minimini99/phi3-lora-mergedata

README.md

@@ -0,0 +1,135 @@
+---
+base_model: microsoft/Phi-3-mini-4k-instruct
+library_name: peft
+license: mit
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: phi-3-mini-LoRA-mergedatafilter3_split
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/jongmin4422/Phi3-mini-ft-python-code2_split/runs/24vjhm5l)
+# phi-3-mini-LoRA-mergedatafilter3_split
+
+This model is a fine-tuned version of [microsoft/Phi-3-mini-4k-instruct](https://huggingface.co/microsoft/Phi-3-mini-4k-instruct) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3387
+
+## 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: 0.0001
+- train_batch_size: 12
+- eval_batch_size: 12
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 192
+- total_eval_batch_size: 48
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 0.4848        | 0.1462 | 800   | 0.4776          |
+| 0.4265        | 0.2924 | 1600  | 0.4238          |
+| 0.3995        | 0.4386 | 2400  | 0.3986          |
+| 0.3848        | 0.5848 | 3200  | 0.3839          |
+| 0.3742        | 0.7310 | 4000  | 0.3742          |
+| 0.3679        | 0.8772 | 4800  | 0.3669          |
+| 0.3616        | 1.0233 | 5600  | 0.3625          |
+| 0.3574        | 1.1695 | 6400  | 0.3569          |
+| 0.3537        | 1.3157 | 7200  | 0.3537          |
+| 0.3523        | 1.4619 | 8000  | 0.3516          |
+| 0.3491        | 1.6081 | 8800  | 0.3495          |
+| 0.3478        | 1.7543 | 9600  | 0.3483          |
+| 0.3467        | 1.9005 | 10400 | 0.3470          |
+| 0.3455        | 2.0467 | 11200 | 0.3459          |
+| 0.3455        | 2.1929 | 12000 | 0.3451          |
+| 0.3442        | 2.3391 | 12800 | 0.3444          |
+| 0.3424        | 2.4853 | 13600 | 0.3436          |
+| 0.3431        | 2.6315 | 14400 | 0.3432          |
+| 0.3427        | 2.7777 | 15200 | 0.3426          |
+| 0.3424        | 2.9238 | 16000 | 0.3423          |
+| 0.3419        | 3.0700 | 16800 | 0.3418          |
+| 0.3413        | 3.2162 | 17600 | 0.3415          |
+| 0.3417        | 3.3624 | 18400 | 0.3412          |
+| 0.3406        | 3.5086 | 19200 | 0.3408          |
+| 0.34          | 3.6548 | 20000 | 0.3407          |
+| 0.341         | 3.8010 | 20800 | 0.3406          |
+| 0.3395        | 3.9472 | 21600 | 0.3403          |
+| 0.3415        | 4.0934 | 22400 | 0.3401          |
+| 0.3398        | 4.2396 | 23200 | 0.3400          |
+| 0.3395        | 4.3858 | 24000 | 0.3398          |
+| 0.3405        | 4.5320 | 24800 | 0.3396          |
+| 0.3385        | 4.6781 | 25600 | 0.3396          |
+| 0.339         | 4.8243 | 26400 | 0.3395          |
+| 0.3391        | 4.9705 | 27200 | 0.3395          |
+| 0.3397        | 5.1167 | 28000 | 0.3393          |
+| 0.337         | 5.2629 | 28800 | 0.3393          |
+| 0.3383        | 5.4091 | 29600 | 0.3392          |
+| 0.3384        | 5.5553 | 30400 | 0.3391          |
+| 0.3383        | 5.7015 | 31200 | 0.3391          |
+| 0.3386        | 5.8477 | 32000 | 0.3390          |
+| 0.3391        | 5.9939 | 32800 | 0.3390          |
+| 0.3384        | 6.1401 | 33600 | 0.3390          |
+| 0.3391        | 6.2863 | 34400 | 0.3390          |
+| 0.3385        | 6.4325 | 35200 | 0.3389          |
+| 0.338         | 6.5786 | 36000 | 0.3389          |
+| 0.3384        | 6.7248 | 36800 | 0.3389          |
+| 0.3377        | 6.8710 | 37600 | 0.3388          |
+| 0.338         | 7.0172 | 38400 | 0.3388          |
+| 0.3385        | 7.1634 | 39200 | 0.3388          |
+| 0.3393        | 7.3096 | 40000 | 0.3388          |
+| 0.3377        | 7.4558 | 40800 | 0.3388          |
+| 0.3382        | 7.6020 | 41600 | 0.3387          |
+| 0.3387        | 7.7482 | 42400 | 0.3387          |
+| 0.3391        | 7.8944 | 43200 | 0.3387          |
+| 0.338         | 8.0406 | 44000 | 0.3387          |
+| 0.3386        | 8.1868 | 44800 | 0.3387          |
+| 0.3385        | 8.3330 | 45600 | 0.3387          |
+| 0.3372        | 8.4791 | 46400 | 0.3387          |
+| 0.338         | 8.6253 | 47200 | 0.3387          |
+| 0.3387        | 8.7715 | 48000 | 0.3387          |
+| 0.3391        | 8.9177 | 48800 | 0.3387          |
+| 0.3379        | 9.0639 | 49600 | 0.3387          |
+| 0.3386        | 9.2101 | 50400 | 0.3387          |
+| 0.3385        | 9.3563 | 51200 | 0.3387          |
+| 0.3385        | 9.5025 | 52000 | 0.3387          |
+| 0.3385        | 9.6487 | 52800 | 0.3387          |
+| 0.3386        | 9.7949 | 53600 | 0.3387          |
+| 0.3373        | 9.9411 | 54400 | 0.3387          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.43.2
+- Pytorch 2.3.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/Phi-3-mini-4k-instruct",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "up_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8e45823690794aa124d942bc681dc832b7431910917dd02aecbe469c749dcfc
+size 17842848

added_tokens.json

@@ -0,0 +1,13 @@
+{
+  "<|assistant|>": 32001,
+  "<|endoftext|>": 32000,
+  "<|end|>": 32007,
+  "<|placeholder1|>": 32002,
+  "<|placeholder2|>": 32003,
+  "<|placeholder3|>": 32004,
+  "<|placeholder4|>": 32005,
+  "<|placeholder5|>": 32008,
+  "<|placeholder6|>": 32009,
+  "<|system|>": 32006,
+  "<|user|>": 32010
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<unk>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,131 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": true,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": false
+    },
+    "32000": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "<|placeholder1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|placeholder2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|placeholder3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32005": {
+      "content": "<|placeholder4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32006": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32007": {
+      "content": "<|end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32008": {
+      "content": "<|placeholder5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32009": {
+      "content": "<|placeholder6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "32010": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{{'<|system|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'user' %}{{'<|user|>\n' + message['content'] + '<|end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|assistant|>\n' + message['content'] + '<|end|>\n'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": false,
+  "model_max_length": 4096,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b00b98c654301ba1a8d568cf1202f8d1a3c61c9d49a64035bfd4f019d52c933
+size 5432