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="KMasaki/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/kawamuramasaki/open-r1/runs/gd8q6gsy) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.3.0
+- 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 +1,8 @@
+{
+    "total_flos": 76774385909760.0,
+    "train_loss": 0.7816469167035835,
+    "train_runtime": 1423.7517,
+    "train_samples": 16610,
+    "train_samples_per_second": 15.187,
+    "train_steps_per_second": 0.237
+}

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": 32768,
+  "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:f73bb8b5ba4eb26fbbc9ed82622e3a60b419b1a95d8c2e6a8f62a09e08f6a706
+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 +1,8 @@
+{
+    "total_flos": 76774385909760.0,
+    "train_loss": 0.7816469167035835,
+    "train_runtime": 1423.7517,
+    "train_samples": 16610,
+    "train_samples_per_second": 15.187,
+    "train_steps_per_second": 0.237
+}

trainer_state.json

@@ -0,0 +1,606 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9974102848686645,
+  "eval_steps": 100,
+  "global_step": 337,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014798372179060304,
+      "grad_norm": 2.5306930186826753,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 1.0934,
+      "mean_token_accuracy": 0.7109322207107002,
+      "step": 5
+    },
+    {
+      "epoch": 0.029596744358120607,
+      "grad_norm": 1.424866180903984,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 1.0769,
+      "mean_token_accuracy": 0.7137517687949484,
+      "step": 10
+    },
+    {
+      "epoch": 0.04439511653718091,
+      "grad_norm": 1.2478783156769773,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.9837,
+      "mean_token_accuracy": 0.729848266965647,
+      "step": 15
+    },
+    {
+      "epoch": 0.059193488716241215,
+      "grad_norm": 0.8826111856086888,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.959,
+      "mean_token_accuracy": 0.7301244143895347,
+      "step": 20
+    },
+    {
+      "epoch": 0.07399186089530152,
+      "grad_norm": 0.7993494942599797,
+      "learning_rate": 1.4705882352941179e-05,
+      "loss": 0.8946,
+      "mean_token_accuracy": 0.7440491925839592,
+      "step": 25
+    },
+    {
+      "epoch": 0.08879023307436182,
+      "grad_norm": 0.721065476095799,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.8869,
+      "mean_token_accuracy": 0.7441089304674472,
+      "step": 30
+    },
+    {
+      "epoch": 0.10358860525342212,
+      "grad_norm": 0.6204667399419895,
+      "learning_rate": 1.9999462497359468e-05,
+      "loss": 0.846,
+      "mean_token_accuracy": 0.7537384849780143,
+      "step": 35
+    },
+    {
+      "epoch": 0.11838697743248243,
+      "grad_norm": 0.6052034221434552,
+      "learning_rate": 1.9980655971335944e-05,
+      "loss": 0.8244,
+      "mean_token_accuracy": 0.758586463622919,
+      "step": 40
+    },
+    {
+      "epoch": 0.13318534961154274,
+      "grad_norm": 0.5309283723367797,
+      "learning_rate": 1.993503206718859e-05,
+      "loss": 0.8234,
+      "mean_token_accuracy": 0.7581668826046202,
+      "step": 45
+    },
+    {
+      "epoch": 0.14798372179060304,
+      "grad_norm": 0.5894152921837318,
+      "learning_rate": 1.986271337340182e-05,
+      "loss": 0.8062,
+      "mean_token_accuracy": 0.7622244554453599,
+      "step": 50
+    },
+    {
+      "epoch": 0.16278209396966334,
+      "grad_norm": 0.5353168662445701,
+      "learning_rate": 1.976389420563607e-05,
+      "loss": 0.8147,
