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 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+library_name: transformers
+model_name: RLVR-pmdata-fatigue
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for RLVR-pmdata-fatigue
+
+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="RyanFan/RLVR-pmdata-fatigue", 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/ryanzhang123-the-university-of-auckland/RLCR/runs/8fodpixn) 
+
+
+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: 4.48.3
+- Pytorch: 2.5.1
+- Datasets: 4.0.0
+- Tokenizers: 0.21.4
+
+## 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
+}

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": "4.48.3",
+  "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": "4.48.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40380a8dfbb132c829e91c184360e092c9c619dd8b1b99075e291f9719bd601e
+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": "<|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
+}

trainer_state.json

@@ -0,0 +1,382 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9790660225442833,
+  "eval_steps": 50,
+  "global_step": 57,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.01796875,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1460.2,
+      "completions/mean_length": 279.752734375,
+      "completions/mean_terminated_length": 256.78699951171876,
+      "completions/min_length": 18.6,
+      "completions/min_terminated_length": 18.6,
+      "epoch": 0.2576489533011272,
+      "grad_norm": 0.0036736442707479,
+      "learning_rate": 1e-06,
+      "loss": 0.0517,
+      "num_tokens": 2633967.0,
+      "reward": 0.449609375,
+      "reward_std": 0.26302570104599,
+      "rewards/accuracy_reward": 0.1078125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.79140625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0203125,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1427.2,
+      "completions/mean_length": 264.9375,
+      "completions/mean_terminated_length": 238.61123046875,
+      "completions/min_length": 20.4,
+      "completions/min_terminated_length": 20.4,
+      "epoch": 0.5152979066022544,
+      "grad_norm": 0.0027966429479420185,
+      "learning_rate": 1e-06,
+      "loss": 0.0573,
+      "num_tokens": 5253343.0,
+      "reward": 0.48828125,
+      "reward_std": 0.22618062496185304,
+      "rewards/accuracy_reward": 0.11171875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.86484375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.013671875,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1427.8,
+      "completions/mean_length": 243.132421875,
+      "completions/mean_terminated_length": 225.1757385253906,
+      "completions/min_length": 19.2,
+      "completions/min_terminated_length": 19.2,
+      "epoch": 0.7729468599033816,
+      "grad_norm": 0.0027919576968997717,
+      "learning_rate": 1e-06,
+      "loss": 0.0508,
+      "num_tokens": 7785930.0,
+      "reward": 0.5384765625,
+      "reward_std": 0.20729482173919678,
+      "rewards/accuracy_reward": 0.151171875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.92578125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.008984375,
+      "completions/max_length": 1500.2,
+      "completions/max_terminated_length": 1367.0,
+      "completions/mean_length": 194.6075469970703,
+      "completions/mean_terminated_length": 182.4259765625,
+      "completions/min_length": 25.6,
+      "completions/min_terminated_length": 25.6,
+      "epoch": 1.0515297906602254,
+      "grad_norm": 0.0026636295951902866,
+      "learning_rate": 1e-06,
+      "loss": 0.0368,
+      "num_tokens": 10185722.0,
+      "reward": 0.5662109375,
+      "reward_std": 0.18961112201213837,
+      "rewards/accuracy_reward": 0.168359375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9640625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00859375,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1419.8,
+      "completions/mean_length": 188.075,
+      "completions/mean_terminated_length": 176.3938751220703,
+      "completions/min_length": 21.4,
+      "completions/min_terminated_length": 21.4,
+      "epoch": 1.3091787439613527,
+      "grad_norm": 0.22164781391620636,
+      "learning_rate": 1e-06,
+      "loss": 0.0405,
+      "num_tokens": 12578554.0,
+      "reward": 0.5794921875,
+      "reward_std": 0.19335586726665496,
+      "rewards/accuracy_reward": 0.183984375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.975,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.005859375,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1215.2,
+      "completions/mean_length": 155.2171875,
+      "completions/mean_terminated_length": 147.11905822753906,
+      "completions/min_length": 24.0,
+      "completions/min_terminated_length": 24.0,
+      "epoch": 1.5668276972624797,
+      "grad_norm": 0.0035365140065550804,
+      "learning_rate": 1e-06,
+      "loss": 0.0301,
+      "num_tokens": 14894734.0,
+      "reward": 0.6017578125,
+      "reward_std": 0.19969140589237214,
+      "rewards/accuracy_reward": 0.226171875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.97734375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0046875,
+      "completions/max_length": 1496.2,
+      "completions/max_terminated_length": 1239.8,
+      "completions/mean_length": 137.501171875,
