Upload folder using huggingface_hub

.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

@@ -1,3 +1,66 @@
----
-license: mit
----
+---
+datasets: creative_ad
+library_name: transformers
+tags:
+- generated_from_trainer
+- open-r1
+licence: license
+---
+
+# Model Card for None
+
+This model is a fine-tuned version of [None](https://huggingface.co/None) on the [creative_ad](https://huggingface.co/datasets/creative_ad) dataset.
+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="None", 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/zhangjiayi/huggingface/runs/ukmal5l5) 
+
+
+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: 4.48.2
+- Pytorch: 2.4.0
+- 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}}
+}
+```

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": 0.0009153305456556123,
+    "train_runtime": 28649.5238,
+    "train_samples": 1166,
+    "train_samples_per_second": 0.081,
+    "train_steps_per_second": 0.01
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/maindata/data/user/jiayi.zhang/pretrained_models/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": "4.48.2",
+  "use_cache": true,
+  "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": "4.48.2"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d122c26e5ec1f7cf283b35c479bb5b57a73b105d8d8bc90a165a4b2b0eb07c2
+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
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.0009153305456556123,
+    "train_runtime": 28649.5238,
+    "train_samples": 1166,
+    "train_samples_per_second": 0.081,
+    "train_steps_per_second": 0.01
+}

trainer_state.json

@@ -0,0 +1,2072 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.987993138936535,
+  "eval_steps": 2000,
+  "global_step": 290,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 280.9453125,
+      "epoch": 0.0137221269296741,
+      "grad_norm": 0.200531005859375,
+      "kl": 0.0,
+      "learning_rate": 6.89655172413793e-08,
+      "loss": 0.0,
+      "reward": 1.2636350020766258,
+      "reward_std": 0.7326151318848133,
+      "rewards/answer_quality_reward_func": 0.240364583209157,
+      "rewards/format_reward_func": 0.558687087148428,
+      "rewards/think_quality_reward_func": 0.4645833298563957,
+      "step": 2
+    },
+    {
+      "completion_length": 254.1484375,
+      "epoch": 0.0274442538593482,
+      "grad_norm": 0.23695461452007294,
+      "kl": 0.0004696846008300781,
+      "learning_rate": 1.379310344827586e-07,
+      "loss": 0.0,
+      "reward": 1.4313375726342201,
+      "reward_std": 0.5982592245563865,
+      "rewards/answer_quality_reward_func": 0.22890624788124114,
+      "rewards/format_reward_func": 0.6692282650619745,
+      "rewards/think_quality_reward_func": 0.5332031268626451,
+      "step": 4
+    },
+    {
+      "completion_length": 270.3671875,
+      "epoch": 0.0411663807890223,
+      "grad_norm": 0.20797939598560333,
+      "kl": 0.0005097389221191406,
+      "learning_rate": 2.0689655172413793e-07,
+      "loss": 0.0,
+      "reward": 1.3857495188713074,
+      "reward_std": 0.6331189293414354,
+      "rewards/answer_quality_reward_func": 0.2459635380655527,
+      "rewards/format_reward_func": 0.6181714087724686,
+      "rewards/think_quality_reward_func": 0.5216145776212215,
+      "step": 6
+    },
+    {
+      "completion_length": 263.7578125,
+      "epoch": 0.0548885077186964,
+      "grad_norm": 0.2095089852809906,
+      "kl": 0.00047576427459716797,
+      "learning_rate": 2.758620689655172e-07,
+      "loss": 0.0,
+      "reward": 1.4237127974629402,
+      "reward_std": 0.6548625286668539,
+      "rewards/answer_quality_reward_func": 0.2583333342336118,
+      "rewards/format_reward_func": 0.6428534537553787,
+      "rewards/think_quality_reward_func": 0.5225260313600302,
+      "step": 8
+    },
+    {
+      "completion_length": 262.7421875,
+      "epoch": 0.0686106346483705,
+      "grad_norm": 0.22044678032398224,
+      "kl": 0.0004361867904663086,
+      "learning_rate": 3.4482758620689656e-07,
+      "loss": 0.0,
+      "reward": 1.3745320364832878,
+      "reward_std": 0.5780904749408364,
+      "rewards/answer_quality_reward_func": 0.2433593743480742,
+      "rewards/format_reward_func": 0.6129435263574123,
+      "rewards/think_quality_reward_func": 0.5182291641831398,
+      "step": 10
+    },
+    {
+      "completion_length": 253.8515625,
+      "epoch": 0.0823327615780446,
+      "grad_norm": 0.21221238374710083,
+      "kl": 0.00046944618225097656,
+      "learning_rate": 4.1379310344827586e-07,
+      "loss": 0.0,
+      "reward": 1.4099359475076199,
+      "reward_std": 0.5978407869115472,
+      "rewards/answer_quality_reward_func": 0.21627604262903333,
+      "rewards/format_reward_func": 0.6960036773234606,
+      "rewards/think_quality_reward_func": 0.49765624944120646,
+      "step": 12
+    },
+    {
+      "completion_length": 269.65625,
+      "epoch": 0.09605488850771869,
+      "grad_norm": 0.21109910309314728,
+      "kl": 0.0004999637603759766,
+      "learning_rate": 4.827586206896552e-07,
+      "loss": 0.0,
+      "reward": 1.4609676226973534,
+      "reward_std": 0.6565476767718792,
+      "rewards/answer_quality_reward_func": 0.23294270923361182,
+      "rewards/format_reward_func": 0.6721655614674091,
+      "rewards/think_quality_reward_func": 0.5558593682944775,
+      "step": 14
+    },
+    {
+      "completion_length": 272.3828125,
+      "epoch": 0.1097770154373928,
+      "grad_norm": 0.2218167930841446,
+      "kl": 0.0005079507827758789,
+      "learning_rate": 5.517241379310344e-07,
+      "loss": 0.0,
+      "reward": 1.4886968657374382,
+      "reward_std": 0.6304780375212431,
+      "rewards/answer_quality_reward_func": 0.26992187229916453,
+      "rewards/format_reward_func": 0.6970302406698465,
+      "rewards/think_quality_reward_func": 0.5217447821050882,
+      "step": 16
+    },
+    {
+      "completion_length": 257.5,
+      "epoch": 0.1234991423670669,
+      "grad_norm": 0.24383482336997986,
+      "kl": 0.0006282329559326172,
+      "learning_rate": 6.206896551724138e-07,
+      "loss": 0.0,
+      "reward": 1.509253829717636,
+      "reward_std": 0.5901340646669269,
+      "rewards/answer_quality_reward_func": 0.26093749701976776,
+      "rewards/format_reward_func": 0.7028736304491758,
+      "rewards/think_quality_reward_func": 0.5454427022486925,
+      "step": 18
+    },
+    {
+      "completion_length": 261.0625,
+      "epoch": 0.137221269296741,
+      "grad_norm": 0.22092702984809875,
+      "kl": 0.0006501674652099609,
+      "learning_rate": 6.896551724137931e-07,
+      "loss": 0.0,
+      "reward": 1.5030930899083614,
+      "reward_std": 0.5783230252563953,
+      "rewards/answer_quality_reward_func": 0.2360677090473473,
+      "rewards/format_reward_func": 0.7079108189791441,
+      "rewards/think_quality_reward_func": 0.5591145856305957,
+      "step": 20
+    },
+    {
+      "completion_length": 281.9375,
+      "epoch": 0.1509433962264151,
+      "grad_norm": 0.19880710542201996,
+      "kl": 0.0008211135864257812,
+      "learning_rate": 7.586206896551724e-07,
+      "loss": 0.0,
+      "reward": 1.5285571739077568,
+      "reward_std": 0.5852111494168639,
+      "rewards/answer_quality_reward_func": 0.24830729141831398,
+      "rewards/format_reward_func": 0.7565519884228706,
