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 +1,67 @@
+---
+library_name: transformers
+model_name: Qwen-2.5-1.5B-Simple-RL
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen-2.5-1.5B-Simple-RL
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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="superdocker/Qwen-2.5-1.5B-Simple-RL", 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/superdocker/huggingface/runs/qfyea8pv) 
+
+
+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: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.4.1
+- 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}}
+}
+```

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": 42253.74840821018,
+    "train_runtime": 36420.7375,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.206,
+    "train_steps_per_second": 0.004
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/raid/LLM/qwen2.5-math-1.5b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 131072,
+  "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": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157c3f586b20e85db4bff9b820ce78e2535b21fcaf92f5fa026253e1635b23d3
+size 3554214752

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": "<|endoftext|>",
+    "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 +1,208 @@
+{
+  "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        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\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\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 42253.74840821018,
+    "train_runtime": 36420.7375,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.206,
+    "train_steps_per_second": 0.004
+}

trainer_state.json

@@ -0,0 +1,505 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 100,
+  "global_step": 156,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 653.8359603881836,
+      "epoch": 0.0064,
+      "grad_norm": 0.36436545848846436,
+      "kl": 0.0,
+      "learning_rate": 1.875e-07,
+      "loss": 0.0432,
+      "reward": 0.4322916753590107,
+      "reward_std": 0.38348349183797836,
+      "rewards/accuracy_reward": 0.4322916753590107,
+      "rewards/format_reward": 0.0,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 613.5866012573242,
+      "epoch": 0.032,
+      "grad_norm": 0.5317748188972473,
+      "kl": 0.00015977025032043457,
+      "learning_rate": 9.375e-07,
+      "loss": 0.0488,
+      "reward": 0.4667968899011612,
+      "reward_std": 0.37143108155578375,
+      "rewards/accuracy_reward": 0.4667968899011612,
+      "rewards/format_reward": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 631.8177268981933,
+      "epoch": 0.064,
+      "grad_norm": 0.40818989276885986,
+      "kl": 0.00026123523712158204,
+      "learning_rate": 1.875e-06,
+      "loss": 0.0416,
+      "reward": 0.4348958468064666,
+      "reward_std": 0.39116307385265825,
+      "rewards/accuracy_reward": 0.4348958468064666,
+      "rewards/format_reward": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 599.0187690734863,
+      "epoch": 0.096,
+      "grad_norm": 0.432265967130661,
+      "kl": 0.024783754348754884,
+      "learning_rate": 2.8125e-06,
+      "loss": 0.0572,
+      "reward": 0.42291667982935904,
+      "reward_std": 0.3527421932667494,
+      "rewards/accuracy_reward": 0.42291667982935904,
+      "rewards/format_reward": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 622.3146034240723,
+      "epoch": 0.128,
+      "grad_norm": 4.753727912902832,
+      "kl": 2060.8252431869505,
+      "learning_rate": 2.993961440992859e-06,
+      "loss": 95.1839,
+      "reward": 0.4718750104308128,
+      "reward_std": 0.37911620922386646,
+      "rewards/accuracy_reward": 0.4718750104308128,
+      "rewards/format_reward": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 607.3390830993652,
+      "epoch": 0.16,
+      "grad_norm": 770.6433715820312,
+      "kl": 46.15056457519531,
+      "learning_rate": 2.9695130976348534e-06,
+      "loss": 2.3634,