+      "mean_token_accuracy": 0.759568330707116,
+      "step": 55
+    },
+    {
+      "epoch": 0.17758046614872364,
+      "grad_norm": 0.528729950753381,
+      "learning_rate": 1.9638840084614182e-05,
+      "loss": 0.8023,
+      "mean_token_accuracy": 0.7627516453096803,
+      "step": 60
+    },
+    {
+      "epoch": 0.19237883832778394,
+      "grad_norm": 0.5765062600953095,
+      "learning_rate": 1.9487887022684336e-05,
+      "loss": 0.792,
+      "mean_token_accuracy": 0.764091510669518,
+      "step": 65
+    },
+    {
+      "epoch": 0.20717721050684423,
+      "grad_norm": 0.4833574803759776,
+      "learning_rate": 1.9311440620976597e-05,
+      "loss": 0.7952,
+      "mean_token_accuracy": 0.7633997295679061,
+      "step": 70
+    },
+    {
+      "epoch": 0.22197558268590456,
+      "grad_norm": 0.4965117379550902,
+      "learning_rate": 1.9109974979578852e-05,
+      "loss": 0.7766,
+      "mean_token_accuracy": 0.7679723449940277,
+      "step": 75
+    },
+    {
+      "epoch": 0.23677395486496486,
+      "grad_norm": 0.5422842186683082,
+      "learning_rate": 1.8884031423660492e-05,
+      "loss": 0.7858,
+      "mean_token_accuracy": 0.7659705075688521,
+      "step": 80
+    },
+    {
+      "epoch": 0.25157232704402516,
+      "grad_norm": 0.4648874115836066,
+      "learning_rate": 1.8634217048966638e-05,
+      "loss": 0.7899,
+      "mean_token_accuracy": 0.7642684446686183,
+      "step": 85
+    },
+    {
+      "epoch": 0.2663706992230855,
+      "grad_norm": 0.49864787202920896,
+      "learning_rate": 1.836120309059107e-05,
+      "loss": 0.7653,
+      "mean_token_accuracy": 0.7711662704053502,
+      "step": 90
+    },
+    {
+      "epoch": 0.28116907140214575,
+      "grad_norm": 0.4941848577820338,
+      "learning_rate": 1.8065723119410885e-05,
+      "loss": 0.773,
+      "mean_token_accuracy": 0.7688954388012983,
+      "step": 95
+    },
+    {
+      "epoch": 0.2959674435812061,
+      "grad_norm": 0.5083313834658424,
+      "learning_rate": 1.77485710710289e-05,
+      "loss": 0.777,
+      "mean_token_accuracy": 0.7671037906593839,
+      "step": 100
+    },
+    {
+      "epoch": 0.2959674435812061,
+      "eval_loss": 0.7992699146270752,
+      "eval_mean_token_accuracy": 0.7526490923736796,
+      "eval_runtime": 2.725,
+      "eval_samples_per_second": 47.339,
+      "eval_steps_per_second": 3.303,
+      "step": 100
+    },
+    {
+      "epoch": 0.31076581576026635,
+      "grad_norm": 0.502008043498686,
+      "learning_rate": 1.741059911251997e-05,
+      "loss": 0.7743,
+      "mean_token_accuracy": 0.7680230417759751,
+      "step": 105
+    },
+    {
+      "epoch": 0.3255641879393267,
+      "grad_norm": 0.5074124492783709,
+      "learning_rate": 1.7052715352713076e-05,
+      "loss": 0.7702,
+      "mean_token_accuracy": 0.7686136108964321,
+      "step": 110
+    },
+    {
+      "epoch": 0.340362560118387,
+      "grad_norm": 0.5071131760392499,
+      "learning_rate": 1.667588140216154e-05,
+      "loss": 0.781,
+      "mean_token_accuracy": 0.7663267032780435,
+      "step": 115
+    },
+    {
+      "epoch": 0.3551609322974473,
+      "grad_norm": 0.4904030530326049,
+      "learning_rate": 1.628110978935756e-05,
+      "loss": 0.7858,
+      "mean_token_accuracy": 0.7642852493388534,
+      "step": 120
+    },
+    {
+      "epoch": 0.3699593044765076,
+      "grad_norm": 0.48343334479760786,
+      "learning_rate": 1.586946124013354e-05,
+      "loss": 0.7721,
+      "mean_token_accuracy": 0.767507805528747,
+      "step": 125
+    },
+    {