+      "rewards/think_quality_reward_func": 0.5236979145556688,
+      "step": 22
+    },
+    {
+      "completion_length": 285.203125,
+      "epoch": 0.1646655231560892,
+      "grad_norm": 0.1880275309085846,
+      "kl": 0.0008184909820556641,
+      "learning_rate": 8.275862068965517e-07,
+      "loss": 0.0,
+      "reward": 1.654343031346798,
+      "reward_std": 0.519588727504015,
+      "rewards/answer_quality_reward_func": 0.281510416418314,
+      "rewards/format_reward_func": 0.7728326376527548,
+      "rewards/think_quality_reward_func": 0.5999999903142452,
+      "step": 24
+    },
+    {
+      "completion_length": 265.8515625,
+      "epoch": 0.1783876500857633,
+      "grad_norm": 0.22054816782474518,
+      "kl": 0.0016040802001953125,
+      "learning_rate": 8.96551724137931e-07,
+      "loss": 0.0,
+      "reward": 1.6120254769921303,
+      "reward_std": 0.604787390679121,
+      "rewards/answer_quality_reward_func": 0.268749990966171,
+      "rewards/format_reward_func": 0.7706192433834076,
+      "rewards/think_quality_reward_func": 0.572656249627471,
+      "step": 26
+    },
+    {
+      "completion_length": 265.0234375,
+      "epoch": 0.19210977701543738,
+      "grad_norm": 0.23350445926189423,
+      "kl": 0.0037322044372558594,
+      "learning_rate": 9.655172413793103e-07,
+      "loss": 0.0,
+      "reward": 1.6360950246453285,
+      "reward_std": 0.5475883986800909,
+      "rewards/answer_quality_reward_func": 0.25533853890374303,
+      "rewards/format_reward_func": 0.7984648458659649,
+      "rewards/think_quality_reward_func": 0.5822916477918625,
+      "step": 28
+    },
+    {
+      "completion_length": 257.2421875,
+      "epoch": 0.2058319039451115,
+      "grad_norm": 0.2340281456708908,
+      "kl": 0.0024671554565429688,
+      "learning_rate": 9.999637795788383e-07,
+      "loss": 0.0,
+      "reward": 1.8156483098864555,
+      "reward_std": 0.3590877242386341,
+      "rewards/answer_quality_reward_func": 0.2725260416045785,
+      "rewards/format_reward_func": 0.9140858538448811,
+      "rewards/think_quality_reward_func": 0.6290364563465118,
+      "step": 30
+    },
+    {
+      "completion_length": 270.328125,
+      "epoch": 0.2195540308747856,
+      "grad_norm": 0.23865526914596558,
+      "kl": 0.0035905838012695312,
+      "learning_rate": 9.996740476948384e-07,
+      "loss": 0.0,
+      "reward": 1.7573274821043015,
+      "reward_std": 0.3837462617084384,
+      "rewards/answer_quality_reward_func": 0.23046874720603228,
+      "rewards/format_reward_func": 0.8756869100034237,
+      "rewards/think_quality_reward_func": 0.6511718779802322,
+      "step": 32
+    },
+    {
+      "completion_length": 270.6484375,
+      "epoch": 0.2332761578044597,
+      "grad_norm": 0.2162395566701889,
+      "kl": 0.0037336349487304688,
+      "learning_rate": 9.99094751828131e-07,
+      "loss": 0.0,
+      "reward": 1.7991406917572021,
+      "reward_std": 0.370311891194433,
+      "rewards/answer_quality_reward_func": 0.27330729039385915,
+      "rewards/format_reward_func": 0.862942773848772,
+      "rewards/think_quality_reward_func": 0.6628906093537807,
+      "step": 34
+    },
+    {
+      "completion_length": 266.4140625,
+      "epoch": 0.2469982847341338,
+      "grad_norm": 0.2209404557943344,
+      "kl": 0.004337310791015625,
+      "learning_rate": 9.98226227684e-07,
+      "loss": 0.0,
+      "reward": 1.7452938333153725,
+      "reward_std": 0.43817455042153597,
+      "rewards/answer_quality_reward_func": 0.2700520819053054,
+      "rewards/format_reward_func": 0.8469865471124649,
+      "rewards/think_quality_reward_func": 0.6282551977783442,
+      "step": 36
+    },
+    {
+      "completion_length": 275.84375,
+      "epoch": 0.2607204116638079,
+      "grad_norm": 0.20049536228179932,
+      "kl": 0.0059051513671875,
+      "learning_rate": 9.970689785771798e-07,
+      "loss": 0.0001,
+      "reward": 1.8387366831302643,
+      "reward_std": 0.40058660972863436,
+      "rewards/answer_quality_reward_func": 0.3001302042976022,
+      "rewards/format_reward_func": 0.8624346293509007,
+      "rewards/think_quality_reward_func": 0.6761718727648258,
+      "step": 38
+    },
+    {
+      "completion_length": 262.953125,
+      "epoch": 0.274442538593482,
+      "grad_norm": 0.21914814412593842,
+      "kl": 0.0074634552001953125,
+      "learning_rate": 9.95623675140179e-07,
+      "loss": 0.0001,
+      "reward": 1.9225089848041534,
+      "reward_std": 0.3085475550033152,
+      "rewards/answer_quality_reward_func": 0.31132812052965164,
+      "rewards/format_reward_func": 0.926415242254734,
+      "rewards/think_quality_reward_func": 0.6847656071186066,
+      "step": 40
+    },
+    {
+      "completion_length": 266.7734375,
+      "epoch": 0.2881646655231561,
+      "grad_norm": 0.20505952835083008,
+      "kl": 0.012746810913085938,
+      "learning_rate": 9.93891154934647e-07,
+      "loss": 0.0001,
+      "reward": 1.8400960639119148,
+      "reward_std": 0.31889354810118675,
+      "rewards/answer_quality_reward_func": 0.2800781219266355,
+      "rewards/format_reward_func": 0.88736167922616,
+      "rewards/think_quality_reward_func": 0.6726562399417162,
+      "step": 42
+    },
+    {
+      "completion_length": 283.03125,
+      "epoch": 0.3018867924528302,
+      "grad_norm": 0.20089682936668396,
+      "kl": 0.009592056274414062,
+      "learning_rate": 9.918724219660013e-07,
+      "loss": 0.0001,
+      "reward": 1.9255277439951897,
+      "reward_std": 0.3338128034956753,
+      "rewards/answer_quality_reward_func": 0.3057291600853205,
+      "rewards/format_reward_func": 0.9056058898568153,
+      "rewards/think_quality_reward_func": 0.714192695915699,
+      "step": 44
+    },
+    {
+      "completion_length": 299.015625,
+      "epoch": 0.3156089193825043,
+      "grad_norm": 0.21208344399929047,
+      "kl": 0.012195587158203125,
+      "learning_rate": 9.895686461016005e-07,
+      "loss": 0.0001,
+      "reward": 1.9222128614783287,
+      "reward_std": 0.3133280505426228,
+      "rewards/answer_quality_reward_func": 0.2837239555083215,
+      "rewards/format_reward_func": 0.9119264185428619,
+      "rewards/think_quality_reward_func": 0.7265624850988388,
+      "step": 46
+    },
+    {
+      "completion_length": 323.4921875,
+      "epoch": 0.3293310463121784,
+      "grad_norm": 0.18190930783748627,
+      "kl": 0.016071319580078125,
+      "learning_rate": 9.869811623928e-07,
+      "loss": 0.0002,
+      "reward": 1.9156172946095467,
+      "reward_std": 0.33059287490323186,
+      "rewards/answer_quality_reward_func": 0.2911458294838667,
+      "rewards/format_reward_func": 0.884627740830183,
+      "rewards/think_quality_reward_func": 0.7398437410593033,
+      "step": 48
+    },
+    {
+      "completion_length": 325.640625,
+      "epoch": 0.34305317324185247,
+      "grad_norm": 0.18641796708106995,
+      "kl": 0.015377044677734375,
+      "learning_rate": 9.841114703012817e-07,
+      "loss": 0.0002,
+      "reward": 1.9938555285334587,
+      "reward_std": 0.3317244155332446,
+      "rewards/answer_quality_reward_func": 0.34179686568677425,
+      "rewards/format_reward_func": 0.9001055397093296,
+      "rewards/think_quality_reward_func": 0.751953125,
+      "step": 50
