add model files

randomcomb_mlm_ep5/README.md

@@ -0,0 +1,57 @@
+---
+license: mit
+tags:
+- generated_from_trainer
+model-index:
+- name: randomcomb_mlm_ep5
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# randomcomb_mlm_ep5
+
+This model is a fine-tuned version of [roberta-base](https://huggingface.co/roberta-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.5062
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 16
+- eval_batch_size: 16
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 5.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step   | Validation Loss |
+|:-------------:|:-----:|:------:|:---------------:|
+| 1.8998        | 2.57  | 200000 | 1.6606          |
+
+
+### Framework versions
+
+- Transformers 4.13.0.dev0
+- Pytorch 1.8.0
+- Datasets 1.15.1
+- Tokenizers 0.10.3

randomcomb_mlm_ep5/all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 1.5061932802200317,
+    "eval_runtime": 1068.1883,
+    "eval_samples": 138195,
+    "eval_samples_per_second": 129.373,
+    "eval_steps_per_second": 8.087,
+    "perplexity": 4.5095315557713995,
+    "train_loss": 1.7809591078664695,
+    "train_runtime": 139562.9056,
+    "train_samples": 1243753,
+    "train_samples_per_second": 44.559,
+    "train_steps_per_second": 2.785
+}

randomcomb_mlm_ep5/checkpoint-200000/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

randomcomb_mlm_ep5/checkpoint-200000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b336ebdd8510e2ec2847b6021cebe21dcfefee6f1d4b6c02e2a0fb1926bad3dd
+size 997706595

randomcomb_mlm_ep5/checkpoint-200000/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec69e9fd7bb3e50718768c181588be63926e9a88b7f5e1644e16f5c62cd76433
+size 498880594

randomcomb_mlm_ep5/checkpoint-200000/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf13c88685005b17fac38d90a62bc4f6e002321fb009598613a98a1189053740
+size 15690

randomcomb_mlm_ep5/checkpoint-200000/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9ccc41a927f21310d033565b1364aba313733701696cabc6a441404047a6901
+size 559

randomcomb_mlm_ep5/checkpoint-200000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1115ded262dd695c64e895fdc433cb710fca587cb71bd80f27825c4a51e0890
+size 623

randomcomb_mlm_ep5/checkpoint-200000/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

randomcomb_mlm_ep5/checkpoint-200000/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

randomcomb_mlm_ep5/checkpoint-200000/trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.5728436354280566,
+  "global_step": 200000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.4280954524988745e-05,
+      "loss": 1.8998,
+      "step": 200000
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 1.6605522632598877,
+      "eval_runtime": 1064.795,
+      "eval_samples_per_second": 129.786,
+      "eval_steps_per_second": 8.112,
+      "step": 200000
+    }
+  ],
+  "max_steps": 388675,
+  "num_train_epochs": 5,
+  "total_flos": 1.53636993828252e+17,
+  "trial_name": null,
+  "trial_params": null
+}

randomcomb_mlm_ep5/checkpoint-200000/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e400e663b7f67aadfb2815e255927a2d6e17765897a960c972b13851365792db
+size 2799

randomcomb_mlm_ep5/config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "roberta-base",
+  "architectures": [
+    "RobertaForMaskedLM"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "classifier_dropout": null,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.13.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

randomcomb_mlm_ep5/eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 5.0,
+    "eval_loss": 1.5061932802200317,
+    "eval_runtime": 1068.1883,
+    "eval_samples": 138195,
+    "eval_samples_per_second": 129.373,
+    "eval_steps_per_second": 8.087,
+    "perplexity": 4.5095315557713995
+}

randomcomb_mlm_ep5/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5492a1f29ea154dd26217f60614c614cc1cdb3f5c1d4385a9b289d58c6a1a769
+size 498880594

randomcomb_mlm_ep5/runs/Dec16_12-57-55_slug/1639619972.0444322/events.out.tfevents.1639619972.slug.1802.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f7db48a3d09dd8bbbc85ba74c60a82388f70b2d58714d40fe8eddf4101cfa32
+size 4514

randomcomb_mlm_ep5/runs/Dec16_12-57-55_slug/events.out.tfevents.1639619972.slug.1802.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a13ca19d2a19c215a7c885ebf08bbf8f060a4adf4929664cc28658157a348f1
+size 3962

randomcomb_mlm_ep5/runs/Dec16_12-57-55_slug/events.out.tfevents.1639760604.slug.1802.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1defeeaf4819eaafe3c31c5b1c4a628254f8d39d8a130c7fb10df2d8d26de5be
+size 316

randomcomb_mlm_ep5/special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

randomcomb_mlm_ep5/tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "roberta-base", "tokenizer_class": "RobertaTokenizer"}

randomcomb_mlm_ep5/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 5.0,
+    "train_loss": 1.7809591078664695,
+    "train_runtime": 139562.9056,
+    "train_samples": 1243753,
+    "train_samples_per_second": 44.559,
+    "train_steps_per_second": 2.785
+}

randomcomb_mlm_ep5/trainer_state.json

@@ -0,0 +1,39 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "global_step": 388675,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.57,
+      "learning_rate": 2.4280954524988745e-05,
+      "loss": 1.8998,
+      "step": 200000
+    },
+    {
+      "epoch": 2.57,
+      "eval_loss": 1.6605522632598877,
+      "eval_runtime": 1064.795,
+      "eval_samples_per_second": 129.786,
+      "eval_steps_per_second": 8.112,
+      "step": 200000
+    },
+    {
+      "epoch": 5.0,
+      "step": 388675,
+      "total_flos": 2.98603105152047e+17,
+      "train_loss": 1.7809591078664695,
+      "train_runtime": 139562.9056,
+      "train_samples_per_second": 44.559,
+      "train_steps_per_second": 2.785
+    }
+  ],
+  "max_steps": 388675,
+  "num_train_epochs": 5,
+  "total_flos": 2.98603105152047e+17,
+  "trial_name": null,
+  "trial_params": null
+}

randomcomb_mlm_ep5/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e400e663b7f67aadfb2815e255927a2d6e17765897a960c972b13851365792db
+size 2799