 0.7651019096374512, 'learning_rate': 3.951076017959436e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5189/6464 [1:34:21<23:17, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1851, 'grad_norm': 0.7402471899986267, 'learning_rate': 3.947979563399907e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5190/6464 [1:34:22<22:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9792, 'grad_norm': 1.1671556234359741, 'learning_rate': 3.9448831088403784e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5191/6464 [1:34:23<22:59, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0787, 'grad_norm': 0.7083786725997925, 'learning_rate': 3.941786654280848e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5192/6464 [1:34:25<23:23, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0966, 'grad_norm': 0.6384579539299011, 'learning_rate': 3.938690199721319e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5193/6464 [1:34:26<22:16, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9785, 'grad_norm': 0.7593061327934265, 'learning_rate': 3.93559374516179e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5194/6464 [1:34:27<21:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0767, 'grad_norm': 0.7026800513267517, 'learning_rate': 3.93249729060226e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5195/6464 [1:34:28<22:13, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0645, 'grad_norm': 0.7381207942962646, 'learning_rate': 3.9294008360427314e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5196/6464 [1:34:29<21:30, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1523, 'grad_norm': 0.7616084814071655, 'learning_rate': 3.926304381483202e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5197/6464 [1:34:30<21:36, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1191, 'grad_norm': 0.6931054592132568, 'learning_rate': 3.923207926923673e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5198/6464 [1:34:31<22:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1517, 'grad_norm': 0.7843918204307556, 'learning_rate': 3.920111472364143e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5199/6464 [1:34:32<21:17, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2575, 'grad_norm': 0.7926410436630249, 'learning_rate': 3.917015017804614e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5200/6464 [1:34:33<21:27, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8338, 'grad_norm': 0.6503440737724304, 'learning_rate': 3.913918563245085e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5201/6464 [1:34:34<23:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0631, 'grad_norm': 0.7511479258537292, 'learning_rate': 3.910822108685555e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5202/6464 [1:34:35<23:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0152, 'grad_norm': 0.6833363771438599, 'learning_rate': 3.907725654126026e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 80%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5203/6464 [1:34:36<24:06, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2957, 'grad_norm': 0.7136831283569336, 'learning_rate': 3.9046291995664964e-05, 'epoch': 0.8}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5204/6464 [1:34:37<22:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8316, 'grad_norm': 0.6394976377487183, 'learning_rate': 3.9015327450069675e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5205/6464 [1:34:38<22:51, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.009, 'grad_norm': 0.6633114814758301, 'learning_rate': 3.898436290447438e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5206/6464 [1:34:40<23:46, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0572, 'grad_norm': 0.6112269163131714, 'learning_rate': 3.8953398358879084e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5207/6464 [1:34:41<22:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0448, 'grad_norm': 0.7297282218933105, 'learning_rate': 3.8922433813283796e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5208/6464 [1:34:42<22:33, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1316, 'grad_norm': 0.6886746287345886, 'learning_rate': 3.8891469267688494e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5209/6464 [1:34:43<22:02, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1316, 'grad_norm': 0.7118772268295288, 'learning_rate': 3.8860504722093205e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5210/6464 [1:34:44<22:16, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1513, 'grad_norm': 0.7486311793327332, 'learning_rate': 3.8829540176497916e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5211/6464 [1:34:45<22:46, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0036, 'grad_norm': 0.6903826594352722, 'learning_rate': 3.8798575630902614e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5212/6464 [1:34:46<21:40, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9882, 'grad_norm': 0.7601447701454163, 'learning_rate': 3.8767611085307325e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5213/6464 [1:34:47<22:02, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8713, 'grad_norm': 0.6964239478111267, 'learning_rate': 3.873664653971203e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5214/6464 [1:34:48<20:55, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0011, 'grad_norm': 0.7430259585380554, 'learning_rate': 3.870568199411674e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5215/6464 [1:34:49<21:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3134, 'grad_norm': 0.7152525186538696, 'learning_rate': 3.8674717448521446e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5216/6464 [1:34:50<22:56, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5338, 'grad_norm': 0.8774245381355286, 'learning_rate': 3.864375290292615e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5217/6464 [1:34:51<23:54, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3886, 'grad_norm': 0.6316500902175903, 'learning_rate': 3.861278835733086e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5218/6464 [1:34:52<22:46, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0221, 'grad_norm': 0.7189867496490479, 'learning_rate': 3.858182381173556e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5219/6464 [1:34:53<22:22, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1106, 'grad_norm': 0.745890736579895, 'learning_rate': 3.855085926614027e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5220/6464 [1:34:54<22:06, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0691, 'grad_norm': 0.7364062070846558, 'learning_rate': 3.851989472054498e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5221/6464 [1:34:56<23:56, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9598, 'grad_norm': 0.5678910613059998, 'learning_rate': 3.848893017494968e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5222/6464 [1:34:57<22:58, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.14, 'grad_norm': 0.8013848066329956, 'learning_rate': 3.845796562935439e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5223/6464 [1:34:58<22:38, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9145, 'grad_norm': 0.7186180353164673, 'learning_rate': 3.8427001083759096e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5224/6464 [1:34:59<22:18, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.905, 'grad_norm': 0.5725998878479004, 'learning_rate': 3.839603653816381e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5225/6464 [1:35:00<21:34, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2659, 'grad_norm': 0.760848879814148, 'learning_rate': 3.836507199256851e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5226/6464 [1:35:01<21:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.184, 'grad_norm': 0.6910958290100098, 'learning_rate': 3.833410744697322e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5227/6464 [1:35:02<21:16, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2206, 'grad_norm': 0.8589369654655457, 'learning_rate': 3.830314290137793e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5228/6464 [1:35:03<21:01, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1635, 'grad_norm': 0.7084581255912781, 'learning_rate': 3.8272178355782626e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5229/6464 [1:35:04<21:43, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1195, 'grad_norm': 0.7298749685287476, 'learning_rate': 3.824121381018734e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5230/6464 [1:35:05<21:56, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1668, 'grad_norm': 0.6708138585090637, 'learning_rate': 3.821024926459205e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5231/6464 [1:35:06<20:55, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9968, 'grad_norm': 0.7029337882995605, 'learning_rate': 3.8179284718996746e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5232/6464 [1:35:07<21:05, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8829, 'grad_norm': 0.6378611922264099, 'learning_rate': 3.814832017340146e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5233/6464 [1:35:08<20:33, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0022, 'grad_norm': 0.7701823115348816, 'learning_rate': 3.811735562780616e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5234/6464 [1:35:09<20:57, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1201, 'grad_norm': 0.7058101892471313, 'learning_rate': 3.8086391082210874e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5235/6464 [1:35:10<20:56, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9702, 'grad_norm': 0.7514177560806274, 'learning_rate': 3.805542653661558e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5236/6464 [1:35:12<23:16, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1559, 'grad_norm': 0.6949059367179871, 'learning_rate': 3.802446199102028e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5237/6464 [1:35:13<23:56, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1612, 'grad_norm': 0.5847645998001099, 'learning_rate': 3.7993497445424994e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5238/6464 [1:35:14<23:43, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1587, 'grad_norm': 0.7132701873779297, 'learning_rate': 3.796253289982969e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5239/6464 [1:35:15<22:52, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1243, 'grad_norm': 0.7359314560890198, 'learning_rate': 3.79315683542344e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5240/6464 [1:35:16<23:54, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1726, 'grad_norm': 0.6357913613319397, 'learning_rate': 3.7900603808639115e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5241/6464 [1:35:17<22:31, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.862, 'grad_norm': 0.6098902225494385, 'learning_rate': 3.786963926304381e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5242/6464 [1:35:19<24:19, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2131, 'grad_norm': 0.6624987721443176, 'learning_rate': 3.7838674717448524e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5243/6464 [1:35:20<23:24, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9232, 'grad_norm': 0.704439640045166, 'learning_rate': 3.780771017185323e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5244/6464 [1:35:21<23:33, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0935, 'grad_norm': 0.7232704162597656, 'learning_rate': 3.777674562625794e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5245/6464 [1:35:22<22:34, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8916, 'grad_norm': 0.6544843912124634, 'learning_rate': 3.7745781080662644e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5246/6464 [1:35:23<22:22, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1044, 'grad_norm': 0.7023689150810242, 'learning_rate': 3.771481653506735e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5247/6464 [1:35:24<20:58, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0488, 'grad_norm': 0.8580260872840881, 'learning_rate': 3.768385198947206e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5248/6464 [1:35:25<20:08, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9711, 'grad_norm': 0.7984265089035034, 'learning_rate': 3.765288744387676e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5249/6464 [1:35:26<20:46, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.177, 'grad_norm': 0.7420030832290649, 'learning_rate': 3.762192289828147e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5250/6464 [1:35:27<20:35, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1973, 'grad_norm': 0.7995045185089111, 'learning_rate': 3.759095835268618e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5251/6464 [1:35:28<20:37, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2054, 'grad_norm': 0.9643868207931519, 'learning_rate': 3.755999380709088e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5252/6464 [1:35:29<20:43, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0816, 'grad_norm': 0.7087801694869995, 'learning_rate': 3.752902926149559e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5253/6464 [1:35:30<21:05, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1881, 'grad_norm': 0.7639394402503967, 'learning_rate': 3.7498064715900295e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5254/6464 [1:35:31<21:32, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2105, 'grad_norm': 0.6567826867103577, 'learning_rate': 3.7467100170305006e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5255/6464 [1:35:32<20:53, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2229, 'grad_norm': 0.8913034200668335, 'learning_rate': 3.743613562470971e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5256/6464 [1:35:33<20:30, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9649, 'grad_norm': 0.6949189901351929, 'learning_rate': 3.7405171079114415e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5257/6464 [1:35:34<21:42, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0732, 'grad_norm': 0.6180838942527771, 'learning_rate': 3.7374206533519126e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5258/6464 [1:35:35<20:39, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1569, 'grad_norm': 0.8213254809379578, 'learning_rate': 3.7343241987923824e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5259/6464 [1:35:36<21:38, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0962, 'grad_norm': 0.657292902469635, 'learning_rate': 3.7312277442328536e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5260/6464 [1:35:37<20:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0194, 'grad_norm': 0.8083762526512146, 'learning_rate': 3.728131289673325e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5261/6464 [1:35:38<20:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0585, 'grad_norm': 0.748213529586792, 'learning_rate': 3.7250348351137945e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5262/6464 [1:35:39<20:36, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0399, 'grad_norm': 0.7275370359420776, 'learning_rate': 3.7219383805542656e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5263/6464 [1:35:41<23:23, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3528, 'grad_norm': 0.6860643029212952, 'learning_rate': 3.718841925994736e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5264/6464 [1:35:42<22:40, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1233, 'grad_norm': 0.7450210452079773, 'learning_rate': 3.715745471435207e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5265/6464 [1:35:43<21:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9187, 'grad_norm': 0.745711088180542, 'learning_rate': 3.712649016875678e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5266/6464 [1:35:44<19:58, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9587, 'grad_norm': 0.7754723429679871, 'learning_rate': 3.709552562316148e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5267/6464 [1:35:45<19:41, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8609, 'grad_norm': 0.7157600522041321, 'learning_rate': 3.706456107756619e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 81%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5268/6464 [1:35:46<20:08, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2323, 'grad_norm': 0.9011712670326233, 'learning_rate': 3.703359653197089e-05, 'epoch': 0.81}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5269/6464 [1:35:47<19:42, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0172, 'grad_norm': 0.7817054390907288, 'learning_rate': 3.70026319863756e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5270/6464 [1:35:48<21:11, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1921, 'grad_norm': 0.7706435918807983, 'learning_rate': 3.697166744078031e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5271/6464 [1:35:49<21:36, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1252, 'grad_norm': 0.7326743006706238, 'learning_rate': 3.694070289518501e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5272/6464 [1:35:50<23:16, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3827, 'grad_norm': 0.6252304315567017, 'learning_rate': 3.690973834958972e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5273/6464 [1:35:52<23:14, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9919, 'grad_norm': 0.7324017882347107, 'learning_rate': 3.687877380399443e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5274/6464 [1:35:53<22:45, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2354, 'grad_norm': 0.7912763953208923, 'learning_rate': 3.684780925839914e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5275/6464 [1:35:54<22:09, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1202, 'grad_norm': 0.7104099988937378, 'learning_rate': 3.681684471280384e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5276/6464 [1:35:55<22:05, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.348, 'grad_norm': 0.7330620884895325, 'learning_rate': 3.678588016720855e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5277/6464 [1:35:56<22:16, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1502, 'grad_norm': 0.7547183036804199, 'learning_rate': 3.675491562161326e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5278/6464 [1:35:57<22:45, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.217, 'grad_norm': 0.6571875214576721, 'learning_rate': 3.6723951076017956e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5279/6464 [1:35:58<23:23, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2268, 'grad_norm': 0.7226694822311401, 'learning_rate': 3.669298653042267e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5280/6464 [1:35:59<22:12, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2162, 'grad_norm': 0.8497636914253235, 'learning_rate': 3.666202198482738e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5281/6464 [1:36:00<21:24, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9752, 'grad_norm': 0.7482522130012512, 'learning_rate': 3.6631057439232084e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5282/6464 [1:36:01<21:35, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1771, 'grad_norm': 0.7109049558639526, 'learning_rate': 3.660009289363679e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5283/6464 [1:36:02<20:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3401, 'grad_norm': 0.9520250558853149, 'learning_rate': 3.656912834804149e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5284/6464 [1:36:03<20:27, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2535, 'grad_norm': 0.755916953086853, 'learning_rate': 3.6538163802446204e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5285/6464 [1:36:05<20:46, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1312, 'grad_norm': 0.7482356429100037, 'learning_rate': 3.65071992568509e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5286/6464 [1:36:06<20:24, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1195, 'grad_norm': 0.7022709250450134, 'learning_rate': 3.6476234711255613e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5287/6464 [1:36:07<22:01, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3633, 'grad_norm': 0.7319328784942627, 'learning_rate': 3.6445270165660325e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5288/6464 [1:36:08<21:49, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1823, 'grad_norm': 0.682601273059845, 'learning_rate': 3.641430562006502e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5289/6464 [1:36:09<20:28, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.042, 'grad_norm': 0.8398153781890869, 'learning_rate': 3.6383341074469734e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5290/6464 [1:36:10<20:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9732, 'grad_norm': 0.6318056583404541, 'learning_rate': 3.635237652887444e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5291/6464 [1:36:11<21:06, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0999, 'grad_norm': 0.6951815485954285, 'learning_rate': 3.632141198327915e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5292/6464 [1:36:12<21:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1901, 'grad_norm': 0.6974775195121765, 'learning_rate': 3.6290447437683854e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5293/6464 [1:36:13<20:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1211, 'grad_norm': 0.7505661249160767, 'learning_rate': 3.625948289208856e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5294/6464 [1:36:14<20:37, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0688, 'grad_norm': 0.7333738803863525, 'learning_rate': 3.622851834649327e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5295/6464 [1:36:15<20:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1257, 'grad_norm': 0.7117434144020081, 'learning_rate': 3.619755380089797e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5296/6464 [1:36:16<21:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1906, 'grad_norm': 0.7801632881164551, 'learning_rate': 3.616658925530268e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5297/6464 [1:36:18<21:27, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1646, 'grad_norm': 0.7722020149230957, 'learning_rate': 3.613562470970739e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5298/6464 [1:36:19<23:22, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.232, 'grad_norm': 0.6386875510215759, 'learning_rate': 3.610466016411209e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5299/6464 [1:36:20<23:48, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3019, 'grad_norm': 0.7598816752433777, 'learning_rate': 3.60736956185168e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5300/6464 [1:36:21<23:01, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0677, 'grad_norm': 0.68121737241745, 'learning_rate': 3.6042731072921505e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5301/6464 [1:36:22<22:10, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1106, 'grad_norm': 0.7147106528282166, 'learning_rate': 3.6011766527326216e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5302/6464 [1:36:23<21:36, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.087, 'grad_norm': 0.7180469036102295, 'learning_rate': 3.598080198173092e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5303/6464 [1:36:24<20:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9993, 'grad_norm': 0.7639851570129395, 'learning_rate': 3.5949837436135625e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5304/6464 [1:36:25<19:15, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0552, 'grad_norm': 0.7976819276809692, 'learning_rate': 3.5918872890540337e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5305/6464 [1:36:26<19:07, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.04, 'grad_norm': 0.762945830821991, 'learning_rate': 3.5887908344945034e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5306/6464 [1:36:28<21:06, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0891, 'grad_norm': 0.5940061807632446, 'learning_rate': 3.5856943799349746e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5307/6464 [1:36:29<21:30, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1047, 'grad_norm': 0.7059971690177917, 'learning_rate': 3.582597925375446e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5308/6464 [1:36:30<20:28, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2275, 'grad_norm': 0.8236611485481262, 'learning_rate': 3.5795014708159155e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5309/6464 [1:36:31<21:05, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2672, 'grad_norm': 0.7732686996459961, 'learning_rate': 3.5764050162563866e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5310/6464 [1:36:32<19:47, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9329, 'grad_norm': 0.7428220510482788, 'learning_rate': 3.573308561696857e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5311/6464 [1:36:33<20:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8383, 'grad_norm': 0.7397980093955994, 'learning_rate': 3.570212107137328e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5312/6464 [1:36:34<20:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3676, 'grad_norm': 0.7067403793334961, 'learning_rate': 3.567115652577799e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5313/6464 [1:36:35<20:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0439, 'grad_norm': 0.7035689949989319, 'learning_rate': 3.564019198018269e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5314/6464 [1:36:36<19:57, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8643, 'grad_norm': 0.7332860231399536, 'learning_rate': 3.56092274345874e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5315/6464 [1:36:37<20:36, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1231, 'grad_norm': 0.6607322692871094, 'learning_rate': 3.55782628889921e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5316/6464 [1:36:38<21:16, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9938, 'grad_norm': 0.611254870891571, 'learning_rate': 3.554729834339681e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5317/6464 [1:36:40<22:40, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1967, 'grad_norm': 0.6592238545417786, 'learning_rate': 3.551633379780152e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5318/6464 [1:36:41<22:39, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2538, 'grad_norm': 0.7337603569030762, 'learning_rate': 3.548536925220622e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5319/6464 [1:36:42<22:22, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0858, 'grad_norm': 0.720649778842926, 'learning_rate': 3.545440470661093e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5320/6464 [1:36:43<22:06, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2229, 'grad_norm': 0.7465639710426331, 'learning_rate': 3.542344016101564e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5321/6464 [1:36:44<20:08, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8668, 'grad_norm': 0.7480098605155945, 'learning_rate': 3.539247561542035e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5322/6464 [1:36:45<20:54, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2738, 'grad_norm': 0.7140259146690369, 'learning_rate': 3.536151106982505e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5323/6464 [1:36:46<21:20, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2474, 'grad_norm': 0.6593645811080933, 'learning_rate': 3.533054652422976e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5324/6464 [1:36:48<21:26, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1034, 'grad_norm': 0.6431949138641357, 'learning_rate': 3.529958197863447e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5325/6464 [1:36:49<21:41, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1668, 'grad_norm': 0.7235196232795715, 'learning_rate': 3.5268617433039167e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5326/6464 [1:36:50<20:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2182, 'grad_norm': 0.7908056378364563, 'learning_rate': 3.523765288744388e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5327/6464 [1:36:51<20:42, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1582, 'grad_norm': 0.7747386693954468, 'learning_rate': 3.520668834184859e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5328/6464 [1:36:52<19:32, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9454, 'grad_norm': 0.739438533782959, 'learning_rate': 3.517572379625329e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5329/6464 [1:36:53<19:41, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0325, 'grad_norm': 0.6539432406425476, 'learning_rate': 3.5144759250658e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5330/6464 [1:36:54<20:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2378, 'grad_norm': 0.6273197531700134, 'learning_rate': 3.51137947050627e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5331/6464 [1:36:55<20:41, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1783, 'grad_norm': 0.6875300407409668, 'learning_rate': 3.5082830159467414e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 82%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5332/6464 [1:36:56<19:13, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8744, 'grad_norm': 0.7985610365867615, 'learning_rate': 3.505186561387212e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5333/6464 [1:36:57<18:45, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.31, 'grad_norm': 0.8161163330078125, 'learning_rate': 3.5020901068276824e-05, 'epoch': 0.82}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5334/6464 [1:36:58<18:28, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1127, 'grad_norm': 0.7233881950378418, 'learning_rate': 3.4989936522681535e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5335/6464 [1:36:59<18:55, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0448, 'grad_norm': 0.6944867968559265, 'learning_rate': 3.495897197708623e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5336/6464 [1:37:00<18:14, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0439, 'grad_norm': 0.7878615856170654, 'learning_rate': 3.4928007431490944e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5337/6464 [1:37:01<19:02, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3601, 'grad_norm': 0.8023691177368164, 'learning_rate': 3.4897042885895655e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5338/6464 [1:37:02<19:02, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2333, 'grad_norm': 0.7388765215873718, 'learning_rate': 3.486607834030035e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5339/6464 [1:37:03<20:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1417, 'grad_norm': 0.6939775943756104, 'learning_rate': 3.4835113794705065e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5340/6464 [1:37:04<20:01, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9986, 'grad_norm': 0.6552546620368958, 'learning_rate': 3.480414924910977e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5341/6464 [1:37:05<20:49, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.214, 'grad_norm': 0.7313109636306763, 'learning_rate': 3.477318470351448e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5342/6464 [1:37:06<19:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9707, 'grad_norm': 0.9386375546455383, 'learning_rate': 3.4742220157919185e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5343/6464 [1:37:07<19:25, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.128, 'grad_norm': 0.7080686092376709, 'learning_rate': 3.471125561232389e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5344/6464 [1:37:08<18:59, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8554, 'grad_norm': 0.6151601672172546, 'learning_rate': 3.46802910667286e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5345/6464 [1:37:09<19:29, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.103, 'grad_norm': 0.7685462832450867, 'learning_rate': 3.46493265211333e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5346/6464 [1:37:10<19:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.124, 'grad_norm': 0.7165085673332214, 'learning_rate': 3.461836197553801e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5347/6464 [1:37:12<20:37, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2543, 'grad_norm': 0.6611863374710083, 'learning_rate': 3.458739742994272e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5348/6464 [1:37:13<20:49, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1203, 'grad_norm': 0.6821208596229553, 'learning_rate': 3.4556432884347426e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5349/6464 [1:37:14<21:47, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0192, 'grad_norm': 0.6207703351974487, 'learning_rate': 3.452546833875213e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5350/6464 [1:37:15<20:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0173, 'grad_norm': 0.834904670715332, 'learning_rate': 3.4494503793156835e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5351/6464 [1:37:16<19:24, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1588, 'grad_norm': 0.8064426183700562, 'learning_rate': 3.446353924756155e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5352/6464 [1:37:17<18:40, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1063, 'grad_norm': 0.8182348012924194, 'learning_rate': 3.443257470196625e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5353/6464 [1:37:18<18:20, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2111, 'grad_norm': 0.7535254955291748, 'learning_rate': 3.4401610156370956e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5354/6464 [1:37:19<18:27, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0954, 'grad_norm': 0.7600870728492737, 'learning_rate': 3.437064561077567e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5355/6464 [1:37:20<17:53, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.06, 'grad_norm': 0.722375214099884, 'learning_rate': 3.4339681065180365e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5356/6464 [1:37:21<17:52, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9065, 'grad_norm': 0.6919851303100586, 'learning_rate': 3.4308716519585076e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5357/6464 [1:37:22<18:31, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9189, 'grad_norm': 0.6028034090995789, 'learning_rate': 3.427775197398979e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5358/6464 [1:37:23<19:11, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9924, 'grad_norm': 0.680018424987793, 'learning_rate': 3.424678742839449e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5359/6464 [1:37:24<19:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1355, 'grad_norm': 0.7407569289207458, 'learning_rate': 3.42158228827992e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5360/6464 [1:37:25<20:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3957, 'grad_norm': 0.7566336989402771, 'learning_rate': 3.41848583372039e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5361/6464 [1:37:26<19:15, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.181, 'grad_norm': 0.8613432049751282, 'learning_rate': 3.415389379160861e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5362/6464 [1:37:27<18:49, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2035, 'grad_norm': 0.7480749487876892, 'learning_rate': 3.412292924601332e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5363/6464 [1:37:28<18:07, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8308, 'grad_norm': 0.647040843963623, 'learning_rate': 3.409196470041802e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5364/6464 [1:37:29<18:28, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1356, 'grad_norm': 0.7825866937637329, 'learning_rate': 3.406100015482273e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5365/6464 [1:37:30<17:53, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0757, 'grad_norm': 0.7631927132606506, 'learning_rate': 3.403003560922743e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5366/6464 [1:37:31<19:23, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2784, 'grad_norm': 0.661360502243042, 'learning_rate': 3.399907106363214e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5367/6464 [1:37:32<19:16, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1592, 'grad_norm': 0.7048453688621521, 'learning_rate': 3.3968106518036854e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5368/6464 [1:37:33<19:28, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1648, 'grad_norm': 0.7208485007286072, 'learning_rate': 3.393714197244156e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5369/6464 [1:37:34<19:12, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1806, 'grad_norm': 0.7143778204917908, 'learning_rate': 3.390617742684626e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5370/6464 [1:37:36<19:52, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.118, 'grad_norm': 0.6663089394569397, 'learning_rate': 3.387521288125097e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5371/6464 [1:37:37<19:23, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9286, 'grad_norm': 0.7160811424255371, 'learning_rate': 3.384424833565568e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5372/6464 [1:37:38<18:40, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2389, 'grad_norm': 0.9396677017211914, 'learning_rate': 3.3813283790060383e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5373/6464 [1:37:39<18:38, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9521, 'grad_norm': 0.8053677678108215, 'learning_rate': 