+    },
+    {
+      "completion_length": 343.453125,
+      "epoch": 0.3567753001715266,
+      "grad_norm": 0.18672624230384827,
+      "kl": 0.017429351806640625,
+      "learning_rate": 9.809612328301069e-07,
+      "loss": 0.0002,
+      "reward": 1.8535542637109756,
+      "reward_std": 0.41525313816964626,
+      "rewards/answer_quality_reward_func": 0.27578124683350325,
+      "rewards/format_reward_func": 0.8310282342135906,
+      "rewards/think_quality_reward_func": 0.7467447854578495,
+      "step": 52
+    },
+    {
+      "completion_length": 340.90625,
+      "epoch": 0.3704974271012007,
+      "grad_norm": 0.18769648671150208,
+      "kl": 0.0204010009765625,
+      "learning_rate": 9.775322755599977e-07,
+      "loss": 0.0002,
+      "reward": 1.9808814227581024,
+      "reward_std": 0.37413908122107387,
+      "rewards/answer_quality_reward_func": 0.32903645373880863,
+      "rewards/format_reward_func": 0.9088762328028679,
+      "rewards/think_quality_reward_func": 0.742968738079071,
+      "step": 54
+    },
+    {
+      "completion_length": 342.3984375,
+      "epoch": 0.38421955403087477,
+      "grad_norm": 0.18268480896949768,
+      "kl": 0.0240936279296875,
+      "learning_rate": 9.738265855914012e-07,
+      "loss": 0.0002,
+      "reward": 1.9932566732168198,
+      "reward_std": 0.3731453288346529,
+      "rewards/answer_quality_reward_func": 0.3510416531935334,
+      "rewards/format_reward_func": 0.8945587873458862,
+      "rewards/think_quality_reward_func": 0.7476562485098839,
+      "step": 56
+    },
+    {
+      "completion_length": 344.28125,
+      "epoch": 0.3979416809605489,
+      "grad_norm": 0.18100802600383759,
+      "kl": 0.0281982421875,
+      "learning_rate": 9.698463103929541e-07,
+      "loss": 0.0003,
+      "reward": 2.0352731719613075,
+      "reward_std": 0.2896303874440491,
+      "rewards/answer_quality_reward_func": 0.325651032384485,
+      "rewards/format_reward_func": 0.9258981980383396,
+      "rewards/think_quality_reward_func": 0.783723957836628,
+      "step": 58
+    },
+    {
+      "completion_length": 370.65625,
+      "epoch": 0.411663807890223,
+      "grad_norm": 0.1758911907672882,
+      "kl": 0.02741241455078125,
+      "learning_rate": 9.655937565570122e-07,
+      "loss": 0.0003,
+      "reward": 1.971546895802021,
+      "reward_std": 0.330893627833575,
+      "rewards/answer_quality_reward_func": 0.3313802005723119,
+      "rewards/format_reward_func": 0.8548802100121975,
+      "rewards/think_quality_reward_func": 0.785286445170641,
+      "step": 60
+    },
+    {
+      "completion_length": 377.0859375,
+      "epoch": 0.42538593481989706,
+      "grad_norm": 0.1705077588558197,
+      "kl": 0.02756500244140625,
+      "learning_rate": 9.610713884629666e-07,
+      "loss": 0.0003,
+      "reward": 1.976484701037407,
+      "reward_std": 0.4069426618516445,
+      "rewards/answer_quality_reward_func": 0.3708333196118474,
+      "rewards/format_reward_func": 0.8344273716211319,
+      "rewards/think_quality_reward_func": 0.7712239511311054,
+      "step": 62
+    },
+    {
+      "completion_length": 372.3125,
+      "epoch": 0.4391080617495712,
+      "grad_norm": 0.17809398472309113,
+      "kl": 0.03229522705078125,
+      "learning_rate": 9.562818268491215e-07,
+      "loss": 0.0003,
+      "reward": 2.1156445741653442,
+      "reward_std": 0.3222670303657651,
+      "rewards/answer_quality_reward_func": 0.41289061680436134,
+      "rewards/format_reward_func": 0.9118685647845268,
+      "rewards/think_quality_reward_func": 0.7908854149281979,
+      "step": 64
+    },
+    {
+      "completion_length": 369.984375,
+      "epoch": 0.4528301886792453,
+      "grad_norm": 0.1842561960220337,
+      "kl": 0.0321044921875,
+      "learning_rate": 9.512278472939626e-07,
+      "loss": 0.0003,
+      "reward": 2.0863697454333305,
+      "reward_std": 0.3673935355618596,
+      "rewards/answer_quality_reward_func": 0.3654947765171528,
+      "rewards/format_reward_func": 0.9190520793199539,
+      "rewards/think_quality_reward_func": 0.801822904497385,
+      "step": 66
+    },
+    {
+      "completion_length": 371.796875,
+      "epoch": 0.4665523156089194,
+      "grad_norm": 0.16658607125282288,
+      "kl": 0.033203125,
+      "learning_rate": 9.45912378607691e-07,
+      "loss": 0.0003,
+      "reward": 2.1010902896523476,
+      "reward_std": 0.3480951292440295,
+      "rewards/answer_quality_reward_func": 0.4162760265171528,
+      "rewards/format_reward_func": 0.8799964934587479,
+      "rewards/think_quality_reward_func": 0.8048176988959312,
+      "step": 68
+    },
+    {
+      "completion_length": 381.078125,
+      "epoch": 0.48027444253859347,
+      "grad_norm": 0.1765335500240326,
+      "kl": 0.035369873046875,
+      "learning_rate": 9.403385011349638e-07,
+      "loss": 0.0004,
+      "reward": 2.148190885782242,
+      "reward_std": 0.35688082315027714,
+      "rewards/answer_quality_reward_func": 0.4567708168178797,
+      "rewards/format_reward_func": 0.8810034319758415,
+      "rewards/think_quality_reward_func": 0.8104166649281979,
+      "step": 70
+    },
+    {
+      "completion_length": 376.375,
+      "epoch": 0.4939965694682676,
+      "grad_norm": 0.17420853674411774,
+      "kl": 0.0396728515625,
+      "learning_rate": 9.345094449698143e-07,
+      "loss": 0.0004,
+      "reward": 2.137619011104107,
+      "reward_std": 0.32480568066239357,
+      "rewards/answer_quality_reward_func": 0.42669269628822803,
+      "rewards/format_reward_func": 0.8950408771634102,
+      "rewards/think_quality_reward_func": 0.8158854097127914,
+      "step": 72
+    },
+    {
+      "completion_length": 368.203125,
+      "epoch": 0.5077186963979416,
+      "grad_norm": 0.17609168589115143,
+      "kl": 0.042266845703125,
+      "learning_rate": 9.284285880837946e-07,
+      "loss": 0.0004,
+      "reward": 2.1166791021823883,
+      "reward_std": 0.3095300702843815,
+      "rewards/answer_quality_reward_func": 0.42252602614462376,
+      "rewards/format_reward_func": 0.9080853573977947,
+      "rewards/think_quality_reward_func": 0.7860677056014538,
+      "step": 74
+    },
+    {
+      "completion_length": 378.0625,
+      "epoch": 0.5214408233276158,
+      "grad_norm": 0.18319210410118103,
+      "kl": 0.0416717529296875,
+      "learning_rate": 9.220994543684224e-07,
+      "loss": 0.0004,
+      "reward": 2.198269546031952,
+      "reward_std": 0.3282247083261609,
+      "rewards/answer_quality_reward_func": 0.47773435711860657,
+      "rewards/format_reward_func": 0.9036081247031689,
+      "rewards/think_quality_reward_func": 0.8169270791113377,
+      "step": 76
+    },
+    {
+      "completion_length": 372.0546875,
+      "epoch": 0.5351629502572899,
+      "grad_norm": 0.18346504867076874,
+      "kl": 0.0488739013671875,
+      "learning_rate": 9.15525711593065e-07,
+      "loss": 0.0005,
+      "reward": 2.090093567967415,
+      "reward_std": 0.36066758376546204,
+      "rewards/answer_quality_reward_func": 0.40429685823619366,
+      "rewards/format_reward_func": 0.8623591773211956,
+      "rewards/think_quality_reward_func": 0.8234374895691872,
+      "step": 78
+    },
+    {
+      "completion_length": 356.4296875,
+      "epoch": 0.548885077186964,
+      "grad_norm": 0.1822659820318222,
