End of training

.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 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+library_name: transformers
+model_name: qwen-r1-aha-moment
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for qwen-r1-aha-moment
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-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="Chris126/qwen-r1-aha-moment", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.14.0
+- Transformers: 4.48.1
+- Pytorch: 2.5.1+cu124
+- Datasets: 3.1.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+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}}
+}
+```

adapter_config.json

@@ -0,0 +1,32 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 32,
+  "lora_bias": false,
+  "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": [
+    "q_proj",
+    "v_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 sha256:0c9f0276ad530f8b43b1190ca8f7d30379c90509d4dd9bc11ac8658cfa68d1e4
+size 14764792

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": 0.0,
+    "train_loss": 5.925413926080284e-07,
+    "train_runtime": 35343.127,
+    "train_samples": 45000,
+    "train_samples_per_second": 0.013,
+    "train_steps_per_second": 0.013
+}

runs/Feb05_00-35-25_AVA-STATION/events.out.tfevents.1738712130.AVA-STATION.381779.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0fcb2720df793c9462f33f6d8d668311a53dfb051e0af60add4a45e602796f
+size 31280

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 5.925413926080284e-07,
+    "train_runtime": 35343.127,
+    "train_samples": 45000,
+    "train_samples_per_second": 0.013,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,627 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.01,
+  "eval_steps": 500,
+  "global_step": 450,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 342.55,
+      "epoch": 0.00022222222222222223,
+      "grad_norm": 0.21378593146800995,
+      "kl": 0.0005054072127677501,
+      "learning_rate": 4.99391012564956e-07,
+      "loss": 0.0,
+      "reward": 0.25,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.25,
+      "step": 10
+    },
+    {
+      "completion_length": 337.3,
+      "epoch": 0.00044444444444444447,
+      "grad_norm": 1.5290135706891306e-05,
+      "kl": 0.0005718494998291135,
+      "learning_rate": 4.975670171853925e-07,
+      "loss": 0.0,
+      "reward": 0.65,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.65,
+      "step": 20
+    },
+    {
+      "completion_length": 388.8,
+      "epoch": 0.0006666666666666666,
+      "grad_norm": 0.31574714183807373,
+      "kl": 0.0005932338128332049,
+      "learning_rate": 4.945369001834514e-07,
+      "loss": 0.0,
+      "reward": 0.35,
+      "reward_std": 0.49497473835945127,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.35,
+      "step": 30
+    },
+    {
+      "completion_length": 390.3,
+      "epoch": 0.0008888888888888889,
+      "grad_norm": 1.8352753613726236e-05,
+      "kl": 0.0006036393286194652,
+      "learning_rate": 4.903154239845797e-07,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.1414213538169861,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 40
+    },
+    {
+      "completion_length": 466.7,
+      "epoch": 0.0011111111111111111,
+      "grad_norm": 1.8186246961704455e-05,
+      "kl": 0.0005532185896299779,
+      "learning_rate": 4.849231551964771e-07,
+      "loss": 0.0,
+      "reward": 0.5,
+      "reward_std": 0.42426406145095824,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.5,
+      "step": 50
+    },
+    {
+      "completion_length": 446.8,
+      "epoch": 0.0013333333333333333,
+      "grad_norm": 3.2005907996790484e-05,
+      "kl": 0.0006301910732872784,
+      "learning_rate": 4.783863644106502e-07,
+      "loss": 0.0,
+      "reward": 0.35,
+      "reward_std": 0.49497473835945127,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.35,
+      "step": 60
+    },
+    {
+      "completion_length": 371.15,
+      "epoch": 0.0015555555555555555,
+      "grad_norm": 1.834248541854322e-05,
+      "kl": 0.0005721298075513914,
+      "learning_rate": 4.707368982147317e-07,
+      "loss": 0.0,
+      "reward": 0.3,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.3,
+      "step": 70
+    },
+    {
+      "completion_length": 380.9,
+      "epoch": 0.0017777777777777779,
+      "grad_norm": 0.24635720252990723,
+      "kl": 0.0005963630188489333,