+      "epoch": 0.38475767665556787,
+      "grad_norm": 0.46212293051128184,
+      "learning_rate": 1.5442041827560274e-05,
+      "loss": 0.7701,
+      "mean_token_accuracy": 0.7681742018100668,
+      "step": 130
+    },
+    {
+      "epoch": 0.3995560488346282,
+      "grad_norm": 0.49005232010020267,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7784,
+      "mean_token_accuracy": 0.7659993526780575,
+      "step": 135
+    },
+    {
+      "epoch": 0.41435442101368847,
+      "grad_norm": 0.5802473751849121,
+      "learning_rate": 1.4544523495299843e-05,
+      "loss": 0.7479,
+      "mean_token_accuracy": 0.7748897409687096,
+      "step": 140
+    },
+    {
+      "epoch": 0.4291527931927488,
+      "grad_norm": 0.46697081136404445,
+      "learning_rate": 1.4076836149416889e-05,
+      "loss": 0.7624,
+      "mean_token_accuracy": 0.7699376399284426,
+      "step": 145
+    },
+    {
+      "epoch": 0.4439511653718091,
+      "grad_norm": 0.45324269226549363,
+      "learning_rate": 1.3598194608050011e-05,
+      "loss": 0.7615,
+      "mean_token_accuracy": 0.7710725608185627,
+      "step": 150
+    },
+    {
+      "epoch": 0.4587495375508694,
+      "grad_norm": 0.5162747380370616,
+      "learning_rate": 1.3109884950114007e-05,
+      "loss": 0.7483,
+      "mean_token_accuracy": 0.7738950295545084,
+      "step": 155
+    },
+    {
+      "epoch": 0.4735479097299297,
+      "grad_norm": 0.48161770993187064,
+      "learning_rate": 1.2613219232128608e-05,
+      "loss": 0.7785,
+      "mean_token_accuracy": 0.7653272694417022,
+      "step": 160
+    },
+    {
+      "epoch": 0.48834628190899,
+      "grad_norm": 0.4962066320847415,
+      "learning_rate": 1.2109531962807333e-05,
+      "loss": 0.7583,
+      "mean_token_accuracy": 0.7716915300692998,
+      "step": 165
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "grad_norm": 0.5055381412821207,
+      "learning_rate": 1.1600176517318742e-05,
+      "loss": 0.7697,
+      "mean_token_accuracy": 0.767747381709197,
+      "step": 170
+    },
+    {
+      "epoch": 0.5179430262671106,
+      "grad_norm": 0.5054786127986631,
+      "learning_rate": 1.1086521500854746e-05,
+      "loss": 0.7644,
+      "mean_token_accuracy": 0.7690235533127754,
+      "step": 175
+    },
+    {
+      "epoch": 0.532741398446171,
+      "grad_norm": 0.46152729464852277,
+      "learning_rate": 1.0569947071276847e-05,
+      "loss": 0.7507,
+      "mean_token_accuracy": 0.7737928590432877,
+      "step": 180
+    },
+    {
+      "epoch": 0.5475397706252312,
+      "grad_norm": 0.4695612487616888,
+      "learning_rate": 1.0051841230721065e-05,
+      "loss": 0.757,
+      "mean_token_accuracy": 0.7718499416080608,
+      "step": 185
+    },
+    {
+      "epoch": 0.5623381428042915,
+      "grad_norm": 0.5218859694830563,
+      "learning_rate": 9.533596096125826e-06,
+      "loss": 0.7474,
+      "mean_token_accuracy": 0.7735829404733993,
+      "step": 190
+    },
+    {
+      "epoch": 0.5771365149833518,
+      "grad_norm": 0.49416648779707545,
+      "learning_rate": 9.016604158703654e-06,
+      "loss": 0.7367,
+      "mean_token_accuracy": 0.7761640741138002,
+      "step": 195
+    },
+    {
+      "epoch": 0.5919348871624122,
+      "grad_norm": 0.4744299622799445,
+      "learning_rate": 8.502254542407186e-06,
+      "loss": 0.751,
+      "mean_token_accuracy": 0.7724703236279267,
+      "step": 200
+    },
+    {
+      "epoch": 0.5919348871624122,
+      "eval_loss": 0.7737040519714355,
+      "eval_mean_token_accuracy": 0.7571218561628608,