+      "kl": 0.0575714111328125,
+      "learning_rate": 9.087111692794459e-07,
+      "loss": 0.0006,
+      "reward": 2.2176768332719803,
+      "reward_std": 0.31258356431499124,
+      "rewards/answer_quality_reward_func": 0.47734372690320015,
+      "rewards/format_reward_func": 0.9133799523115158,
+      "rewards/think_quality_reward_func": 0.8269531093537807,
+      "step": 80
+    },
+    {
+      "completion_length": 356.765625,
+      "epoch": 0.5626072041166381,
+      "grad_norm": 0.1832280308008194,
+      "kl": 0.0583343505859375,
+      "learning_rate": 9.016597764940048e-07,
+      "loss": 0.0006,
+      "reward": 2.232508063316345,
+      "reward_std": 0.3021385227330029,
+      "rewards/answer_quality_reward_func": 0.4899739436805248,
+      "rewards/format_reward_func": 0.9207892827689648,
+      "rewards/think_quality_reward_func": 0.8217447772622108,
+      "step": 82
+    },
+    {
+      "completion_length": 350.6171875,
+      "epoch": 0.5763293310463122,
+      "grad_norm": 0.18824546039104462,
+      "kl": 0.0598297119140625,
+      "learning_rate": 8.943756195593915e-07,
+      "loss": 0.0006,
+      "reward": 2.267571359872818,
+      "reward_std": 0.24662064015865326,
+      "rewards/answer_quality_reward_func": 0.4873697739094496,
+      "rewards/format_reward_func": 0.948951605707407,
+      "rewards/think_quality_reward_func": 0.8312499709427357,
+      "step": 84
+    },
+    {
+      "completion_length": 348.296875,
+      "epoch": 0.5900514579759862,
+      "grad_norm": 0.1910252869129181,
+      "kl": 0.065399169921875,
+      "learning_rate": 8.868629196864181e-07,
+      "loss": 0.0007,
+      "reward": 2.3059453517198563,
+      "reward_std": 0.26139099057763815,
+      "rewards/answer_quality_reward_func": 0.5234374795109034,
+      "rewards/format_reward_func": 0.942143302410841,
+      "rewards/think_quality_reward_func": 0.8403645902872086,
+      "step": 86
+    },
+    {
+      "completion_length": 334.828125,
+      "epoch": 0.6037735849056604,
+      "grad_norm": 0.1994294971227646,
+      "kl": 0.07464599609375,
+      "learning_rate": 8.791260305278431e-07,
+      "loss": 0.0007,
+      "reward": 2.293788820505142,
+      "reward_std": 0.2987233167514205,
+      "rewards/answer_quality_reward_func": 0.522656224668026,
+      "rewards/format_reward_func": 0.9411846846342087,
+      "rewards/think_quality_reward_func": 0.829947903752327,
+      "step": 88
+    },
+    {
+      "completion_length": 346.265625,
+      "epoch": 0.6174957118353345,
+      "grad_norm": 0.19464552402496338,
+      "kl": 0.076629638671875,
+      "learning_rate": 8.711694356554049e-07,
+      "loss": 0.0008,
+      "reward": 2.33330599963665,
+      "reward_std": 0.24258170742541552,
+      "rewards/answer_quality_reward_func": 0.5442708116024733,
+      "rewards/format_reward_func": 0.9519257470965385,
+      "rewards/think_quality_reward_func": 0.8371093608438969,
+      "step": 90
+    },
+    {
+      "completion_length": 354.9765625,
+      "epoch": 0.6312178387650086,
+      "grad_norm": 0.19240236282348633,
+      "kl": 0.07568359375,
+      "learning_rate": 8.629977459615654e-07,
+      "loss": 0.0008,
+      "reward": 2.341018781065941,
+      "reward_std": 0.22859826777130365,
+      "rewards/answer_quality_reward_func": 0.5540364384651184,
+      "rewards/format_reward_func": 0.9518261030316353,
+      "rewards/think_quality_reward_func": 0.8351562432944775,
+      "step": 92
+    },
+    {
+      "completion_length": 353.5859375,
+      "epoch": 0.6449399656946827,
+      "grad_norm": 0.18257762491703033,
+      "kl": 0.081939697265625,
+      "learning_rate": 8.546156969874722e-07,
+      "loss": 0.0008,
+      "reward": 2.3477097898721695,
+      "reward_std": 0.25754671171307564,
+      "rewards/answer_quality_reward_func": 0.5748697761446238,
+      "rewards/format_reward_func": 0.9367722757160664,
+      "rewards/think_quality_reward_func": 0.8360677100718021,
+      "step": 94
+    },
+    {
+      "completion_length": 347.875,
+      "epoch": 0.6586620926243568,
+      "grad_norm": 0.1859983652830124,
+      "kl": 0.08270263671875,
+      "learning_rate": 8.460281461786846e-07,
+      "loss": 0.0008,
+      "reward": 2.3241832330822945,
+      "reward_std": 0.29706390388309956,
+      "rewards/answer_quality_reward_func": 0.586718738079071,
+      "rewards/format_reward_func": 0.9118134751915932,
+      "rewards/think_quality_reward_func": 0.8256510272622108,
+      "step": 96
+    },
+    {
+      "completion_length": 351.1875,
+      "epoch": 0.6723842195540308,
+      "grad_norm": 0.21329373121261597,
+      "kl": 0.093017578125,
+      "learning_rate": 8.372400700702569e-07,
+      "loss": 0.0009,
+      "reward": 2.332564875483513,
+      "reward_std": 0.2945901188068092,
+      "rewards/answer_quality_reward_func": 0.5587239470332861,
+      "rewards/format_reward_func": 0.9394659325480461,
+      "rewards/think_quality_reward_func": 0.8343749977648258,
+      "step": 98
+    },
+    {
+      "completion_length": 353.2578125,
+      "epoch": 0.6861063464837049,
+      "grad_norm": 0.19502753019332886,
+      "kl": 0.0947265625,
+      "learning_rate": 8.282565614028067e-07,
+      "loss": 0.0009,
+      "reward": 2.3509654104709625,
+      "reward_std": 0.2975193331949413,
+      "rewards/answer_quality_reward_func": 0.5841145645827055,
+      "rewards/format_reward_func": 0.9238821342587471,
+      "rewards/think_quality_reward_func": 0.8429687507450581,
+      "step": 100
+    },
+    {
+      "completion_length": 361.328125,
+      "epoch": 0.6998284734133791,
+      "grad_norm": 0.19681787490844727,
+      "kl": 0.098175048828125,
+      "learning_rate": 8.190828261712428e-07,
+      "loss": 0.001,
+      "reward": 2.32693400233984,
+      "reward_std": 0.295138499699533,
+      "rewards/answer_quality_reward_func": 0.5571614364162087,
+      "rewards/format_reward_func": 0.9269340261816978,
+      "rewards/think_quality_reward_func": 0.8428385220468044,
+      "step": 102
+    },
+    {
+      "completion_length": 366.6875,
+      "epoch": 0.7135506003430532,
+      "grad_norm": 0.17757786810398102,
+      "kl": 0.097869873046875,
+      "learning_rate": 8.097241806078615e-07,
+      "loss": 0.001,
+      "reward": 2.3718064725399017,
+      "reward_std": 0.2993803401477635,
+      "rewards/answer_quality_reward_func": 0.5914062261581421,
+      "rewards/format_reward_func": 0.9395148195326328,
+      "rewards/think_quality_reward_func": 0.8408853933215141,
+      "step": 104
+    },
+    {
+      "completion_length": 370.078125,
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.18709802627563477,
+      "kl": 0.09759521484375,
+      "learning_rate": 8.001860481015592e-07,
+      "loss": 0.001,
+      "reward": 2.4007676392793655,
+      "reward_std": 0.2506851116195321,
+      "rewards/answer_quality_reward_func": 0.5985676925629377,
+      "rewards/format_reward_func": 0.9528510197997093,
+      "rewards/think_quality_reward_func": 0.8493489474058151,
+      "step": 106
+    },
+    {
+      "completion_length": 388.96875,
+      "epoch": 0.7409948542024014,
+      "grad_norm": 0.17249542474746704,
+      "kl": 0.09429931640625,
+      "learning_rate": 7.904739560549474e-07,
+      "loss": 0.0009,
+      "reward": 2.3758395314216614,
