Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: transformers
+model_name: Qwen2.5-1.5B-Open-R1-Distill
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Open-R1-Distill
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="saemin21/Qwen2.5-1.5B-Open-R1-Distill", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/saemin21-postech/huggingface/runs/b2xvukxr) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.997779422649889,
+    "total_flos": 76745898196992.0,
+    "train_loss": 0.7814422148979029,
+    "train_runtime": 1966.4009,
+    "train_samples": 16610,
+    "train_samples_per_second": 10.99,
+    "train_steps_per_second": 0.171
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eea43246bd3b0f285656e8a9c8b6d564a6023ac4c9207801605c43ccedb93e8a
+size 3087467144

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.997779422649889,
+    "total_flos": 76745898196992.0,
+    "train_loss": 0.7814422148979029,
+    "train_runtime": 1966.4009,
+    "train_samples": 16610,
+    "train_samples_per_second": 10.99,
+    "train_steps_per_second": 0.171
+}

trainer_state.json

@@ -0,0 +1,535 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.997779422649889,
+  "eval_steps": 100,
+  "global_step": 337,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014803849000740192,
+      "grad_norm": 2.59954963103659,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 1.09,
+      "step": 5
+    },
+    {
+      "epoch": 0.029607698001480384,
+      "grad_norm": 1.5110785471948693,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 1.0788,
+      "step": 10
+    },
+    {
+      "epoch": 0.04441154700222058,
+      "grad_norm": 1.2662915154052385,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 1.0147,
+      "step": 15
+    },
+    {
+      "epoch": 0.05921539600296077,
+      "grad_norm": 0.8975184617412112,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.9334,
+      "step": 20
+    },
+    {
+      "epoch": 0.07401924500370097,
+      "grad_norm": 0.7923521691073661,
+      "learning_rate": 1.4705882352941179e-05,
+      "loss": 0.9,
+      "step": 25
+    },
+    {
+      "epoch": 0.08882309400444116,
+      "grad_norm": 0.6747031888758434,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.8802,
+      "step": 30
+    },
+    {
+      "epoch": 0.10362694300518134,
+      "grad_norm": 0.6214058638516932,
+      "learning_rate": 1.9999462497359468e-05,
+      "loss": 0.8536,
+      "step": 35
+    },
+    {
+      "epoch": 0.11843079200592153,
+      "grad_norm": 0.5379219947595423,
+      "learning_rate": 1.9980655971335944e-05,
+      "loss": 0.8349,
+      "step": 40
+    },
+    {
+      "epoch": 0.13323464100666174,
+      "grad_norm": 0.5073745152108753,
+      "learning_rate": 1.993503206718859e-05,
+      "loss": 0.8137,
+      "step": 45
+    },
+    {
+      "epoch": 0.14803849000740193,
+      "grad_norm": 0.600812767490673,
+      "learning_rate": 1.986271337340182e-05,
+      "loss": 0.8197,
+      "step": 50
+    },
+    {
+      "epoch": 0.16284233900814213,
+      "grad_norm": 0.5106373121493422,
+      "learning_rate": 1.976389420563607e-05,
+      "loss": 0.8028,
+      "step": 55
+    },
+    {
+      "epoch": 0.17764618800888232,
+      "grad_norm": 0.49037184533529493,
+      "learning_rate": 1.9638840084614182e-05,
+      "loss": 0.7893,
+      "step": 60
+    },
+    {
+      "epoch": 0.19245003700962252,
+      "grad_norm": 0.5729839316722111,
+      "learning_rate": 1.9487887022684336e-05,
+      "loss": 0.7993,
+      "step": 65
+    },
+    {
+      "epoch": 0.20725388601036268,
+      "grad_norm": 0.5149633307341998,