+      "reward": 0.5104166828095913,
+      "reward_std": 0.35664580315351485,
+      "rewards/accuracy_reward": 0.5104166828095913,
+      "rewards/format_reward": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 603.0812713623047,
+      "epoch": 0.192,
+      "grad_norm": 204.195556640625,
+      "kl": 8.570521545410156,
+      "learning_rate": 2.9265847744427307e-06,
+      "loss": 0.4851,
+      "reward": 0.5395833477377892,
+      "reward_std": 0.36477144751697776,
+      "rewards/accuracy_reward": 0.5395833477377892,
+      "rewards/format_reward": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 574.7453285217285,
+      "epoch": 0.224,
+      "grad_norm": 32.18656921386719,
+      "kl": 3.325732421875,
+      "learning_rate": 2.865716319988224e-06,
+      "loss": 0.2502,
+      "reward": 0.5796875208616257,
+      "reward_std": 0.3091961059719324,
+      "rewards/accuracy_reward": 0.5796875208616257,
+      "rewards/format_reward": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 599.6526222229004,
+      "epoch": 0.256,
+      "grad_norm": 50.4512825012207,
+      "kl": 38.948974609375,
+      "learning_rate": 2.7876731904027993e-06,
+      "loss": 1.7796,
+      "reward": 0.5656250193715096,
+      "reward_std": 0.31268223002552986,
+      "rewards/accuracy_reward": 0.5656250193715096,
+      "rewards/format_reward": 0.0,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 599.9609573364257,
+      "epoch": 0.288,
+      "grad_norm": 16.936426162719727,
+      "kl": 3.242694091796875,
+      "learning_rate": 2.6934368233226715e-06,
+      "loss": 0.2207,
+      "reward": 0.5697916842997074,
+      "reward_std": 0.3523787297308445,
+      "rewards/accuracy_reward": 0.5697916842997074,
+      "rewards/format_reward": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 605.2927291870117,
+      "epoch": 0.32,
+      "grad_norm": 66.08646392822266,
+      "kl": 0.9429168701171875,
+      "learning_rate": 2.584192295741087e-06,
+      "loss": 0.051,
+      "reward": 0.5895833544433117,
+      "reward_std": 0.31378277521580455,
+      "rewards/accuracy_reward": 0.5895833544433117,
+      "rewards/format_reward": 0.0,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 581.4265869140625,
+      "epoch": 0.352,
+      "grad_norm": 15.162301063537598,
+      "kl": 1.656298828125,
+      "learning_rate": 2.461313420977536e-06,
+      "loss": 0.1251,
+      "reward": 0.5880208499729633,
+      "reward_std": 0.3129058893769979,
+      "rewards/accuracy_reward": 0.5880208499729633,
+      "rewards/format_reward": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 592.2036628723145,
+      "epoch": 0.384,
+      "grad_norm": 453.90277099609375,
+      "kl": 3.770269775390625,
+      "learning_rate": 2.3263454721781537e-06,
+      "loss": 0.2258,
+      "reward": 0.5901041820645332,
+      "reward_std": 0.34070247821509836,
+      "rewards/accuracy_reward": 0.5901041820645332,
+      "rewards/format_reward": 0.0,
+      "step": 60
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 588.8729347229004,
+      "epoch": 0.416,
+      "grad_norm": 11.494514465332031,
+      "kl": 18979226.522857666,
+      "learning_rate": 2.18098574960932e-06,
+      "loss": 1317335.5,
+      "reward": 0.5802083477377892,
+      "reward_std": 0.32252306006848813,
+      "rewards/accuracy_reward": 0.5802083477377892,
+      "rewards/format_reward": 0.0,
+      "step": 65
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 614.9432525634766,
+      "epoch": 0.448,
+      "grad_norm": 33.81232833862305,
+      "kl": 11880.595022583007,
+      "learning_rate": 2.027062236122014e-06,
+      "loss": 793.7966,
+      "reward": 0.5052083469927311,
+      "reward_std": 0.34817213341593745,
+      "rewards/accuracy_reward": 0.5052083469927311,
+      "rewards/format_reward": 0.0,
+      "step": 70
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 607.9666870117187,
+      "epoch": 0.48,
+      "grad_norm": 2.919191598892212,
+      "kl": 1.0650543212890624,