+      "reward_std": 0.3589801371563226,
+      "rewards/answer_quality_reward_func": 0.6082031019032001,
+      "rewards/format_reward_func": 0.8922458067536354,
+      "rewards/think_quality_reward_func": 0.8753906153142452,
+      "step": 108
+    },
+    {
+      "completion_length": 390.2421875,
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.17211292684078217,
+      "kl": 0.1004638671875,
+      "learning_rate": 7.805935326811912e-07,
+      "loss": 0.001,
+      "reward": 2.417878970503807,
+      "reward_std": 0.2655462478287518,
+      "rewards/answer_quality_reward_func": 0.6291666571050882,
+      "rewards/format_reward_func": 0.9228268675506115,
+      "rewards/think_quality_reward_func": 0.8658854141831398,
+      "step": 110
+    },
+    {
+      "completion_length": 393.5703125,
+      "epoch": 0.7684391080617495,
+      "grad_norm": 0.175153449177742,
+      "kl": 0.101959228515625,
+      "learning_rate": 7.705505037424269e-07,
+      "loss": 0.001,
+      "reward": 2.3483614027500153,
+      "reward_std": 0.35932604828849435,
+      "rewards/answer_quality_reward_func": 0.6335937343537807,
+      "rewards/format_reward_func": 0.8592989183962345,
+      "rewards/think_quality_reward_func": 0.8554687425494194,
+      "step": 112
+    },
+    {
+      "completion_length": 386.6640625,
+      "epoch": 0.7821612349914236,
+      "grad_norm": 0.17615902423858643,
+      "kl": 0.099761962890625,
+      "learning_rate": 7.603506892316511e-07,
+      "loss": 0.001,
+      "reward": 2.384554073214531,
+      "reward_std": 0.3326480337418616,
+      "rewards/answer_quality_reward_func": 0.6402343511581421,
+      "rewards/format_reward_func": 0.8822103515267372,
+      "rewards/think_quality_reward_func": 0.8621093593537807,
+      "step": 114
+    },
+    {
+      "completion_length": 368.5546875,
+      "epoch": 0.7958833619210978,
+      "grad_norm": 0.18490657210350037,
+      "kl": 0.107513427734375,
+      "learning_rate": 7.5e-07,
+      "loss": 0.0011,
+      "reward": 2.3982376605272293,
+      "reward_std": 0.30952252680435777,
+      "rewards/answer_quality_reward_func": 0.6122395601123571,
+      "rewards/format_reward_func": 0.9280553907155991,
+      "rewards/think_quality_reward_func": 0.8579427003860474,
+      "step": 116
+    },
+    {
+      "completion_length": 371.59375,
+      "epoch": 0.8096054888507719,
+      "grad_norm": 0.1820589005947113,
+      "kl": 0.10858154296875,
+      "learning_rate": 7.395044343313777e-07,
+      "loss": 0.0011,
+      "reward": 2.448230743408203,
+      "reward_std": 0.1958690125029534,
+      "rewards/answer_quality_reward_func": 0.6305989418178797,
+      "rewards/format_reward_func": 0.9505745209753513,
+      "rewards/think_quality_reward_func": 0.8670572713017464,
+      "step": 118
+    },
+    {
+      "completion_length": 370.3984375,
+      "epoch": 0.823327615780446,
+      "grad_norm": 0.18224012851715088,
+      "kl": 0.104736328125,
+      "learning_rate": 7.288700744664167e-07,
+      "loss": 0.001,
+      "reward": 2.4031564742326736,
+      "reward_std": 0.27395217306911945,
+      "rewards/answer_quality_reward_func": 0.614583307877183,
+      "rewards/format_reward_func": 0.9246408343315125,
+      "rewards/think_quality_reward_func": 0.8639322705566883,
+      "step": 120
+    },
+    {
+      "completion_length": 360.171875,
+      "epoch": 0.8370497427101201,
+      "grad_norm": 0.18499115109443665,
+      "kl": 0.10662841796875,
+      "learning_rate": 7.181030830777837e-07,
+      "loss": 0.0011,
+      "reward": 2.441983327269554,
+      "reward_std": 0.20215876307338476,
+      "rewards/answer_quality_reward_func": 0.6157551910728216,
+      "rewards/format_reward_func": 0.9664624892175198,
+      "rewards/think_quality_reward_func": 0.8597656190395355,
+      "step": 122
+    },
+    {
+      "completion_length": 353.9140625,
+      "epoch": 0.8507718696397941,
+      "grad_norm": 0.1921129673719406,
+      "kl": 0.107757568359375,
+      "learning_rate": 7.072096996988759e-07,
+      "loss": 0.0011,
+      "reward": 2.4199374318122864,
+      "reward_std": 0.26074777147732675,
+      "rewards/answer_quality_reward_func": 0.6037760153412819,
+      "rewards/format_reward_func": 0.9530103541910648,
+      "rewards/think_quality_reward_func": 0.8631510399281979,
+      "step": 124
+    },
+    {
+      "completion_length": 362.0078125,
+      "epoch": 0.8644939965694682,
+      "grad_norm": 0.1788560301065445,
+      "kl": 0.111907958984375,
+      "learning_rate": 6.961962371079751e-07,
+      "loss": 0.0011,
+      "reward": 2.4374969750642776,
+      "reward_std": 0.2772186954971403,
+      "rewards/answer_quality_reward_func": 0.6238281093537807,
+      "rewards/format_reward_func": 0.9298147335648537,
+      "rewards/think_quality_reward_func": 0.8838541470468044,
+      "step": 126
+    },
+    {
+      "completion_length": 348.953125,
+      "epoch": 0.8782161234991424,
+      "grad_norm": 0.19293126463890076,
+      "kl": 0.1082763671875,
+      "learning_rate": 6.850690776699573e-07,
+      "loss": 0.0011,
+      "reward": 2.382745623588562,
+      "reward_std": 0.2466182792559266,
+      "rewards/answer_quality_reward_func": 0.5884114345535636,
+      "rewards/format_reward_func": 0.943943552672863,
+      "rewards/think_quality_reward_func": 0.8503906205296516,
+      "step": 128
+    },
+    {
+      "completion_length": 353.9140625,
+      "epoch": 0.8919382504288165,
+      "grad_norm": 0.19949260354042053,
+      "kl": 0.11865234375,
+      "learning_rate": 6.738346696376738e-07,
+      "loss": 0.0012,
+      "reward": 2.4676217436790466,
+      "reward_std": 0.19183522614184767,
+      "rewards/answer_quality_reward_func": 0.6332031097263098,
+      "rewards/format_reward_func": 0.9665800370275974,
+      "rewards/think_quality_reward_func": 0.8678385056555271,
+      "step": 130
+    },
+    {
+      "completion_length": 343.453125,
+      "epoch": 0.9056603773584906,
+      "grad_norm": 0.20649074018001556,
+      "kl": 0.115142822265625,
+      "learning_rate": 6.624995234151538e-07,
+      "loss": 0.0012,
+      "reward": 2.4805327653884888,
+      "reward_std": 0.21587521908804774,
+      "rewards/answer_quality_reward_func": 0.6450520530343056,
+      "rewards/format_reward_func": 0.96295465528965,
+      "rewards/think_quality_reward_func": 0.8725260309875011,
+      "step": 132
+    },
+    {
+      "completion_length": 369.375,
+      "epoch": 0.9193825042881647,
+      "grad_norm": 0.17965266108512878,
+      "kl": 0.125030517578125,
+      "learning_rate": 6.510702077847863e-07,
+      "loss": 0.0012,
+      "reward": 2.472148522734642,
+      "reward_std": 0.2227725691627711,
+      "rewards/answer_quality_reward_func": 0.6566405966877937,
+      "rewards/format_reward_func": 0.9466277174651623,
+      "rewards/think_quality_reward_func": 0.868880208581686,
+      "step": 134
+    },
+    {
+      "completion_length": 358.6171875,
+      "epoch": 0.9331046312178388,
+      "grad_norm": 0.18341581523418427,
+      "kl": 0.114044189453125,
+      "learning_rate": 6.395533461006735e-07,
+      "loss": 0.0011,
+      "reward": 2.4762252867221832,
+      "reward_std": 0.21157550485804677,
+      "rewards/answer_quality_reward_func": 0.6544270627200603,