3.378231924446509e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5374/6464 [1:37:40<19:21, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0873, 'grad_norm': 0.7322975397109985, 'learning_rate': 3.37513546988698e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5375/6464 [1:37:41<21:10, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3947, 'grad_norm': 0.6521808505058289, 'learning_rate': 3.37203901532745e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5376/6464 [1:37:42<20:27, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0389, 'grad_norm': 0.7021231055259705, 'learning_rate': 3.368942560767921e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5377/6464 [1:37:43<20:18, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.072, 'grad_norm': 0.7644325494766235, 'learning_rate': 3.365846106208392e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5378/6464 [1:37:44<19:34, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9048, 'grad_norm': 0.666067898273468, 'learning_rate': 3.3627496516488624e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5379/6464 [1:37:45<19:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3695, 'grad_norm': 0.7865363955497742, 'learning_rate': 3.359653197089333e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5380/6464 [1:37:47<20:03, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.073, 'grad_norm': 0.6457797884941101, 'learning_rate': 3.3565567425298034e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5381/6464 [1:37:48<20:33, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2445, 'grad_norm': 0.684442400932312, 'learning_rate': 3.3534602879702745e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5382/6464 [1:37:49<18:50, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.053, 'grad_norm': 0.7919034361839294, 'learning_rate': 3.350363833410745e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5383/6464 [1:37:50<19:20, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.191, 'grad_norm': 0.7208141684532166, 'learning_rate': 3.3472673788512154e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5384/6464 [1:37:51<18:59, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0929, 'grad_norm': 0.7980848550796509, 'learning_rate': 3.3441709242916866e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5385/6464 [1:37:52<20:24, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1474, 'grad_norm': 0.657014787197113, 'learning_rate': 3.341074469732156e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5386/6464 [1:37:53<19:02, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8605, 'grad_norm': 0.7463647127151489, 'learning_rate': 3.3379780151726275e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5387/6464 [1:37:54<18:44, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9418, 'grad_norm': 0.6587544083595276, 'learning_rate': 3.3348815606130986e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5388/6464 [1:37:55<19:02, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3186, 'grad_norm': 0.739129900932312, 'learning_rate': 3.331785106053569e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5389/6464 [1:37:56<19:56, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2126, 'grad_norm': 0.6462284922599792, 'learning_rate': 3.3286886514940395e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5390/6464 [1:37:57<19:31, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0967, 'grad_norm': 0.6492094993591309, 'learning_rate': 3.32559219693451e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5391/6464 [1:37:58<18:46, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9869, 'grad_norm': 0.6973142027854919, 'learning_rate': 3.322495742374981e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5392/6464 [1:37:59<18:06, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9015, 'grad_norm': 0.6997606158256531, 'learning_rate': 3.3193992878154516e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5393/6464 [1:38:00<17:57, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.124, 'grad_norm': 0.8426434993743896, 'learning_rate': 3.316302833255922e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5394/6464 [1:38:01<18:40, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0636, 'grad_norm': 0.7600712776184082, 'learning_rate': 3.313206378696393e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5395/6464 [1:38:02<19:06, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0865, 'grad_norm': 0.6802762150764465, 'learning_rate': 3.310109924136863e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5396/6464 [1:38:03<18:23, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8809, 'grad_norm': 0.7236692309379578, 'learning_rate': 3.307013469577334e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 83%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5397/6464 [1:38:05<19:33, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3549, 'grad_norm': 0.7309622764587402, 'learning_rate': 3.303917015017805e-05, 'epoch': 0.83}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5398/6464 [1:38:06<19:17, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0197, 'grad_norm': 0.6970983743667603, 'learning_rate': 3.300820560458276e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5399/6464 [1:38:07<17:59, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8338, 'grad_norm': 0.6883323192596436, 'learning_rate': 3.297724105898746e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5400/6464 [1:38:08<17:50, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0485, 'grad_norm': 0.7088056802749634, 'learning_rate': 3.2946276513392166e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5401/6464 [1:38:08<17:29, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9181, 'grad_norm': 0.718248188495636, 'learning_rate': 3.291531196779688e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5402/6464 [1:38:09<16:55, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9437, 'grad_norm': 0.7124057412147522, 'learning_rate': 3.288434742220158e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5403/6464 [1:38:10<17:23, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9132, 'grad_norm': 0.7357911467552185, 'learning_rate': 3.2853382876606286e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5404/6464 [1:38:11<17:58, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1381, 'grad_norm': 0.6484049558639526, 'learning_rate': 3.2822418331011e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5405/6464 [1:38:13<18:05, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9264, 'grad_norm': 0.6981768012046814, 'learning_rate': 3.2791453785415696e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5406/6464 [1:38:14<17:53, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0053, 'grad_norm': 0.7058355808258057, 'learning_rate': 3.276048923982041e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5407/6464 [1:38:15<17:46, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0067, 'grad_norm': 0.7515254616737366, 'learning_rate': 3.272952469422512e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5408/6464 [1:38:16<17:56, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1162, 'grad_norm': 0.6675436496734619, 'learning_rate': 3.269856014862982e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5409/6464 [1:38:17<17:48, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2736, 'grad_norm': 0.8675552010536194, 'learning_rate': 3.266759560303453e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5410/6464 [1:38:18<18:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0459, 'grad_norm': 0.6292269229888916, 'learning_rate': 3.263663105743923e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5411/6464 [1:38:19<19:02, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2706, 'grad_norm': 0.7653900384902954, 'learning_rate': 3.260566651184394e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5412/6464 [1:38:20<17:28, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9946, 'grad_norm': 0.879409909248352, 'learning_rate': 3.257470196624864e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž | 5413/6464 [1:38:21<18:24, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0977, 'grad_norm': 0.6369203329086304, 'learning_rate': 3.254373742065335e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5414/6464 [1:38:22<17:33, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9443, 'grad_norm': 0.7838242650032043, 'learning_rate': 3.2512772875058064e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5415/6464 [1:38:23<17:51, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1614, 'grad_norm': 0.7589995861053467, 'learning_rate': 3.248180832946277e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5416/6464 [1:38:24<18:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0564, 'grad_norm': 0.7015503644943237, 'learning_rate': 3.245084378386747e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5417/6464 [1:38:25<18:18, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1266, 'grad_norm': 0.7741891145706177, 'learning_rate': 3.241987923827218e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5418/6464 [1:38:26<19:06, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.09, 'grad_norm': 0.6334030032157898, 'learning_rate': 3.238891469267689e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5419/6464 [1:38:27<19:41, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2246, 'grad_norm': 0.6911303997039795, 'learning_rate': 3.2357950147081594e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5420/6464 [1:38:28<19:07, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0292, 'grad_norm': 0.7324188947677612, 'learning_rate': 3.23269856014863e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5421/6464 [1:38:30<19:57, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1602, 'grad_norm': 0.6116246581077576, 'learning_rate': 3.229602105589101e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5422/6464 [1:38:31<18:58, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.123, 'grad_norm': 0.757560670375824, 'learning_rate': 3.226505651029571e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5423/6464 [1:38:32<18:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1245, 'grad_norm': 0.787648618221283, 'learning_rate': 3.223409196470042e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5424/6464 [1:38:33<17:47, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9457, 'grad_norm': 0.7138397097587585, 'learning_rate': 3.220312741910513e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5425/6464 [1:38:34<18:06, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0721, 'grad_norm': 0.6680582165718079, 'learning_rate': 3.2172162873509835e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5426/6464 [1:38:35<18:07, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0509, 'grad_norm': 0.8020899295806885, 'learning_rate': 3.214119832791454e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5427/6464 [1:38:36<19:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0719, 'grad_norm': 0.6623438000679016, 'learning_rate': 3.2110233782319244e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5428/6464 [1:38:37<18:50, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0862, 'grad_norm': 0.7223666310310364, 'learning_rate': 3.2079269236723955e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5429/6464 [1:38:38<19:58, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1835, 'grad_norm': 0.6127805113792419, 'learning_rate': 3.204830469112866e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5430/6464 [1:38:39<19:26, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1815, 'grad_norm': 0.8318105936050415, 'learning_rate': 3.2017340145533364e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5431/6464 [1:38:40<19:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0085, 'grad_norm': 0.6451581716537476, 'learning_rate': 3.1986375599938076e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5432/6464 [1:38:42<19:05, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0843, 'grad_norm': 0.6863365769386292, 'learning_rate': 3.1955411054342773e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5433/6464 [1:38:43<19:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0825, 'grad_norm': 0.7254673838615417, 'learning_rate': 3.1924446508747485e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5434/6464 [1:38:44<19:52, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7856, 'grad_norm': 0.6210361123085022, 'learning_rate': 3.1893481963152196e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5435/6464 [1:38:45<19:17, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8886, 'grad_norm': 0.621574878692627, 'learning_rate': 3.18625174175569e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5436/6464 [1:38:46<18:07, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0104, 'grad_norm': 0.8013449311256409, 'learning_rate': 3.1831552871961605e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5437/6464 [1:38:47<18:48, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2522, 'grad_norm': 0.7439652681350708, 'learning_rate': 3.180058832636631e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5438/6464 [1:38:48<19:35, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2568, 'grad_norm': 0.6914841532707214, 'learning_rate': 3.176962378077102e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5439/6464 [1:38:49<19:16, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9711, 'grad_norm': 0.6901119351387024, 'learning_rate': 3.1738659235175726e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5440/6464 [1:38:51<19:07, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.181, 'grad_norm': 0.8693408370018005, 'learning_rate': 3.170769468958043e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5441/6464 [1:38:51<17:53, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9636, 'grad_norm': 0.8221790790557861, 'learning_rate': 3.167673014398514e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5442/6464 [1:38:52<17:55, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9361, 'grad_norm': 0.6295689344406128, 'learning_rate': 3.164576559838984e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5443/6464 [1:38:54<19:21, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3686, 'grad_norm': 0.6612435579299927, 'learning_rate': 3.161480105279455e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5444/6464 [1:38:55<18:51, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2757, 'grad_norm': 0.7864363193511963, 'learning_rate': 3.158383650719926e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5445/6464 [1:38:56<19:08, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2999, 'grad_norm': 0.6798285245895386, 'learning_rate': 3.155287196160397e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5446/6464 [1:38:57<19:48, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2304, 'grad_norm': 0.6450075507164001, 'learning_rate': 3.152190741600867e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5447/6464 [1:38:59<20:56, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9535, 'grad_norm': 0.6377757787704468, 'learning_rate': 3.1490942870413376e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5448/6464 [1:39:00<20:19, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1167, 'grad_norm': 0.7397738099098206, 'learning_rate': 3.145997832481809e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5449/6464 [1:39:01<18:44, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9626, 'grad_norm': 0.80938720703125, 'learning_rate': 3.142901377922279e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5450/6464 [1:39:02<18:16, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1481, 'grad_norm': 0.705309271812439, 'learning_rate': 3.1398049233627497e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5451/6464 [1:39:03<17:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0114, 'grad_norm': 0.7750602960586548, 'learning_rate': 3.136708468803221e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5452/6464 [1:39:04<19:35, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1614, 'grad_norm': 0.6188766956329346, 'learning_rate': 3.1336120142436906e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5453/6464 [1:39:05<19:31, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0543, 'grad_norm': 0.6896393895149231, 'learning_rate': 3.130515559684162e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5454/6464 [1:39:06<18:52, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9763, 'grad_norm': 0.7015329003334045, 'learning_rate': 3.127419105124633e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5455/6464 [1:39:07<17:42, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8942, 'grad_norm': 0.7577632665634155, 'learning_rate': 3.124322650565103e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5456/6464 [1:39:08<18:09, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.135, 'grad_norm': 0.6323253512382507, 'learning_rate': 3.121226196005574e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5457/6464 [1:39:09<17:37, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0876, 'grad_norm': 0.8272978663444519, 'learning_rate': 3.118129741446044e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5458/6464 [1:39:10<17:25, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1321, 'grad_norm': 0.7224549055099487, 'learning_rate': 3.1150332868865153e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5459/6464 [1:39:11<17:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9479, 'grad_norm': 0.681290328502655, 'learning_rate': 3.111936832326986e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5460/6464 [1:39:13<19:38, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.384, 'grad_norm': 0.7632349133491516, 'learning_rate': 3.108840377767456e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5461/6464 [1:39:14<19:04, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1345, 'grad_norm': 0.7089486122131348, 'learning_rate': 3.1057439232079274e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 84%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5462/6464 [1:39:15<18:03, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0249, 'grad_norm': 0.7591439485549927, 'learning_rate': 3.102647468648397e-05, 'epoch': 0.84}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5463/6464 [1:39:16<17:30, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1369, 'grad_norm': 0.9631490111351013, 'learning_rate': 3.099551014088868e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5464/6464 [1:39:17<17:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2106, 'grad_norm': 0.7955505847930908, 'learning_rate': 3.0964545595293394e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5465/6464 [1:39:18<18:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1241, 'grad_norm': 0.6545917391777039, 'learning_rate': 3.09335810496981e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5466/6464 [1:39:19<17:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2239, 'grad_norm': 0.8458883166313171, 'learning_rate': 3.0902616504102804e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5467/6464 [1:39:20<18:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0359, 'grad_norm': 0.7493281960487366, 'learning_rate': 3.087165195850751e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5468/6464 [1:39:21<17:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1182, 'grad_norm': 0.7823588848114014, 'learning_rate': 3.084068741291222e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5469/6464 [1:39:22<18:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0135, 'grad_norm': 0.632209300994873, 'learning_rate': 3.0809722867316924e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5470/6464 [1:39:24<18:45, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.104, 'grad_norm': 0.7709068059921265, 'learning_rate': 3.077875832172163e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5471/6464 [1:39:25<17:51, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2429, 'grad_norm': 0.844050407409668, 'learning_rate': 3.074779377612634e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5472/6464 [1:39:26<17:10, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9979, 'grad_norm': 0.6412907242774963, 'learning_rate': 3.071682923053104e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5473/6464 [1:39:27<17:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0676, 'grad_norm': 0.7128171324729919, 'learning_rate': 3.068586468493575e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5474/6464 [1:39:28<19:22, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3107, 'grad_norm': 0.6793957948684692, 'learning_rate': 3.065490013934046e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5475/6464 [1:39:29<18:22, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9412, 'grad_norm': 0.6905662417411804, 'learning_rate': 3.0623935593745165e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5476/6464 [1:39:30<17:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1368, 'grad_norm': 0.6810845136642456, 'learning_rate': 3.059297104814987e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5477/6464 [1:39:31<18:12, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2601, 'grad_norm': 0.6929471492767334, 'learning_rate': 3.0562006502554574e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5478/6464 [1:39:32<18:08, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1433, 'grad_norm': 0.8147743344306946, 'learning_rate': 3.0531041956959286e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5479/6464 [1:39:33<18:21, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1928, 'grad_norm': 0.711003839969635, 'learning_rate': 3.0500077411363994e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5480/6464 [1:39:35<20:01, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1221, 'grad_norm': 0.6337177157402039, 'learning_rate': 3.0469112865768695e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5481/6464 [1:39:36<19:05, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.074, 'grad_norm': 0.7226598858833313, 'learning_rate': 3.0438148320173403e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5482/6464 [1:39:37<18:34, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2154, 'grad_norm': 0.7604477405548096, 'learning_rate': 3.0407183774578107e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5483/6464 [1:39:38<18:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1638, 'grad_norm': 0.7100871801376343, 'learning_rate': 3.0376219228982815e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5484/6464 [1:39:39<19:13, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9705, 'grad_norm': 0.583130955696106, 'learning_rate': 3.0345254683387527e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5485/6464 [1:39:41<20:06, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0825, 'grad_norm': 0.6241014003753662, 'learning_rate': 3.0314290137792228e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5486/6464 [1:39:42<19:26, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2196, 'grad_norm': 0.8273164629936218, 'learning_rate': 3.0283325592196936e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5487/6464 [1:39:43<19:35, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.017, 'grad_norm': 0.6900531649589539, 'learning_rate': 3.025236104660164e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5488/6464 [1:39:44<19:26, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3785, 'grad_norm': 1.038439393043518, 'learning_rate': 3.022139650100635e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5489/6464 [1:39:45<18:40, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1595, 'grad_norm': 0.676842451095581, 'learning_rate': 3.019043195541106e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5490/6464 [1:39:46<18:30, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0821, 'grad_norm': 0.7003651261329651, 'learning_rate': 3.015946740981576e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5491/6464 [1:39:47<17:20, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2057, 'grad_norm': 0.8435566425323486, 'learning_rate': 3.012850286422047e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5492/6464 [1:39:48<16:06, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.962, 'grad_norm': 0.7884437441825867, 'learning_rate': 3.0097538318625174e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5493/6464 [1:39:50<17:53, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1482, 'grad_norm': 0.654772162437439, 'learning_rate': 3.006657377302988e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ– | 5494/6464 [1:39:50<17:00, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1192, 'grad_norm': 0.746553897857666, 'learning_rate': 3.0035609227434593e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5495/6464 [1:39:52<17:29, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9617, 'grad_norm': 0.6313595771789551, 'learning_rate': 3.0004644681839294e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5496/6464 [1:39:53<16:49, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9688, 'grad_norm': 0.7031683325767517, 'learning_rate': 2.9973680136244002e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5497/6464 [1:39:54<17:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0561, 'grad_norm': 0.6522960662841797, 'learning_rate': 2.9942715590648707e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5498/6464 [1:39:55<16:52, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9251, 'grad_norm': 0.7279539108276367, 'learning_rate': 2.9911751045053415e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5499/6464 [1:39:56<17:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0558, 'grad_norm': 0.689920961856842, 'learning_rate': 2.9880786499458126e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5500/6464 [1:39:57<18:30, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0153, 'grad_norm': 0.6824297308921814, 'learning_rate': 2.9849821953862827e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/other.py:619: UserWarning: Unable to fetch remote file due to the following error (ReadTimeoutError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)\"), '(Request ID: ec1eed8f-f30a-4640-9c6d-b72abf8073db)') - silently ignoring the lookup for the file config.json in Magpie-Align/MagpieLM-4B-Chat-v0.1.\n", " warnings.warn(\n", "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/save_and_load.py:218: UserWarning: Could not find a config file in Magpie-Align/MagpieLM-4B-Chat-v0.1 - will assume that the vocabulary was not modified.\n", " warnings.warn(\n", " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5501/6464 [1:40:09<1:08:01, 4.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0311, 'grad_norm': 0.6705641746520996, 'learning_rate': 2.9818857408267535e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5502/6464 [1:40:10<52:07, 3.25s/it] " ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9769, 'grad_norm': 0.6917800307273865, 'learning_rate': 2.978789286267224e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5503/6464 [1:40:11<41:34, 2.60s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.045, 'grad_norm': 0.733504593372345, 'learning_rate': 2.9756928317076948e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5504/6464 [1:40:12<34:19, 2.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1374, 'grad_norm': 0.6778205633163452, 'learning_rate': 2.972596377148166e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5505/6464 [1:40:13<27:54, 1.75s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9484, 'grad_norm': 0.808890700340271, 'learning_rate': 2.969499922588636e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5506/6464 [1:40:14<24:14, 1.52s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8413, 'grad_norm': 0.62729412317276, 'learning_rate': 2.9664034680291068e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5507/6464 [1:40:15<21:50, 1.37s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8661, 'grad_norm': 0.6463521718978882, 'learning_rate': 2.9633070134695773e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5508/6464 [1:40:15<19:44, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0605, 'grad_norm': 0.7147865295410156, 'learning_rate': 2.960210558910048e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5509/6464 [1:40:17<19:31, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1325, 'grad_norm': 0.7176058292388916, 'learning_rate': 2.9571141043505192e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5510/6464 [1:40:18<19:21, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5173, 'grad_norm': 0.7291633486747742, 'learning_rate': 2.9540176497909893e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5511/6464 [1:40:19<18:26, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9769, 'grad_norm': 0.684683620929718, 'learning_rate': 2.95092119523146e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5512/6464 [1:40:20<18:03, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0704, 'grad_norm': 0.7004538178443909, 'learning_rate': 2.9478247406719306e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5513/6464 [1:40:21<17:37, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3367, 'grad_norm': 0.8018507957458496, 'learning_rate': 2.9447282861124014e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5514/6464 [1:40:22<16:59, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9259, 'grad_norm': 0.7010086178779602, 'learning_rate': 2.9416318315528725e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5515/6464 [1:40:23<16:22, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9604, 'grad_norm': 0.7631054520606995, 'learning_rate': 2.9385353769933426e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5516/6464 [1:40:24<15:36, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1335, 'grad_norm': 0.8118054866790771, 'learning_rate': 2.9354389224338134e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5517/6464 [1:40:25<15:40, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2091, 'grad_norm': 0.7756730914115906, 'learning_rate': 2.932342467874284e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5518/6464 [1:40:26<17:21, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1904, 'grad_norm': 0.6256131529808044, 'learning_rate': 2.9292460133147547e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5519/6464 [1:40:27<16:47, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0695, 'grad_norm': 0.7194271087646484, 'learning_rate': 2.9261495587552258e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5520/6464 [1:40:28<16:37, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0512, 'grad_norm': 0.6777635812759399, 'learning_rate': 2.923053104195696e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5521/6464 [1:40:29<16:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0413, 'grad_norm': 0.6593034863471985, 'learning_rate': 2.9199566496361667e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5522/6464 [1:40:30<16:14, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1717, 'grad_norm': 0.7731529474258423, 'learning_rate': 2.9168601950766372e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5523/6464 [1:40:32<18:36, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3687, 'grad_norm': 0.6685566306114197, 'learning_rate': 2.913763740517108e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5524/6464 [1:40:33<18:31, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0469, 'grad_norm': 0.6704738736152649, 'learning_rate': 2.910667285957579e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5525/6464 [1:40:34<16:54, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9055, 'grad_norm': 0.7151199579238892, 'learning_rate': 2.9075708313980492e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 85%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5526/6464 [1:40:35<16:58, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3587, 'grad_norm': 0.7572448253631592, 'learning_rate': 2.90447437683852e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5527/6464 [1:40:36<16:45, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0021, 'grad_norm': 0.6617503762245178, 'learning_rate': 2.9013779222789905e-05, 'epoch': 0.85}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5528/6464 [1:40:37<16:49, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0959, 'grad_norm': 0.68558669090271, 'learning_rate': 2.8982814677194613e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5529/6464 [1:40:38<17:29, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0285, 'grad_norm': 0.6756428480148315, 'learning_rate': 2.8951850131599324e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5530/6464 [1:40:39<16:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2154, 'grad_norm': 0.7570109963417053, 'learning_rate': 2.8920885586004025e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5531/6464 [1:40:40<16:28, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0642, 'grad_norm': 0.6935478448867798, 'learning_rate': 2.8889921040408733e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5532/6464 [1:40:41<16:52, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1427, 'grad_norm': 0.8379545211791992, 'learning_rate': 2.8858956494813438e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5533/6464 [1:40:43<17:45, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0311, 'grad_norm': 0.62617027759552, 'learning_rate': 2.8827991949218146e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5534/6464 [1:40:44<17:46, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3773, 'grad_norm': 0.7574490904808044, 'learning_rate': 2.879702740362285e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5535/6464 [1:40:45<16:46, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9812, 'grad_norm': 0.7290950417518616, 'learning_rate': 2.876606285802756e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5536/6464 [1:40:46<16:23, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9791, 'grad_norm': 0.7438719868659973, 'learning_rate': 2.8735098312432267e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5537/6464 [1:40:47<15:19, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0054, 'grad_norm': 0.7477177381515503, 'learning_rate': 2.870413376683697e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5538/6464 [1:40:48<16:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0953, 'grad_norm': 0.6676409840583801, 'learning_rate': 2.867316922124168e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5539/6464 [1:40:49<17:36, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0477, 'grad_norm': 0.610973060131073, 'learning_rate': 2.8642204675646384e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5540/6464 [1:40:50<16:26, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0488, 'grad_norm': 0.8826031684875488, 'learning_rate': 2.861124013005109e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5541/6464 [1:40:51<17:08, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3026, 'grad_norm': 0.7208125591278076, 'learning_rate': 2.85802755844558e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5542/6464 [1:40:52<15:58, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9932, 'grad_norm': 0.7654211521148682, 'learning_rate': 2.8549311038860504e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5543/6464 [1:40:53<16:05, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1307, 'grad_norm': 0.6493874192237854, 'learning_rate': 2.8518346493265212e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5544/6464 [1:40:54<16:20, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0766, 'grad_norm': 0.6629924178123474, 'learning_rate': 2.8487381947669917e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5545/6464 [1:40:55<16:41, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2552, 'grad_norm': 0.7782925367355347, 'learning_rate': 2.8456417402074625e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5546/6464 [1:40:57<16:42, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9869, 'grad_norm': 0.6411974430084229, 'learning_rate': 2.8425452856479333e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5547/6464 [1:40:58<17:40, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3282, 'grad_norm': 0.6844737529754639, 'learning_rate': 2.8394488310884037e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5548/6464 [1:40:59<18:25, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9382, 'grad_norm': 0.5839910507202148, 'learning_rate': 2.8363523765288745e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5549/6464 [1:41:00<17:51, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2052, 'grad_norm': 0.7948653697967529, 'learning_rate': 2.833255921969345e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5550/6464 [1:41:01<17:05, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1723, 'grad_norm': 0.7135655283927917, 'learning_rate': 2.8301594674098158e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5551/6464 [1:41:02<16:28, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0136, 'grad_norm': 0.6712592840194702, 'learning_rate': 2.827063012850287e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5552/6464 [1:41:03<15:43, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9894, 'grad_norm': 0.7847715616226196, 'learning_rate': 2.823966558290757e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5553/6464 [1:41:04<15:42, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0213, 'grad_norm': 0.6927708983421326, 'learning_rate': 2.8208701037312278e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5554/6464 [1:41:05<15:00, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0825, 'grad_norm': 0.8121223449707031, 'learning_rate': 2.8177736491716983e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5555/6464 [1:41:06<15:19, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0429, 'grad_norm': 