+      "learning_rate": 4.6201202403910643e-07,
+      "loss": 0.0,
+      "reward": 0.45,
+      "reward_std": 0.6363960921764373,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.45,
+      "step": 80
+    },
+    {
+      "completion_length": 371.1,
+      "epoch": 0.002,
+      "grad_norm": 0.20243793725967407,
+      "kl": 0.0006782339944038541,
+      "learning_rate": 4.5225424859373684e-07,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 90
+    },
+    {
+      "completion_length": 319.75,
+      "epoch": 0.0022222222222222222,
+      "grad_norm": 0.2666068971157074,
+      "kl": 0.0006597590865567327,
+      "learning_rate": 4.415111107797445e-07,
+      "loss": 0.0,
+      "reward": 0.5,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.5,
+      "step": 100
+    },
+    {
+      "completion_length": 464.1,
+      "epoch": 0.0024444444444444444,
+      "grad_norm": 0.19521790742874146,
+      "kl": 0.0005753735254984349,
+      "learning_rate": 4.2983495008466273e-07,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 110
+    },
+    {
+      "completion_length": 413.25,
+      "epoch": 0.0026666666666666666,
+      "grad_norm": 0.18933118879795074,
+      "kl": 0.0005773572018370032,
+      "learning_rate": 4.172826515897145e-07,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.42426406145095824,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 120
+    },
+    {
+      "completion_length": 422.75,
+      "epoch": 0.0028888888888888888,
+      "grad_norm": 0.2125905156135559,
+      "kl": 0.0006250702834222465,
+      "learning_rate": 4.039153688314145e-07,
+      "loss": 0.0,
+      "reward": 0.45,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.45,
+      "step": 130
+    },
+    {
+      "completion_length": 403.05,
+      "epoch": 0.003111111111111111,
+      "grad_norm": 1.8821670892066322e-05,
+      "kl": 0.0005768304574303329,
+      "learning_rate": 3.8979822586768666e-07,
+      "loss": 0.0,
+      "reward": 0.3,
+      "reward_std": 0.1414213538169861,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.3,
+      "step": 140
+    },
+    {
+      "completion_length": 445.75,
+      "epoch": 0.0033333333333333335,
+      "grad_norm": 4.957288547302596e-05,
+      "kl": 0.000591657921904698,
+      "learning_rate": 3.75e-07,
+      "loss": 0.0,
+      "reward": 0.35,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.35,
+      "step": 150
+    },
+    {
+      "completion_length": 409.8,
+      "epoch": 0.0035555555555555557,
+      "grad_norm": 0.20501621067523956,
+      "kl": 0.0005684028874384239,
+      "learning_rate": 3.595927866972693e-07,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.42426406145095824,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 160
+    },
+    {
+      "completion_length": 364.95,
+      "epoch": 0.003777777777777778,
+      "grad_norm": 0.3308781385421753,
+      "kl": 0.0005750875250669196,
+      "learning_rate": 3.43651648353978e-07,
+      "loss": 0.0,
+      "reward": 0.6,
+      "reward_std": 0.42426406145095824,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.6,
+      "step": 170
+    },
+    {
+      "completion_length": 310.55,
+      "epoch": 0.004,
+      "grad_norm": 9.957168913388159e-06,
+      "kl": 0.0005386626056861132,
+      "learning_rate": 3.272542485937368e-07,
+      "loss": 0.0,
+      "reward": 0.5,
+      "reward_std": 0.42426406145095824,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.5,
+      "step": 180
+    },
+    {
+      "completion_length": 378.6,
+      "epoch": 0.004222222222222222,
+      "grad_norm": 0.2291877716779709,
+      "kl": 0.0006608614959986881,
+      "learning_rate": 3.104804738999169e-07,
+      "loss": 0.0,
+      "reward": 0.55,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.55,
+      "step": 190
+    },
+    {
+      "completion_length": 340.6,
+      "epoch": 0.0044444444444444444,
+      "grad_norm": 0.18360783159732819,
+      "kl": 0.0005953012092504651,
+      "learning_rate": 2.934120444167326e-07,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.5656854152679444,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 200
+    },
+    {
+      "completion_length": 396.55,
+      "epoch": 0.004666666666666667,
+      "grad_norm": 2.1740559532190673e-05,
+      "kl": 0.0005484546738443897,
+      "learning_rate": 2.761321158169134e-07,