+      "rewards/format_reward_func": 0.9538294561207294,
+      "rewards/think_quality_reward_func": 0.8679687418043613,
+      "step": 136
+    },
+    {
+      "completion_length": 343.625,
+      "epoch": 0.9468267581475128,
+      "grad_norm": 0.1889878660440445,
+      "kl": 0.11956787109375,
+      "learning_rate": 6.279556124503589e-07,
+      "loss": 0.0012,
+      "reward": 2.489329695701599,
+      "reward_std": 0.22135120234452188,
+      "rewards/answer_quality_reward_func": 0.6286458093672991,
+      "rewards/format_reward_func": 0.9668037220835686,
+      "rewards/think_quality_reward_func": 0.8938801921904087,
+      "step": 138
+    },
+    {
+      "completion_length": 359.296875,
+      "epoch": 0.9605488850771869,
+      "grad_norm": 0.19360192120075226,
+      "kl": 0.12933349609375,
+      "learning_rate": 6.162837277871552e-07,
+      "loss": 0.0013,
+      "reward": 2.495242103934288,
+      "reward_std": 0.1982172103598714,
+      "rewards/answer_quality_reward_func": 0.6470051929354668,
+      "rewards/format_reward_func": 0.9725858978927135,
+      "rewards/think_quality_reward_func": 0.8756510242819786,
+      "step": 140
+    },
+    {
+      "completion_length": 366.046875,
+      "epoch": 0.9742710120068611,
+      "grad_norm": 0.17844274640083313,
+      "kl": 0.115997314453125,
+      "learning_rate": 6.045444560353135e-07,
+      "loss": 0.0012,
+      "reward": 2.4655097872018814,
+      "reward_std": 0.24709907034412026,
+      "rewards/answer_quality_reward_func": 0.6220051907002926,
+      "rewards/format_reward_func": 0.9588691554963589,
+      "rewards/think_quality_reward_func": 0.8846353888511658,
+      "step": 142
+    },
+    {
+      "completion_length": 368.3125,
+      "epoch": 0.9879931389365352,
+      "grad_norm": 0.18252933025360107,
+      "kl": 0.111328125,
+      "learning_rate": 5.927446001702898e-07,
+      "loss": 0.0011,
+      "reward": 2.4636979699134827,
+      "reward_std": 0.2634353074245155,
+      "rewards/answer_quality_reward_func": 0.6384114343672991,
+      "rewards/format_reward_func": 0.9290625713765621,
+      "rewards/think_quality_reward_func": 0.8962239548563957,
+      "step": 144
+    },
+    {
+      "completion_length": 371.55357142857144,
+      "epoch": 1.0,
+      "grad_norm": 0.18851357698440552,
+      "kl": 0.11418805803571429,
+      "learning_rate": 5.808909982763825e-07,
+      "loss": 0.001,
+      "reward": 2.474709987640381,
+      "reward_std": 0.24261566251516342,
+      "rewards/answer_quality_reward_func": 0.6263392716646194,
+      "rewards/format_reward_func": 0.9483707419463566,
+      "rewards/think_quality_reward_func": 0.8999999846730914,
+      "step": 146
+    },
+    {
+      "completion_length": 369.359375,
+      "epoch": 1.0137221269296741,
+      "grad_norm": 0.18597742915153503,
+      "kl": 0.116912841796875,
+      "learning_rate": 5.689905195840216e-07,
+      "loss": 0.0012,
+      "reward": 2.47463421523571,
+      "reward_std": 0.27393683325499296,
+      "rewards/answer_quality_reward_func": 0.6651041470468044,
+      "rewards/format_reward_func": 0.9212488047778606,
+      "rewards/think_quality_reward_func": 0.8882812410593033,
+      "step": 148
+    },
+    {
+      "completion_length": 360.3046875,
+      "epoch": 1.0274442538593482,
+      "grad_norm": 0.19218188524246216,
+      "kl": 0.1177978515625,
+      "learning_rate": 5.570500604890124e-07,
+      "loss": 0.0012,
+      "reward": 2.4746594578027725,
+      "reward_std": 0.1953234658576548,
+      "rewards/answer_quality_reward_func": 0.614192683249712,
+      "rewards/format_reward_func": 0.965414721518755,
+      "rewards/think_quality_reward_func": 0.8950520716607571,
+      "step": 150
+    },
+    {
+      "completion_length": 376.9609375,
+      "epoch": 1.0411663807890223,
+      "grad_norm": 0.1762981414794922,
+      "kl": 0.120758056640625,
+      "learning_rate": 5.450765405560327e-07,
+      "loss": 0.0012,
+      "reward": 2.472753271460533,
+      "reward_std": 0.26024015434086323,
+      "rewards/answer_quality_reward_func": 0.6213541384786367,
+      "rewards/format_reward_func": 0.9413731135427952,
+      "rewards/think_quality_reward_func": 0.9100260213017464,
+      "step": 152
+    },
+    {
+      "completion_length": 377.96875,
+      "epoch": 1.0548885077186965,
+      "grad_norm": 0.19541993737220764,
+      "kl": 0.117156982421875,
+      "learning_rate": 5.330768985087058e-07,
+      "loss": 0.0012,
+      "reward": 2.4561318308115005,
+      "reward_std": 0.22181733208708465,
+      "rewards/answer_quality_reward_func": 0.6152343582361937,
+      "rewards/format_reward_func": 0.9519651383161545,
+      "rewards/think_quality_reward_func": 0.888932254165411,
+      "step": 154
+    },
+    {
+      "completion_length": 373.28125,
+      "epoch": 1.0686106346483706,
+      "grad_norm": 0.18115384876728058,
+      "kl": 0.118011474609375,
+      "learning_rate": 5.210580882085713e-07,
+      "loss": 0.0012,
+      "reward": 2.498711720108986,
+      "reward_std": 0.2194732422940433,
+      "rewards/answer_quality_reward_func": 0.6716145575046539,
+      "rewards/format_reward_func": 0.9273575246334076,
+      "rewards/think_quality_reward_func": 0.8997395783662796,
+      "step": 156
+    },
+    {
+      "completion_length": 363.9140625,
+      "epoch": 1.0823327615780447,
+      "grad_norm": 0.19036605954170227,
+      "kl": 0.11932373046875,
+      "learning_rate": 5.090270746252801e-07,
+      "loss": 0.0012,
+      "reward": 2.5323465019464493,
+      "reward_std": 0.21667650784365833,
+      "rewards/answer_quality_reward_func": 0.6548176892101765,
+      "rewards/format_reward_func": 0.9525288231670856,
+      "rewards/think_quality_reward_func": 0.9249999783933163,
+      "step": 158
+    },
+    {
+      "completion_length": 366.25,
+      "epoch": 1.0960548885077186,
+      "grad_norm": 0.18956132233142853,
+      "kl": 0.123565673828125,
+      "learning_rate": 4.969908298003572e-07,
+      "loss": 0.0012,
+      "reward": 2.4959757924079895,
+      "reward_std": 0.20509447087533772,
+      "rewards/answer_quality_reward_func": 0.6578124761581421,
+      "rewards/format_reward_func": 0.9440227001905441,
+      "rewards/think_quality_reward_func": 0.8941406086087227,
+      "step": 160
+    },
+    {
+      "completion_length": 361.9296875,
+      "epoch": 1.1097770154373927,
+      "grad_norm": 0.1895158886909485,
+      "kl": 0.12139892578125,
+      "learning_rate": 4.849563288068614e-07,
+      "loss": 0.0012,
+      "reward": 2.5265551954507828,
+      "reward_std": 0.1721879404503852,
+      "rewards/answer_quality_reward_func": 0.6660155989229679,
+      "rewards/format_reward_func": 0.9592375345528126,
+      "rewards/think_quality_reward_func": 0.9013020657002926,
+      "step": 162
+    },
+    {
+      "completion_length": 360.3046875,
+      "epoch": 1.1234991423670668,
+      "grad_norm": 0.19486117362976074,
+      "kl": 0.124053955078125,
+      "learning_rate": 4.7293054570729126e-07,
+      "loss": 0.0012,
+      "reward": 2.54917012155056,
+      "reward_std": 0.17394603788852692,
+      "rewards/answer_quality_reward_func": 0.683463528752327,
+      "rewards/format_reward_func": 0.9658367820084095,
+      "rewards/think_quality_reward_func": 0.8998697809875011,
+      "step": 164