0.7121061086654663, 'learning_rate': 2.814677194612169e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5556/6464 [1:41:07<14:42, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0432, 'grad_norm': 0.7751123905181885, 'learning_rate': 2.8115807400526402e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5557/6464 [1:41:08<15:13, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3229, 'grad_norm': 0.777242124080658, 'learning_rate': 2.8084842854931103e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5558/6464 [1:41:09<14:53, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.963, 'grad_norm': 0.7076746225357056, 'learning_rate': 2.805387830933581e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5559/6464 [1:41:11<17:18, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9652, 'grad_norm': 0.5710723400115967, 'learning_rate': 2.8022913763740516e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5560/6464 [1:41:12<16:51, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1499, 'grad_norm': 0.8133497834205627, 'learning_rate': 2.7991949218145224e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5561/6464 [1:41:13<16:29, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0509, 'grad_norm': 0.6765097379684448, 'learning_rate': 2.7960984672549935e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5562/6464 [1:41:14<16:18, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0424, 'grad_norm': 0.7861478924751282, 'learning_rate': 2.7930020126954636e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5563/6464 [1:41:15<15:27, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9594, 'grad_norm': 0.7546853423118591, 'learning_rate': 2.7899055581359344e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5564/6464 [1:41:16<16:04, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2909, 'grad_norm': 0.7973051071166992, 'learning_rate': 2.786809103576405e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5565/6464 [1:41:17<15:57, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0916, 'grad_norm': 0.7558541893959045, 'learning_rate': 2.7837126490168757e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5566/6464 [1:41:18<16:08, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2534, 'grad_norm': 0.6988252997398376, 'learning_rate': 2.7806161944573468e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5567/6464 [1:41:19<16:54, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.448, 'grad_norm': 0.9085793495178223, 'learning_rate': 2.777519739897817e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5568/6464 [1:41:20<17:15, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.231, 'grad_norm': 0.6993464231491089, 'learning_rate': 2.7744232853382877e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5569/6464 [1:41:22<17:39, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1147, 'grad_norm': 0.6216468214988708, 'learning_rate': 2.7713268307787582e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5570/6464 [1:41:23<17:16, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1657, 'grad_norm': 0.638087809085846, 'learning_rate': 2.768230376219229e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5571/6464 [1:41:24<16:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9543, 'grad_norm': 0.7342703342437744, 'learning_rate': 2.7651339216597e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5572/6464 [1:41:25<15:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8254, 'grad_norm': 0.7217993140220642, 'learning_rate': 2.7620374671001703e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5573/6464 [1:41:26<15:26, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1617, 'grad_norm': 0.7676751017570496, 'learning_rate': 2.758941012540641e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5574/6464 [1:41:27<16:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2387, 'grad_norm': 0.6600050330162048, 'learning_rate': 2.7558445579811115e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ | 5575/6464 [1:41:28<16:50, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0936, 'grad_norm': 0.6404508948326111, 'learning_rate': 2.7527481034215823e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5576/6464 [1:41:29<16:39, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1144, 'grad_norm': 0.7285525798797607, 'learning_rate': 2.7496516488620534e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5577/6464 [1:41:30<16:06, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2081, 'grad_norm': 0.7605671286582947, 'learning_rate': 2.7465551943025236e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5578/6464 [1:41:31<15:26, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8757, 'grad_norm': 0.6515191793441772, 'learning_rate': 2.7434587397429944e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5579/6464 [1:41:32<15:10, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1388, 'grad_norm': 0.7507470846176147, 'learning_rate': 2.7403622851834648e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5580/6464 [1:41:33<15:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3753, 'grad_norm': 0.6966956257820129, 'learning_rate': 2.7372658306239356e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5581/6464 [1:41:34<15:32, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8504, 'grad_norm': 0.6289868950843811, 'learning_rate': 2.7341693760644067e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5582/6464 [1:41:35<14:44, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2351, 'grad_norm': 0.75550776720047, 'learning_rate': 2.731072921504877e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5583/6464 [1:41:36<14:42, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0183, 'grad_norm': 0.7288416028022766, 'learning_rate': 2.7279764669453477e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5584/6464 [1:41:37<15:24, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2628, 'grad_norm': 0.7169783711433411, 'learning_rate': 2.724880012385818e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5585/6464 [1:41:39<15:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3023, 'grad_norm': 0.7783254384994507, 'learning_rate': 2.721783557826289e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5586/6464 [1:41:40<16:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0784, 'grad_norm': 0.7115346789360046, 'learning_rate': 2.71868710326676e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5587/6464 [1:41:41<16:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8586, 'grad_norm': 0.6983500123023987, 'learning_rate': 2.7155906487072302e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5588/6464 [1:41:42<15:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1416, 'grad_norm': 0.876497209072113, 'learning_rate': 2.712494194147701e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5589/6464 [1:41:43<16:32, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.135, 'grad_norm': 0.6516756415367126, 'learning_rate': 2.7093977395881714e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5590/6464 [1:41:44<16:04, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3613, 'grad_norm': 0.9232761859893799, 'learning_rate': 2.7063012850286422e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 86%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5591/6464 [1:41:45<15:31, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0116, 'grad_norm': 0.7670150399208069, 'learning_rate': 2.7032048304691134e-05, 'epoch': 0.86}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5592/6464 [1:41:46<14:37, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1713, 'grad_norm': 0.7566428780555725, 'learning_rate': 2.7001083759095835e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5593/6464 [1:41:47<15:12, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1313, 'grad_norm': 0.7662850618362427, 'learning_rate': 2.6970119213500543e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5594/6464 [1:41:48<14:51, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9363, 'grad_norm': 0.6818609833717346, 'learning_rate': 2.6939154667905247e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5595/6464 [1:41:49<14:43, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1307, 'grad_norm': 0.7609825730323792, 'learning_rate': 2.6908190122309955e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5596/6464 [1:41:50<14:53, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.182, 'grad_norm': 0.8335649371147156, 'learning_rate': 2.6877225576714667e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5597/6464 [1:41:51<15:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9012, 'grad_norm': 0.6477106809616089, 'learning_rate': 2.6846261031119368e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5598/6464 [1:41:52<15:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2075, 'grad_norm': 0.7235603332519531, 'learning_rate': 2.6815296485524076e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5599/6464 [1:41:53<14:50, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0211, 'grad_norm': 0.7189304828643799, 'learning_rate': 2.678433193992878e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5600/6464 [1:41:54<14:36, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9407, 'grad_norm': 0.6997379064559937, 'learning_rate': 2.675336739433349e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5601/6464 [1:41:56<15:38, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0192, 'grad_norm': 0.6226233243942261, 'learning_rate': 2.67224028487382e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5602/6464 [1:41:56<14:50, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.979, 'grad_norm': 0.7857241630554199, 'learning_rate': 2.66914383031429e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5603/6464 [1:41:58<15:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1131, 'grad_norm': 0.6692774295806885, 'learning_rate': 2.666047375754761e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5604/6464 [1:41:59<16:23, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.281, 'grad_norm': 0.6892796158790588, 'learning_rate': 2.6629509211952313e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5605/6464 [1:42:00<15:30, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9369, 'grad_norm': 0.776848554611206, 'learning_rate': 2.659854466635702e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5606/6464 [1:42:01<15:31, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2409, 'grad_norm': 0.7266544699668884, 'learning_rate': 2.6567580120761733e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5607/6464 [1:42:02<15:56, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0688, 'grad_norm': 0.7415324449539185, 'learning_rate': 2.6536615575166434e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5608/6464 [1:42:03<16:12, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1487, 'grad_norm': 0.8531137704849243, 'learning_rate': 2.6505651029571142e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5609/6464 [1:42:04<16:17, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.165, 'grad_norm': 0.6895227432250977, 'learning_rate': 2.6474686483975847e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5610/6464 [1:42:06<16:02, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.097, 'grad_norm': 0.7939481139183044, 'learning_rate': 2.6443721938380554e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5611/6464 [1:42:07<17:13, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.226, 'grad_norm': 0.6131337881088257, 'learning_rate': 2.6412757392785266e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5612/6464 [1:42:08<16:07, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8066, 'grad_norm': 0.5908519625663757, 'learning_rate': 2.6381792847189967e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5613/6464 [1:42:09<15:52, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1165, 'grad_norm': 0.67021244764328, 'learning_rate': 2.6350828301594675e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5614/6464 [1:42:10<16:37, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4153, 'grad_norm': 0.6886963248252869, 'learning_rate': 2.631986375599938e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5615/6464 [1:42:11<15:52, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.91, 'grad_norm': 0.7972928881645203, 'learning_rate': 2.6288899210404088e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5616/6464 [1:42:12<15:58, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0995, 'grad_norm': 0.6743228435516357, 'learning_rate': 2.62579346648088e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5617/6464 [1:42:13<14:57, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9478, 'grad_norm': 0.6816587448120117, 'learning_rate': 2.62269701192135e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5618/6464 [1:42:15<15:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1224, 'grad_norm': 0.6983582377433777, 'learning_rate': 2.6196005573618208e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5619/6464 [1:42:16<15:41, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2293, 'grad_norm': 0.7102153301239014, 'learning_rate': 2.6165041028022913e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5620/6464 [1:42:17<15:23, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2224, 'grad_norm': 0.8478062748908997, 'learning_rate': 2.613407648242762e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5621/6464 [1:42:18<15:04, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.99, 'grad_norm': 0.703952431678772, 'learning_rate': 2.6103111936832332e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5622/6464 [1:42:19<14:30, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9775, 'grad_norm': 0.8911207914352417, 'learning_rate': 2.6072147391237033e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5623/6464 [1:42:20<14:02, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2653, 'grad_norm': 0.7633787393569946, 'learning_rate': 2.6041182845641744e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5624/6464 [1:42:21<15:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1259, 'grad_norm': 0.6203123331069946, 'learning_rate': 2.6010218300046446e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5625/6464 [1:42:22<15:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9759, 'grad_norm': 0.7204595804214478, 'learning_rate': 2.5979253754451154e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5626/6464 [1:42:23<15:06, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9402, 'grad_norm': 0.7138081789016724, 'learning_rate': 2.5948289208855865e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5627/6464 [1:42:24<15:01, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2259, 'grad_norm': 0.725480854511261, 'learning_rate': 2.5917324663260566e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5628/6464 [1:42:25<15:08, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0777, 'grad_norm': 0.7858445644378662, 'learning_rate': 2.5886360117665278e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5629/6464 [1:42:26<15:19, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3133, 'grad_norm': 0.7742774486541748, 'learning_rate': 2.585539557206998e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5630/6464 [1:42:28<15:27, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0123, 'grad_norm': 0.6918495297431946, 'learning_rate': 2.5824431026474687e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5631/6464 [1:42:29<15:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1301, 'grad_norm': 0.7802380919456482, 'learning_rate': 2.5793466480879398e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5632/6464 [1:42:30<14:53, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9707, 'grad_norm': 0.7687970399856567, 'learning_rate': 2.57625019352841e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5633/6464 [1:42:31<14:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2013, 'grad_norm': 0.6675381064414978, 'learning_rate': 2.573153738968881e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5634/6464 [1:42:32<14:16, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0515, 'grad_norm': 0.8221282958984375, 'learning_rate': 2.5700572844093512e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5635/6464 [1:42:33<14:13, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2056, 'grad_norm': 0.8872504234313965, 'learning_rate': 2.566960829849822e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5636/6464 [1:42:34<14:56, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1047, 'grad_norm': 0.6680936813354492, 'learning_rate': 2.563864375290293e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5637/6464 [1:42:35<14:17, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0371, 'grad_norm': 0.7635734677314758, 'learning_rate': 2.5607679207307632e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5638/6464 [1:42:36<14:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0203, 'grad_norm': 0.7365794777870178, 'learning_rate': 2.5576714661712344e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5639/6464 [1:42:37<14:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1052, 'grad_norm': 0.7036272883415222, 'learning_rate': 2.5545750116117045e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5640/6464 [1:42:38<14:06, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2146, 'grad_norm': 0.8172095417976379, 'learning_rate': 2.5514785570521753e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5641/6464 [1:42:39<14:30, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.183, 'grad_norm': 0.7814708352088928, 'learning_rate': 2.5483821024926464e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5642/6464 [1:42:40<14:29, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9475, 'grad_norm': 0.7162535190582275, 'learning_rate': 2.5452856479331165e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5643/6464 [1:42:41<15:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1952, 'grad_norm': 0.699003279209137, 'learning_rate': 2.5421891933735877e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5644/6464 [1:42:43<15:29, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9042, 'grad_norm': 0.6421822309494019, 'learning_rate': 2.5390927388140578e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5645/6464 [1:42:44<15:30, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.201, 'grad_norm': 0.7714122533798218, 'learning_rate': 2.5359962842545286e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5646/6464 [1:42:45<15:47, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2759, 'grad_norm': 0.7596993446350098, 'learning_rate': 2.5328998296949997e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5647/6464 [1:42:46<15:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.124, 'grad_norm': 0.7110703587532043, 'learning_rate': 2.52980337513547e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5648/6464 [1:42:47<15:38, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3816, 'grad_norm': 0.8104217648506165, 'learning_rate': 2.526706920575941e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5649/6464 [1:42:48<15:55, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0948, 'grad_norm': 0.6990657448768616, 'learning_rate': 2.523610466016411e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5650/6464 [1:42:50<16:25, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.183, 'grad_norm': 0.6052798628807068, 'learning_rate': 2.520514011456882e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5651/6464 [1:42:51<15:17, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0015, 'grad_norm': 0.7497681975364685, 'learning_rate': 2.517417556897353e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5652/6464 [1:42:52<15:32, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2755, 'grad_norm': 0.7272481918334961, 'learning_rate': 2.514321102337823e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5653/6464 [1:42:53<16:13, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1214, 'grad_norm': 0.6105947494506836, 'learning_rate': 2.5112246477782943e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5654/6464 [1:42:54<15:52, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2012, 'grad_norm': 0.7269555330276489, 'learning_rate': 2.5081281932187644e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 87%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹ | 5655/6464 [1:42:55<14:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9915, 'grad_norm': 0.7593215703964233, 'learning_rate': 2.5050317386592352e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5656/6464 [1:42:56<14:19, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0558, 'grad_norm': 0.8042720556259155, 'learning_rate': 2.5019352840997063e-05, 'epoch': 0.87}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5657/6464 [1:42:57<14:26, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0644, 'grad_norm': 0.672457218170166, 'learning_rate': 2.4988388295401765e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5658/6464 [1:42:58<14:17, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0963, 'grad_norm': 0.7660800814628601, 'learning_rate': 2.4957423749806473e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5659/6464 [1:42:59<13:51, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1443, 'grad_norm': 0.8067205548286438, 'learning_rate': 2.492645920421118e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5660/6464 [1:43:00<14:04, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.977, 'grad_norm': 0.8010644912719727, 'learning_rate': 2.4895494658615885e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5661/6464 [1:43:01<13:33, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1039, 'grad_norm': 0.7671822309494019, 'learning_rate': 2.4864530113020593e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5662/6464 [1:43:02<14:06, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1662, 'grad_norm': 0.7037582397460938, 'learning_rate': 2.4833565567425298e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5663/6464 [1:43:03<14:17, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0659, 'grad_norm': 0.6652404069900513, 'learning_rate': 2.4802601021830006e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5664/6464 [1:43:05<14:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4967, 'grad_norm': 0.7583171129226685, 'learning_rate': 2.4771636476234714e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5665/6464 [1:43:06<14:01, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0358, 'grad_norm': 0.6915725469589233, 'learning_rate': 2.4740671930639418e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5666/6464 [1:43:07<14:59, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0971, 'grad_norm': 0.6503280401229858, 'learning_rate': 2.4709707385044126e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5667/6464 [1:43:08<14:17, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0142, 'grad_norm': 0.7744148969650269, 'learning_rate': 2.467874283944883e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5668/6464 [1:43:09<14:17, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1693, 'grad_norm': 0.695409893989563, 'learning_rate': 2.464777829385354e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5669/6464 [1:43:10<14:11, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0741, 'grad_norm': 0.7302682995796204, 'learning_rate': 2.4616813748258247e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5670/6464 [1:43:11<14:57, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2425, 'grad_norm': 0.6689329147338867, 'learning_rate': 2.458584920266295e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5671/6464 [1:43:13<15:32, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1845, 'grad_norm': 0.636257529258728, 'learning_rate': 2.455488465706766e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5672/6464 [1:43:14<15:22, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2445, 'grad_norm': 0.7037861347198486, 'learning_rate': 2.4523920111472364e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5673/6464 [1:43:15<14:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0924, 'grad_norm': 0.693962574005127, 'learning_rate': 2.4492955565877072e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5674/6464 [1:43:16<14:55, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0983, 'grad_norm': 0.6632038950920105, 'learning_rate': 2.446199102028178e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5675/6464 [1:43:17<14:46, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2877, 'grad_norm': 0.697367787361145, 'learning_rate': 2.4431026474686484e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5676/6464 [1:43:18<14:04, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0045, 'grad_norm': 0.749660313129425, 'learning_rate': 2.4400061929091192e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5677/6464 [1:43:19<14:03, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1089, 'grad_norm': 0.6861196160316467, 'learning_rate': 2.4369097383495897e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5678/6464 [1:43:20<13:06, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8419, 'grad_norm': 0.7865208983421326, 'learning_rate': 2.4338132837900605e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5679/6464 [1:43:21<14:47, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1746, 'grad_norm': 0.622975766658783, 'learning_rate': 2.4307168292305313e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5680/6464 [1:43:22<14:32, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0782, 'grad_norm': 0.834696352481842, 'learning_rate': 2.4276203746710017e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5681/6464 [1:43:23<14:31, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1211, 'grad_norm': 0.8151229023933411, 'learning_rate': 2.4245239201114725e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5682/6464 [1:43:24<14:21, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1021, 'grad_norm': 0.6801294088363647, 'learning_rate': 2.421427465551943e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5683/6464 [1:43:25<13:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0539, 'grad_norm': 0.8146852850914001, 'learning_rate': 2.4183310109924138e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5684/6464 [1:43:26<12:53, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9375, 'grad_norm': 0.7385876774787903, 'learning_rate': 2.4152345564328846e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5685/6464 [1:43:27<13:00, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2805, 'grad_norm': 0.7779750823974609, 'learning_rate': 2.412138101873355e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5686/6464 [1:43:28<13:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1874, 'grad_norm': 0.7308889627456665, 'learning_rate': 2.409041647313826e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5687/6464 [1:43:29<13:31, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2372, 'grad_norm': 0.7917817831039429, 'learning_rate': 2.4059451927542963e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5688/6464 [1:43:31<13:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0046, 'grad_norm': 0.6463086009025574, 'learning_rate': 2.402848738194767e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5689/6464 [1:43:32<13:35, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9754, 'grad_norm': 0.6676445603370667, 'learning_rate': 2.3997522836352375e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5690/6464 [1:43:33<14:12, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3425, 'grad_norm': 0.7380005717277527, 'learning_rate': 2.3966558290757083e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5691/6464 [1:43:34<13:55, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9578, 'grad_norm': 0.6747445464134216, 'learning_rate': 2.393559374516179e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5692/6464 [1:43:35<13:38, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9748, 'grad_norm': 0.7072435021400452, 'learning_rate': 2.3904629199566496e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5693/6464 [1:43:36<14:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0956, 'grad_norm': 0.5863468647003174, 'learning_rate': 2.3873664653971204e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5694/6464 [1:43:37<14:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2745, 'grad_norm': 0.8559296131134033, 'learning_rate': 2.384270010837591e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5695/6464 [1:43:38<13:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0258, 'grad_norm': 0.6731916666030884, 'learning_rate': 2.381173556278062e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5696/6464 [1:43:39<13:17, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0965, 'grad_norm': 0.8072247505187988, 'learning_rate': 2.3780771017185324e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5697/6464 [1:43:40<13:16, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.91, 'grad_norm': 0.6865248680114746, 'learning_rate': 2.374980647159003e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5698/6464 [1:43:41<13:42, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3136, 'grad_norm': 0.8301133513450623, 'learning_rate': 2.3718841925994737e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5699/6464 [1:43:43<14:30, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1969, 'grad_norm': 0.6504660248756409, 'learning_rate': 2.368787738039944e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5700/6464 [1:43:44<13:56, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0919, 'grad_norm': 0.7791113257408142, 'learning_rate': 2.3656912834804153e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5701/6464 [1:43:45<14:06, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2264, 'grad_norm': 0.7419556379318237, 'learning_rate': 2.3625948289208858e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5702/6464 [1:43:46<14:11, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.944, 'grad_norm': 0.5869855284690857, 'learning_rate': 2.3594983743613562e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5703/6464 [1:43:47<14:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3376, 'grad_norm': 0.7615855932235718, 'learning_rate': 2.356401919801827e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5704/6464 [1:43:48<13:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0588, 'grad_norm': 0.7277713418006897, 'learning_rate': 2.3533054652422975e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5705/6464 [1:43:49<14:03, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2533, 'grad_norm': 0.6677352786064148, 'learning_rate': 2.3502090106827686e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5706/6464 [1:43:50<14:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.938, 'grad_norm': 0.6793085336685181, 'learning_rate': 2.347112556123239e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5707/6464 [1:43:52<14:17, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1853, 'grad_norm': 0.7205166220664978, 'learning_rate': 2.3440161015637095e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5708/6464 [1:43:53<13:55, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0682, 'grad_norm': 0.6979305744171143, 'learning_rate': 2.3409196470041803e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5709/6464 [1:43:54<13:23, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1682, 'grad_norm': 0.7686036825180054, 'learning_rate': 2.3378231924446508e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5710/6464 [1:43:55<13:03, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0866, 'grad_norm': 0.7756782174110413, 'learning_rate': 2.334726737885122e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5711/6464 [1:43:56<13:34, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3, 'grad_norm': 0.764369010925293, 'learning_rate': 2.3316302833255924e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5712/6464 [1:43:57<13:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0387, 'grad_norm': 0.7191053628921509, 'learning_rate': 2.3285338287660628e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5713/6464 [1:43:58<13:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.075, 'grad_norm': 0.7926813364028931, 'learning_rate': 2.3254373742065336e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5714/6464 [1:43:59<15:08, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1125, 'grad_norm': 0.6574953198432922, 'learning_rate': 2.322340919647004e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5715/6464 [1:44:00<13:59, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0496, 'grad_norm': 1.171818733215332, 'learning_rate': 2.3192444650874752e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5716/6464 [1:44:01<13:29, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0264, 'grad_norm': 0.712628185749054, 'learning_rate': 2.3161480105279457e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5717/6464 [1:44:02<12:30, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1071, 'grad_norm': 1.0144001245498657, 'learning_rate': 2.313051555968416e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5718/6464 [1:44:03<12:32, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0127, 'grad_norm': 0.7352516651153564, 'learning_rate': 2.309955101408887e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5719/6464 [1:44:04<14:00, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3002, 'grad_norm': 0.6730492115020752, 'learning_rate': 2.3068586468493574e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 88%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5720/6464 [1:44:06<14:13, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0719, 'grad_norm': 0.6759416460990906, 'learning_rate': 2.3037621922898285e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5721/6464 [1:44:07<13:58, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0897, 'grad_norm': 0.7282549738883972, 'learning_rate': 2.300665737730299e-05, 'epoch': 0.88}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5722/6464 [1:44:08<13:48, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3246, 'grad_norm': 0.811318039894104, 'learning_rate': 2.2975692831707694e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5723/6464 [1:44:09<13:10, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2322, 'grad_norm': 1.0027042627334595, 'learning_rate': 2.2944728286112402e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5724/6464 [1:44:10<12:42, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9398, 'grad_norm': 0.7608251571655273, 'learning_rate': 2.2913763740517107e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5725/6464 [1:44:11<12:15, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1594, 'grad_norm': 0.8228017687797546, 'learning_rate': 2.2882799194921818e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5726/6464 [1:44:12<13:38, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.853, 'grad_norm': 0.642467200756073, 'learning_rate': 2.2851834649326523e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5727/6464 [1:44:13<13:57, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2172, 'grad_norm': 0.6121441721916199, 'learning_rate': 2.2820870103731227e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5728/6464 [1:44:14<14:24, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.229, 'grad_norm': 0.6801014542579651, 'learning_rate': 2.2789905558135935e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5729/6464 [1:44:15<13:36, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0376, 'grad_norm': 0.7212291955947876, 'learning_rate': 2.275894101254064e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5730/6464 [1:44:17<14:08, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2376, 'grad_norm': 0.6806726455688477, 'learning_rate': 2.272797646694535e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5731/6464 [1:44:18<13:55, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3187, 'grad_norm': 0.7187930345535278, 'learning_rate': 2.2697011921350056e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5732/6464 [1:44:19<13:55, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9027, 'grad_norm': 0.657213032245636, 'learning_rate': 2.266604737575476e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5733/6464 [1:44:20<14:25, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2274, 'grad_norm': 0.6665317416191101, 'learning_rate': 2.263508283015947e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5734/6464 [1:44:21<13:40, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0486, 'grad_norm': 0.7409642338752747, 'learning_rate': 2.2604118284564173e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5735/6464 [1:44:22<13:33, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3285, 'grad_norm': 0.7439264059066772, 'learning_rate': 2.2573153738968884e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š | 5736/6464 [1:44:23<13:09, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0014, 'grad_norm': 0.6775535941123962, 'learning_rate': 2.254218919337359e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5737/6464 [1:44:24<12:41, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0965, 'grad_norm': 0.7625368237495422, 'learning_rate': 2.2511224647778294e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5738/6464 [1:44:25<12:06, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0444, 'grad_norm': 0.8076110482215881, 'learning_rate': 2.2480260102183e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5739/6464 [1:44:26<11:47, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0663, 'grad_norm': 0.7317711710929871, 'learning_rate': 2.2449295556587706e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5740/6464 [1:44:27<12:01, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2576, 