+      "completions/mean_terminated_length": 130.90984344482422,
+      "completions/min_length": 26.0,
+      "completions/min_terminated_length": 26.0,
+      "epoch": 1.8244766505636072,
+      "grad_norm": 0.0037556523457169533,
+      "learning_rate": 1e-06,
+      "loss": 0.024,
+      "num_tokens": 17157569.0,
+      "reward": 0.6326171875,
+      "reward_std": 0.21426038444042206,
+      "rewards/accuracy_reward": 0.27890625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.986328125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.003125,
+      "completions/max_length": 1443.0,
+      "completions/max_terminated_length": 1248.8,
+      "completions/mean_length": 115.93357849121094,
+      "completions/mean_terminated_length": 111.49920654296875,
+      "completions/min_length": 22.6,
+      "completions/min_terminated_length": 22.6,
+      "epoch": 2.103059581320451,
+      "grad_norm": 0.003962252289056778,
+      "learning_rate": 1e-06,
+      "loss": 0.0231,
+      "num_tokens": 19372337.0,
+      "reward": 0.6611328125,
+      "reward_std": 0.21592704355716705,
+      "rewards/accuracy_reward": 0.330078125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9921875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00390625,
+      "completions/max_length": 1472.2,
+      "completions/max_terminated_length": 1166.6,
+      "completions/mean_length": 110.8234375,
+      "completions/mean_terminated_length": 105.24631805419922,
+      "completions/min_length": 23.8,
+      "completions/min_terminated_length": 23.8,
+      "epoch": 2.360708534621578,
+      "grad_norm": 0.00423570116981864,
+      "learning_rate": 1e-06,
+      "loss": 0.0169,
+      "num_tokens": 21575605.0,
+      "reward": 0.673046875,
+      "reward_std": 0.21441609561443328,
+      "rewards/accuracy_reward": 0.352734375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.993359375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.001171875,
+      "completions/max_length": 1278.6,
+      "completions/max_terminated_length": 1227.6,
+      "completions/mean_length": 103.966796875,
+      "completions/mean_terminated_length": 102.2909912109375,
+      "completions/min_length": 25.4,
+      "completions/min_terminated_length": 25.4,
+      "epoch": 2.6183574879227054,
+      "grad_norm": 0.004094306379556656,
+      "learning_rate": 1e-06,
+      "loss": 0.0155,
+      "num_tokens": 23731264.0,
+      "reward": 0.6849609375,
+      "reward_std": 0.20115672945976257,
+      "rewards/accuracy_reward": 0.373046875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.996875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 2.6183574879227054,
+      "eval_completions/clipped_ratio": 0.0018115942028985507,
+      "eval_completions/max_length": 290.5144927536232,
+      "eval_completions/max_terminated_length": 271.78985507246375,
+      "eval_completions/mean_length": 98.78260869565217,
+      "eval_completions/mean_terminated_length": 96.16291411026664,
+      "eval_completions/min_length": 44.02173913043478,
+      "eval_completions/min_terminated_length": 44.02173913043478,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 23731264.0,
+      "eval_reward": 0.7006340579710145,
+      "eval_reward_std": 0.1998574921618337,
+      "eval_rewards/accuracy_reward": 0.4057971014492754,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 0.9954710144927537,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 218.3081,
+      "eval_samples_per_second": 0.632,
+      "eval_steps_per_second": 0.082,
+      "step": 50
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0015625,
+      "completions/max_length": 1389.4,
+      "completions/max_terminated_length": 1131.6,
+      "completions/mean_length": 99.516796875,
+      "completions/mean_terminated_length": 97.26914672851562,
+      "completions/min_length": 26.6,
+      "completions/min_terminated_length": 26.6,
+      "epoch": 2.8760064412238324,
+      "grad_norm": 0.004530761390924454,
+      "learning_rate": 1e-06,
+      "loss": 0.0119,
+      "num_tokens": 25926723.0,
+      "reward": 0.7265625,
+      "reward_std": 0.19322206377983092,
+      "rewards/accuracy_reward": 0.455078125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.998046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0032701404816513624,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 976.0,
+      "completions/mean_length": 94.65605926513672,
+      "completions/mean_terminated_length": 89.92797088623047,
+      "completions/min_length": 28.0,
+      "completions/min_terminated_length": 28.0,
+      "epoch": 2.9790660225442833,
+      "num_tokens": 26798038.0,
+      "reward": 0.7451171875,
+      "reward_std": 0.18223696947097778,
+      "rewards/accuracy_reward": 0.494140625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 57,
+      "total_flos": 0.0,
+      "train_loss": 0.03191714903764557,
+      "train_runtime": 6840.6585,
+      "train_samples_per_second": 0.545,
+      "train_steps_per_second": 0.008
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 57,
+  "num_input_tokens_seen": 26798038,
+  "num_train_epochs": 3,
+  "save_steps": 60,
+  "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": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77303ee5cb82ddd81c365006fcae39f4332acff80bfdba5b9367543dde750194
+size 8056