+      "loss": 0.0,
+      "reward": 0.55,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.55,
+      "step": 210
+    },
+    {
+      "completion_length": 330.25,
+      "epoch": 0.004888888888888889,
+      "grad_norm": 6.363703869283199e-05,
+      "kl": 0.0006559955596458167,
+      "learning_rate": 2.5872487417562527e-07,
+      "loss": 0.0,
+      "reward": 0.35,
+      "reward_std": 0.49497473835945127,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.35,
+      "step": 220
+    },
+    {
+      "completion_length": 419.25,
+      "epoch": 0.005111111111111111,
+      "grad_norm": 0.1977580189704895,
+      "kl": 0.0006136057461844757,
+      "learning_rate": 2.412751258243748e-07,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.42426406145095824,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 230
+    },
+    {
+      "completion_length": 399.65,
+      "epoch": 0.005333333333333333,
+      "grad_norm": 2.009019226534292e-05,
+      "kl": 0.000605167931644246,
+      "learning_rate": 2.2386788418308665e-07,
+      "loss": 0.0,
+      "reward": 0.5,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.5,
+      "step": 240
+    },
+    {
+      "completion_length": 365.25,
+      "epoch": 0.005555555555555556,
+      "grad_norm": 9.316376963397488e-05,
+      "kl": 0.0005963615287328139,
+      "learning_rate": 2.065879555832674e-07,
+      "loss": 0.0,
+      "reward": 0.6,
+      "reward_std": 0.42426406145095824,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.6,
+      "step": 250
+    },
+    {
+      "completion_length": 422.1,
+      "epoch": 0.0057777777777777775,
+      "grad_norm": 0.16928204894065857,
+      "kl": 0.0006461634649895132,
+      "learning_rate": 1.895195261000831e-07,
+      "loss": 0.0,
+      "reward": 0.7,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.7,
+      "step": 260
+    },
+    {
+      "completion_length": 445.45,
+      "epoch": 0.006,
+      "grad_norm": 0.17555122077465057,
+      "kl": 0.0005888437968678773,
+      "learning_rate": 1.7274575140626315e-07,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 270
+    },
+    {
+      "completion_length": 409.55,
+      "epoch": 0.006222222222222222,
+      "grad_norm": 2.910105285991449e-05,
+      "kl": 0.0005833886214531958,
+      "learning_rate": 1.5634835164602196e-07,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 280
+    },
+    {
+      "completion_length": 355.3,
+      "epoch": 0.0064444444444444445,
+      "grad_norm": 0.2147456258535385,
+      "kl": 0.000609121096204035,
+      "learning_rate": 1.404072133027306e-07,
+      "loss": 0.0,
+      "reward": 0.45,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.45,
+      "step": 290
+    },
+    {
+      "completion_length": 380.9,
+      "epoch": 0.006666666666666667,
+      "grad_norm": 2.5209470550180413e-05,
+      "kl": 0.0006293962011113763,
+      "learning_rate": 1.2500000000000005e-07,
+      "loss": 0.0,
+      "reward": 0.6,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.6,
+      "step": 300
+    },
+    {
+      "completion_length": 385.7,
+      "epoch": 0.006888888888888889,
+      "grad_norm": 7.603858830407262e-05,
+      "kl": 0.0006043465342372656,
+      "learning_rate": 1.1020177413231332e-07,
+      "loss": 0.0,
+      "reward": 0.35,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.35,
+      "step": 310
+    },
+    {
+      "completion_length": 369.15,
+      "epoch": 0.0071111111111111115,
+      "grad_norm": 1.2851673091063276e-05,
+      "kl": 0.0005439497355837375,
+      "learning_rate": 9.608463116858542e-08,
+      "loss": 0.0,
+      "reward": 0.3,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.3,
+      "step": 320
+    },
+    {
+      "completion_length": 316.85,
+      "epoch": 0.007333333333333333,
+      "grad_norm": 0.20440705120563507,
+      "kl": 0.0005756207800004631,
+      "learning_rate": 8.271734841028552e-08,
+      "loss": 0.0,
+      "reward": 0.75,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.75,
+      "step": 330
+    },
+    {
+      "completion_length": 429.55,
+      "epoch": 0.007555555555555556,
+      "grad_norm": 0.2662304639816284,
+      "kl": 0.0005803581763757393,
+      "learning_rate": 7.016504991533726e-08,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.5656854152679444,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 340
+    },