'grad_norm': 0.8222006559371948, 'learning_rate': 2.2418331010992417e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5741/6464 [1:44:28<13:13, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2301, 'grad_norm': 0.6430379152297974, 'learning_rate': 2.2387366465397122e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5742/6464 [1:44:30<12:53, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1145, 'grad_norm': 0.7597680687904358, 'learning_rate': 2.2356401919801827e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5743/6464 [1:44:31<13:12, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2077, 'grad_norm': 0.6937164068222046, 'learning_rate': 2.2325437374206535e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5744/6464 [1:44:32<14:01, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0811, 'grad_norm': 0.6296209096908569, 'learning_rate': 2.229447282861124e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5745/6464 [1:44:33<13:48, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0698, 'grad_norm': 0.7092345952987671, 'learning_rate': 2.226350828301595e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5746/6464 [1:44:34<13:23, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9744, 'grad_norm': 0.7303741574287415, 'learning_rate': 2.2232543737420655e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5747/6464 [1:44:35<13:39, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0671, 'grad_norm': 0.6245599389076233, 'learning_rate': 2.220157919182536e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5748/6464 [1:44:37<14:07, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1323, 'grad_norm': 0.6246895790100098, 'learning_rate': 2.2170614646230068e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5749/6464 [1:44:38<13:35, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.091, 'grad_norm': 0.755077600479126, 'learning_rate': 2.2139650100634772e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5750/6464 [1:44:39<13:48, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2464, 'grad_norm': 0.6965595483779907, 'learning_rate': 2.210868555503948e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5751/6464 [1:44:40<13:32, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1791, 'grad_norm': 0.7089296579360962, 'learning_rate': 2.2077721009444188e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5752/6464 [1:44:41<13:06, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1361, 'grad_norm': 0.7326869368553162, 'learning_rate': 2.2046756463848893e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5753/6464 [1:44:42<12:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0418, 'grad_norm': 0.7360954284667969, 'learning_rate': 2.20157919182536e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5754/6464 [1:44:43<12:09, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0141, 'grad_norm': 0.7509725093841553, 'learning_rate': 2.1984827372658305e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5755/6464 [1:44:44<12:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9906, 'grad_norm': 0.6151594519615173, 'learning_rate': 2.1953862827063013e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5756/6464 [1:44:45<12:12, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0479, 'grad_norm': 0.7787107825279236, 'learning_rate': 2.192289828146772e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5757/6464 [1:44:46<12:25, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.292, 'grad_norm': 0.6985688805580139, 'learning_rate': 2.1891933735872426e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5758/6464 [1:44:47<12:18, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9295, 'grad_norm': 0.7233052253723145, 'learning_rate': 2.1860969190277134e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5759/6464 [1:44:48<12:20, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1602, 'grad_norm': 0.716178834438324, 'learning_rate': 2.183000464468184e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5760/6464 [1:44:49<11:39, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8846, 'grad_norm': 0.8343560695648193, 'learning_rate': 2.1799040099086546e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5761/6464 [1:44:50<13:08, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1934, 'grad_norm': 0.6755686402320862, 'learning_rate': 2.1768075553491254e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5762/6464 [1:44:52<15:38, 1.34s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3231, 'grad_norm': 0.6806195974349976, 'learning_rate': 2.1737111007895962e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5763/6464 [1:44:53<14:26, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1767, 'grad_norm': 0.7401412129402161, 'learning_rate': 2.1706146462300667e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5764/6464 [1:44:54<13:34, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1286, 'grad_norm': 0.8008297681808472, 'learning_rate': 2.167518191670537e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5765/6464 [1:44:55<12:43, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.961, 'grad_norm': 0.7217435836791992, 'learning_rate': 2.164421737111008e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5766/6464 [1:44:57<14:03, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0857, 'grad_norm': 0.6515520215034485, 'learning_rate': 2.1613252825514787e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5767/6464 [1:44:58<13:51, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2599, 'grad_norm': 0.6854629516601562, 'learning_rate': 2.1582288279919495e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5768/6464 [1:44:59<13:06, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1116, 'grad_norm': 0.8083747029304504, 'learning_rate': 2.15513237343242e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5769/6464 [1:45:00<12:26, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1588, 'grad_norm': 0.7160460352897644, 'learning_rate': 2.1520359188728904e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5770/6464 [1:45:01<12:53, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.215, 'grad_norm': 0.7399593591690063, 'learning_rate': 2.1489394643133612e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5771/6464 [1:45:02<12:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9466, 'grad_norm': 0.8297262191772461, 'learning_rate': 2.145843009753832e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5772/6464 [1:45:03<12:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1706, 'grad_norm': 0.7999864220619202, 'learning_rate': 2.142746555194303e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5773/6464 [1:45:04<11:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8458, 'grad_norm': 0.7303597927093506, 'learning_rate': 2.1396501006347733e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5774/6464 [1:45:05<11:12, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9947, 'grad_norm': 0.8993570804595947, 'learning_rate': 2.1365536460752438e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5775/6464 [1:45:06<11:17, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.183, 'grad_norm': 0.8054178357124329, 'learning_rate': 2.1334571915157145e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5776/6464 [1:45:07<11:43, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2968, 'grad_norm': 0.789781391620636, 'learning_rate': 2.1303607369561853e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5777/6464 [1:45:08<12:02, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1241, 'grad_norm': 0.6654016971588135, 'learning_rate': 2.127264282396656e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5778/6464 [1:45:09<11:33, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9963, 'grad_norm': 0.8810896277427673, 'learning_rate': 2.1241678278371266e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5779/6464 [1:45:10<12:13, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2871, 'grad_norm': 0.7827114462852478, 'learning_rate': 2.121071373277597e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5780/6464 [1:45:11<12:51, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1803, 'grad_norm': 0.5911723971366882, 'learning_rate': 2.117974918718068e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5781/6464 [1:45:12<12:00, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.186, 'grad_norm': 0.9406797885894775, 'learning_rate': 2.1148784641585387e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5782/6464 [1:45:14<12:49, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0784, 'grad_norm': 0.6345741152763367, 'learning_rate': 2.1117820095990094e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5783/6464 [1:45:15<12:44, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9748, 'grad_norm': 0.6671848297119141, 'learning_rate': 2.10868555503948e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5784/6464 [1:45:16<12:12, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8634, 'grad_norm': 0.8099400997161865, 'learning_rate': 2.1055891004799504e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 89%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5785/6464 [1:45:17<11:45, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0117, 'grad_norm': 0.9096324443817139, 'learning_rate': 2.102492645920421e-05, 'epoch': 0.89}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5786/6464 [1:45:17<11:11, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9064, 'grad_norm': 0.7755172848701477, 'learning_rate': 2.099396191360892e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5787/6464 [1:45:19<11:48, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2794, 'grad_norm': 0.6707507371902466, 'learning_rate': 2.0962997368013628e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5788/6464 [1:45:19<11:01, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0136, 'grad_norm': 0.9065127968788147, 'learning_rate': 2.0932032822418332e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5789/6464 [1:45:20<10:42, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9873, 'grad_norm': 0.7182977795600891, 'learning_rate': 2.0901068276823037e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5790/6464 [1:45:21<10:58, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1914, 'grad_norm': 0.7816423773765564, 'learning_rate': 2.0870103731227745e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5791/6464 [1:45:22<10:47, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2265, 'grad_norm': 0.8833832144737244, 'learning_rate': 2.0839139185632453e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5792/6464 [1:45:23<10:43, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.306, 'grad_norm': 0.8092823028564453, 'learning_rate': 2.080817464003716e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5793/6464 [1:45:25<11:43, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1686, 'grad_norm': 0.6821004748344421, 'learning_rate': 2.0777210094441865e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5794/6464 [1:45:26<13:24, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3158, 'grad_norm': 0.6517209410667419, 'learning_rate': 2.074624554884657e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5795/6464 [1:45:27<12:47, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1055, 'grad_norm': 0.7379775643348694, 'learning_rate': 2.0715281003251278e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5796/6464 [1:45:28<12:34, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0025, 'grad_norm': 0.6466277837753296, 'learning_rate': 2.0684316457655986e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5797/6464 [1:45:30<13:08, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8843, 'grad_norm': 0.5838921666145325, 'learning_rate': 2.0653351912060694e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5798/6464 [1:45:31<12:59, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9526, 'grad_norm': 0.6012259721755981, 'learning_rate': 2.0622387366465398e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5799/6464 [1:45:32<12:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1863, 'grad_norm': 0.7011843919754028, 'learning_rate': 2.0591422820870103e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5800/6464 [1:45:33<12:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1986, 'grad_norm': 0.7012043595314026, 'learning_rate': 2.056045827527481e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5801/6464 [1:45:34<11:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.824, 'grad_norm': 0.6286553144454956, 'learning_rate': 2.052949372967952e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5802/6464 [1:45:35<11:23, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1788, 'grad_norm': 0.8003726005554199, 'learning_rate': 2.0498529184084227e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5803/6464 [1:45:36<11:23, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1103, 'grad_norm': 0.7233453989028931, 'learning_rate': 2.046756463848893e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5804/6464 [1:45:37<11:23, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0399, 'grad_norm': 0.8187729716300964, 'learning_rate': 2.0436600092893636e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5805/6464 [1:45:38<10:49, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0295, 'grad_norm': 0.723224937915802, 'learning_rate': 2.0405635547298344e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5806/6464 [1:45:39<11:21, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2264, 'grad_norm': 0.7705606818199158, 'learning_rate': 2.0374671001703052e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5807/6464 [1:45:40<11:04, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9473, 'grad_norm': 0.6886305212974548, 'learning_rate': 2.034370645610776e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5808/6464 [1:45:41<11:00, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.188, 'grad_norm': 0.7839593887329102, 'learning_rate': 2.0312741910512464e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5809/6464 [1:45:42<11:16, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9489, 'grad_norm': 0.6578908562660217, 'learning_rate': 2.028177736491717e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5810/6464 [1:45:43<11:50, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0753, 'grad_norm': 0.727189838886261, 'learning_rate': 2.0250812819321877e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5811/6464 [1:45:44<11:20, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.051, 'grad_norm': 0.8135550618171692, 'learning_rate': 2.0219848273726585e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5812/6464 [1:45:45<11:08, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.109, 'grad_norm': 0.8044416308403015, 'learning_rate': 2.0188883728131293e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5813/6464 [1:45:46<11:34, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0929, 'grad_norm': 0.7507031559944153, 'learning_rate': 2.0157919182535997e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5814/6464 [1:45:47<11:32, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1056, 'grad_norm': 0.8868914842605591, 'learning_rate': 2.0126954636940702e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5815/6464 [1:45:48<11:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2571, 'grad_norm': 0.795566737651825, 'learning_rate': 2.009599009134541e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5816/6464 [1:45:49<10:57, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8639, 'grad_norm': 0.6240898966789246, 'learning_rate': 2.0065025545750115e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰ | 5817/6464 [1:45:50<10:34, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0231, 'grad_norm': 0.9134687781333923, 'learning_rate': 2.0034061000154826e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5818/6464 [1:45:51<11:05, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0845, 'grad_norm': 0.6182709336280823, 'learning_rate': 2.000309645455953e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5819/6464 [1:45:52<11:10, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9241, 'grad_norm': 0.6414080858230591, 'learning_rate': 1.9972131908964235e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5820/6464 [1:45:53<10:43, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0177, 'grad_norm': 0.7386557459831238, 'learning_rate': 1.9941167363368943e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5821/6464 [1:45:54<10:31, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2328, 'grad_norm': 0.745261549949646, 'learning_rate': 1.9910202817773648e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5822/6464 [1:45:55<11:02, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2185, 'grad_norm': 0.9125165939331055, 'learning_rate': 1.987923827217836e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5823/6464 [1:45:56<11:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1765, 'grad_norm': 0.7110575437545776, 'learning_rate': 1.9848273726583064e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5824/6464 [1:45:57<11:43, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1091, 'grad_norm': 0.6533633470535278, 'learning_rate': 1.9817309180987768e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5825/6464 [1:45:59<12:01, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3755, 'grad_norm': 0.7464072704315186, 'learning_rate': 1.9786344635392476e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5826/6464 [1:46:00<11:22, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0067, 'grad_norm': 0.7415231466293335, 'learning_rate': 1.975538008979718e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5827/6464 [1:46:01<11:40, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0968, 'grad_norm': 0.7140441536903381, 'learning_rate': 1.9724415544201892e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5828/6464 [1:46:02<11:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1863, 'grad_norm': 0.791741132736206, 'learning_rate': 1.9693450998606597e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5829/6464 [1:46:03<12:23, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1772, 'grad_norm': 0.7276507019996643, 'learning_rate': 1.96624864530113e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5830/6464 [1:46:04<11:43, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.013, 'grad_norm': 0.6816506385803223, 'learning_rate': 1.963152190741601e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5831/6464 [1:46:05<11:44, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.909, 'grad_norm': 0.6832137107849121, 'learning_rate': 1.9600557361820714e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5832/6464 [1:46:06<11:31, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1538, 'grad_norm': 0.9030308127403259, 'learning_rate': 1.9569592816225425e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5833/6464 [1:46:07<11:02, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.944, 'grad_norm': 0.8098479509353638, 'learning_rate': 1.953862827063013e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5834/6464 [1:46:08<11:22, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2936, 'grad_norm': 0.785529613494873, 'learning_rate': 1.9507663725034838e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5835/6464 [1:46:09<11:14, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.091, 'grad_norm': 0.7336817979812622, 'learning_rate': 1.9476699179439542e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5836/6464 [1:46:10<11:00, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.098, 'grad_norm': 0.8520419597625732, 'learning_rate': 1.9445734633844247e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5837/6464 [1:46:11<10:10, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7845, 'grad_norm': 0.688773512840271, 'learning_rate': 1.9414770088248958e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5838/6464 [1:46:12<10:14, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0275, 'grad_norm': 0.7633606791496277, 'learning_rate': 1.9383805542653663e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5839/6464 [1:46:13<10:28, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2251, 'grad_norm': 0.8423069715499878, 'learning_rate': 1.935284099705837e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5840/6464 [1:46:14<10:25, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3983, 'grad_norm': 0.9018849730491638, 'learning_rate': 1.9321876451463075e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5841/6464 [1:46:15<10:16, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2194, 'grad_norm': 0.7700192928314209, 'learning_rate': 1.929091190586778e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5842/6464 [1:46:16<10:10, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.986, 'grad_norm': 0.759456217288971, 'learning_rate': 1.925994736027249e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5843/6464 [1:46:17<10:20, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1166, 'grad_norm': 0.7686682343482971, 'learning_rate': 1.9228982814677196e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5844/6464 [1:46:18<09:49, 1.05it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0649, 'grad_norm': 0.7864891886711121, 'learning_rate': 1.9198018269081904e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5845/6464 [1:46:19<10:03, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0396, 'grad_norm': 0.7352988123893738, 'learning_rate': 1.916705372348661e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5846/6464 [1:46:20<10:32, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0674, 'grad_norm': 0.785466730594635, 'learning_rate': 1.9136089177891313e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5847/6464 [1:46:22<11:26, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0789, 'grad_norm': 0.8688552379608154, 'learning_rate': 1.9105124632296024e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5848/6464 [1:46:22<10:37, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0248, 'grad_norm': 0.896057665348053, 'learning_rate': 1.907416008670073e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 90%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5849/6464 [1:46:24<10:47, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0782, 'grad_norm': 0.6699956059455872, 'learning_rate': 1.9043195541105437e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5850/6464 [1:46:25<11:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1084, 'grad_norm': 0.6416440606117249, 'learning_rate': 1.901223099551014e-05, 'epoch': 0.9}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5851/6464 [1:46:26<11:15, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1099, 'grad_norm': 0.7083049416542053, 'learning_rate': 1.8981266449914846e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5852/6464 [1:46:27<10:37, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0342, 'grad_norm': 0.8117756843566895, 'learning_rate': 1.8950301904319557e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5853/6464 [1:46:28<11:01, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2293, 'grad_norm': 0.6879546642303467, 'learning_rate': 1.8919337358724262e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5854/6464 [1:46:29<11:12, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2576, 'grad_norm': 0.8230358958244324, 'learning_rate': 1.888837281312897e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5855/6464 [1:46:30<10:42, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1329, 'grad_norm': 0.8493309617042542, 'learning_rate': 1.8857408267533674e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5856/6464 [1:46:31<10:41, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9187, 'grad_norm': 0.6702700853347778, 'learning_rate': 1.882644372193838e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5857/6464 [1:46:32<10:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0239, 'grad_norm': 0.7422271370887756, 'learning_rate': 1.879547917634309e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5858/6464 [1:46:33<10:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0776, 'grad_norm': 0.7129503488540649, 'learning_rate': 1.8764514630747795e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5859/6464 [1:46:34<10:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2244, 'grad_norm': 0.7641783356666565, 'learning_rate': 1.8733550085152503e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5860/6464 [1:46:35<10:47, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.067, 'grad_norm': 0.6501004695892334, 'learning_rate': 1.8702585539557208e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5861/6464 [1:46:37<10:57, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3482, 'grad_norm': 0.7516937851905823, 'learning_rate': 1.8671620993961912e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5862/6464 [1:46:38<11:23, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.245, 'grad_norm': 0.6697789430618286, 'learning_rate': 1.8640656448366623e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5863/6464 [1:46:39<10:42, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8827, 'grad_norm': 0.6824066042900085, 'learning_rate': 1.8609691902771328e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5864/6464 [1:46:40<11:13, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3766, 'grad_norm': 0.7215158939361572, 'learning_rate': 1.8578727357176036e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5865/6464 [1:46:41<11:16, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9994, 'grad_norm': 0.7056976556777954, 'learning_rate': 1.854776281158074e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5866/6464 [1:46:42<11:26, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2857, 'grad_norm': 0.8022074699401855, 'learning_rate': 1.8516798265985445e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5867/6464 [1:46:43<11:22, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.18, 'grad_norm': 0.7238292098045349, 'learning_rate': 1.8485833720390157e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5868/6464 [1:46:44<10:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1322, 'grad_norm': 0.8392151594161987, 'learning_rate': 1.845486917479486e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5869/6464 [1:46:45<10:32, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1228, 'grad_norm': 0.6959034204483032, 'learning_rate': 1.842390462919957e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5870/6464 [1:46:46<10:10, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9937, 'grad_norm': 0.8077359795570374, 'learning_rate': 1.8392940083604274e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5871/6464 [1:46:47<10:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1304, 'grad_norm': 0.7040769457817078, 'learning_rate': 1.8361975538008978e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5872/6464 [1:46:49<10:40, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9947, 'grad_norm': 0.721845269203186, 'learning_rate': 1.833101099241369e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5873/6464 [1:46:50<10:36, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1459, 'grad_norm': 0.9392522573471069, 'learning_rate': 1.8300046446818394e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5874/6464 [1:46:51<10:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2906, 'grad_norm': 0.7238472104072571, 'learning_rate': 1.8269081901223102e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5875/6464 [1:46:52<10:29, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1403, 'grad_norm': 0.7337970733642578, 'learning_rate': 1.8238117355627807e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5876/6464 [1:46:53<11:24, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9202, 'grad_norm': 0.6218986511230469, 'learning_rate': 1.820715281003251e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5877/6464 [1:46:54<10:53, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1218, 'grad_norm': 0.7589055895805359, 'learning_rate': 1.817618826443722e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5878/6464 [1:46:55<10:24, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1896, 'grad_norm': 0.8057571053504944, 'learning_rate': 1.8145223718841927e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5879/6464 [1:46:56<09:53, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1745, 'grad_norm': 0.7535368800163269, 'learning_rate': 1.8114259173246635e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5880/6464 [1:46:57<10:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0949, 'grad_norm': 0.6796030402183533, 'learning_rate': 1.808329462765134e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5881/6464 [1:46:58<10:02, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1567, 'grad_norm': 0.8089624047279358, 'learning_rate': 1.8052330082056044e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5882/6464 [1:46:59<10:43, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1571, 'grad_norm': 0.7060322165489197, 'learning_rate': 1.8021365536460752e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5883/6464 [1:47:00<10:15, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.071, 'grad_norm': 0.7568135857582092, 'learning_rate': 1.799040099086546e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5884/6464 [1:47:01<09:55, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.055, 'grad_norm': 0.7095547914505005, 'learning_rate': 1.7959436445270168e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5885/6464 [1:47:03<11:17, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0037, 'grad_norm': 0.5241321325302124, 'learning_rate': 1.7928471899674873e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5886/6464 [1:47:04<10:55, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0497, 'grad_norm': 0.7232323884963989, 'learning_rate': 1.7897507354079577e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5887/6464 [1:47:05<10:50, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3175, 'grad_norm': 0.794096052646637, 'learning_rate': 1.7866542808484285e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5888/6464 [1:47:06<10:45, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1101, 'grad_norm': 0.6613047122955322, 'learning_rate': 1.7835578262888993e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5889/6464 [1:47:07<10:15, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0405, 'grad_norm': 0.7214303612709045, 'learning_rate': 1.78046137172937e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5890/6464 [1:47:08<09:45, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0342, 'grad_norm': 1.1430681943893433, 'learning_rate': 1.7773649171698406e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5891/6464 [1:47:09<09:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.065, 'grad_norm': 0.7732034921646118, 'learning_rate': 1.774268462610311e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5892/6464 [1:47:10<09:59, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2073, 'grad_norm': 0.6734325289726257, 'learning_rate': 1.771172008050782e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5893/6464 [1:47:11<10:25, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3658, 'grad_norm': 0.7648294568061829, 'learning_rate': 1.7680755534912526e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5894/6464 [1:47:12<10:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8846, 'grad_norm': 0.6456655859947205, 'learning_rate': 1.7649790989317234e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5895/6464 [1:47:14<10:36, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2571, 'grad_norm': 0.6778927445411682, 'learning_rate': 1.761882644372194e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5896/6464 [1:47:15<10:49, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0217, 'grad_norm': 0.744106650352478, 'learning_rate': 1.7587861898126644e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5897/6464 [1:47:16<11:07, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2295, 'grad_norm': 0.6386494040489197, 'learning_rate': 1.755689735253135e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ | 5898/6464 [1:47:17<10:49, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2116, 'grad_norm': 0.6995556950569153, 'learning_rate': 1.752593280693606e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5899/6464 [1:47:18<10:14, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.924, 'grad_norm': 0.7007271647453308, 'learning_rate': 1.7494968261340767e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5900/6464 [1:47:19<10:12, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1477, 'grad_norm': 0.738571286201477, 'learning_rate': 1.7464003715745472e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5901/6464 [1:47:20<09:49, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7929, 'grad_norm': 0.6571714878082275, 'learning_rate': 1.7433039170150177e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5902/6464 [1:47:21<10:18, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1577, 'grad_norm': 0.6759105920791626, 'learning_rate': 1.7402074624554885e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5903/6464 [1:47:22<10:26, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1033, 'grad_norm': 0.6930140256881714, 'learning_rate': 1.7371110078959593e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5904/6464 [1:47:24<10:13, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3975, 'grad_norm': 0.8388245105743408, 'learning_rate': 1.73401455333643e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5905/6464 [1:47:25<10:27, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0171, 'grad_norm': 0.6913900375366211, 'learning_rate': 1.7309180987769005e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5906/6464 [1:47:26<10:19, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0613, 'grad_norm': 0.7262400984764099, 'learning_rate': 1.7278216442173713e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5907/6464 [1:47:27<10:05, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.056, 'grad_norm': 0.7794367671012878, 'learning_rate': 1.7247251896578418e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5908/6464 [1:47:28<10:16, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0422, 'grad_norm': 0.7882606387138367, 'learning_rate': 1.7216287350983126e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5909/6464 [1:47:29<09:46, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0702, 'grad_norm': 0.8306285738945007, 'learning_rate': 1.7185322805387834e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5910/6464 [1:47:30<09:44, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0223, 'grad_norm': 0.7311496138572693, 'learning_rate': 1.7154358259792538e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5911/6464 [1:47:31<09:59, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.143, 'grad_norm': 0.6590734720230103, 'learning_rate': 1.7123393714197246e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5912/6464 [1:47:32<09:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3356, 'grad_norm': 0.8401901125907898, 'learning_rate': 1.709242916860195e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5913/6464 [1:47:33<09:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1592, 'grad_norm': 0.7524523138999939, 'learning_rate': 1.706146462300666e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 91%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5914/6464 [1:47:34<10:11, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3092, 'grad_norm': 0.7259702682495117, 'learning_rate': 1.7030500077411367e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5915/6464 [1:47:35<09:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0856, 'grad_norm': 0.8009961247444153, 'learning_rate': 1.699953553181607e-05, 'epoch': 0.91}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5916/6464 [1:47:37<10:36, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9746, 'grad_norm': 0.5775201320648193, 'learning_rate': 1.696857098622078e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5917/6464 [1:47:38<10:35, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0643, 'grad_norm': 0.6264006495475769, 'learning_rate': 1.6937606440625484e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5918/6464 [1:47:39<09:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0166, 'grad_norm': 0.8533318042755127, 'learning_rate': 1.6906641895030192e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5919/6464 [1:47:40<09:44, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0793, 'grad_norm': 0.7200674414634705, 'learning_rate': 1.68756773494349e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5920/6464 [1:47:41<09:32, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9959, 'grad_norm': 0.7563113570213318, 'learning_rate': 1.6844712803839604e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5921/6464 [1:47:42<09:55, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.172, 'grad_norm': 0.6667971611022949, 'learning_rate': 1.6813748258244312e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5922/6464 [1:47:43<09:57, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1487, 'grad_norm': 0.7711338996887207, 'learning_rate': 1.6782783712649017e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5923/6464 [1:47:44<09:45, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.114, 'grad_norm': 0.7589380145072937, 'learning_rate': 1.6751819167053725e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5924/6464 [1:47:45<09:22, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.012, 'grad_norm': 0.769470751285553, 'learning_rate': 1.6720854621458433e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5925/6464 [1:47:46<09:29, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0848, 'grad_norm': 0.7392747402191162, 'learning_rate': 1.6689890075863137e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5926/6464 [1:47:47<09:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9458, 'grad_norm': 0.6378597021102905, 'learning_rate': 1.6658925530267845e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5927/6464 [1:47:49<10:29, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2503, 'grad_norm': 0.6608964800834656, 'learning_rate': 1.662796098467255e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5928/6464 [1:47:50<10:13, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3876, 'grad_norm': 0.838436484336853, 'learning_rate': 1.6596996439077258e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5929/6464 [1:47:51<10:05, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1096, 'grad_norm': 0.7113776803016663, 'learning_rate': 1.6566031893481966e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5930/6464 [1:47:52<10:12, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1944, 'grad_norm': 0.659794270992279, 'learning_rate': 1.653506734788667e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5931/6464 [1:47:53<10:09, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1004, 'grad_norm': 0.6954743266105652, 'learning_rate': 1.650410280229138e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5932/6464 [1:47:54<09:55, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4226, 'grad_norm': 0.8605102896690369, 'learning_rate': 1.6473138256696083e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5933/6464 [1:47:56<09:54, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2642, 'grad_norm': 0.6761541962623596, 'learning_rate': 1.644217371110079e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5934/6464 [1:47:57<09:35, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0395, 'grad_norm': 0.7046400904655457, 'learning_rate': 1.64112091655055e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5935/6464 [1:47:57<09:11, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0645, 'grad_norm': 0.7542245388031006, 'learning_rate': 1.6380244619910203e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5936/6464 [1:47:58<08:55, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.049, 'grad_norm': 0.7889218330383301, 'learning_rate': 1.634928007431491e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5937/6464 [1:48:00<09:30, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9357, 'grad_norm': 0.7543901801109314, 'learning_rate': 1.6318315528719616e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5938/6464 [1:48:01<09:40, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.222, 'grad_norm': 0.6870136857032776, 'learning_rate': 1.628735098312432e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5939/6464 [1:48:02<09:22, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8234, 'grad_norm': 0.6247357130050659, 'learning_rate': 1.6256386437529032e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5940/6464 [1:48:03<09:58, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0815, 'grad_norm': 0.7291203737258911, 'learning_rate': 1.6225421891933737e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5941/6464 [1:48:04<09:30, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1554, 'grad_norm': 0.9305973052978516, 'learning_rate': 1.6194457346338444e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5942/6464 [1:48:05<09:14, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3829, 'grad_norm': 0.7836402058601379, 'learning_rate': 1.616349280074315e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5943/6464 [1:48:06<09:10, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1718, 'grad_norm': 0.7056885361671448, 'learning_rate': 1.6132528255147854e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5944/6464 [1:48:07<09:03, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1675, 'grad_norm': 0.7317572832107544, 'learning_rate': 1.6101563709552565e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5945/6464 [1:48:08<08:37, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9971, 'grad_norm': 0.7172269225120544, 'learning_rate': 1.607059916395727e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5946/6464 [1:48:09<08:48, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0479, 'grad_norm': 0.7620733976364136, 'learning_rate': 1.6039634618361978e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5947/6464 [1:48:10<08:51, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.999, 'grad_norm': 0.7125412225723267, 'learning_rate': 1.6008670072766682e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5948/6464 [1:48:11<08:57, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1834, 'grad_norm': 0.7181864380836487, 'learning_rate': 1.5977705527171387e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5949/6464 [1:48:12<09:16, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1344, 'grad_norm': 0.7260935306549072, 'learning_rate': 1.5946740981576098e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5950/6464 [1:48:13<08:57, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.891, 'grad_norm': 0.6536502838134766, 'learning_rate': 1.5915776435980803e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5951/6464 [1:48:14<08:52, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2437, 'grad_norm': 0.7475945949554443, 'learning_rate': 1.588481189038551e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5952/6464 [1:48:16<09:08, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3014, 'grad_norm': 0.644844114780426, 'learning_rate': 1.5853847344790215e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5953/6464 [1:48:17<08:58, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0407, 'grad_norm': 0.6900034546852112, 'learning_rate': 1.582288279919492e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5954/6464 [1:48:18<08:54, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8258, 'grad_norm': 0.7175720930099487, 'learning_rate': 1.579191825359963e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5955/6464 [1:48:19<09:43, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2163, 'grad_norm': 0.635608434677124, 'learning_rate': 1.5760953708004336e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5956/6464 [1:48:20<09:23, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.063, 'grad_norm': 0.6972677707672119, 'learning_rate': 1.5729989162409044e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5957/6464 [1:48:21<09:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1476, 'grad_norm': 0.8564653992652893, 'learning_rate': 1.5699024616813748e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5958/6464 [1:48:22<08:59, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8834, 'grad_norm': 0.6257413029670715, 'learning_rate': 1.5668060071218453e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5959/6464 [1:48:23<09:12, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1875, 'grad_norm': 0.656972348690033, 'learning_rate': 1.5637095525623164e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5960/6464 [1:48:24<08:56, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9787, 'grad_norm': 0.7519820332527161, 'learning_rate': 1.560613098002787e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5961/6464 [1:48:25<09:28, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2281, 'grad_norm': 0.6350556015968323, 'learning_rate': 1.5575166434432577e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5962/6464 [1:48:27<09:47, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0024, 'grad_norm': 0.6823769807815552, 'learning_rate': 1.554420188883728e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5963/6464 [1:48:28<09:15, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1599, 'grad_norm': 0.7602130770683289, 'learning_rate': 1.5513237343241986e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5964/6464 [1:48:29<08:39, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8762, 'grad_norm': 0.7904995679855347, 'learning_rate': 1.5482272797646697e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5965/6464 [1:48:30<08:31, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9833, 'grad_norm': 0.7322966456413269, 'learning_rate': 1.5451308252051402e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5966/6464 [1:48:31<08:35, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0757, 'grad_norm': 0.7428930997848511, 'learning_rate': 1.542034370645611e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5967/6464 [1:48:32<08:37, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1311, 'grad_norm': 0.7715522646903992, 'learning_rate': 1.5389379160860814e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5968/6464 [1:48:33<08:16, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8487, 'grad_norm': 0.5970438718795776, 'learning_rate': 1.535841461526552e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5969/6464 [1:48:34<08:35, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0742, 'grad_norm': 0.7957717776298523, 'learning_rate': 1.532745006967023e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5970/6464 [1:48:35<08:20, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0156, 'grad_norm': 0.7720217108726501, 'learning_rate': 1.5296485524074935e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5971/6464 [1:48:36<08:34, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.147, 'grad_norm': 0.7119736075401306, 'learning_rate': 1.5265520978479643e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5972/6464 [1:48:37<09:18, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2699, 'grad_norm': 0.7990818619728088, 'learning_rate': 1.5234556432884347e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5973/6464 [1:48:38<08:56, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.099, 'grad_norm': 0.873652994632721, 'learning_rate': 1.5203591887289054e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5974/6464 [1:48:39<09:00, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1765, 'grad_norm': 0.8867635130882263, 'learning_rate': 1.5172627341693763e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5975/6464 [1:48:40<08:48, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1059, 'grad_norm': 0.7306917905807495, 'learning_rate': 1.5141662796098468e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5976/6464 [1:48:41<08:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0177, 'grad_norm': 0.714067816734314, 'learning_rate': 1.5110698250503174e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5977/6464 [1:48:42<08:51, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1022, 'grad_norm': 0.6756592988967896, 'learning_rate': 1.507973370490788e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5978/6464 [1:48:43<08:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1521, 'grad_norm': 0.6946887373924255, 'learning_rate': 1.5048769159312587e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 92%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 5979/6464 [1:48:45<08:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9143, 'grad_norm': 0.6538533568382263, 'learning_rate': 1.5017804613717296e-05, 'epoch': 0.92}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5980/6464 [1:48:46<08:24, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9602, 'grad_norm': 0.7082088589668274, 'learning_rate': 1.4986840068122001e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5981/6464 [1:48:47<08:39, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1717, 'grad_norm': 0.6364863514900208, 'learning_rate': 1.4955875522526707e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5982/6464 [1:48:48<08:27, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8636, 'grad_norm': 0.8227074146270752, 'learning_rate': 1.4924910976931414e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5983/6464 [1:48:49<08:47, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2514, 'grad_norm': 0.8468334078788757, 'learning_rate': 1.489394643133612e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5984/6464 [1:48:50<08:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9839, 'grad_norm': 0.7620775103569031, 'learning_rate': 1.486298188574083e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5985/6464 [1:48:51<08:13, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0719, 'grad_norm': 0.8263278007507324, 'learning_rate': 1.4832017340145534e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5986/6464 [1:48:52<07:45, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9765, 'grad_norm': 0.750892162322998, 'learning_rate': 1.480105279455024e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5987/6464 [1:48:53<07:49, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0696, 'grad_norm': 0.6724781394004822, 'learning_rate': 1.4770088248954947e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5988/6464 [1:48:54<07:51, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9385, 'grad_norm': 0.6750346422195435, 'learning_rate': 1.4739123703359653e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5989/6464 [1:48:55<08:17, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.293, 'grad_norm': 0.6998451948165894, 'learning_rate': 1.4708159157764363e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5990/6464 [1:48:56<08:58, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1407, 'grad_norm': 0.8044747114181519, 'learning_rate': 1.4677194612169067e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5991/6464 [1:48:57<08:26, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0263, 'grad_norm': 0.8073660135269165, 'learning_rate': 1.4646230066573773e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5992/6464 [1:48:58<08:12, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1535, 'grad_norm': 0.747413694858551, 'learning_rate': 1.461526552097848e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5993/6464 [1:48:59<08:04, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9739, 'grad_norm': 0.785234808921814, 'learning_rate': 1.4584300975383186e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5994/6464 [1:49:00<08:34, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1949, 'grad_norm': 0.6292325258255005, 'learning_rate': 1.4553336429787896e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5995/6464 [1:49:01<08:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1685, 'grad_norm': 0.7231199145317078, 'learning_rate': 1.45223718841926e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5996/6464 [1:49:03<08:45, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0037, 'grad_norm': 0.7220306396484375, 'learning_rate': 1.4491407338597306e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5997/6464 [1:49:04<08:18, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9474, 'grad_norm': 0.7267279624938965, 'learning_rate': 1.4460442793002013e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5998/6464 [1:49:04<07:59, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9336, 'grad_norm': 0.7452868819236755, 'learning_rate': 1.4429478247406719e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 5999/6464 [1:49:05<07:38, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0163, 'grad_norm': 0.8353631496429443, 'learning_rate': 1.4398513701811425e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6000/6464 [1:49:06<07:30, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1208, 'grad_norm': 0.8903546929359436, 'learning_rate': 1.4367549156216133e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6001/6464 [1:49:08<09:31, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0184, 'grad_norm': 0.7984151244163513, 'learning_rate': 1.433658461062084e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6002/6464 [1:49:09<08:48, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9903, 'grad_norm': 0.7394759058952332, 'learning_rate': 1.4305620065025546e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6003/6464 [1:49:10<08:40, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2078, 'grad_norm': 0.6811690330505371, 'learning_rate': 1.4274655519430252e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6004/6464 [1:49:11<08:48, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1002, 'grad_norm': 0.6947084069252014, 'learning_rate': 1.4243690973834958e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6005/6464 [1:49:13<09:24, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4004, 'grad_norm': 0.7968404293060303, 'learning_rate': 1.4212726428239666e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6006/6464 [1:49:14<08:58, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1854, 'grad_norm': 0.7613944411277771, 'learning_rate': 1.4181761882644373e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6007/6464 [1:49:15<08:59, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1021, 'grad_norm': 0.6812794208526611, 'learning_rate': 1.4150797337049079e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6008/6464 [1:49:16<08:52, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1777, 'grad_norm': 0.7387716174125671, 'learning_rate': 1.4119832791453785e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6009/6464 [1:49:17<08:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9341, 'grad_norm': 0.6654379963874817, 'learning_rate': 1.4088868245858491e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6010/6464 [1:49:18<08:33, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9745, 'grad_norm': 0.6392068862915039, 'learning_rate': 1.4057903700263201e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6011/6464 [1:49:19<08:18, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9044, 'grad_norm': 0.6674706935882568, 'learning_rate': 1.4026939154667906e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6012/6464 [1:49:20<08:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2188, 'grad_norm': 0.718081533908844, 'learning_rate': 1.3995974609072612e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6013/6464 [1:49:21<07:51, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0828, 'grad_norm': 0.8659002184867859, 'learning_rate': 1.3965010063477318e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6014/6464 [1:49:22<07:59, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9948, 'grad_norm': 0.6319586038589478, 'learning_rate': 1.3934045517882024e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6015/6464 [1:49:23<07:47, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2684, 'grad_norm': 0.8941777944564819, 'learning_rate': 1.3903080972286734e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6016/6464 [1:49:25<07:45, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0078, 'grad_norm': 0.7438393235206604, 'learning_rate': 1.3872116426691439e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6017/6464 [1:49:25<07:31, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8596, 'grad_norm': 0.9851499795913696, 'learning_rate': 1.3841151881096145e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6018/6464 [1:49:26<07:18, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9955, 'grad_norm': 0.7038230299949646, 'learning_rate': 1.3810187335500851e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6019/6464 [1:49:27<06:59, 1.06it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0088, 'grad_norm': 0.813321590423584, 'learning_rate': 1.3779222789905558e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6020/6464 [1:49:28<07:07, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0767, 'grad_norm': 0.7646569609642029, 'learning_rate': 1.3748258244310267e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6021/6464 [1:49:29<06:54, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0862, 'grad_norm': 0.8530437350273132, 'learning_rate': 1.3717293698714972e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6022/6464 [1:49:30<06:41, 1.10it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7696, 'grad_norm': 0.6687250733375549, 'learning_rate': 1.3686329153119678e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6023/6464 [1:49:31<06:54, 1.07it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0025, 'grad_norm': 0.702031135559082, 'learning_rate': 1.3655364607524384e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6024/6464 [1:49:32<07:12, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1397, 'grad_norm': 0.6787034869194031, 'learning_rate': 1.362440006192909e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6025/6464 [1:49:33<07:21, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.273, 'grad_norm': 0.742148220539093, 'learning_rate': 1.35934355163338e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6026/6464 [1:49:34<07:07, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9972, 'grad_norm': 0.7958897948265076, 'learning_rate': 1.3562470970738505e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6027/6464 [1:49:35<07:08, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9753, 'grad_norm': 0.720756471157074, 'learning_rate': 1.3531506425143211e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6028/6464 [1:49:36<07:04, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9904, 'grad_norm': 0.7844934463500977, 'learning_rate': 1.3500541879547917e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6029/6464 [1:49:37<06:57, 1.04it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0381, 'grad_norm': 0.7616201043128967, 'learning_rate': 1.3469577333952624e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6030/6464 [1:49:38<07:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3836, 'grad_norm': 0.7790842652320862, 'learning_rate': 1.3438612788357333e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6031/6464 [1:49:39<07:47, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0386, 'grad_norm': 0.6323429346084595, 'learning_rate': 1.3407648242762038e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6032/6464 [1:49:40<07:29, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9673, 'grad_norm': 0.7376095056533813, 'learning_rate': 1.3376683697166744e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6033/6464 [1:49:42<08:03, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3907, 'grad_norm': 0.7366645336151123, 'learning_rate': 1.334571915157145e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6034/6464 [1:49:42<07:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0438, 'grad_norm': 0.7436796426773071, 'learning_rate': 1.3314754605976157e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6035/6464 [1:49:44<07:46, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0617, 'grad_norm': 0.6426711082458496, 'learning_rate': 1.3283790060380866e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6036/6464 [1:49:45<07:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2765, 'grad_norm': 0.809403657913208, 'learning_rate': 1.3252825514785571e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6037/6464 [1:49:46<07:55, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.5784, 'grad_norm': 0.7556561827659607, 'learning_rate': 1.3221860969190277e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6038/6464 [1:49:47<08:07, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1752, 'grad_norm': 0.7347787022590637, 'learning_rate': 1.3190896423594984e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6039/6464 [1:49:48<08:05, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2198, 'grad_norm': 0.6845679879188538, 'learning_rate': 1.315993187799969e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6040/6464 [1:49:49<07:54, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0385, 'grad_norm': 0.6689537167549133, 'learning_rate': 1.31289673324044e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6041/6464 [1:49:50<07:46, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1327, 'grad_norm': 0.7747564315795898, 'learning_rate': 1.3098002786809104e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6042/6464 [1:49:51<07:42, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2405, 'grad_norm': 0.8464855551719666, 'learning_rate': 1.306703824121381e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 93%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6043/6464 [1:49:53<07:41, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2613, 'grad_norm': 0.8434434533119202, 'learning_rate': 1.3036073695618517e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6044/6464 [1:49:54<07:28, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2362, 'grad_norm': 0.8287317752838135, 'learning_rate': 1.3005109150023223e-05, 'epoch': 0.93}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6045/6464 [1:49:55<07:17, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9702, 'grad_norm': 0.6528289318084717, 'learning_rate': 1.2974144604427933e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6046/6464 [1:49:56<07:27, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0652, 'grad_norm': 0.6150069236755371, 'learning_rate': 1.2943180058832639e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6047/6464 [1:49:57<07:49, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1362, 'grad_norm': 0.7287429571151733, 'learning_rate': 1.2912215513237343e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6048/6464 [1:49:58<07:33, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.916, 'grad_norm': 0.6905711889266968, 'learning_rate': 1.288125096764205e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6049/6464 [1:49:59<07:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2265, 'grad_norm': 0.8017783164978027, 'learning_rate': 1.2850286422046756e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6050/6464 [1:50:00<07:31, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1927, 'grad_norm': 0.7013878226280212, 'learning_rate': 1.2819321876451466e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6051/6464 [1:50:01<07:11, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9844, 'grad_norm': 0.7624514698982239, 'learning_rate': 1.2788357330856172e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6052/6464 [1:50:02<07:10, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1357, 'grad_norm': 0.7364188432693481, 'learning_rate': 1.2757392785260876e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6053/6464 [1:50:03<07:07, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1336, 'grad_norm': 0.865298330783844, 'learning_rate': 1.2726428239665583e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6054/6464 [1:50:04<07:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0463, 'grad_norm': 0.6549538373947144, 'learning_rate': 1.2695463694070289e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6055/6464 [1:50:05<07:22, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.449, 'grad_norm': 0.8834600448608398, 'learning_rate': 1.2664499148474999e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6056/6464 [1:50:06<07:27, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0544, 'grad_norm': 0.7573268413543701, 'learning_rate': 1.2633534602879705e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6057/6464 [1:50:07<07:16, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9924, 'grad_norm': 0.6902898550033569, 'learning_rate': 1.260257005728441e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6058/6464 [1:50:09<07:34, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1772, 'grad_norm': 0.7182676196098328, 'learning_rate': 1.2571605511689116e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Ž| 6059/6464 [1:50:10<07:25, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2436, 'grad_norm': 0.6894518733024597, 'learning_rate': 1.2540640966093822e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6060/6464 [1:50:11<07:31, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9656, 'grad_norm': 0.6050233840942383, 'learning_rate': 1.2509676420498532e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6061/6464 [1:50:12<07:39, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1103, 'grad_norm': 0.7725242972373962, 'learning_rate': 1.2478711874903236e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6062/6464 [1:50:13<07:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.087, 'grad_norm': 0.776115894317627, 'learning_rate': 1.2447747329307943e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6063/6464 [1:50:14<07:06, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0411, 'grad_norm': 0.6680818796157837, 'learning_rate': 1.2416782783712649e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6064/6464 [1:50:16<07:53, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0323, 'grad_norm': 0.6922734975814819, 'learning_rate': 1.2385818238117357e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6065/6464 [1:50:17<07:40, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0685, 'grad_norm': 0.7136076092720032, 'learning_rate': 1.2354853692522063e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6066/6464 [1:50:18<07:37, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1782, 'grad_norm': 0.800709068775177, 'learning_rate': 1.232388914692677e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6067/6464 [1:50:19<07:53, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1452, 'grad_norm': 0.6222375631332397, 'learning_rate': 1.2292924601331476e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6068/6464 [1:50:20<07:37, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9293, 'grad_norm': 0.6561319231987, 'learning_rate': 1.2261960055736182e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6069/6464 [1:50:21<07:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9812, 'grad_norm': 0.7252603769302368, 'learning_rate': 1.223099551014089e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6070/6464 [1:50:22<06:58, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0442, 'grad_norm': 0.8000838160514832, 'learning_rate': 1.2200030964545596e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6071/6464 [1:50:23<07:03, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3528, 'grad_norm': 0.7296555638313293, 'learning_rate': 1.2169066418950302e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6072/6464 [1:50:24<06:38, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7514, 'grad_norm': 0.6381885409355164, 'learning_rate': 1.2138101873355009e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6073/6464 [1:50:25<06:46, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9298, 'grad_norm': 0.663142204284668, 'learning_rate': 1.2107137327759715e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6074/6464 [1:50:26<06:31, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.036, 'grad_norm': 0.7959104776382446, 'learning_rate': 1.2076172782164423e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6075/6464 [1:50:27<06:24, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1365, 'grad_norm': 0.737559974193573, 'learning_rate': 1.204520823656913e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6076/6464 [1:50:28<06:30, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2382, 'grad_norm': 0.7472779154777527, 'learning_rate': 1.2014243690973835e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6077/6464 [1:50:29<06:51, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2031, 'grad_norm': 0.7207368612289429, 'learning_rate': 1.1983279145378542e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6078/6464 [1:50:30<07:08, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3186, 'grad_norm': 0.7444981932640076, 'learning_rate': 1.1952314599783248e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6079/6464 [1:50:32<07:20, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0406, 'grad_norm': 0.6924589276313782, 'learning_rate': 1.1921350054187954e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6080/6464 [1:50:33<07:10, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1876, 'grad_norm': 0.8094896674156189, 'learning_rate': 1.1890385508592662e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6081/6464 [1:50:34<07:25, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2466, 'grad_norm': 0.7186263203620911, 'learning_rate': 1.1859420962997369e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6082/6464 [1:50:35<07:02, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8876, 'grad_norm': 0.6814413070678711, 'learning_rate': 1.1828456417402076e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6083/6464 [1:50:36<06:55, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2587, 'grad_norm': 0.8328304886817932, 'learning_rate': 1.1797491871806781e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6084/6464 [1:50:37<06:43, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1786, 'grad_norm': 0.8255326151847839, 'learning_rate': 1.1766527326211487e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6085/6464 [1:50:38<06:53, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9539, 'grad_norm': 0.6576258540153503, 'learning_rate': 1.1735562780616195e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6086/6464 [1:50:39<06:32, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9364, 'grad_norm': 0.7022855281829834, 'learning_rate': 1.1704598235020902e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6087/6464 [1:50:41<07:10, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1436, 'grad_norm': 0.6503647565841675, 'learning_rate': 1.167363368942561e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6088/6464 [1:50:42<07:05, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0583, 'grad_norm': 0.7221968770027161, 'learning_rate': 1.1642669143830314e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6089/6464 [1:50:43<07:12, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0828, 'grad_norm': 0.6117902994155884, 'learning_rate': 1.161170459823502e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6090/6464 [1:50:44<07:12, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1837, 'grad_norm': 0.7610912322998047, 'learning_rate': 1.1580740052639728e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6091/6464 [1:50:45<07:07, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1888, 'grad_norm': 0.7747974395751953, 'learning_rate': 1.1549775507044435e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6092/6464 [1:50:46<06:51, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1798, 'grad_norm': 0.7176006436347961, 'learning_rate': 1.1518810961449143e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6093/6464 [1:50:47<06:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4114, 'grad_norm': 0.8337028622627258, 'learning_rate': 1.1487846415853847e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6094/6464 [1:50:48<07:03, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2358, 'grad_norm': 0.6806665062904358, 'learning_rate': 1.1456881870258553e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6095/6464 [1:50:50<06:53, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1296, 'grad_norm': 0.7075831890106201, 'learning_rate': 1.1425917324663261e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6096/6464 [1:50:51<06:59, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.227, 'grad_norm': 0.7494515776634216, 'learning_rate': 1.1394952779067968e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6097/6464 [1:50:52<06:30, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9461, 'grad_norm': 0.7418597936630249, 'learning_rate': 1.1363988233472676e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6098/6464 [1:50:53<06:52, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3586, 'grad_norm': 0.6748602390289307, 'learning_rate': 1.133302368787738e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6099/6464 [1:50:54<07:16, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0816, 'grad_norm': 0.703335165977478, 'learning_rate': 1.1302059142282087e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6100/6464 [1:50:55<07:01, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0417, 'grad_norm': 0.8090852499008179, 'learning_rate': 1.1271094596686794e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6101/6464 [1:50:56<06:41, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1239, 'grad_norm': 0.7782056927680969, 'learning_rate': 1.12401300510915e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6102/6464 [1:50:57<06:39, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0258, 'grad_norm': 0.8429294228553772, 'learning_rate': 1.1209165505496209e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6103/6464 [1:50:58<06:32, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0031, 'grad_norm': 0.7514006495475769, 'learning_rate': 1.1178200959900913e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6104/6464 [1:50:59<06:16, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0105, 'grad_norm': 0.6875583529472351, 'learning_rate': 1.114723641430562e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6105/6464 [1:51:01<06:26, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0059, 'grad_norm': 0.6666913032531738, 'learning_rate': 1.1116271868710328e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6106/6464 [1:51:02<06:38, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2278, 'grad_norm': 0.7334925532341003, 'learning_rate': 1.1085307323115034e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6107/6464 [1:51:03<06:53, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9406, 'grad_norm': 0.6066502332687378, 'learning_rate': 1.105434277751974e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 94%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6108/6464 [1:51:04<06:21, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8647, 'grad_norm': 0.7766785025596619, 'learning_rate': 1.1023378231924446e-05, 'epoch': 0.94}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6109/6464 [1:51:05<06:08, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9948, 'grad_norm': 0.8055647015571594, 