+      "learning_rate": 1.9311440620976597e-05,
+      "loss": 0.7927,
+      "step": 70
+    },
+    {
+      "epoch": 0.22205773501110287,
+      "grad_norm": 0.5351239659846057,
+      "learning_rate": 1.9109974979578852e-05,
+      "loss": 0.7836,
+      "step": 75
+    },
+    {
+      "epoch": 0.23686158401184307,
+      "grad_norm": 0.5284767724010426,
+      "learning_rate": 1.8884031423660492e-05,
+      "loss": 0.8122,
+      "step": 80
+    },
+    {
+      "epoch": 0.25166543301258326,
+      "grad_norm": 0.5280821848350826,
+      "learning_rate": 1.8634217048966638e-05,
+      "loss": 0.795,
+      "step": 85
+    },
+    {
+      "epoch": 0.2664692820133235,
+      "grad_norm": 0.5385026157906161,
+      "learning_rate": 1.836120309059107e-05,
+      "loss": 0.7777,
+      "step": 90
+    },
+    {
+      "epoch": 0.28127313101406365,
+      "grad_norm": 0.521912661438978,
+      "learning_rate": 1.8065723119410885e-05,
+      "loss": 0.7755,
+      "step": 95
+    },
+    {
+      "epoch": 0.29607698001480387,
+      "grad_norm": 0.5500915161891787,
+      "learning_rate": 1.77485710710289e-05,
+      "loss": 0.7824,
+      "step": 100
+    },
+    {
+      "epoch": 0.29607698001480387,
+      "eval_loss": 0.7986670732498169,
+      "eval_runtime": 3.1511,
+      "eval_samples_per_second": 40.621,
+      "eval_steps_per_second": 2.539,
+      "step": 100
+    },
+    {
+      "epoch": 0.31088082901554404,
+      "grad_norm": 0.4847857266437136,
+      "learning_rate": 1.741059911251997e-05,
+      "loss": 0.773,
+      "step": 105
+    },
+    {
+      "epoch": 0.32568467801628426,
+      "grad_norm": 0.5248466723356767,
+      "learning_rate": 1.7052715352713076e-05,
+      "loss": 0.7674,
+      "step": 110
+    },
+    {
+      "epoch": 0.3404885270170244,
+      "grad_norm": 0.5196269233230336,
+      "learning_rate": 1.667588140216154e-05,
+      "loss": 0.7942,
+      "step": 115
+    },
+    {
+      "epoch": 0.35529237601776464,
+      "grad_norm": 0.5258552082740311,
+      "learning_rate": 1.628110978935756e-05,
+      "loss": 0.7687,
+      "step": 120
+    },
+    {
+      "epoch": 0.3700962250185048,
+      "grad_norm": 0.5357998635392313,
+      "learning_rate": 1.586946124013354e-05,
+      "loss": 0.7683,
+      "step": 125
+    },
+    {
+      "epoch": 0.38490007401924503,
+      "grad_norm": 0.5124786446604577,
+      "learning_rate": 1.5442041827560274e-05,
+      "loss": 0.7449,
+      "step": 130
+    },
+    {
+      "epoch": 0.3997039230199852,
+      "grad_norm": 0.5364960128016644,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7558,
+      "step": 135
+    },
+    {
+      "epoch": 0.41450777202072536,
+      "grad_norm": 0.5239651426651067,
+      "learning_rate": 1.4544523495299843e-05,
+      "loss": 0.762,
+      "step": 140
+    },
+    {
+      "epoch": 0.4293116210214656,
+      "grad_norm": 0.5685304188161404,
+      "learning_rate": 1.4076836149416889e-05,
+      "loss": 0.7779,
+      "step": 145
+    },
+    {
+      "epoch": 0.44411547002220575,
+      "grad_norm": 0.5292768738334391,
+      "learning_rate": 1.3598194608050011e-05,
+      "loss": 0.7628,
+      "step": 150
+    },
+    {
+      "epoch": 0.45891931902294597,
+      "grad_norm": 0.47169065654852255,
+      "learning_rate": 1.3109884950114007e-05,
+      "loss": 0.752,
+      "step": 155
+    },
+    {
+      "epoch": 0.47372316802368614,
+      "grad_norm": 0.4850168790165624,
+      "learning_rate": 1.2613219232128608e-05,
+      "loss": 0.752,
+      "step": 160
+    },
+    {
+      "epoch": 0.48852701702442636,