+      "eval_runtime": 2.3677,
+      "eval_samples_per_second": 54.482,
+      "eval_steps_per_second": 3.801,
+      "step": 200
+    },
+    {
+      "epoch": 0.6067332593414725,
+      "grad_norm": 0.4571681698469847,
+      "learning_rate": 7.991929271442817e-06,
+      "loss": 0.7407,
+      "mean_token_accuracy": 0.7755988044467611,
+      "step": 205
+    },
+    {
+      "epoch": 0.6215316315205327,
+      "grad_norm": 0.43278950100088054,
+      "learning_rate": 7.48699955686089e-06,
+      "loss": 0.7481,
+      "mean_token_accuracy": 0.7735502754860193,
+      "step": 210
+    },
+    {
+      "epoch": 0.636330003699593,
+      "grad_norm": 0.49468417784151203,
+      "learning_rate": 6.988822112200157e-06,
+      "loss": 0.775,
+      "mean_token_accuracy": 0.7659379638471053,
+      "step": 215
+    },
+    {
+      "epoch": 0.6511283758786534,
+      "grad_norm": 0.41822862138228684,
+      "learning_rate": 6.498735508086094e-06,
+      "loss": 0.7498,
+      "mean_token_accuracy": 0.7731720478189318,
+      "step": 220
+    },
+    {
+      "epoch": 0.6659267480577137,
+      "grad_norm": 0.46770169407773693,
+      "learning_rate": 6.018056575578075e-06,
+      "loss": 0.7592,
+      "mean_token_accuracy": 0.7701622621932589,
+      "step": 225
+    },
+    {
+      "epoch": 0.680725120236774,
+      "grad_norm": 0.4301879679864597,
+      "learning_rate": 5.548076867929331e-06,
+      "loss": 0.7378,
+      "mean_token_accuracy": 0.7768001644788849,
+      "step": 230
+    },
+    {
+      "epoch": 0.6955234924158342,
+      "grad_norm": 0.4110320515268362,
+      "learning_rate": 5.090059190266779e-06,
+      "loss": 0.7406,
+      "mean_token_accuracy": 0.7764935034563292,
+      "step": 235
+    },
+    {
+      "epoch": 0.7103218645948945,
+      "grad_norm": 0.45215243130813015,
+      "learning_rate": 4.645234206515171e-06,
+      "loss": 0.7316,
+      "mean_token_accuracy": 0.7781838814007387,
+      "step": 240
+    },
+    {
+      "epoch": 0.7251202367739549,
+      "grad_norm": 0.4306166903504155,
+      "learning_rate": 4.214797132682597e-06,
+      "loss": 0.7441,
+      "mean_token_accuracy": 0.774896818627263,
+      "step": 245
+    },
+    {
+      "epoch": 0.7399186089530152,
+      "grad_norm": 0.4677549708375624,
+      "learning_rate": 3.799904525392251e-06,
+      "loss": 0.7444,
+      "mean_token_accuracy": 0.7746876413515387,
+      "step": 250
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.4579244444523011,
+      "learning_rate": 3.401671174289469e-06,
+      "loss": 0.7487,
+      "mean_token_accuracy": 0.7736023686798276,
+      "step": 255
+    },
+    {
+      "epoch": 0.7695153533111357,
+      "grad_norm": 0.44650439788033275,
+      "learning_rate": 3.021167106673928e-06,
+      "loss": 0.7445,
+      "mean_token_accuracy": 0.7743245251087528,
+      "step": 260
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.4478153652502043,
+      "learning_rate": 2.6594147124053983e-06,
+      "loss": 0.7611,
+      "mean_token_accuracy": 0.769372799551824,
+      "step": 265
+    },
+    {
+      "epoch": 0.7991120976692564,
+      "grad_norm": 0.4271237650794528,
+      "learning_rate": 2.317385996808195e-06,
+      "loss": 0.7446,
+      "mean_token_accuracy": 0.77473731038134,
+      "step": 270
+    },
+    {
+      "epoch": 0.8139104698483167,
+      "grad_norm": 0.42405749633429296,
+      "learning_rate": 1.9959999689556407e-06,
+      "loss": 0.7434,
+      "mean_token_accuracy": 0.774948955827694,
+      "step": 275
+    },