+      "learning_rate": 1.866510609206841e-06,
+      "loss": 0.0985,
+      "reward": 0.5817708484828472,
+      "reward_std": 0.32593765016645193,
+      "rewards/accuracy_reward": 0.5817708484828472,
+      "rewards/format_reward": 0.0,
+      "step": 75
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 629.8442901611328,
+      "epoch": 0.512,
+      "grad_norm": 14.79494571685791,
+      "kl": 74.44385070800782,
+      "learning_rate": 1.7013498987264833e-06,
+      "loss": 1.66,
+      "reward": 0.5494791820645333,
+      "reward_std": 0.30361743047833445,
+      "rewards/accuracy_reward": 0.5494791820645333,
+      "rewards/format_reward": 0.0,
+      "step": 80
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 600.0541847229003,
+      "epoch": 0.544,
+      "grad_norm": 724178.6875,
+      "kl": 1415.3565673828125,
+      "learning_rate": 1.5336570964437077e-06,
+      "loss": 81.5247,
+      "reward": 0.5484375156462192,
+      "reward_std": 0.3187117656692863,
+      "rewards/accuracy_reward": 0.5484375156462192,
+      "rewards/format_reward": 0.0,
+      "step": 85
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 580.4109558105469,
+      "epoch": 0.576,
+      "grad_norm": 32.454586029052734,
+      "kl": 0.6003936767578125,
+      "learning_rate": 1.3655410366448499e-06,
+      "loss": 0.0909,
+      "reward": 0.5557291798293591,
+      "reward_std": 0.33659778758883474,
+      "rewards/accuracy_reward": 0.5557291798293591,
+      "rewards/format_reward": 0.0,
+      "step": 90
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 612.1968910217286,
+      "epoch": 0.608,
+      "grad_norm": 227.21060180664062,
+      "kl": 4.417057800292969,
+      "learning_rate": 1.199115876325091e-06,
+      "loss": 0.1735,
+      "reward": 0.49843751490116117,
+      "reward_std": 0.32474707160145044,
+      "rewards/accuracy_reward": 0.49843751490116117,
+      "rewards/format_reward": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 2.434352159500122,
+      "learning_rate": 1.036474508437579e-06,
+      "loss": 0.5235,
+      "step": 100
+    },
+    {
+      "epoch": 0.64,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 598.3372240684015,
+      "eval_kl": 479.5919916898512,
+      "eval_loss": 14.18670654296875,
+      "eval_reward": 0.46924961448537644,
+      "eval_reward_std": 0.32887630529112094,
+      "eval_rewards/accuracy_reward": 0.46922463449321206,
+      "eval_rewards/format_reward": 2.498001673167272e-05,
+      "eval_runtime": 11244.4676,
+      "eval_samples_per_second": 0.445,
+      "eval_steps_per_second": 0.009,
+      "step": 100
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 594.5505378723144,
+      "epoch": 0.672,
+      "grad_norm": 6.814489841461182,
+      "kl": 5.030734252929688,
+      "learning_rate": 8.796622425502193e-07,
+      "loss": 0.0663,
+      "reward": 0.5638021010905504,
+      "reward_std": 0.3266499313525856,
+      "rewards/accuracy_reward": 0.5638021010905504,
+      "rewards/format_reward": 0.0,
+      "step": 105
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 624.2099197387695,
+      "epoch": 0.704,
+      "grad_norm": 1.0256500244140625,
+      "kl": 0.5462493896484375,
+      "learning_rate": 7.30651083891141e-07,
+      "loss": 0.0706,
+      "reward": 0.5015625156462192,
+      "reward_std": 0.3283187661319971,
+      "rewards/accuracy_reward": 0.5015625156462192,
+      "rewards/format_reward": 0.0,
+      "step": 110
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 638.3364791870117,
+      "epoch": 0.736,
+      "grad_norm": 25.669376373291016,
+      "kl": 0.4528076171875,
+      "learning_rate": 5.913149342387704e-07,
+      "loss": 0.0513,
+      "reward": 0.5244791820645333,
+      "reward_std": 0.32383032198995354,
+      "rewards/accuracy_reward": 0.5244791820645333,
+      "rewards/format_reward": 0.0,
+      "step": 115
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 589.191682434082,
+      "epoch": 0.768,