+    {
+      "completion_length": 467.8,
+      "epoch": 0.0077777777777777776,
+      "grad_norm": 1.7572709111846052e-05,
+      "kl": 0.0005397438129875809,
+      "learning_rate": 5.848888922025552e-08,
+      "loss": 0.0,
+      "reward": 0.35,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.35,
+      "step": 350
+    },
+    {
+      "completion_length": 430.1,
+      "epoch": 0.008,
+      "grad_norm": 1.761410203471314e-05,
+      "kl": 0.0005661552131641656,
+      "learning_rate": 4.774575140626316e-08,
+      "loss": 0.0,
+      "reward": 0.5,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.5,
+      "step": 360
+    },
+    {
+      "completion_length": 386.6,
+      "epoch": 0.008222222222222223,
+      "grad_norm": 0.18963927030563354,
+      "kl": 0.0005982606788165867,
+      "learning_rate": 3.798797596089351e-08,
+      "loss": 0.0,
+      "reward": 0.45,
+      "reward_std": 0.49497473835945127,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.45,
+      "step": 370
+    },
+    {
+      "completion_length": 378.0,
+      "epoch": 0.008444444444444444,
+      "grad_norm": 2.9212462322902866e-05,
+      "kl": 0.0006032192788552493,
+      "learning_rate": 2.9263101785268252e-08,
+      "loss": 0.0,
+      "reward": 0.2,
+      "reward_std": 0.1414213538169861,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.2,
+      "step": 380
+    },
+    {
+      "completion_length": 375.95,
+      "epoch": 0.008666666666666666,
+      "grad_norm": 1.570535641803872e-05,
+      "kl": 0.0006192138127516956,
+      "learning_rate": 2.1613635589349756e-08,
+      "loss": 0.0,
+      "reward": 0.55,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.55,
+      "step": 390
+    },
+    {
+      "completion_length": 399.75,
+      "epoch": 0.008888888888888889,
+      "grad_norm": 0.1566227674484253,
+      "kl": 0.0005766067682998255,
+      "learning_rate": 1.507684480352292e-08,
+      "loss": 0.0,
+      "reward": 0.4,
+      "reward_std": 0.42426406145095824,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.4,
+      "step": 400
+    },
+    {
+      "completion_length": 317.9,
+      "epoch": 0.009111111111111111,
+      "grad_norm": 0.42514702677726746,
+      "kl": 0.000586391575052403,
+      "learning_rate": 9.684576015420275e-09,
+      "loss": 0.0,
+      "reward": 0.5,
+      "reward_std": 0.42426406145095824,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.5,
+      "step": 410
+    },
+    {
+      "completion_length": 440.05,
+      "epoch": 0.009333333333333334,
+      "grad_norm": 1.8029251805273816e-05,
+      "kl": 0.0005952615960268304,
+      "learning_rate": 5.463099816548577e-09,
+      "loss": 0.0,
+      "reward": 0.35,
+      "reward_std": 0.49497473835945127,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.35,
+      "step": 420
+    },
+    {
+      "completion_length": 391.65,
+      "epoch": 0.009555555555555555,
+      "grad_norm": 0.23369018733501434,
+      "kl": 0.0005777814978500829,
+      "learning_rate": 2.4329828146074096e-09,
+      "loss": 0.0,
+      "reward": 0.45,
+      "reward_std": 0.3535533845424652,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.45,
+      "step": 430
+    },
+    {
+      "completion_length": 368.75,
+      "epoch": 0.009777777777777778,
+      "grad_norm": 0.27213847637176514,
+      "kl": 0.0006278897577431053,
+      "learning_rate": 6.089874350439505e-10,
+      "loss": 0.0,
+      "reward": 0.45,
+      "reward_std": 0.49497473835945127,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.45,
+      "step": 440
+    },
+    {
+      "completion_length": 445.5,
+      "epoch": 0.01,
+      "grad_norm": 2.1452080545714125e-05,
+      "kl": 0.000612707485561259,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "reward": 0.2,
+      "reward_std": 0.2828427076339722,
+      "rewards/equation_reward_func": 0.0,
+      "rewards/format_reward_func": 0.2,
+      "step": 450
+    },
+    {
+      "epoch": 0.01,
+      "step": 450,
+      "total_flos": 0.0,
+      "train_loss": 5.925413926080284e-07,
+      "train_runtime": 35343.127,
+      "train_samples_per_second": 0.013,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 450,
+  "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": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d875b2ce3ec833cc1adfdd719f3e676ad7c17cebd64ffc4e6f8bed2655a8f164
+size 5624