+    {
+      "epoch": 0.8287088420273769,
+      "grad_norm": 0.40531426206243515,
+      "learning_rate": 1.6961201723520248e-06,
+      "loss": 0.745,
+      "mean_token_accuracy": 0.7748197167655329,
+      "step": 280
+    },
+    {
+      "epoch": 0.8435072142064373,
+      "grad_norm": 0.3984324465873538,
+      "learning_rate": 1.4185523646469822e-06,
+      "loss": 0.7453,
+      "mean_token_accuracy": 0.7744560602643948,
+      "step": 285
+    },
+    {
+      "epoch": 0.8583055863854976,
+      "grad_norm": 0.4447093659563818,
+      "learning_rate": 1.1640423526166987e-06,
+      "loss": 0.742,
+      "mean_token_accuracy": 0.7752281674755013,
+      "step": 290
+    },
+    {
+      "epoch": 0.8731039585645579,
+      "grad_norm": 0.4327215713613019,
+      "learning_rate": 9.332739882292752e-07,
+      "loss": 0.7389,
+      "mean_token_accuracy": 0.7759098786496285,
+      "step": 295
+    },
+    {
+      "epoch": 0.8879023307436182,
+      "grad_norm": 0.4101532450607113,
+      "learning_rate": 7.268673311786378e-07,
+      "loss": 0.731,
+      "mean_token_accuracy": 0.7786051446835451,
+      "step": 300
+    },
+    {
+      "epoch": 0.8879023307436182,
+      "eval_loss": 0.7651976346969604,
+      "eval_mean_token_accuracy": 0.7605418336104682,
+      "eval_runtime": 2.367,
+      "eval_samples_per_second": 54.498,
+      "eval_steps_per_second": 3.802,
+      "step": 300
+    },
+    {
+      "epoch": 0.9027007029226785,
+      "grad_norm": 0.40006809741836763,
+      "learning_rate": 5.453769828241872e-07,
+      "loss": 0.7391,
+      "mean_token_accuracy": 0.7762730269882686,
+      "step": 305
+    },
+    {
+      "epoch": 0.9174990751017388,
+      "grad_norm": 0.39372929687209135,
+      "learning_rate": 3.8929059601275463e-07,
+      "loss": 0.7121,
+      "mean_token_accuracy": 0.7837936652524417,
+      "step": 310
+    },
+    {
+      "epoch": 0.9322974472807991,
+      "grad_norm": 0.4077726046346767,
+      "learning_rate": 2.5902756478688674e-07,
+      "loss": 0.74,
+      "mean_token_accuracy": 0.7763787219346148,
+      "step": 315
+    },
+    {
+      "epoch": 0.9470958194598594,
+      "grad_norm": 0.4018494029172172,
+      "learning_rate": 1.5493789750014032e-07,
+      "loss": 0.7373,
+      "mean_token_accuracy": 0.7766823185717946,
+      "step": 320
+    },
+    {
+      "epoch": 0.9618941916389198,
+      "grad_norm": 0.41372722235636705,
+      "learning_rate": 7.730127636723539e-08,
+      "loss": 0.7237,
+      "mean_token_accuracy": 0.7803516061745327,
+      "step": 325
+    },
+    {
+      "epoch": 0.97669256381798,
+      "grad_norm": 0.3881396504405612,
+      "learning_rate": 2.6326305976001054e-08,
+      "loss": 0.7384,
+      "mean_token_accuracy": 0.7763774804489217,
+      "step": 330
+    },
+    {
+      "epoch": 0.9914909359970403,
+      "grad_norm": 0.42105668844246164,
+      "learning_rate": 2.149952780321485e-09,
+      "loss": 0.7369,
+      "mean_token_accuracy": 0.7762607021245872,
+      "step": 335
+    },
+    {
+      "epoch": 0.9974102848686645,
+      "mean_token_accuracy": 0.7690690041104019,
+      "step": 337,
+      "total_flos": 76774385909760.0,
+      "train_loss": 0.7816469167035835,
+      "train_runtime": 1423.7517,
+      "train_samples_per_second": 15.187,
+      "train_steps_per_second": 0.237
+    }
+  ],
+  "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": 76774385909760.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:431f268d11f20a91453b79de07c6915ff9902f05f38d697870cc45f9627a3309
+size 7480