+      "grad_norm": 0.48457640581841005,
+      "learning_rate": 1.2109531962807333e-05,
+      "loss": 0.7537,
+      "step": 165
+    },
+    {
+      "epoch": 0.5033308660251665,
+      "grad_norm": 0.47059560359305813,
+      "learning_rate": 1.1600176517318742e-05,
+      "loss": 0.758,
+      "step": 170
+    },
+    {
+      "epoch": 0.5181347150259067,
+      "grad_norm": 0.49863777355480526,
+      "learning_rate": 1.1086521500854746e-05,
+      "loss": 0.7452,
+      "step": 175
+    },
+    {
+      "epoch": 0.532938564026647,
+      "grad_norm": 0.48976052377434126,
+      "learning_rate": 1.0569947071276847e-05,
+      "loss": 0.7659,
+      "step": 180
+    },
+    {
+      "epoch": 0.5477424130273871,
+      "grad_norm": 0.5598681522777179,
+      "learning_rate": 1.0051841230721065e-05,
+      "loss": 0.759,
+      "step": 185
+    },
+    {
+      "epoch": 0.5625462620281273,
+      "grad_norm": 0.5055386224558781,
+      "learning_rate": 9.533596096125826e-06,
+      "loss": 0.7656,
+      "step": 190
+    },
+    {
+      "epoch": 0.5773501110288675,
+      "grad_norm": 0.47686736961322373,
+      "learning_rate": 9.016604158703654e-06,
+      "loss": 0.7397,
+      "step": 195
+    },
+    {
+      "epoch": 0.5921539600296077,
+      "grad_norm": 0.4816519635005245,
+      "learning_rate": 8.502254542407186e-06,
+      "loss": 0.7375,
+      "step": 200
+    },
+    {
+      "epoch": 0.5921539600296077,
+      "eval_loss": 0.7732692360877991,
+      "eval_runtime": 3.1502,
+      "eval_samples_per_second": 40.632,
+      "eval_steps_per_second": 2.539,
+      "step": 200
+    },
+    {
+      "epoch": 0.6069578090303479,
+      "grad_norm": 0.472466582768516,
+      "learning_rate": 7.991929271442817e-06,
+      "loss": 0.7415,
+      "step": 205
+    },
+    {
+      "epoch": 0.6217616580310881,
+      "grad_norm": 0.487913132976027,
+      "learning_rate": 7.48699955686089e-06,
+      "loss": 0.7437,
+      "step": 210
+    },
+    {
+      "epoch": 0.6365655070318282,
+      "grad_norm": 0.4632798898820171,
+      "learning_rate": 6.988822112200157e-06,
+      "loss": 0.7517,
+      "step": 215
+    },
+    {
+      "epoch": 0.6513693560325685,
+      "grad_norm": 0.5015321297817941,
+      "learning_rate": 6.498735508086094e-06,
+      "loss": 0.7551,
+      "step": 220
+    },
+    {
+      "epoch": 0.6661732050333087,
+      "grad_norm": 0.44486759806175513,
+      "learning_rate": 6.018056575578075e-06,
+      "loss": 0.7487,
+      "step": 225
+    },
+    {
+      "epoch": 0.6809770540340488,
+      "grad_norm": 0.41329178229089025,
+      "learning_rate": 5.548076867929331e-06,
+      "loss": 0.7455,
+      "step": 230
+    },
+    {
+      "epoch": 0.695780903034789,
+      "grad_norm": 0.43609737258438114,
+      "learning_rate": 5.090059190266779e-06,
+      "loss": 0.7335,
+      "step": 235
+    },
+    {
+      "epoch": 0.7105847520355293,
+      "grad_norm": 0.42748504875171905,
+      "learning_rate": 4.645234206515171e-06,
+      "loss": 0.7389,
+      "step": 240
+    },
+    {
+      "epoch": 0.7253886010362695,
+      "grad_norm": 0.4523178271776836,
+      "learning_rate": 4.214797132682597e-06,
+      "loss": 0.7352,
+      "step": 245
+    },
+    {
+      "epoch": 0.7401924500370096,
+      "grad_norm": 0.45335660235354563,
+      "learning_rate": 3.799904525392251e-06,
+      "loss": 0.7421,
+      "step": 250
+    },
+    {
+      "epoch": 0.7549962990377498,
+      "grad_norm": 0.4431613740543571,
+      "learning_rate": 3.401671174289469e-06,
+      "loss": 0.7322,
+      "step": 255
+    },
+    {