+      "grad_norm": 71.88641357421875,
+      "kl": 2.2827545166015626,
+      "learning_rate": 4.63406026519703e-07,
+      "loss": 0.1746,
+      "reward": 0.5442708507180214,
+      "reward_std": 0.3280566889792681,
+      "rewards/accuracy_reward": 0.5442708507180214,
+      "rewards/format_reward": 0.0,
+      "step": 120
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 622.8927276611328,
+      "epoch": 0.8,
+      "grad_norm": 1.517931580543518,
+      "kl": 0.1043121337890625,
+      "learning_rate": 3.4853288946298335e-07,
+      "loss": 0.0476,
+      "reward": 0.5057291813194752,
+      "reward_std": 0.3326381642371416,
+      "rewards/accuracy_reward": 0.5057291813194752,
+      "rewards/format_reward": 0.0,
+      "step": 125
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 598.4495010375977,
+      "epoch": 0.832,
+      "grad_norm": 0.7930722236633301,
+      "kl": 0.6085357666015625,
+      "learning_rate": 2.48140119418046e-07,
+      "loss": 0.0675,
+      "reward": 0.5453125152736902,
+      "reward_std": 0.3504544053226709,
+      "rewards/accuracy_reward": 0.5453125152736902,
+      "rewards/format_reward": 0.0,
+      "step": 130
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 614.9172065734863,
+      "epoch": 0.864,
+      "grad_norm": 1384.82177734375,
+      "kl": 1.9542694091796875,
+      "learning_rate": 1.634902137174483e-07,
+      "loss": 0.1328,
+      "reward": 0.5380208536982536,
+      "reward_std": 0.33980549313127995,
+      "rewards/accuracy_reward": 0.5380208536982536,
+      "rewards/format_reward": 0.0,
+      "step": 135
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 611.6901245117188,
+      "epoch": 0.896,
+      "grad_norm": 3.5404388904571533,
+      "kl": 6.846340942382812,
+      "learning_rate": 9.564769404039419e-08,
+      "loss": 0.4182,
+      "reward": 0.5447916828095913,
+      "reward_std": 0.3115722266957164,
+      "rewards/accuracy_reward": 0.5447916828095913,
+      "rewards/format_reward": 0.0,
+      "step": 140
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 603.5270988464356,
+      "epoch": 0.928,
+      "grad_norm": 11.985507011413574,
+      "kl": 20.116134643554688,
+      "learning_rate": 4.546571943496969e-08,
+      "loss": 1.5089,
+      "reward": 0.5437500163912773,
+      "reward_std": 0.3408747211098671,
+      "rewards/accuracy_reward": 0.5437500163912773,
+      "rewards/format_reward": 0.0,
+      "step": 145
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 601.6755386352539,
+      "epoch": 0.96,
+      "grad_norm": 1.2476218938827515,
+      "kl": 0.5209381103515625,
+      "learning_rate": 1.357535734809795e-08,
+      "loss": 0.0685,
+      "reward": 0.5718750171363354,
+      "reward_std": 0.32924772184342144,
+      "rewards/accuracy_reward": 0.5718750171363354,
+      "rewards/format_reward": 0.0,
+      "step": 150
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 608.6760620117187,
+      "epoch": 0.992,
+      "grad_norm": 40.877498626708984,
+      "kl": 0.2295989990234375,
+      "learning_rate": 3.77647586240204e-10,
+      "loss": 0.0664,
+      "reward": 0.5557291798293591,
+      "reward_std": 0.3136133692227304,
+      "rewards/accuracy_reward": 0.5557291798293591,
+      "rewards/format_reward": 0.0,
+      "step": 155
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 594.5208511352539,
+      "epoch": 0.9984,
+      "kl": 3.6969146728515625,
+      "reward": 0.5312500149011612,
+      "reward_std": 0.2874857783317566,
+      "rewards/accuracy_reward": 0.5312500149011612,
+      "rewards/format_reward": 0.0,
+      "step": 156,
+      "total_flos": 0.0,
+      "train_loss": 42253.74840821018,
+      "train_runtime": 36420.7375,
+      "train_samples_per_second": 0.206,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 156,
+  "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": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6cf80d5abeb929323b58b23e0ee41bb65f4cf0e02e865c65ad431664c56afdd1
+size 7992