'learning_rate': 1.0992413686329153e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6110/6464 [1:51:06<06:20, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4117, 'grad_norm': 0.7139821648597717, 'learning_rate': 1.096144914073386e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6111/6464 [1:51:07<06:19, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.956, 'grad_norm': 0.663327693939209, 'learning_rate': 1.0930484595138567e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6112/6464 [1:51:08<06:26, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9128, 'grad_norm': 0.5958645939826965, 'learning_rate': 1.0899520049543273e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6113/6464 [1:51:09<06:09, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0382, 'grad_norm': 0.755944013595581, 'learning_rate': 1.0868555503947981e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6114/6464 [1:51:10<06:22, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2268, 'grad_norm': 0.7052169442176819, 'learning_rate': 1.0837590958352686e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6115/6464 [1:51:11<06:20, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0254, 'grad_norm': 0.7936398983001709, 'learning_rate': 1.0806626412757394e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6116/6464 [1:51:12<06:13, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0996, 'grad_norm': 0.6999161243438721, 'learning_rate': 1.07756618671621e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6117/6464 [1:51:13<06:05, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2085, 'grad_norm': 0.9033050537109375, 'learning_rate': 1.0744697321566806e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6118/6464 [1:51:15<06:10, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1718, 'grad_norm': 0.6926135420799255, 'learning_rate': 1.0713732775971514e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6119/6464 [1:51:16<06:13, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9974, 'grad_norm': 0.6514447927474976, 'learning_rate': 1.0682768230376219e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6120/6464 [1:51:17<06:03, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0197, 'grad_norm': 0.7384715676307678, 'learning_rate': 1.0651803684780927e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6121/6464 [1:51:18<06:04, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1828, 'grad_norm': 0.785918653011322, 'learning_rate': 1.0620839139185633e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6122/6464 [1:51:19<05:47, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.92, 'grad_norm': 0.7806263566017151, 'learning_rate': 1.058987459359034e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6123/6464 [1:51:20<06:04, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0567, 'grad_norm': 0.6936910152435303, 'learning_rate': 1.0558910047995047e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6124/6464 [1:51:21<06:11, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1387, 'grad_norm': 0.6896028518676758, 'learning_rate': 1.0527945502399752e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6125/6464 [1:51:22<06:14, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9933, 'grad_norm': 0.6663902401924133, 'learning_rate': 1.049698095680446e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6126/6464 [1:51:23<06:18, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2659, 'grad_norm': 0.7570734024047852, 'learning_rate': 1.0466016411209166e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6127/6464 [1:51:24<06:07, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0987, 'grad_norm': 0.7289426922798157, 'learning_rate': 1.0435051865613872e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6128/6464 [1:51:25<05:46, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0003, 'grad_norm': 0.7522514462471008, 'learning_rate': 1.040408732001858e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6129/6464 [1:51:26<05:56, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0345, 'grad_norm': 0.745081901550293, 'learning_rate': 1.0373122774423285e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6130/6464 [1:51:28<06:10, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2158, 'grad_norm': 0.6454722881317139, 'learning_rate': 1.0342158228827993e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6131/6464 [1:51:29<06:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0005, 'grad_norm': 0.714115560054779, 'learning_rate': 1.0311193683232699e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6132/6464 [1:51:30<06:11, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9478, 'grad_norm': 0.5984063148498535, 'learning_rate': 1.0280229137637405e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6133/6464 [1:51:31<06:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9543, 'grad_norm': 0.6927739381790161, 'learning_rate': 1.0249264592042113e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6134/6464 [1:51:32<06:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2037, 'grad_norm': 0.7080563306808472, 'learning_rate': 1.0218300046446818e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6135/6464 [1:51:33<06:05, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1741, 'grad_norm': 0.7593572735786438, 'learning_rate': 1.0187335500851526e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6136/6464 [1:51:34<06:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9874, 'grad_norm': 0.7269288897514343, 'learning_rate': 1.0156370955256232e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6137/6464 [1:51:35<05:52, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9736, 'grad_norm': 0.6400807499885559, 'learning_rate': 1.0125406409660938e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6138/6464 [1:51:36<05:49, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0098, 'grad_norm': 0.7438717484474182, 'learning_rate': 1.0094441864065646e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6139/6464 [1:51:37<05:33, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9618, 'grad_norm': 0.7460315227508545, 'learning_rate': 1.0063477318470351e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–| 6140/6464 [1:51:38<06:01, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1505, 'grad_norm': 0.7027944922447205, 'learning_rate': 1.0032512772875057e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6141/6464 [1:51:39<05:43, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0766, 'grad_norm': 0.7150508165359497, 'learning_rate': 1.0001548227279765e-05, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6142/6464 [1:51:40<05:31, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0425, 'grad_norm': 0.799757182598114, 'learning_rate': 9.970583681684472e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6143/6464 [1:51:41<05:13, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9305, 'grad_norm': 0.7315821051597595, 'learning_rate': 9.93961913608918e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6144/6464 [1:51:42<05:09, 1.03it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.01, 'grad_norm': 0.7063149809837341, 'learning_rate': 9.908654590493884e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6145/6464 [1:51:43<05:17, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1082, 'grad_norm': 0.7180485725402832, 'learning_rate': 9.87769004489859e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6146/6464 [1:51:44<05:19, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0012, 'grad_norm': 0.7056120038032532, 'learning_rate': 9.846725499303298e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6147/6464 [1:51:45<05:36, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2565, 'grad_norm': 0.7740292549133301, 'learning_rate': 9.815760953708005e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6148/6464 [1:51:47<05:38, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8892, 'grad_norm': 0.6041938662528992, 'learning_rate': 9.784796408112713e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6149/6464 [1:51:47<05:21, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8829, 'grad_norm': 0.7748526334762573, 'learning_rate': 9.753831862517419e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6150/6464 [1:51:48<05:16, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2222, 'grad_norm': 0.7417736649513245, 'learning_rate': 9.722867316922123e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6151/6464 [1:51:50<05:39, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3401, 'grad_norm': 0.7212684154510498, 'learning_rate': 9.691902771326831e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6152/6464 [1:51:51<05:54, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2768, 'grad_norm': 0.7409665584564209, 'learning_rate': 9.660938225731538e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6153/6464 [1:51:52<05:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1547, 'grad_norm': 0.767113983631134, 'learning_rate': 9.629973680136246e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6154/6464 [1:51:53<05:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1771, 'grad_norm': 0.7961496710777283, 'learning_rate': 9.599009134540952e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6155/6464 [1:51:54<05:23, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3954, 'grad_norm': 0.7743737101554871, 'learning_rate': 9.568044588945656e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6156/6464 [1:51:55<05:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8841, 'grad_norm': 0.6425191164016724, 'learning_rate': 9.537080043350364e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6157/6464 [1:51:56<05:20, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9043, 'grad_norm': 0.6767885684967041, 'learning_rate': 9.50611549775507e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6158/6464 [1:51:57<05:19, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.086, 'grad_norm': 0.6918661594390869, 'learning_rate': 9.475150952159779e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6159/6464 [1:51:58<05:34, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9824, 'grad_norm': 0.6308749318122864, 'learning_rate': 9.444186406564485e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6160/6464 [1:51:59<05:11, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1397, 'grad_norm': 0.8105279803276062, 'learning_rate': 9.41322186096919e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6161/6464 [1:52:00<05:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2008, 'grad_norm': 0.8033198714256287, 'learning_rate': 9.382257315373897e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6162/6464 [1:52:02<05:40, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3665, 'grad_norm': 0.6907389163970947, 'learning_rate': 9.351292769778604e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6163/6464 [1:52:03<05:32, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1545, 'grad_norm': 0.6963345408439636, 'learning_rate': 9.320328224183312e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6164/6464 [1:52:04<05:45, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3077, 'grad_norm': 0.6995038390159607, 'learning_rate': 9.289363678588018e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6165/6464 [1:52:05<05:51, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4296, 'grad_norm': 0.7779677510261536, 'learning_rate': 9.258399132992723e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6166/6464 [1:52:06<05:44, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1746, 'grad_norm': 0.731975257396698, 'learning_rate': 9.22743458739743e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6167/6464 [1:52:07<05:35, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9657, 'grad_norm': 0.64762282371521, 'learning_rate': 9.196470041802137e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6168/6464 [1:52:09<05:41, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2859, 'grad_norm': 0.7532076835632324, 'learning_rate': 9.165505496206845e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6169/6464 [1:52:10<05:31, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1067, 'grad_norm': 0.7292687296867371, 'learning_rate': 9.134540950611551e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6170/6464 [1:52:11<05:23, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0811, 'grad_norm': 0.7099891304969788, 'learning_rate': 9.103576405016256e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6171/6464 [1:52:12<05:18, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.283, 'grad_norm': 0.7920886874198914, 'learning_rate': 9.072611859420964e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6172/6464 [1:52:13<05:06, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9635, 'grad_norm': 0.746236264705658, 'learning_rate': 9.04164731382567e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 95%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6173/6464 [1:52:14<05:09, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2134, 'grad_norm': 0.6881935000419617, 'learning_rate': 9.010682768230376e-06, 'epoch': 0.95}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6174/6464 [1:52:15<05:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8774, 'grad_norm': 0.7048290967941284, 'learning_rate': 8.979718222635084e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6175/6464 [1:52:16<05:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1792, 'grad_norm': 0.6745209097862244, 'learning_rate': 8.948753677039789e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6176/6464 [1:52:17<05:25, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4698, 'grad_norm': 0.7674632668495178, 'learning_rate': 8.917789131444497e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6177/6464 [1:52:18<05:30, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1094, 'grad_norm': 0.6944257616996765, 'learning_rate': 8.886824585849203e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6178/6464 [1:52:19<05:10, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0539, 'grad_norm': 0.7543038129806519, 'learning_rate': 8.85586004025391e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6179/6464 [1:52:21<05:33, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2835, 'grad_norm': 0.6703681945800781, 'learning_rate': 8.824895494658617e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6180/6464 [1:52:22<05:13, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9068, 'grad_norm': 0.6676964163780212, 'learning_rate': 8.793930949063322e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6181/6464 [1:52:23<05:23, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1844, 'grad_norm': 0.8421143889427185, 'learning_rate': 8.76296640346803e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6182/6464 [1:52:24<05:19, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2556, 'grad_norm': 0.7449273467063904, 'learning_rate': 8.732001857872736e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6183/6464 [1:52:25<05:18, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1167, 'grad_norm': 0.7306602597236633, 'learning_rate': 8.701037312277442e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6184/6464 [1:52:26<05:18, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9212, 'grad_norm': 0.7216421365737915, 'learning_rate': 8.67007276668215e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6185/6464 [1:52:27<05:20, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0499, 'grad_norm': 0.6483009457588196, 'learning_rate': 8.639108221086857e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6186/6464 [1:52:29<05:15, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1893, 'grad_norm': 0.7892354726791382, 'learning_rate': 8.608143675491563e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6187/6464 [1:52:30<05:04, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3744, 'grad_norm': 0.7740828990936279, 'learning_rate': 8.577179129896269e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6188/6464 [1:52:31<05:03, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0682, 'grad_norm': 0.7017830610275269, 'learning_rate': 8.546214584300975e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6189/6464 [1:52:32<04:59, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1012, 'grad_norm': 0.6649497151374817, 'learning_rate': 8.515250038705683e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6190/6464 [1:52:33<04:53, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2043, 'grad_norm': 0.8182793855667114, 'learning_rate': 8.48428549311039e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6191/6464 [1:52:34<04:39, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9001, 'grad_norm': 0.7007230520248413, 'learning_rate': 8.453320947515096e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6192/6464 [1:52:35<04:42, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1717, 'grad_norm': 0.7045168876647949, 'learning_rate': 8.422356401919802e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6193/6464 [1:52:36<04:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0825, 'grad_norm': 0.6790217757225037, 'learning_rate': 8.391391856324508e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6194/6464 [1:52:37<04:47, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1696, 'grad_norm': 0.7933171391487122, 'learning_rate': 8.360427310729216e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6195/6464 [1:52:38<04:33, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9772, 'grad_norm': 0.8776745200157166, 'learning_rate': 8.329462765133923e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6196/6464 [1:52:39<04:28, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0383, 'grad_norm': 0.6998895406723022, 'learning_rate': 8.298498219538629e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6197/6464 [1:52:40<04:38, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1986, 'grad_norm': 0.6688068509101868, 'learning_rate': 8.267533673943335e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6198/6464 [1:52:41<04:39, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0735, 'grad_norm': 0.6748147010803223, 'learning_rate': 8.236569128348041e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6199/6464 [1:52:42<04:36, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0084, 'grad_norm': 0.6592279076576233, 'learning_rate': 8.20560458275275e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6200/6464 [1:52:43<04:24, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1482, 'grad_norm': 0.7915459275245667, 'learning_rate': 8.174640037157456e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6201/6464 [1:52:44<04:32, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0879, 'grad_norm': 0.7561859488487244, 'learning_rate': 8.14367549156216e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6202/6464 [1:52:45<04:33, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1291, 'grad_norm': 0.6961678862571716, 'learning_rate': 8.112710945966868e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6203/6464 [1:52:46<04:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3782, 'grad_norm': 0.746642529964447, 'learning_rate': 8.081746400371575e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6204/6464 [1:52:47<04:30, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1337, 'grad_norm': 0.751498818397522, 'learning_rate': 8.050781854776283e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6205/6464 [1:52:48<04:29, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0002, 'grad_norm': 0.7525529265403748, 'learning_rate': 8.019817309180989e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6206/6464 [1:52:50<04:50, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3908, 'grad_norm': 0.6728494763374329, 'learning_rate': 7.988852763585693e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6207/6464 [1:52:51<04:34, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9646, 'grad_norm': 0.7167695760726929, 'learning_rate': 7.957888217990401e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6208/6464 [1:52:52<04:32, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1403, 'grad_norm': 0.7214434146881104, 'learning_rate': 7.926923672395108e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6209/6464 [1:52:53<04:40, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9095, 'grad_norm': 0.6521071195602417, 'learning_rate': 7.895959126799816e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6210/6464 [1:52:54<04:18, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1335, 'grad_norm': 1.010145902633667, 'learning_rate': 7.864994581204522e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6211/6464 [1:52:55<05:20, 1.27s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3037, 'grad_norm': 0.641684353351593, 'learning_rate': 7.834030035609226e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6212/6464 [1:52:57<05:07, 1.22s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9911, 'grad_norm': 0.7675653100013733, 'learning_rate': 7.803065490013934e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6213/6464 [1:52:58<05:00, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9302, 'grad_norm': 0.6103814244270325, 'learning_rate': 7.77210094441864e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6214/6464 [1:52:59<04:50, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1744, 'grad_norm': 0.7264071106910706, 'learning_rate': 7.741136398823349e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6215/6464 [1:53:00<04:48, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0425, 'grad_norm': 0.6969607472419739, 'learning_rate': 7.710171853228055e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6216/6464 [1:53:01<04:44, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1565, 'grad_norm': 0.8469471335411072, 'learning_rate': 7.67920730763276e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6217/6464 [1:53:02<04:44, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2112, 'grad_norm': 0.7417719960212708, 'learning_rate': 7.648242762037467e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6218/6464 [1:53:03<04:43, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1059, 'grad_norm': 0.8376610279083252, 'learning_rate': 7.617278216442174e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6219/6464 [1:53:05<04:48, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2605, 'grad_norm': 0.8120513558387756, 'learning_rate': 7.586313670846882e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6220/6464 [1:53:06<04:40, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1452, 'grad_norm': 0.6883100271224976, 'learning_rate': 7.555349125251587e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Œ| 6221/6464 [1:53:07<04:42, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0958, 'grad_norm': 0.687289834022522, 'learning_rate': 7.524384579656293e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6222/6464 [1:53:08<04:30, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4132, 'grad_norm': 0.8877328634262085, 'learning_rate': 7.4934200340610005e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6223/6464 [1:53:09<04:31, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3196, 'grad_norm': 0.7470777034759521, 'learning_rate': 7.462455488465707e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6224/6464 [1:53:10<04:51, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1513, 'grad_norm': 0.6738355755805969, 'learning_rate': 7.431490942870415e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6225/6464 [1:53:11<04:30, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1232, 'grad_norm': 0.823180615901947, 'learning_rate': 7.40052639727512e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6226/6464 [1:53:13<04:29, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2761, 'grad_norm': 0.7858986258506775, 'learning_rate': 7.3695618516798264e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6227/6464 [1:53:14<04:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1588, 'grad_norm': 0.7578523755073547, 'learning_rate': 7.3385973060845336e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6228/6464 [1:53:15<04:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0904, 'grad_norm': 0.6221215128898621, 'learning_rate': 7.30763276048924e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6229/6464 [1:53:16<04:05, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8417, 'grad_norm': 0.7795819044113159, 'learning_rate': 7.276668214893948e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6230/6464 [1:53:17<04:16, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1143, 'grad_norm': 0.6526833772659302, 'learning_rate': 7.245703669298653e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6231/6464 [1:53:18<04:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0764, 'grad_norm': 0.8156328797340393, 'learning_rate': 7.2147391237033595e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6232/6464 [1:53:19<04:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0562, 'grad_norm': 0.6723642349243164, 'learning_rate': 7.183774578108067e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6233/6464 [1:53:20<04:01, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2523, 'grad_norm': 0.8951084613800049, 'learning_rate': 7.152810032512773e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6234/6464 [1:53:21<03:57, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9931, 'grad_norm': 0.7953217029571533, 'learning_rate': 7.121845486917479e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6235/6464 [1:53:22<03:51, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0266, 'grad_norm': 0.7070714831352234, 'learning_rate': 7.090880941322186e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6236/6464 [1:53:23<03:49, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0415, 'grad_norm': 0.7459718585014343, 'learning_rate': 7.0599163957268926e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 96%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6237/6464 [1:53:24<04:00, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.04, 'grad_norm': 0.6514926552772522, 'learning_rate': 7.0289518501316005e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6238/6464 [1:53:25<04:12, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2133, 'grad_norm': 0.6514918804168701, 'learning_rate': 6.997987304536306e-06, 'epoch': 0.96}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6239/6464 [1:53:26<04:11, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2191, 'grad_norm': 0.6652721166610718, 'learning_rate': 6.967022758941012e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6240/6464 [1:53:27<04:04, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2245, 'grad_norm': 0.886877179145813, 'learning_rate': 6.936058213345719e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6241/6464 [1:53:28<03:57, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9048, 'grad_norm': 0.6353622078895569, 'learning_rate': 6.905093667750426e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6242/6464 [1:53:29<03:55, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8528, 'grad_norm': 0.6464487910270691, 'learning_rate': 6.874129122155134e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6243/6464 [1:53:31<03:53, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2291, 'grad_norm': 0.8245118260383606, 'learning_rate': 6.843164576559839e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6244/6464 [1:53:32<03:48, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0423, 'grad_norm': 0.6921374797821045, 'learning_rate': 6.812200030964545e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6245/6464 [1:53:33<04:04, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0551, 'grad_norm': 0.678176999092102, 'learning_rate': 6.781235485369252e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6246/6464 [1:53:34<04:12, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1876, 'grad_norm': 0.6665492057800293, 'learning_rate': 6.750270939773959e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6247/6464 [1:53:35<03:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1788, 'grad_norm': 0.8140139579772949, 'learning_rate': 6.719306394178667e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6248/6464 [1:53:36<03:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0611, 'grad_norm': 0.6946382522583008, 'learning_rate': 6.688341848583372e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6249/6464 [1:53:37<03:44, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1113, 'grad_norm': 0.7855856418609619, 'learning_rate': 6.657377302988078e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6250/6464 [1:53:38<03:59, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1284, 'grad_norm': 0.7386621236801147, 'learning_rate': 6.6264127573927855e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6251/6464 [1:53:40<04:04, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1347, 'grad_norm': 0.6922546029090881, 'learning_rate': 6.595448211797492e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6252/6464 [1:53:41<03:54, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9787, 'grad_norm': 0.7132231593132019, 'learning_rate': 6.5644836662022e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6253/6464 [1:53:42<03:54, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2032, 'grad_norm': 0.7925822734832764, 'learning_rate': 6.533519120606905e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6254/6464 [1:53:43<03:57, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0527, 'grad_norm': 0.68798828125, 'learning_rate': 6.502554575011611e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6255/6464 [1:53:44<03:54, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0608, 'grad_norm': 0.6790725588798523, 'learning_rate': 6.471590029416319e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6256/6464 [1:53:45<03:46, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.197, 'grad_norm': 0.7249159812927246, 'learning_rate': 6.440625483821025e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6257/6464 [1:53:46<03:36, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9296, 'grad_norm': 0.6792775988578796, 'learning_rate': 6.409660938225733e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6258/6464 [1:53:47<03:30, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0624, 'grad_norm': 0.7242748737335205, 'learning_rate': 6.378696392630438e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6259/6464 [1:53:48<03:28, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1122, 'grad_norm': 0.7932643294334412, 'learning_rate': 6.3477318470351445e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6260/6464 [1:53:49<03:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0801, 'grad_norm': 0.6941478252410889, 'learning_rate': 6.3167673014398525e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6261/6464 [1:53:50<03:40, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0861, 'grad_norm': 0.67449551820755, 'learning_rate': 6.285802755844558e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6262/6464 [1:53:51<03:30, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0388, 'grad_norm': 0.8251277804374695, 'learning_rate': 6.254838210249266e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6263/6464 [1:53:52<03:39, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0604, 'grad_norm': 0.6233731508255005, 'learning_rate': 6.223873664653971e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6264/6464 [1:53:54<03:57, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1638, 'grad_norm': 0.6433247327804565, 'learning_rate': 6.192909119058678e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6265/6464 [1:53:55<03:48, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1747, 'grad_norm': 0.6751717925071716, 'learning_rate': 6.161944573463385e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6266/6464 [1:53:56<03:39, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9646, 'grad_norm': 0.665816605091095, 'learning_rate': 6.130980027868091e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6267/6464 [1:53:57<03:46, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3164, 'grad_norm': 0.6871161460876465, 'learning_rate': 6.100015482272798e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6268/6464 [1:53:58<03:49, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3833, 'grad_norm': 0.6454440355300903, 'learning_rate': 6.069050936677504e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6269/6464 [1:53:59<03:44, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0367, 'grad_norm': 0.7151509523391724, 'learning_rate': 6.0380863910822115e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6270/6464 [1:54:00<03:37, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1077, 'grad_norm': 0.7117139101028442, 'learning_rate': 6.007121845486918e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6271/6464 [1:54:02<03:40, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2842, 'grad_norm': 0.6789916157722473, 'learning_rate': 5.976157299891624e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6272/6464 [1:54:03<03:27, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0811, 'grad_norm': 0.7487647533416748, 'learning_rate': 5.945192754296331e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6273/6464 [1:54:04<03:41, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0491, 'grad_norm': 0.6047787070274353, 'learning_rate': 5.914228208701038e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6274/6464 [1:54:05<03:30, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0338, 'grad_norm': 0.728877067565918, 'learning_rate': 5.883263663105744e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6275/6464 [1:54:06<03:49, 1.21s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3049, 'grad_norm': 0.62032151222229, 'learning_rate': 5.852299117510451e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6276/6464 [1:54:08<03:51, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0842, 'grad_norm': 0.5817559361457825, 'learning_rate': 5.821334571915157e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6277/6464 [1:54:09<03:42, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.039, 'grad_norm': 0.8441981673240662, 'learning_rate': 5.790370026319864e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6278/6464 [1:54:10<03:39, 1.18s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.228, 'grad_norm': 0.709690272808075, 'learning_rate': 5.759405480724571e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6279/6464 [1:54:11<03:30, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0223, 'grad_norm': 0.7060588598251343, 'learning_rate': 5.728440935129277e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6280/6464 [1:54:12<03:17, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.019, 'grad_norm': 0.8618728518486023, 'learning_rate': 5.697476389533984e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6281/6464 [1:54:13<03:10, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9968, 'grad_norm': 0.7314029335975647, 'learning_rate': 5.66651184393869e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6282/6464 [1:54:14<03:15, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0473, 'grad_norm': 0.7134976387023926, 'learning_rate': 5.635547298343397e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6283/6464 [1:54:15<03:16, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3014, 'grad_norm': 0.7463049292564392, 'learning_rate': 5.604582752748104e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6284/6464 [1:54:16<03:13, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0804, 'grad_norm': 0.659194827079773, 'learning_rate': 5.57361820715281e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6285/6464 [1:54:17<03:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2518, 'grad_norm': 0.7165722250938416, 'learning_rate': 5.542653661557517e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6286/6464 [1:54:18<03:21, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0294, 'grad_norm': 0.7314486503601074, 'learning_rate': 5.511689115962223e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6287/6464 [1:54:19<03:06, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8981, 'grad_norm': 0.7468152642250061, 'learning_rate': 5.48072457036693e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6288/6464 [1:54:20<03:03, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1675, 'grad_norm': 1.1266075372695923, 'learning_rate': 5.449760024771637e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6289/6464 [1:54:21<02:58, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0994, 'grad_norm': 0.965049147605896, 'learning_rate': 5.418795479176343e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6290/6464 [1:54:22<02:50, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0442, 'grad_norm': 0.7907286882400513, 'learning_rate': 5.38783093358105e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6291/6464 [1:54:23<02:55, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1803, 'grad_norm': 0.7681965231895447, 'learning_rate': 5.356866387985757e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6292/6464 [1:54:25<03:05, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2277, 'grad_norm': 0.7634093165397644, 'learning_rate': 5.325901842390463e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6293/6464 [1:54:26<03:17, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0779, 'grad_norm': 0.5918500423431396, 'learning_rate': 5.29493729679517e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6294/6464 [1:54:27<03:08, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.7604, 'grad_norm': 0.5580567121505737, 'learning_rate': 5.263972751199876e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6295/6464 [1:54:28<02:59, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.144, 'grad_norm': 0.7245799899101257, 'learning_rate': 5.233008205604583e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6296/6464 [1:54:29<03:03, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2039, 'grad_norm': 0.7137886881828308, 'learning_rate': 5.20204366000929e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6297/6464 [1:54:30<03:12, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1277, 'grad_norm': 0.6545876264572144, 'learning_rate': 5.1710791144139964e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6298/6464 [1:54:31<03:09, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0502, 'grad_norm': 0.6846231818199158, 'learning_rate': 5.140114568818703e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6299/6464 [1:54:33<03:17, 1.20s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1222, 'grad_norm': 0.6102810502052307, 'learning_rate': 5.109150023223409e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6300/6464 [1:54:34<03:09, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.925, 'grad_norm': 0.6737794876098633, 'learning_rate': 5.078185477628116e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6301/6464 [1:54:35<02:58, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9045, 'grad_norm': 0.7827260494232178, 'learning_rate': 5.047220932032823e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 97%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‹| 6302/6464 [1:54:36<02:56, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.208, 'grad_norm': 0.7482419013977051, 'learning_rate': 5.016256386437529e-06, 'epoch': 0.97}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6303/6464 [1:54:37<02:53, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8703, 'grad_norm': 0.6478527784347534, 'learning_rate': 4.985291840842236e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6304/6464 [1:54:38<02:58, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3312, 'grad_norm': 0.7636555433273315, 'learning_rate': 4.954327295246942e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6305/6464 [1:54:39<02:47, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8852, 'grad_norm': 0.7073574066162109, 'learning_rate': 4.923362749651649e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6306/6464 [1:54:40<02:50, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0088, 'grad_norm': 0.6478416323661804, 'learning_rate': 4.892398204056356e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6307/6464 [1:54:41<02:48, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0145, 'grad_norm': 0.7022079229354858, 'learning_rate': 4.861433658461062e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6308/6464 [1:54:43<03:11, 1.23s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2387, 'grad_norm': 0.5905323624610901, 'learning_rate': 4.830469112865769e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6309/6464 [1:54:44<03:12, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1751, 'grad_norm': 0.7964683175086975, 'learning_rate': 4.799504567270476e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6310/6464 [1:54:45<03:14, 1.26s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3446, 'grad_norm': 0.6688273549079895, 'learning_rate': 4.768540021675182e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6311/6464 [1:54:47<03:09, 1.24s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.139, 'grad_norm': 0.6816748976707458, 'learning_rate': 4.737575476079889e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6312/6464 [1:54:47<02:51, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9824, 'grad_norm': 0.7719330191612244, 'learning_rate': 4.706610930484595e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6313/6464 [1:54:49<02:49, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9735, 'grad_norm': 0.7015283703804016, 'learning_rate': 4.675646384889302e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6314/6464 [1:54:50<02:47, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1331, 'grad_norm': 0.7234323620796204, 'learning_rate': 4.644681839294009e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6315/6464 [1:54:51<02:41, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.278, 'grad_norm': 0.7985410094261169, 'learning_rate': 4.613717293698715e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6316/6464 [1:54:52<02:37, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3541, 'grad_norm': 0.7596659660339355, 'learning_rate': 4.582752748103422e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6317/6464 [1:54:53<02:41, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9594, 'grad_norm': 0.6817618012428284, 'learning_rate': 4.551788202508128e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6318/6464 [1:54:54<02:44, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1712, 'grad_norm': 0.6772673726081848, 'learning_rate': 4.520823656912835e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6319/6464 [1:54:55<02:45, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1958, 'grad_norm': 0.6133381724357605, 'learning_rate': 4.489859111317542e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6320/6464 [1:54:56<02:35, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0612, 'grad_norm': 0.8218144178390503, 'learning_rate': 4.458894565722248e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6321/6464 [1:54:57<02:35, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2723, 'grad_norm': 0.6682705283164978, 'learning_rate': 4.427930020126955e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6322/6464 [1:54:58<02:36, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1792, 'grad_norm': 0.7219808101654053, 'learning_rate': 4.396965474531661e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6323/6464 [1:55:00<02:35, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.085, 'grad_norm': 0.7028492093086243, 'learning_rate': 4.366000928936368e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6324/6464 [1:55:00<02:27, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8899, 'grad_norm': 0.6537131071090698, 'learning_rate': 4.335036383341075e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6325/6464 [1:55:01<02:20, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0382, 'grad_norm': 0.7249526381492615, 'learning_rate': 4.304071837745781e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6326/6464 [1:55:02<02:18, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9356, 'grad_norm': 0.72031569480896, 'learning_rate': 4.273107292150488e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6327/6464 [1:55:03<02:18, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.28, 'grad_norm': 0.8835470676422119, 'learning_rate': 4.242142746555195e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6328/6464 [1:55:04<02:20, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9423, 'grad_norm': 0.6579557657241821, 'learning_rate': 4.211178200959901e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6329/6464 [1:55:06<02:27, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0966, 'grad_norm': 0.7002262473106384, 'learning_rate': 4.180213655364608e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6330/6464 [1:55:07<02:22, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0297, 'grad_norm': 0.7713639140129089, 'learning_rate': 4.1492491097693145e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6331/6464 [1:55:08<02:23, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0887, 'grad_norm': 0.7088030576705933, 'learning_rate': 4.118284564174021e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6332/6464 [1:55:09<02:23, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1511, 'grad_norm': 0.7033181190490723, 'learning_rate': 4.087320018578728e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6333/6464 [1:55:10<02:26, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1561, 'grad_norm': 0.6680731177330017, 'learning_rate': 4.056355472983434e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6334/6464 [1:55:11<02:25, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0114, 'grad_norm': 0.7168923020362854, 'learning_rate': 4.025390927388141e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6335/6464 [1:55:12<02:24, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1041, 'grad_norm': 0.7134062647819519, 'learning_rate': 3.994426381792847e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6336/6464 [1:55:13<02:23, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2835, 'grad_norm': 0.8149298429489136, 'learning_rate': 3.963461836197554e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6337/6464 [1:55:15<02:23, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.4238, 'grad_norm': 0.799555242061615, 'learning_rate': 3.932497290602261e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6338/6464 [1:55:16<02:26, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.207, 'grad_norm': 0.7298685908317566, 'learning_rate': 3.901532745006967e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6339/6464 [1:55:17<02:12, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8146, 'grad_norm': 0.7869361639022827, 'learning_rate': 3.870568199411674e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6340/6464 [1:55:18<02:16, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1297, 'grad_norm': 0.6750180721282959, 'learning_rate': 3.83960365381638e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6341/6464 [1:55:19<02:17, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.274, 'grad_norm': 0.6863314509391785, 'learning_rate': 3.808639108221087e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6342/6464 [1:55:20<02:19, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.397, 'grad_norm': 0.6632447242736816, 'learning_rate': 3.7776745626257936e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6343/6464 [1:55:21<02:14, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1767, 'grad_norm': 0.7716890573501587, 'learning_rate': 3.7467100170305003e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6344/6464 [1:55:22<02:04, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8222, 'grad_norm': 0.6904069781303406, 'learning_rate': 3.7157454714352074e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6345/6464 [1:55:23<02:00, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.114, 'grad_norm': 0.8119975328445435, 'learning_rate': 3.6847809258399132e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6346/6464 [1:55:24<02:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2128, 'grad_norm': 0.6818786263465881, 'learning_rate': 3.65381638024462e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6347/6464 [1:55:25<02:02, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1792, 'grad_norm': 0.7713095545768738, 'learning_rate': 3.6228518346493266e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6348/6464 [1:55:26<02:00, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0994, 'grad_norm': 0.6876352429389954, 'learning_rate': 3.5918872890540333e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6349/6464 [1:55:27<02:01, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0133, 'grad_norm': 0.692415177822113, 'learning_rate': 3.5609227434587396e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6350/6464 [1:55:29<02:05, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1313, 'grad_norm': 0.6555089354515076, 'learning_rate': 3.5299581978634463e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6351/6464 [1:55:30<02:04, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2057, 'grad_norm': 0.8469429016113281, 'learning_rate': 3.498993652268153e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6352/6464 [1:55:31<02:02, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.285, 'grad_norm': 0.8278331160545349, 'learning_rate': 3.4680291066728597e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6353/6464 [1:55:32<01:58, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1956, 'grad_norm': 0.7551913857460022, 'learning_rate': 3.437064561077567e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6354/6464 [1:55:33<01:56, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2787, 'grad_norm': 0.7731183171272278, 'learning_rate': 3.4061000154822726e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6355/6464 [1:55:34<02:02, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9382, 'grad_norm': 0.6269389986991882, 'learning_rate': 3.3751354698869793e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6356/6464 [1:55:35<02:05, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3516, 'grad_norm': 0.6534362435340881, 'learning_rate': 3.344170924291686e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6357/6464 [1:55:37<02:07, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0186, 'grad_norm': 0.6683214902877808, 'learning_rate': 3.3132063786963927e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6358/6464 [1:55:38<01:57, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8388, 'grad_norm': 0.6425167322158813, 'learning_rate': 3.2822418331011e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6359/6464 [1:55:38<01:52, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0425, 'grad_norm': 0.7584932446479797, 'learning_rate': 3.2512772875058057e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6360/6464 [1:55:40<01:57, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0704, 'grad_norm': 0.6264423131942749, 'learning_rate': 3.2203127419105124e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6361/6464 [1:55:41<01:54, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1951, 'grad_norm': 0.8082621097564697, 'learning_rate': 3.189348196315219e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6362/6464 [1:55:42<01:58, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2585, 'grad_norm': 0.6673972010612488, 'learning_rate': 3.1583836507199262e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6363/6464 [1:55:43<01:55, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1131, 'grad_norm': 0.7804420590400696, 'learning_rate': 3.127419105124633e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6364/6464 [1:55:44<01:52, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1006, 'grad_norm': 0.7082564830780029, 'learning_rate': 3.096454559529339e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6365/6464 [1:55:45<01:50, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1696, 'grad_norm': 0.7295549511909485, 'learning_rate': 3.0654900139340455e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6366/6464 [1:55:46<01:46, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0336, 'grad_norm': 0.6753019094467163, 'learning_rate': 3.034525468338752e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 98%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6367/6464 [1:55:47<01:45, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0413, 'grad_norm': 0.7390074133872986, 'learning_rate': 3.003560922743459e-06, 'epoch': 0.98}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6368/6464 [1:55:49<01:44, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8581, 'grad_norm': 0.6410005688667297, 'learning_rate': 2.9725963771481656e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6369/6464 [1:55:50<01:48, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3951, 'grad_norm': 0.7540284991264343, 'learning_rate': 2.941631831552872e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6370/6464 [1:55:51<01:41, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9995, 'grad_norm': 0.6722819805145264, 'learning_rate': 2.9106672859575785e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6371/6464 [1:55:52<01:43, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1832, 'grad_norm': 0.6331114172935486, 'learning_rate': 2.8797027403622857e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6372/6464 [1:55:53<01:37, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9472, 'grad_norm': 0.7292405962944031, 'learning_rate': 2.848738194766992e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6373/6464 [1:55:54<01:43, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2096, 'grad_norm': 0.657503068447113, 'learning_rate': 2.8177736491716986e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6374/6464 [1:55:55<01:44, 1.17s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1602, 'grad_norm': 0.8012603521347046, 'learning_rate': 2.786809103576405e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6375/6464 [1:55:57<01:42, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.917, 'grad_norm': 0.6399195194244385, 'learning_rate': 2.7558445579811116e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6376/6464 [1:55:58<01:35, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0585, 'grad_norm': 0.7046133279800415, 'learning_rate': 2.7248800123858183e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6377/6464 [1:55:59<01:37, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3854, 'grad_norm': 0.6821272969245911, 'learning_rate': 2.693915466790525e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6378/6464 [1:56:00<01:39, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2384, 'grad_norm': 0.7483945488929749, 'learning_rate': 2.6629509211952317e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6379/6464 [1:56:01<01:35, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1972, 'grad_norm': 0.7490980625152588, 'learning_rate': 2.631986375599938e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6380/6464 [1:56:02<01:33, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0921, 'grad_norm': 0.7279440760612488, 'learning_rate': 2.601021830004645e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6381/6464 [1:56:03<01:30, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0818, 'grad_norm': 0.7201806306838989, 'learning_rate': 2.5700572844093514e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6382/6464 [1:56:04<01:30, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9814, 'grad_norm': 0.7464375495910645, 'learning_rate': 2.539092738814058e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–Š| 6383/6464 [1:56:05<01:28, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1168, 'grad_norm': 0.6540102958679199, 'learning_rate': 2.5081281932187643e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6384/6464 [1:56:06<01:25, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1096, 'grad_norm': 0.7785307168960571, 'learning_rate': 2.477163647623471e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6385/6464 [1:56:07<01:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2912, 'grad_norm': 0.8298912048339844, 'learning_rate': 2.446199102028178e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6386/6464 [1:56:08<01:21, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1654, 'grad_norm': 0.7811036705970764, 'learning_rate': 2.4152345564328844e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6387/6464 [1:56:10<01:22, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2491, 'grad_norm': 0.7399193644523621, 'learning_rate': 2.384270010837591e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6388/6464 [1:56:11<01:21, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0685, 'grad_norm': 0.7006844282150269, 'learning_rate': 2.3533054652422974e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6389/6464 [1:56:11<01:15, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8914, 'grad_norm': 0.7157745361328125, 'learning_rate': 2.3223409196470045e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6390/6464 [1:56:13<01:16, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0704, 'grad_norm': 0.621545135974884, 'learning_rate': 2.291376374051711e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6391/6464 [1:56:14<01:16, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.15, 'grad_norm': 0.7183223366737366, 'learning_rate': 2.2604118284564175e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6392/6464 [1:56:15<01:14, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0366, 'grad_norm': 0.7894322276115417, 'learning_rate': 2.229447282861124e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6393/6464 [1:56:16<01:11, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0256, 'grad_norm': 0.7151550054550171, 'learning_rate': 2.1984827372658304e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6394/6464 [1:56:17<01:10, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0954, 'grad_norm': 0.7665427327156067, 'learning_rate': 2.1675181916705376e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6395/6464 [1:56:18<01:10, 1.02s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1682, 'grad_norm': 0.6998807191848755, 'learning_rate': 2.136553646075244e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6396/6464 [1:56:19<01:10, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2907, 'grad_norm': 0.7684157490730286, 'learning_rate': 2.1055891004799505e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6397/6464 [1:56:20<01:17, 1.16s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3272, 'grad_norm': 0.7093941569328308, 'learning_rate': 2.0746245548846572e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6398/6464 [1:56:21<01:11, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0929, 'grad_norm': 0.8614110350608826, 'learning_rate': 2.043660009289364e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6399/6464 [1:56:22<01:11, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0788, 'grad_norm': 0.6850066781044006, 'learning_rate': 2.0126954636940706e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6400/6464 [1:56:23<01:11, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1656, 'grad_norm': 0.7045127153396606, 'learning_rate': 1.981730918098777e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6401/6464 [1:56:24<01:07, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0885, 'grad_norm': 0.783488929271698, 'learning_rate': 1.9507663725034836e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6402/6464 [1:56:25<01:05, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.217, 'grad_norm': 0.7794950008392334, 'learning_rate': 1.91980182690819e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6403/6464 [1:56:26<01:04, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9433, 'grad_norm': 0.6665590405464172, 'learning_rate': 1.8888372813128968e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6404/6464 [1:56:27<01:02, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9201, 'grad_norm': 0.643775463104248, 'learning_rate': 1.8578727357176037e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6405/6464 [1:56:28<01:02, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0479, 'grad_norm': 0.6462951898574829, 'learning_rate': 1.82690819012231e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6406/6464 [1:56:30<01:02, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9949, 'grad_norm': 0.7038905620574951, 'learning_rate': 1.7959436445270167e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6407/6464 [1:56:31<00:59, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9518, 'grad_norm': 0.7519775629043579, 'learning_rate': 1.7649790989317231e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6408/6464 [1:56:31<00:56, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8065, 'grad_norm': 0.7187811732292175, 'learning_rate': 1.7340145533364298e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6409/6464 [1:56:32<00:55, 1.00s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1237, 'grad_norm': 0.74610435962677, 'learning_rate': 1.7030500077411363e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6410/6464 [1:56:34<00:56, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9982, 'grad_norm': 0.6918217539787292, 'learning_rate': 1.672085462145843e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6411/6464 [1:56:35<00:55, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1958, 'grad_norm': 0.79875648021698, 'learning_rate': 1.64112091655055e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6412/6464 [1:56:36<00:54, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0925, 'grad_norm': 0.8646512031555176, 'learning_rate': 1.6101563709552562e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6413/6464 [1:56:37<00:54, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.256, 'grad_norm': 0.7325049042701721, 'learning_rate': 1.5791918253599631e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6414/6464 [1:56:38<00:49, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0153, 'grad_norm': 0.6548733115196228, 'learning_rate': 1.5482272797646696e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6415/6464 [1:56:39<00:51, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1231, 'grad_norm': 0.6532686352729797, 'learning_rate': 1.517262734169376e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6416/6464 [1:56:40<00:49, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9422, 'grad_norm': 0.8029704093933105, 'learning_rate': 1.4862981885740828e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6417/6464 [1:56:41<00:50, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0638, 'grad_norm': 0.6450291872024536, 'learning_rate': 1.4553336429787893e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6418/6464 [1:56:42<00:49, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0277, 'grad_norm': 0.6776067018508911, 'learning_rate': 1.424369097383496e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6419/6464 [1:56:43<00:46, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9996, 'grad_norm': 0.9168949127197266, 'learning_rate': 1.3934045517882024e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6420/6464 [1:56:44<00:48, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0959, 'grad_norm': 0.6178362965583801, 'learning_rate': 1.3624400061929091e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6421/6464 [1:56:45<00:47, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3253, 'grad_norm': 0.8615742921829224, 'learning_rate': 1.3314754605976158e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6422/6464 [1:56:46<00:45, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8144, 'grad_norm': 0.6506487131118774, 'learning_rate': 1.3005109150023225e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6423/6464 [1:56:48<00:47, 1.15s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0035, 'grad_norm': 0.7399870753288269, 'learning_rate': 1.269546369407029e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6424/6464 [1:56:49<00:44, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2075, 'grad_norm': 0.8291976451873779, 'learning_rate': 1.2385818238117355e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6425/6464 [1:56:50<00:41, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0107, 'grad_norm': 0.7112247347831726, 'learning_rate': 1.2076172782164422e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6426/6464 [1:56:51<00:40, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2299, 'grad_norm': 0.7570468187332153, 'learning_rate': 1.1766527326211487e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6427/6464 [1:56:52<00:36, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.064, 'grad_norm': 0.9665707945823669, 'learning_rate': 1.1456881870258556e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6428/6464 [1:56:52<00:35, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.8103, 'grad_norm': 0.6680392622947693, 'learning_rate': 1.114723641430562e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6429/6464 [1:56:53<00:34, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1774, 'grad_norm': 0.8253955245018005, 'learning_rate': 1.0837590958352688e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6430/6464 [1:56:55<00:33, 1.00it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0731, 'grad_norm': 0.8140466809272766, 'learning_rate': 1.0527945502399753e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ " 99%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6431/6464 [1:56:56<00:35, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1422, 'grad_norm': 0.6528241038322449, 'learning_rate': 1.021830004644682e-06, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6432/6464 [1:56:57<00:32, 1.03s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9421, 'grad_norm': 0.6919160485267639, 'learning_rate': 9.908654590493884e-07, 'epoch': 0.99}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6433/6464 [1:56:58<00:30, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9244, 'grad_norm': 0.7624881267547607, 'learning_rate': 9.59900913454095e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6434/6464 [1:56:59<00:29, 1.01it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.969, 'grad_norm': 0.6342328786849976, 'learning_rate': 9.289363678588018e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6435/6464 [1:57:00<00:28, 1.02it/s]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1027, 'grad_norm': 0.7087175846099854, 'learning_rate': 8.979718222635083e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6436/6464 [1:57:01<00:28, 1.01s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2996, 'grad_norm': 0.8563559651374817, 'learning_rate': 8.670072766682149e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6437/6464 [1:57:02<00:28, 1.04s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0443, 'grad_norm': 0.6645273566246033, 'learning_rate': 8.360427310729215e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6438/6464 [1:57:03<00:27, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9966, 'grad_norm': 0.6103857159614563, 'learning_rate': 8.050781854776281e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6439/6464 [1:57:04<00:27, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9139, 'grad_norm': 0.5565854907035828, 'learning_rate': 7.741136398823348e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6440/6464 [1:57:05<00:27, 1.13s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0817, 'grad_norm': 0.6503405570983887, 'learning_rate': 7.431490942870414e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6441/6464 [1:57:06<00:24, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9102, 'grad_norm': 0.7807184457778931, 'learning_rate': 7.12184548691748e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6442/6464 [1:57:07<00:23, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0712, 'grad_norm': 0.6944224238395691, 'learning_rate': 6.812200030964546e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6443/6464 [1:57:08<00:22, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0617, 'grad_norm': 0.7436178922653198, 'learning_rate': 6.502554575011613e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6444/6464 [1:57:09<00:21, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2127, 'grad_norm': 0.7587950229644775, 'learning_rate': 6.192909119058678e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6445/6464 [1:57:11<00:20, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2674, 'grad_norm': 0.6783324480056763, 'learning_rate': 5.883263663105743e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6446/6464 [1:57:12<00:19, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2544, 'grad_norm': 0.7126736044883728, 'learning_rate': 5.57361820715281e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6447/6464 [1:57:13<00:17, 1.05s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9636, 'grad_norm': 0.7560374736785889, 'learning_rate': 5.263972751199876e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6448/6464 [1:57:14<00:17, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1691, 'grad_norm': 0.7575001120567322, 'learning_rate': 4.954327295246942e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6449/6464 [1:57:15<00:16, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2599, 'grad_norm': 0.683562159538269, 'learning_rate': 4.644681839294009e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6450/6464 [1:57:16<00:15, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9332, 'grad_norm': 0.6549513339996338, 'learning_rate': 4.3350363833410746e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6451/6464 [1:57:17<00:14, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0555, 'grad_norm': 0.6779701709747314, 'learning_rate': 4.0253909273881405e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6452/6464 [1:57:18<00:13, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1753, 'grad_norm': 0.6556872129440308, 'learning_rate': 3.715745471435207e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6453/6464 [1:57:19<00:12, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1068, 'grad_norm': 0.6523771286010742, 'learning_rate': 3.406100015482273e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6454/6464 [1:57:20<00:10, 1.08s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.2666, 'grad_norm': 0.7596547603607178, 'learning_rate': 3.096454559529339e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6455/6464 [1:57:21<00:09, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.3239, 'grad_norm': 0.828758716583252, 'learning_rate': 2.786809103576405e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6456/6464 [1:57:23<00:09, 1.19s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1962, 'grad_norm': 0.5984361171722412, 'learning_rate': 2.477163647623471e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6457/6464 [1:57:24<00:07, 1.12s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9686, 'grad_norm': 0.9020242691040039, 'learning_rate': 2.1675181916705373e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6458/6464 [1:57:25<00:06, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0573, 'grad_norm': 0.6775802969932556, 'learning_rate': 1.8578727357176035e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6459/6464 [1:57:26<00:05, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.1543, 'grad_norm': 0.7034054398536682, 'learning_rate': 1.5482272797646694e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6460/6464 [1:57:27<00:04, 1.14s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.444, 'grad_norm': 0.7666020393371582, 'learning_rate': 1.2385818238117356e-07, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6461/6464 [1:57:28<00:03, 1.11s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 0.9566, 'grad_norm': 0.6697487831115723, 'learning_rate': 9.289363678588017e-08, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6462/6464 [1:57:29<00:02, 1.10s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0524, 'grad_norm': 0.6974988579750061, 'learning_rate': 6.192909119058678e-08, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–‰| 6463/6464 [1:57:30<00:01, 1.06s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0376, 'grad_norm': 0.7251172661781311, 'learning_rate': 3.096454559529339e-08, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 6464/6464 [1:57:31<00:00, 1.07s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'loss': 1.0192, 'grad_norm': 0.6451247334480286, 'learning_rate': 0.0, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/other.py:619: UserWarning: Unable to fetch remote file due to the following error (ReadTimeoutError(\"HTTPSConnectionPool(host='huggingface.co', port=443): Read timed out. (read timeout=10)\"), '(Request ID: 8061bbf6-46f5-44a5-b661-3ea9aa37d1b1)') - silently ignoring the lookup for the file config.json in Magpie-Align/MagpieLM-4B-Chat-v0.1.\n", " warnings.warn(\n", "/home/kurogane/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/utils/save_and_load.py:218: UserWarning: Could not find a config file in Magpie-Align/MagpieLM-4B-Chat-v0.1 - will assume that the vocabulary was not modified.\n", " warnings.warn(\n", "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 6464/6464 [1:57:42<00:00, 1.09s/it]" ] }, { "name": "stdout", "output_type": "stream", "text": [ "{'train_runtime': 7062.299, 'train_samples_per_second': 7.323, 'train_steps_per_second': 0.915, 'train_loss': 1.1757623720914125, 'epoch': 1.0}\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "\n" ] } ], "source": [ "trainer_stats = trainer.train()" ] }, { "cell_type": "code", "execution_count": 22, "metadata": { "cellView": "form", "colab": { "base_uri": "https://localhost:8080/" }, "id": "pCqnaKmlO1U9", "outputId": "edf33a96-b12c-4bba-9771-59e18aee707c" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "7062.299 seconds used for training.\n", "117.7 minutes used for training.\n", "Peak reserved memory = 11.314 GB.\n", "Peak reserved memory for training = 0.0 GB.\n", "Peak reserved memory % of max memory = 23.808 %.\n", "Peak reserved memory for training % of max memory = 0.0 %.\n" ] } ], "source": [ "#@title Show final memory and time stats\n", "used_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)\n", "used_memory_for_lora = round(used_memory - start_gpu_memory, 3)\n", "used_percentage = round(used_memory /max_memory*100, 3)\n", "lora_percentage = round(used_memory_for_lora/max_memory*100, 3)\n", "print(f\"{trainer_stats.metrics['train_runtime']} seconds used for training.\")\n", "print(f\"{round(trainer_stats.metrics['train_runtime']/60, 2)} minutes used for training.\")\n", "print(f\"Peak reserved memory = {used_memory} GB.\")\n", "print(f\"Peak reserved memory for training = {used_memory_for_lora} GB.\")\n", "print(f\"Peak reserved memory % of max memory = {used_percentage} %.\")\n", "print(f\"Peak reserved memory for training % of max memory = {lora_percentage} %.\")" ] }, { "cell_type": "code", "execution_count": 25, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Unsloth: Merging 4bit and LoRA weights to 16bit...\n", "Unsloth: Will use up to 70.79 out of 124.92 RAM for saving.\n" ] }, { "name": "stderr", "output_type": "stream", "text": [ "100%|โ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆโ–ˆ| 32/32 [00:00<00:00, 71.86it/s]\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "Unsloth: Saving tokenizer... Done.