+    },
+    {
+      "completion_length": 360.515625,
+      "epoch": 1.137221269296741,
+      "grad_norm": 0.19098356366157532,
+      "kl": 0.122344970703125,
+      "learning_rate": 4.609204495120758e-07,
+      "loss": 0.0012,
+      "reward": 2.5028335452079773,
+      "reward_std": 0.2457677097991109,
+      "rewards/answer_quality_reward_func": 0.6618489362299442,
+      "rewards/format_reward_func": 0.9369481801986694,
+      "rewards/think_quality_reward_func": 0.9040364250540733,
+      "step": 166
+    },
+    {
+      "completion_length": 364.890625,
+      "epoch": 1.150943396226415,
+      "grad_norm": 0.19031932950019836,
+      "kl": 0.11676025390625,
+      "learning_rate": 4.489330001409928e-07,
+      "loss": 0.0012,
+      "reward": 2.45595820248127,
+      "reward_std": 0.28007590724155307,
+      "rewards/answer_quality_reward_func": 0.5999999810010195,
+      "rewards/format_reward_func": 0.9426769465208054,
+      "rewards/think_quality_reward_func": 0.9132812172174454,
+      "step": 168
+    },
+    {
+      "completion_length": 355.3671875,
+      "epoch": 1.1646655231560892,
+      "grad_norm": 0.18619748950004578,
+      "kl": 0.120269775390625,
+      "learning_rate": 4.3697514438985533e-07,
+      "loss": 0.0012,
+      "reward": 2.5062869787216187,
+      "reward_std": 0.21448821807280183,
+      "rewards/answer_quality_reward_func": 0.6533853933215141,
+      "rewards/format_reward_func": 0.9431359395384789,
+      "rewards/think_quality_reward_func": 0.9097656086087227,
+      "step": 170
+    },
+    {
+      "completion_length": 348.796875,
+      "epoch": 1.1783876500857633,
+      "grad_norm": 0.19050396978855133,
+      "kl": 0.1275634765625,
+      "learning_rate": 4.250538119048035e-07,
+      "loss": 0.0013,
+      "reward": 2.5452406853437424,
+      "reward_std": 0.149537174962461,
+      "rewards/answer_quality_reward_func": 0.6768228895962238,
+      "rewards/format_reward_func": 0.9680271856486797,
+      "rewards/think_quality_reward_func": 0.9003906063735485,
+      "step": 172
+    },
+    {
+      "completion_length": 357.890625,
+      "epoch": 1.1921097770154374,
+      "grad_norm": 0.18828432261943817,
+      "kl": 0.12005615234375,
+      "learning_rate": 4.131759111665348e-07,
+      "loss": 0.0012,
+      "reward": 2.4967699497938156,
+      "reward_std": 0.25045857671648264,
+      "rewards/answer_quality_reward_func": 0.6696614325046539,
+      "rewards/format_reward_func": 0.9291918762028217,
+      "rewards/think_quality_reward_func": 0.8979166373610497,
+      "step": 174
+    },
+    {
+      "completion_length": 345.671875,
+      "epoch": 1.2058319039451115,
+      "grad_norm": 0.18515987694263458,
+      "kl": 0.131256103515625,
+      "learning_rate": 4.0134832548680004e-07,
+      "loss": 0.0013,
+      "reward": 2.5093913823366165,
+      "reward_std": 0.2006161748431623,
+      "rewards/answer_quality_reward_func": 0.6694010123610497,
+      "rewards/format_reward_func": 0.9375163912773132,
+      "rewards/think_quality_reward_func": 0.9024739414453506,
+      "step": 176
+    },
+    {
+      "completion_length": 348.34375,
+      "epoch": 1.2195540308747856,
+      "grad_norm": 0.18641041219234467,
+      "kl": 0.13995361328125,
+      "learning_rate": 3.895779090194839e-07,
+      "loss": 0.0014,
+      "reward": 2.506752409040928,
+      "reward_std": 0.21386745991185308,
+      "rewards/answer_quality_reward_func": 0.6436197720468044,
+      "rewards/format_reward_func": 0.9637836627662182,
+      "rewards/think_quality_reward_func": 0.8993489407002926,
+      "step": 178
+    },
+    {
+      "completion_length": 354.5625,
+      "epoch": 1.2332761578044598,
+      "grad_norm": 0.18596898019313812,
+      "kl": 0.12200927734375,
+      "learning_rate": 3.778714827885845e-07,
+      "loss": 0.0012,
+      "reward": 2.5159292072057724,
+      "reward_std": 0.25320152961649,
+      "rewards/answer_quality_reward_func": 0.6770833060145378,
+      "rewards/format_reward_func": 0.9437938258051872,
+      "rewards/think_quality_reward_func": 0.8950520679354668,
+      "step": 180
+    },
+    {
+      "completion_length": 349.234375,
+      "epoch": 1.2469982847341339,
+      "grad_norm": 0.19616776704788208,
+      "kl": 0.135406494140625,
+      "learning_rate": 3.6623583073538965e-07,
+      "loss": 0.0014,
+      "reward": 2.5217062681913376,
+      "reward_std": 0.24421244207769632,
+      "rewards/answer_quality_reward_func": 0.6640624795109034,
+      "rewards/format_reward_func": 0.9450135640799999,
+      "rewards/think_quality_reward_func": 0.9126301892101765,
+      "step": 182
+    },
+    {
+      "completion_length": 336.640625,
+      "epoch": 1.260720411663808,
+      "grad_norm": 0.1916990876197815,
+      "kl": 0.130828857421875,
+      "learning_rate": 3.5467769578714454e-07,
+      "loss": 0.0013,
+      "reward": 2.525185465812683,
+      "reward_std": 0.19241666281595826,
+      "rewards/answer_quality_reward_func": 0.6600260268896818,
+      "rewards/format_reward_func": 0.9552635550498962,
+      "rewards/think_quality_reward_func": 0.9098958112299442,
+      "step": 184
+    },
+    {
+      "completion_length": 339.5859375,
+      "epoch": 1.2744425385934819,
+      "grad_norm": 0.189711794257164,
+      "kl": 0.124908447265625,
+      "learning_rate": 3.4320377594948665e-07,
+      "loss": 0.0012,
+      "reward": 2.533364176750183,
+      "reward_std": 0.22958510927855968,
+      "rewards/answer_quality_reward_func": 0.6528645679354668,
+      "rewards/format_reward_func": 0.9596662856638432,
+      "rewards/think_quality_reward_func": 0.9208333119750023,
+      "step": 186
+    },
+    {
+      "completion_length": 347.9921875,
+      "epoch": 1.2881646655231562,
+      "grad_norm": 0.1930411010980606,
+      "kl": 0.127105712890625,
+      "learning_rate": 3.3182072042491236e-07,
+      "loss": 0.0013,
+      "reward": 2.557098478078842,
+      "reward_std": 0.14185759902466089,
+      "rewards/answer_quality_reward_func": 0.6786458119750023,
+      "rewards/format_reward_func": 0.9770203158259392,
+      "rewards/think_quality_reward_func": 0.9014322869479656,
+      "step": 188
+    },
+    {
+      "completion_length": 342.4609375,
+      "epoch": 1.3018867924528301,
+      "grad_norm": 0.18663766980171204,
+      "kl": 0.132171630859375,
+      "learning_rate": 3.205351257595271e-07,
+      "loss": 0.0013,
+      "reward": 2.4972847253084183,
+      "reward_std": 0.24701333232223988,
+      "rewards/answer_quality_reward_func": 0.6700520683079958,
+      "rewards/format_reward_func": 0.9386910498142242,
+      "rewards/think_quality_reward_func": 0.8885416612029076,
+      "step": 190
+    },
+    {
+      "completion_length": 346.5625,
+      "epoch": 1.3156089193825042,
+      "grad_norm": 0.20097313821315765,
+      "kl": 0.134857177734375,
+      "learning_rate": 3.0935353202030735e-07,
+      "loss": 0.0013,
+      "reward": 2.5310726016759872,
+      "reward_std": 0.17734773899428546,
+      "rewards/answer_quality_reward_func": 0.649609349668026,
+      "rewards/format_reward_func": 0.9632340855896473,
+      "rewards/think_quality_reward_func": 0.9182291477918625,
+      "step": 192
+    },
+    {
+      "completion_length": 346.28125,
+      "epoch": 1.3293310463121784,