+      "epoch": 0.7698001480384901,
+      "grad_norm": 0.441027343079403,
+      "learning_rate": 3.021167106673928e-06,
+      "loss": 0.7482,
+      "step": 260
+    },
+    {
+      "epoch": 0.7846039970392302,
+      "grad_norm": 0.4359036566755757,
+      "learning_rate": 2.6594147124053983e-06,
+      "loss": 0.7371,
+      "step": 265
+    },
+    {
+      "epoch": 0.7994078460399704,
+      "grad_norm": 0.4416118935243017,
+      "learning_rate": 2.317385996808195e-06,
+      "loss": 0.7488,
+      "step": 270
+    },
+    {
+      "epoch": 0.8142116950407106,
+      "grad_norm": 0.41053173678708244,
+      "learning_rate": 1.9959999689556407e-06,
+      "loss": 0.7413,
+      "step": 275
+    },
+    {
+      "epoch": 0.8290155440414507,
+      "grad_norm": 0.42016591584889007,
+      "learning_rate": 1.6961201723520248e-06,
+      "loss": 0.7271,
+      "step": 280
+    },
+    {
+      "epoch": 0.843819393042191,
+      "grad_norm": 0.3979209641920834,
+      "learning_rate": 1.4185523646469822e-06,
+      "loss": 0.752,
+      "step": 285
+    },
+    {
+      "epoch": 0.8586232420429312,
+      "grad_norm": 0.4209074468787367,
+      "learning_rate": 1.1640423526166987e-06,
+      "loss": 0.7298,
+      "step": 290
+    },
+    {
+      "epoch": 0.8734270910436713,
+      "grad_norm": 0.40170247214575744,
+      "learning_rate": 9.332739882292752e-07,
+      "loss": 0.7558,
+      "step": 295
+    },
+    {
+      "epoch": 0.8882309400444115,
+      "grad_norm": 0.3998873661177466,
+      "learning_rate": 7.268673311786378e-07,
+      "loss": 0.7455,
+      "step": 300
+    },
+    {
+      "epoch": 0.8882309400444115,
+      "eval_loss": 0.7647631168365479,
+      "eval_runtime": 3.1498,
+      "eval_samples_per_second": 40.638,
+      "eval_steps_per_second": 2.54,
+      "step": 300
+    },
+    {
+      "epoch": 0.9030347890451518,
+      "grad_norm": 0.3874560972460433,
+      "learning_rate": 5.453769828241872e-07,
+      "loss": 0.7294,
+      "step": 305
+    },
+    {
+      "epoch": 0.9178386380458919,
+      "grad_norm": 0.41392350576095466,
+      "learning_rate": 3.8929059601275463e-07,
+      "loss": 0.7617,
+      "step": 310
+    },
+    {
+      "epoch": 0.9326424870466321,
+      "grad_norm": 0.3930717618662023,
+      "learning_rate": 2.5902756478688674e-07,
+      "loss": 0.7441,
+      "step": 315
+    },
+    {
+      "epoch": 0.9474463360473723,
+      "grad_norm": 0.39942376949400493,
+      "learning_rate": 1.5493789750014032e-07,
+      "loss": 0.7458,
+      "step": 320
+    },
+    {
+      "epoch": 0.9622501850481125,
+      "grad_norm": 0.4246898762898355,
+      "learning_rate": 7.730127636723539e-08,
+      "loss": 0.7265,
+      "step": 325
+    },
+    {
+      "epoch": 0.9770540340488527,
+      "grad_norm": 0.4184289722311908,
+      "learning_rate": 2.6326305976001054e-08,
+      "loss": 0.7312,
+      "step": 330
+    },
+    {
+      "epoch": 0.9918578830495929,
+      "grad_norm": 0.44006851649772194,
+      "learning_rate": 2.149952780321485e-09,
+      "loss": 0.7525,
+      "step": 335
+    },
+    {
+      "epoch": 0.997779422649889,
+      "step": 337,
+      "total_flos": 76745898196992.0,
+      "train_loss": 0.7814422148979029,
+      "train_runtime": 1966.4009,
+      "train_samples_per_second": 10.99,
+      "train_steps_per_second": 0.171
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 337,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 76745898196992.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f67d7c8457911830dfa9d77bcc693274e6a6b904902cc98540104f4261416f81
+size 7352