\n", "Unsloth: Saving model... This might take 5 minutes for Llama-7b...\n", "Done.\n" ] } ], "source": [ "import os \n", "dir_save_lora = \"/home/kurogane/devs/llm/minitron/models/02/lora\"\n", "dir_save_model = \"/home/kurogane/devs/llm/minitron/models/02/model\"\n", "\n", "# ใใ‚Œใžใ‚Œใฎใƒ•ใ‚ฉใƒซใƒ€ใŒใชใ„ๅ ดๅˆใฏไฝœๆˆ\n", "os.makedirs(dir_save_lora, exist_ok=True)\n", "os.makedirs(dir_save_model, exist_ok=True)\n", "\n", "\n", "model.save_pretrained(dir_save_lora) # Local saving\n", "tokenizer.save_pretrained(dir_save_lora)\n", "# Merge to 16bit\n", "model.save_pretrained_merged(dir_save_model, tokenizer, save_method = \"merged_16bit\",)" ] }, { "cell_type": "markdown", "metadata": { "id": "ekOmTR1hSNcr" }, "source": [ "\n", "### Inference\n", "Let's run the model! You can change the instruction and input - leave the output blank!\n", "\n", "**[NEW] Try 2x faster inference in a free Colab for Llama-3.1 8b Instruct [here](https://colab.research.google.com/drive/1T-YBVfnphoVc8E2E854qF3jdia2Ll2W2?usp=sharing)**" ] }, { "cell_type": "code", "execution_count": 27, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "kR3gIAX-SM2q", "outputId": "087c5c13-e946-4c35-e4f2-e07a88f9ac32" }, "outputs": [ { "ename": "ValueError", "evalue": "Invalid `cache_implementation` (dynamic). Choose one of: ['static', 'offloaded_static', 'sliding_window', 'hybrid', 'mamba', 'quantized', 'static']", "output_type": "error", "traceback": [ "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", "\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)", "Cell \u001b[0;32mIn[27], line 12\u001b[0m\n\u001b[1;32m 2\u001b[0m FastLanguageModel\u001b[38;5;241m.\u001b[39mfor_inference(model) \u001b[38;5;66;03m# Enable native 2x faster inference\u001b[39;00m\n\u001b[1;32m 3\u001b[0m inputs \u001b[38;5;241m=\u001b[39m tokenizer(\n\u001b[1;32m 4\u001b[0m [\n\u001b[1;32m 5\u001b[0m alpaca_prompt\u001b[38;5;241m.\u001b[39mformat(\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 9\u001b[0m )\n\u001b[1;32m 10\u001b[0m ], return_tensors \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpt\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mto(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcuda\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 12\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmax_new_tokens\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m64\u001b[39;49m\u001b[43m)\u001b[49m\n\u001b[1;32m 13\u001b[0m tokenizer\u001b[38;5;241m.\u001b[39mbatch_decode(outputs)\n", "File \u001b[0;32m~/anaconda3/envs/llmfact/lib/python3.12/site-packages/torch/utils/_contextlib.py:116\u001b[0m, in \u001b[0;36mcontext_decorator..decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 113\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 114\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 115\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[0;32m--> 116\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/anaconda3/envs/llmfact/lib/python3.12/site-packages/unsloth/models/llama.py:1343\u001b[0m, in \u001b[0;36m_wrap_fast_inference.._fast_generate\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 1336\u001b[0m \u001b[38;5;66;03m# Set pad token\u001b[39;00m\n\u001b[1;32m 1337\u001b[0m \u001b[38;5;66;03m# old_pad_token_id = getattr(model.config, \"pad_token_id\", None)\u001b[39;00m\n\u001b[1;32m 1338\u001b[0m \u001b[38;5;66;03m# old_eos_token_id = getattr(model.config, \"eos_token_id\", None)\u001b[39;00m\n\u001b[1;32m 1339\u001b[0m \u001b[38;5;66;03m# model.config.pad_token_id = old_eos_token_id\u001b[39;00m\n\u001b[1;32m 1340\u001b[0m \n\u001b[1;32m 1341\u001b[0m \u001b[38;5;66;03m# Autocasted\u001b[39;00m\n\u001b[1;32m 1342\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m torch\u001b[38;5;241m.\u001b[39mautocast(device_type \u001b[38;5;241m=\u001b[39m device_type, dtype \u001b[38;5;241m=\u001b[39m dtype):\n\u001b[0;32m-> 1343\u001b[0m output \u001b[38;5;241m=\u001b[39m \u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1344\u001b[0m \u001b[38;5;28;01mpass\u001b[39;00m\n\u001b[1;32m 1346\u001b[0m \u001b[38;5;66;03m# Revert\u001b[39;00m\n\u001b[1;32m 1347\u001b[0m \u001b[38;5;66;03m# model.config.pad_token_id = old_pad_token_id\u001b[39;00m\n\u001b[1;32m 1348\u001b[0m \n\u001b[1;32m 1349\u001b[0m \u001b[38;5;66;03m# Unset a flag for generation!\u001b[39;00m\n", "File \u001b[0;32m~/anaconda3/envs/llmfact/lib/python3.12/site-packages/peft/peft_model.py:1638\u001b[0m, in \u001b[0;36mPeftModelForCausalLM.generate\u001b[0;34m(self, *args, **kwargs)\u001b[0m\n\u001b[1;32m 1636\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_enable_peft_forward_hooks(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 1637\u001b[0m kwargs \u001b[38;5;241m=\u001b[39m {k: v \u001b[38;5;28;01mfor\u001b[39;00m k, v \u001b[38;5;129;01min\u001b[39;00m kwargs\u001b[38;5;241m.\u001b[39mitems() \u001b[38;5;28;01mif\u001b[39;00m k \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mspecial_peft_forward_args}\n\u001b[0;32m-> 1638\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbase_model\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mgenerate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1639\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1640\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mbase_model\u001b[38;5;241m.\u001b[39mgenerate(\u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n", "File \u001b[0;32m~/anaconda3/envs/llmfact/lib/python3.12/site-packages/torch/utils/_contextlib.py:116\u001b[0m, in \u001b[0;36mcontext_decorator..decorate_context\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 113\u001b[0m \u001b[38;5;129m@functools\u001b[39m\u001b[38;5;241m.\u001b[39mwraps(func)\n\u001b[1;32m 114\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mdecorate_context\u001b[39m(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs):\n\u001b[1;32m 115\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m ctx_factory():\n\u001b[0;32m--> 116\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n", "File \u001b[0;32m~/anaconda3/envs/llmfact/lib/python3.12/site-packages/transformers/generation/utils.py:1810\u001b[0m, in \u001b[0;36mGenerationMixin.generate\u001b[0;34m(self, inputs, generation_config, logits_processor, stopping_criteria, prefix_allowed_tokens_fn, synced_gpus, assistant_model, streamer, negative_prompt_ids, negative_prompt_attention_mask, **kwargs)\u001b[0m\n\u001b[1;32m 1808\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_model_class()\n\u001b[1;32m 1809\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtokenizer\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m) \u001b[38;5;66;03m# Pull this out first, we only use it for stopping criteria\u001b[39;00m\n\u001b[0;32m-> 1810\u001b[0m generation_config, model_kwargs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_prepare_generation_config\u001b[49m\u001b[43m(\u001b[49m\u001b[43mgeneration_config\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1811\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_model_kwargs(model_kwargs\u001b[38;5;241m.\u001b[39mcopy())\n\u001b[1;32m 1812\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_validate_assistant(assistant_model)\n", "File \u001b[0;32m~/anaconda3/envs/llmfact/lib/python3.12/site-packages/transformers/generation/utils.py:1362\u001b[0m, in \u001b[0;36mGenerationMixin._prepare_generation_config\u001b[0;34m(self, generation_config, **kwargs)\u001b[0m\n\u001b[1;32m 1360\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m is_torchdynamo_compiling():\n\u001b[1;32m 1361\u001b[0m generation_config \u001b[38;5;241m=\u001b[39m copy\u001b[38;5;241m.\u001b[39mdeepcopy(generation_config)\n\u001b[0;32m-> 1362\u001b[0m model_kwargs \u001b[38;5;241m=\u001b[39m \u001b[43mgeneration_config\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mupdate\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1363\u001b[0m \u001b[38;5;66;03m# If `generation_config` is provided, let's fallback ALL special tokens to the default values for the model\u001b[39;00m\n\u001b[1;32m 1364\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m using_model_generation_config:\n", "File \u001b[0;32m~/anaconda3/envs/llmfact/lib/python3.12/site-packages/transformers/generation/configuration_utils.py:1276\u001b[0m, in \u001b[0;36mGenerationConfig.update\u001b[0;34m(self, **kwargs)\u001b[0m\n\u001b[1;32m 1273\u001b[0m to_remove\u001b[38;5;241m.\u001b[39mappend(key)\n\u001b[1;32m 1275\u001b[0m \u001b[38;5;66;03m# Confirm that the updated instance is still valid\u001b[39;00m\n\u001b[0;32m-> 1276\u001b[0m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mvalidate\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1278\u001b[0m \u001b[38;5;66;03m# Remove all the attributes that were updated, without modifying the input dict\u001b[39;00m\n\u001b[1;32m 1279\u001b[0m unused_kwargs \u001b[38;5;241m=\u001b[39m {key: value \u001b[38;5;28;01mfor\u001b[39;00m key, value \u001b[38;5;129;01min\u001b[39;00m kwargs\u001b[38;5;241m.\u001b[39mitems() \u001b[38;5;28;01mif\u001b[39;00m key \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m to_remove}\n", "File \u001b[0;32m~/anaconda3/envs/llmfact/lib/python3.12/site-packages/transformers/generation/configuration_utils.py:735\u001b[0m, in \u001b[0;36mGenerationConfig.validate\u001b[0;34m(self, is_init)\u001b[0m\n\u001b[1;32m 733\u001b[0m \u001b[38;5;66;03m# 5. check cache-related arguments\u001b[39;00m\n\u001b[1;32m 734\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcache_implementation \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;129;01mand\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcache_implementation \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m ALL_CACHE_IMPLEMENTATIONS:\n\u001b[0;32m--> 735\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 736\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mInvalid `cache_implementation` (\u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcache_implementation\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m). Choose one of: \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 737\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mALL_CACHE_IMPLEMENTATIONS\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 738\u001b[0m )\n\u001b[1;32m 739\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcache_config \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 740\u001b[0m cache_class \u001b[38;5;241m=\u001b[39m NEEDS_CACHE_CONFIG\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mcache_implementation)\n", "\u001b[0;31mValueError\u001b[0m: Invalid `cache_implementation` (dynamic). Choose one of: ['static', 'offloaded_static', 'sliding_window', 'hybrid', 'mamba', 'quantized', 'static']" ] } ], "source": [ "# alpaca_prompt = Copied from above\n", "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", "inputs = tokenizer(\n", "[\n", " alpaca_prompt.format(\n", " \"ใƒ•ใ‚ฃใƒœใƒŠใƒƒใƒๆ•ฐๅˆ—ใฎ็ถšใใ‚’ๆ›ธใ„ใฆใใ ใ•ใ„ใ€‚\", # instruction\n", " \"1, 1, 2, 3, 5, 8\", # input\n", " \"\", # output - leave this blank for generation!\n", " )\n", "], return_tensors = \"pt\").to(\"cuda\")\n", "\n", "outputs = model.generate(**inputs, max_new_tokens = 64)\n", "tokenizer.batch_decode(outputs)" ] }, { "cell_type": "markdown", "metadata": { "id": "CrSvZObor0lY" }, "source": [ " You can also use a `TextStreamer` for continuous inference - so you can see the generation token by token, instead of waiting the whole time!" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "e2pEuRb1r2Vg", "outputId": "b13f5e53-4ca4-4551-dffa-aaa3c514dca4" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", "\n", "### Instruction:\n", "Continue the fibonnaci sequence.\n", "\n", "### Input:\n", "1, 1, 2, 3, 5, 8\n", "\n", "### Response:\n", "13, 21, 34, 55, 89, 144<|end_of_text|>\n" ] } ], "source": [ "# alpaca_prompt = Copied from above\n", "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", "inputs = tokenizer(\n", "[\n", " alpaca_prompt.format(\n", " \"Continue the fibonnaci sequence.\", # instruction\n", " \"1, 1, 2, 3, 5, 8\", # input\n", " \"\", # output - leave this blank for generation!\n", " )\n", "], return_tensors = \"pt\").to(\"cuda\")\n", "\n", "from transformers import TextStreamer\n", "text_streamer = TextStreamer(tokenizer)\n", "_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)" ] }, { "cell_type": "markdown", "metadata": { "id": "uMuVrWbjAzhc" }, "source": [ "\n", "### Saving, loading finetuned models\n", "To save the final model as LoRA adapters, either use Huggingface's `push_to_hub` for an online save or `save_pretrained` for a local save.\n", "\n", "**[NOTE]** This ONLY saves the LoRA adapters, and not the full model. To save to 16bit or GGUF, scroll down!" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "upcOlWe7A1vc", "outputId": "030a6e13-9371-4717-c5c5-d4e3563e0cca" }, "outputs": [ { "data": { "text/plain": [ "('lora_model/tokenizer_config.json',\n", " 'lora_model/special_tokens_map.json',\n", " 'lora_model/tokenizer.json')" ] }, "execution_count": 11, "metadata": {}, "output_type": "execute_result" } ], "source": [ "model.save_pretrained(\"lora_model\") # Local saving\n", "tokenizer.save_pretrained(\"lora_model\")\n", "# model.push_to_hub(\"your_name/lora_model\", token = \"...\") # Online saving\n", "# tokenizer.push_to_hub(\"your_name/lora_model\", token = \"...\") # Online saving" ] }, { "cell_type": "markdown", "metadata": { "id": "AEEcJ4qfC7Lp" }, "source": [ "Now if you want to load the LoRA adapters we just saved for inference, set `False` to `True`:" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "MKX_XKs_BNZR", "outputId": "f8e7d3fe-8e4d-49ee-944f-08e70cdc1d87" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "<|begin_of_text|>Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n", "\n", "### Instruction:\n", "What is a famous tall tower in Paris?\n", "\n", "### Input:\n", "\n", "\n", "### Response:\n", "One of the most famous and iconic tall towers in Paris is the Eiffel Tower. Standing at 324 meters (1,063 feet) tall, this wrought iron tower is a symbol of the city and a must-see attraction for tourists from all over the world.<|end_of_text|>\n" ] } ], "source": [ "if False:\n", " from unsloth import FastLanguageModel\n", " model, tokenizer = FastLanguageModel.from_pretrained(\n", " model_name = \"lora_model\", # YOUR MODEL YOU USED FOR TRAINING\n", " max_seq_length = max_seq_length,\n", " dtype = dtype,\n", " load_in_4bit = load_in_4bit,\n", " )\n", " FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", "\n", "# alpaca_prompt = You MUST copy from above!\n", "\n", "inputs = tokenizer(\n", "[\n", " alpaca_prompt.format(\n", " \"What is a famous tall tower in Paris?\", # instruction\n", " \"\", # input\n", " \"\", # output - leave this blank for generation!\n", " )\n", "], return_tensors = \"pt\").to(\"cuda\")\n", "\n", "from transformers import TextStreamer\n", "text_streamer = TextStreamer(tokenizer)\n", "_ = model.generate(**inputs, streamer = text_streamer, max_new_tokens = 128)" ] }, { "cell_type": "markdown", "metadata": { "id": "QQMjaNrjsU5_" }, "source": [ "You can also use Hugging Face's `AutoModelForPeftCausalLM`. Only use this if you do not have `unsloth` installed. It can be hopelessly slow, since `4bit` model downloading is not supported, and Unsloth's **inference is 2x faster**." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "yFfaXG0WsQuE" }, "outputs": [], "source": [ "if False:\n", " # I highly do NOT suggest - use Unsloth if possible\n", " from peft import AutoPeftModelForCausalLM\n", " from transformers import AutoTokenizer\n", " model = AutoPeftModelForCausalLM.from_pretrained(\n", " \"lora_model\", # YOUR MODEL YOU USED FOR TRAINING\n", " load_in_4bit = load_in_4bit,\n", " )\n", " tokenizer = AutoTokenizer.from_pretrained(\"lora_model\")" ] }, { "cell_type": "markdown", "metadata": { "id": "f422JgM9sdVT" }, "source": [ "### Saving to float16 for VLLM\n", "\n", "We also support saving to `float16` directly. Select `merged_16bit` for float16 or `merged_4bit` for int4. We also allow `lora` adapters as a fallback. Use `push_to_hub_merged` to upload to your Hugging Face account! You can go to https://huggingface.co/settings/tokens for your personal tokens." ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "iHjt_SMYsd3P" }, "outputs": [], "source": [ "# Merge to 16bit\n", "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_16bit\",)\n", "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_16bit\", token = \"\")\n", "\n", "# Merge to 4bit\n", "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_4bit\",)\n", "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_4bit\", token = \"\")\n", "\n", "# Just LoRA adapters\n", "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"lora\",)\n", "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"lora\", token = \"\")" ] }, { "cell_type": "markdown", "metadata": { "id": "TCv4vXHd61i7" }, "source": [ "### GGUF / llama.cpp Conversion\n", "To save to `GGUF` / `llama.cpp`, we support it natively now! We clone `llama.cpp` and we default save it to `q8_0`. We allow all methods like `q4_k_m`. Use `save_pretrained_gguf` for local saving and `push_to_hub_gguf` for uploading to HF.\n", "\n", "Some supported quant methods (full list on our [Wiki page](https://github.com/unslothai/unsloth/wiki#gguf-quantization-options)):\n", "* `q8_0` - Fast conversion. High resource use, but generally acceptable.\n", "* `q4_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K.\n", "* `q5_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K.\n", "\n", "[**NEW**] To finetune and auto export to Ollama, try our [Ollama notebook](https://colab.research.google.com/drive/1WZDi7APtQ9VsvOrQSSC5DDtxq159j8iZ?usp=sharing)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "id": "FqfebeAdT073" }, "outputs": [], "source": [ "# Save to 8bit Q8_0\n", "if False: model.save_pretrained_gguf(\"model\", tokenizer,)\n", "# Remember to go to https://huggingface.co/settings/tokens for a token!\n", "# And change hf to your username!\n", "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, token = \"\")\n", "\n", "# Save to 16bit GGUF\n", "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"f16\")\n", "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"f16\", token = \"\")\n", "\n", "# Save to q4_k_m GGUF\n", "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"q4_k_m\")\n", "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"q4_k_m\", token = \"\")\n", "\n", "# Save to multiple GGUF options - much faster if you want multiple!\n", "if False:\n", " model.push_to_hub_gguf(\n", " \"hf/model\", # Change hf to your username!\n", " tokenizer,\n", " quantization_method = [\"q4_k_m\", \"q8_0\", \"q5_k_m\",],\n", " token = \"\", # Get a token at https://huggingface.co/settings/tokens\n", " )" ] }, { "cell_type": "markdown", "metadata": { "id": "bDp0zNpwe6U_" }, "source": [ "Now, use the `model-unsloth.gguf` file or `model-unsloth-Q4_K_M.gguf` file in `llama.cpp` or a UI based system like `GPT4All`. You can install GPT4All by going [here](https://gpt4all.io/index.html).\n", "\n", "**[NEW] Try 2x faster inference in a free Colab for Llama-3.1 8b Instruct [here](https://colab.research.google.com/drive/1T-YBVfnphoVc8E2E854qF3jdia2Ll2W2?usp=sharing)**" ] }, { "cell_type": "markdown", "metadata": { "id": "Zt9CHJqO6p30" }, "source": [ "And we're done! If you have any questions on Unsloth, we have a [Discord](https://discord.gg/u54VK8m8tk) channel! If you find any bugs or want to keep updated with the latest LLM stuff, or need help, join projects etc, feel free to join our Discord!\n", "\n", "Some other links:\n", "1. Zephyr DPO 2x faster [free Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing)\n", "2. Llama 7b 2x faster [free Colab](https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing)\n", "3. TinyLlama 4x faster full Alpaca 52K in 1 hour [free Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing)\n", "4. CodeLlama 34b 2x faster [A100 on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing)\n", "5. Mistral 7b [free Kaggle version](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook)\n", "6. We also did a [blog](https://huggingface.co/blog/unsloth-trl) with ๐Ÿค— HuggingFace, and we're in the TRL [docs](https://huggingface.co/docs/trl/main/en/sft_trainer#accelerate-fine-tuning-2x-using-unsloth)!\n", "7. `ChatML` for ShareGPT datasets, [conversational notebook](https://colab.research.google.com/drive/1Aau3lgPzeZKQ-98h69CCu1UJcvIBLmy2?usp=sharing)\n", "8. Text completions like novel writing [notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing)\n", "9. [**NEW**] We make Phi-3 Medium / Mini **2x faster**! See our [Phi-3 Medium notebook](https://colab.research.google.com/drive/1hhdhBa1j_hsymiW9m-WzxQtgqTH_NHqi?usp=sharing)\n", "10. [**NEW**] We make Gemma-2 9b / 27b **2x faster**! See our [Gemma-2 9b notebook](https://colab.research.google.com/drive/1vIrqH5uYDQwsJ4-OO3DErvuv4pBgVwk4?usp=sharing)\n", "11. [**NEW**] To finetune and auto export to Ollama, try our [Ollama notebook](https://colab.research.google.com/drive/1WZDi7APtQ9VsvOrQSSC5DDtxq159j8iZ?usp=sharing)\n", "12. [**NEW**] We make Mistral NeMo 12B 2x faster and fit in under 12GB of VRAM! [Mistral NeMo notebook](https://colab.research.google.com/drive/17d3U-CAIwzmbDRqbZ9NnpHxCkmXB6LZ0?usp=sharing)\n", "\n", "
\n", " \n", " \n", " Support our work if you can! Thanks!\n", "
" ] } ], "metadata": { "accelerator": "GPU", "colab": { "gpuType": "T4", "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.4" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "0078f897f2174217a307d95d4f9bd775": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8c195b5809604905b5e404baa30e8449", "placeholder": "โ€‹", "style": "IPY_MODEL_2247efac4283489bbd228330344388ab", "value": "Map:โ€‡100%" } }, "00d425bca350451da6400f9f05c4a659": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "03f492b4b56f4d8e80e9395a65058b1b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_9695a640b0ff4e91af495bb59548e4b6", "placeholder": "โ€‹", "style": "IPY_MODEL_d4bd5559d4134d64a943d57972c6ef39", "value": "Mapโ€‡(num_proc=2):โ€‡100%" } }, "04cc963133d242779572d2e847fa3d65": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "07055fc12b0841aaa5317f8252b5d347": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "0a9dc233674e4096b7a988a5e4ebaf84": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d4b3770433bc41818372b7aed243fb31", "placeholder": "โ€‹", "style": "IPY_MODEL_19bcefcc1d874840ae9a9ca983e474b6", "value": "Downloadingโ€‡readme:โ€‡100%" } }, "0c1835f404db4846bb13b5da8d8f4447": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "19bcefcc1d874840ae9a9ca983e474b6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "1a6db9aea6a64ae3aaef51d6265b35b2": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1bd75ddaf57c4438a4e2c3070b9cef65": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_a3a3ef6d6337403cabea8b23f7c3021b", "IPY_MODEL_c2ea0a3f01f34ffa8c94ab9b5098e9da", "IPY_MODEL_68ea1d7cb8274a639b3fb5326f4218c3" ], "layout": "IPY_MODEL_39fef7b257614a0595f39355fa226b69" } }, "1c7bc5fdb7dd4c39af8d4c2c504ec3ed": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_843a27e619534ea8914f9d36386c364b", "IPY_MODEL_8f5adc70fbf248f2811527f620553be5", "IPY_MODEL_4ffb4b2f015046fb94c1115ed0397a20" ], "layout": "IPY_MODEL_5a232ed040f94633a2a374031284c1f6" } }, "1eb90e686e214122ae763b1b79ae321d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "2006be31c09349738e221295bb84939f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "2247efac4283489bbd228330344388ab": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "29c5b713f07043dda51820523e5c8ff3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_d7375f0f048841b29a20601c122666e8", "IPY_MODEL_f433ced9bfcd4a57ba691d3c1caeed08", "IPY_MODEL_da8ffc70820a48f5a12c6d4b5967015b" ], "layout": "IPY_MODEL_1a6db9aea6a64ae3aaef51d6265b35b2" } }, "2b848e5a85bc42bc87945fd9ed5db038": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_bb9f3379310d4b04be694996f3137b28", "max": 230, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_75082ba15db445df907f5612976590ae", "value": 230 } }, "2be29a4553ad4dfea8a9bc620c81a3ae": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "331f516c7a76456d801bc2a2feb228aa": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "33843107b93647b28985bfc37ea781ca": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "3662f1445ef34a50b462e601ed31bb69": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "36799fbcd90d43128620ff98225a825d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "3719bf6f9c6a4c6fbef93c5328c11a07": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_03f492b4b56f4d8e80e9395a65058b1b", "IPY_MODEL_39d9ef9fb35f47119f319f48eb222070", "IPY_MODEL_3d7cfb33ceaf417e851ac4393c65148b" ], "layout": "IPY_MODEL_ece66fa2f128456fa2a82b8a28d1211c" } }, "374fa9beda4042e1bf9a9b13de6e6674": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_4011ce9370d74fad857ec8e1e99d314f", "max": 11610, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_41f5fed060ad4c8d87b24602b720ef04", "value": 11610 } }, "39d9ef9fb35f47119f319f48eb222070": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_fbae6e599d1644f39e5d86efa0f9f997", "max": 51760, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_00d425bca350451da6400f9f05c4a659", "value": 51760 } }, "39fef7b257614a0595f39355fa226b69": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "3d7cfb33ceaf417e851ac4393c65148b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_6a27d9ad4f064586a87636b10455d15b", "placeholder": "โ€‹", "style": "IPY_MODEL_77f4367616964a01a8c42416f5f4c147", "value": "โ€‡51760/51760โ€‡[00:50<00:00,โ€‡1965.57โ€‡examples/s]" } }, "3fef797403d14440afe599a3bf06b626": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "4011ce9370d74fad857ec8e1e99d314f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "41f5fed060ad4c8d87b24602b720ef04": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "4228734651ca45e19fc7bda79817f9b3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f878c2e00bc240c7b0333cce950080e1", "placeholder": "โ€‹", "style": "IPY_MODEL_6b908368de51428585552dfef6a83088", "value": "โ€‡5.70G/5.70Gโ€‡[00:45<00:00,โ€‡645MB/s]" } }, "4613edbbec6846edb5b1677c25d542b6": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "484e507f14424f2b9173595b985f4101": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "4e7cb8e988114ed4b6fe09ff9f682dff": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4ffb4b2f015046fb94c1115ed0397a20": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8653acb618ad4e76bbf1daa00ea71238", "placeholder": "โ€‹", "style": "IPY_MODEL_e3c3bd9c4c124b0a8c88c83c1fc747d3", "value": "โ€‡50.6k/50.6kโ€‡[00:00<00:00,โ€‡2.29MB/s]" } }, "51ca174d26e94b5cb1e895aa3c770655": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "51cd9026b1664819a67712996ca97bd5": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5310346dd579424fa676b8e8e64790e7": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5a232ed040f94633a2a374031284c1f6": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5e8825fb770b41529f2129113cebc4a9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_0a9dc233674e4096b7a988a5e4ebaf84", "IPY_MODEL_374fa9beda4042e1bf9a9b13de6e6674", "IPY_MODEL_e6533d3c91fd4359bc84ffd8e59af5a3" ], "layout": "IPY_MODEL_f9b01aebcbdc48a585b7942b0ee60a2d" } }, "5f174718e5974a7cab024d113f662513": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "620c0de28ec74f71a021a2be96dccf3a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "634ae4c6cfe04673b1cdc9c9cac4cbf9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "68a32b398e1c490393e01befdc260785": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "68c686291b50430faeef0de7840e2c4b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f4519637bb43400a80ce83505101e8a5", "placeholder": "โ€‹", "style": "IPY_MODEL_805676b197c94f5aa45956daa354640b", "value": "Downloadingโ€‡data:โ€‡100%" } }, "68ea1d7cb8274a639b3fb5326f4218c3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_5310346dd579424fa676b8e8e64790e7", "placeholder": "โ€‹", "style": "IPY_MODEL_0c1835f404db4846bb13b5da8d8f4447", "value": "โ€‡9.09M/9.09Mโ€‡[00:00<00:00,โ€‡17.1MB/s]" } }, "6a27d9ad4f064586a87636b10455d15b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "6b908368de51428585552dfef6a83088": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "6e1aff64771c402ab070f650562fa4c9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_0078f897f2174217a307d95d4f9bd775", "IPY_MODEL_ecdeaab4f8c94d6dade63bb06857c969", "IPY_MODEL_735b85f0a0e9411cac4d704a504fcfc1" ], "layout": "IPY_MODEL_8e992e60416145a8b6eed744287ca0fb" } }, "6e3c281f112b4a86af7a3ef95933d221": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_92395f250a154006923aaf9ea0a9c30b", "IPY_MODEL_f84bfc5390054ec687c157c4d68199a6", "IPY_MODEL_4228734651ca45e19fc7bda79817f9b3" ], "layout": "IPY_MODEL_4613edbbec6846edb5b1677c25d542b6" } }, "735b85f0a0e9411cac4d704a504fcfc1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e99423a1ed3f4f72886b39368468b7c1", "placeholder": "โ€‹", "style": "IPY_MODEL_5f174718e5974a7cab024d113f662513", "value": "โ€‡51760/51760โ€‡[00:00<00:00,โ€‡52999.05โ€‡examples/s]" } }, "75082ba15db445df907f5612976590ae": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "76e5410e286a4a5abd6c213a38aa38bb": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "77f4367616964a01a8c42416f5f4c147": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "7981edf408d54d41bbeac42da7492c6b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_76e5410e286a4a5abd6c213a38aa38bb", "placeholder": "โ€‹", "style": "IPY_MODEL_ae7e90a811f94e75997d6a9ed1be8596", "value": "generation_config.json:โ€‡100%" } }, "7a935956348e47c68fbdf05ddf4752f3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "805676b197c94f5aa45956daa354640b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "80a72037771e4da9be989eefabbc8e76": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c97c40c2bf2a41a8ae1c75e0a9c8ebff", "placeholder": "โ€‹", "style": "IPY_MODEL_484e507f14424f2b9173595b985f4101", "value": "Generatingโ€‡trainโ€‡split:โ€‡100%" } }, "843a27e619534ea8914f9d36386c364b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2006be31c09349738e221295bb84939f", "placeholder": "โ€‹", "style": "IPY_MODEL_07055fc12b0841aaa5317f8252b5d347", "value": "tokenizer_config.json:โ€‡100%" } }, "85cc6f24cba54563acb5598f54fed7b9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_80a72037771e4da9be989eefabbc8e76", "IPY_MODEL_ba68b274c50b44ec9e02642378d271a6", "IPY_MODEL_f84d2fe4f1c24a34948755abf1f32b7f" ], "layout": "IPY_MODEL_86511967834f4484a5ec4af387b7d7a9" } }, "86511967834f4484a5ec4af387b7d7a9": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8653acb618ad4e76bbf1daa00ea71238": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "88fcd51819b5483c9ab22df7ef89ab64": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "89934c4f26834f15b9889ec36fee3b65": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8c195b5809604905b5e404baa30e8449": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8e992e60416145a8b6eed744287ca0fb": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8ea52b105a7e44978caca33c0e7e815b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8f5adc70fbf248f2811527f620553be5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_1eb90e686e214122ae763b1b79ae321d", "max": 50570, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_7a935956348e47c68fbdf05ddf4752f3", "value": 50570 } }, "92395f250a154006923aaf9ea0a9c30b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d032fe2ba5d647d99026fdade758c0cd", "placeholder": "โ€‹", "style": "IPY_MODEL_e9971d220fe24552a1e9aa299765cfb9", "value": "model.safetensors:โ€‡100%" } }, "94730f13e92a4c9aac35c2cfb21fc48c": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "94cbb87829d1486899e2ff6325c2ecdf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "953625aa1e824f8a8d203197b316b302": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ce9fcc5eff1f460d80b703a4ca32dad1", "max": 44307561, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_3fef797403d14440afe599a3bf06b626", "value": 44307561 } }, "9695a640b0ff4e91af495bb59548e4b6": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "98a6716e7438429ea322adb3e3264f91": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_68c686291b50430faeef0de7840e2c4b", "IPY_MODEL_953625aa1e824f8a8d203197b316b302", "IPY_MODEL_f899a815142542219bde22ff792fb60c" ], "layout": "IPY_MODEL_51ca174d26e94b5cb1e895aa3c770655" } }, "9be9074028da42d39d044a78393a861f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "9d45b9a5de3e4cba9ac35ad2cb187f51": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "a14bc1c2130842568a5fde6698731e5f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "a3a3ef6d6337403cabea8b23f7c3021b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d125995cc0934239a01ba01b78529f21", "placeholder": "โ€‹", "style": "IPY_MODEL_634ae4c6cfe04673b1cdc9c9cac4cbf9", "value": "tokenizer.json:โ€‡100%" } }, "ac5eacaaee8346c080e54ea7a52648a4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_7981edf408d54d41bbeac42da7492c6b", "IPY_MODEL_2b848e5a85bc42bc87945fd9ed5db038", "IPY_MODEL_e88c33f37d6849e0b1a6b41254104cb9" ], "layout": "IPY_MODEL_33843107b93647b28985bfc37ea781ca" } }, "ae7e90a811f94e75997d6a9ed1be8596": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "ba68b274c50b44ec9e02642378d271a6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_68a32b398e1c490393e01befdc260785", "max": 51760, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_04cc963133d242779572d2e847fa3d65", "value": 51760 } }, "bb9f3379310d4b04be694996f3137b28": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c2ea0a3f01f34ffa8c94ab9b5098e9da": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d7f92e8332374313bee87ccd427446a4", "max": 9085657, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_36799fbcd90d43128620ff98225a825d", "value": 9085657 } }, "c97c40c2bf2a41a8ae1c75e0a9c8ebff": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ce9fcc5eff1f460d80b703a4ca32dad1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d032fe2ba5d647d99026fdade758c0cd": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d125995cc0934239a01ba01b78529f21": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d4b3770433bc41818372b7aed243fb31": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d4bd5559d4134d64a943d57972c6ef39": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "d7375f0f048841b29a20601c122666e8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_331f516c7a76456d801bc2a2feb228aa", "placeholder": "โ€‹", "style": "IPY_MODEL_9be9074028da42d39d044a78393a861f", "value": "special_tokens_map.json:โ€‡100%" } }, "d7f92e8332374313bee87ccd427446a4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "da8ffc70820a48f5a12c6d4b5967015b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8ea52b105a7e44978caca33c0e7e815b", "placeholder": "โ€‹", "style": "IPY_MODEL_3662f1445ef34a50b462e601ed31bb69", "value": "โ€‡345/345โ€‡[00:00<00:00,โ€‡23.9kB/s]" } }, "e3c3bd9c4c124b0a8c88c83c1fc747d3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e6533d3c91fd4359bc84ffd8e59af5a3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_88fcd51819b5483c9ab22df7ef89ab64", "placeholder": "โ€‹", "style": "IPY_MODEL_e6ffac074f1b476ba2ade11b37732af3", "value": "โ€‡11.6k/11.6kโ€‡[00:00<00:00,โ€‡81.5kB/s]" } }, "e6ffac074f1b476ba2ade11b37732af3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e887160635cb4803b9f33845df615ec6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e88c33f37d6849e0b1a6b41254104cb9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_89934c4f26834f15b9889ec36fee3b65", "placeholder": "โ€‹", "style": "IPY_MODEL_e887160635cb4803b9f33845df615ec6", "value": "โ€‡230/230โ€‡[00:00<00:00,โ€‡11.6kB/s]" } }, "e93d063faf984cc4aa51462418d9b57e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e99423a1ed3f4f72886b39368468b7c1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e9971d220fe24552a1e9aa299765cfb9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "ea55293415ca48a4be97c2e1e4769122": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "ecdeaab4f8c94d6dade63bb06857c969": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e93d063faf984cc4aa51462418d9b57e", "max": 51760, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_9d45b9a5de3e4cba9ac35ad2cb187f51", "value": 51760 } }, "ece66fa2f128456fa2a82b8a28d1211c": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f433ced9bfcd4a57ba691d3c1caeed08": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_51cd9026b1664819a67712996ca97bd5", "max": 345, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_ea55293415ca48a4be97c2e1e4769122", "value": 345 } }, "f4519637bb43400a80ce83505101e8a5": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f84bfc5390054ec687c157c4d68199a6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "danger", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_2be29a4553ad4dfea8a9bc620c81a3ae", "max": 5702746390, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_94cbb87829d1486899e2ff6325c2ecdf", "value": 5702745847 } }, "f84d2fe4f1c24a34948755abf1f32b7f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_94730f13e92a4c9aac35c2cfb21fc48c", "placeholder": "โ€‹", "style": "IPY_MODEL_620c0de28ec74f71a021a2be96dccf3a", "value": "โ€‡51760/51760โ€‡[00:01<00:00,โ€‡52026.13โ€‡examples/s]" } }, "f878c2e00bc240c7b0333cce950080e1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "f899a815142542219bde22ff792fb60c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_4e7cb8e988114ed4b6fe09ff9f682dff", "placeholder": "โ€‹", "style": "IPY_MODEL_a14bc1c2130842568a5fde6698731e5f", "value": "โ€‡44.3M/44.3Mโ€‡[00:00<00:00,โ€‡87.2MB/s]" } }, "f9b01aebcbdc48a585b7942b0ee60a2d": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "fbae6e599d1644f39e5d86efa0f9f997": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } } } } }, "nbformat": 4, "nbformat_minor": 0 }