+      "grad_norm": 0.20021885633468628,
+      "kl": 0.1385498046875,
+      "learning_rate": 2.982824190050958e-07,
+      "loss": 0.0014,
+      "reward": 2.5764601975679398,
+      "reward_std": 0.14514781720936298,
+      "rewards/answer_quality_reward_func": 0.6920572817325592,
+      "rewards/format_reward_func": 0.977632112801075,
+      "rewards/think_quality_reward_func": 0.9067708104848862,
+      "step": 194
+    },
+    {
+      "completion_length": 335.2734375,
+      "epoch": 1.3430531732418525,
+      "grad_norm": 0.19977189600467682,
+      "kl": 0.137115478515625,
+      "learning_rate": 2.873282024875201e-07,
+      "loss": 0.0014,
+      "reward": 2.5549976229667664,
+      "reward_std": 0.15385633730329573,
+      "rewards/answer_quality_reward_func": 0.6760416366159916,
+      "rewards/format_reward_func": 0.9767423868179321,
+      "rewards/think_quality_reward_func": 0.9022135250270367,
+      "step": 196
+    },
+    {
+      "completion_length": 348.4140625,
+      "epoch": 1.3567753001715266,
+      "grad_norm": 0.1882954090833664,
+      "kl": 0.133148193359375,
+      "learning_rate": 2.764972304990155e-07,
+      "loss": 0.0013,
+      "reward": 2.5342080146074295,
+      "reward_std": 0.19009233661927283,
+      "rewards/answer_quality_reward_func": 0.6450520567595959,
+      "rewards/format_reward_func": 0.9774372018873692,
+      "rewards/think_quality_reward_func": 0.911718737334013,
+      "step": 198
+    },
+    {
+      "completion_length": 350.171875,
+      "epoch": 1.3704974271012007,
+      "grad_norm": 0.2033490538597107,
+      "kl": 0.131591796875,
+      "learning_rate": 2.65795779650105e-07,
+      "loss": 0.0013,
+      "reward": 2.579890713095665,
+      "reward_std": 0.1532601253129542,
+      "rewards/answer_quality_reward_func": 0.6912760213017464,
+      "rewards/format_reward_func": 0.9718178138136864,
+      "rewards/think_quality_reward_func": 0.9167968556284904,
+      "step": 200
+    },
+    {
+      "completion_length": 352.4609375,
+      "epoch": 1.3842195540308748,
+      "grad_norm": 0.19278112053871155,
+      "kl": 0.1292724609375,
+      "learning_rate": 2.552300514930657e-07,
+      "loss": 0.0013,
+      "reward": 2.56038960814476,
+      "reward_std": 0.2202644117642194,
+      "rewards/answer_quality_reward_func": 0.6834635138511658,
+      "rewards/format_reward_func": 0.9597385935485363,
+      "rewards/think_quality_reward_func": 0.9171874858438969,
+      "step": 202
+    },
+    {
+      "completion_length": 364.203125,
+      "epoch": 1.397941680960549,
+      "grad_norm": 0.18227829039096832,
+      "kl": 0.139434814453125,
+      "learning_rate": 2.448061689280959e-07,
+      "loss": 0.0014,
+      "reward": 2.52615849673748,
+      "reward_std": 0.24547634995542467,
+      "rewards/answer_quality_reward_func": 0.6756510268896818,
+      "rewards/format_reward_func": 0.9197782725095749,
+      "rewards/think_quality_reward_func": 0.9307291582226753,
+      "step": 204
+    },
+    {
+      "completion_length": 356.203125,
+      "epoch": 1.411663807890223,
+      "grad_norm": 0.19698002934455872,
+      "kl": 0.135955810546875,
+      "learning_rate": 2.345301726550567e-07,
+      "loss": 0.0014,
+      "reward": 2.5625525414943695,
+      "reward_std": 0.17206328525207937,
+      "rewards/answer_quality_reward_func": 0.6782551854848862,
+      "rewards/format_reward_func": 0.9633337929844856,
+      "rewards/think_quality_reward_func": 0.9209635220468044,
+      "step": 206
+    },
+    {
+      "completion_length": 350.0859375,
+      "epoch": 1.425385934819897,
+      "grad_norm": 0.1893555372953415,
+      "kl": 0.128631591796875,
+      "learning_rate": 2.2440801767285355e-07,
+      "loss": 0.0013,
+      "reward": 2.505118504166603,
+      "reward_std": 0.2366794398985803,
+      "rewards/answer_quality_reward_func": 0.6618489399552345,
+      "rewards/format_reward_func": 0.9419674463570118,
+      "rewards/think_quality_reward_func": 0.9013020731508732,
+      "step": 208
+    },
+    {
+      "completion_length": 366.1484375,
+      "epoch": 1.4391080617495713,
+      "grad_norm": 0.1967458426952362,
+      "kl": 0.129638671875,
+      "learning_rate": 2.1444556982847995e-07,
+      "loss": 0.0013,
+      "reward": 2.5725715458393097,
+      "reward_std": 0.16389032220467925,
+      "rewards/answer_quality_reward_func": 0.67786455899477,
+      "rewards/format_reward_func": 0.9789517857134342,
+      "rewards/think_quality_reward_func": 0.9157551899552345,
+      "step": 210
+    },
+    {
+      "completion_length": 346.1328125,
+      "epoch": 1.4528301886792452,
+      "grad_norm": 0.19667966663837433,
+      "kl": 0.12908935546875,
+      "learning_rate": 2.0464860241772452e-07,
+      "loss": 0.0013,
+      "reward": 2.553855299949646,
+      "reward_std": 0.18402364756911993,
+      "rewards/answer_quality_reward_func": 0.6756510175764561,
+      "rewards/format_reward_func": 0.9569803290069103,
+      "rewards/think_quality_reward_func": 0.9212239496409893,
+      "step": 212
+    },
+    {
+      "completion_length": 369.265625,
+      "epoch": 1.4665523156089195,
+      "grad_norm": 0.194555401802063,
+      "kl": 0.12396240234375,
+      "learning_rate": 1.9502279283951362e-07,
+      "loss": 0.0012,
+      "reward": 2.5288901031017303,
+      "reward_std": 0.27191675489302725,
+      "rewards/answer_quality_reward_func": 0.6484374813735485,
+      "rewards/format_reward_func": 0.9503744803369045,
+      "rewards/think_quality_reward_func": 0.9300781227648258,
+      "step": 214
+    },
+    {
+      "completion_length": 368.625,
+      "epoch": 1.4802744425385934,
+      "grad_norm": 0.18107974529266357,
+      "kl": 0.12896728515625,
+      "learning_rate": 1.8557371930582578e-07,
+      "loss": 0.0013,
+      "reward": 2.527914971113205,
+      "reward_std": 0.2384313156362623,
+      "rewards/answer_quality_reward_func": 0.6592447683215141,
+      "rewards/format_reward_func": 0.9423680938780308,
+      "rewards/think_quality_reward_func": 0.9263020679354668,
+      "step": 216
+    },
+    {
+      "completion_length": 360.8671875,
+      "epoch": 1.4939965694682675,
+      "grad_norm": 0.18762701749801636,
+      "kl": 0.1285400390625,
+      "learning_rate": 1.763068576090862e-07,
+      "loss": 0.0013,
+      "reward": 2.526334747672081,
+      "reward_std": 0.23106470075435936,
+      "rewards/answer_quality_reward_func": 0.6510416436940432,
+      "rewards/format_reward_func": 0.9510743319988251,
+      "rewards/think_quality_reward_func": 0.9242187291383743,
+      "step": 218
+    },
+    {
+      "completion_length": 370.875,
+      "epoch": 1.5077186963979416,
+      "grad_norm": 0.1959903985261917,
+      "kl": 0.126739501953125,
+      "learning_rate": 1.6722757794891285e-07,
+      "loss": 0.0013,
+      "reward": 2.4841148406267166,
+      "reward_std": 0.25821185298264027,
+      "rewards/answer_quality_reward_func": 0.626822903752327,
+      "rewards/format_reward_func": 0.9514325559139252,
+      "rewards/think_quality_reward_func": 0.9058593660593033,
+      "step": 220
+    },
+    {
+      "completion_length": 368.3828125,
+      "epoch": 1.5214408233276158,
+      "grad_norm": 0.18461959064006805,
+      "kl": 0.126129150390625,
+      "learning_rate": 1.5834114182005543e-07,
+      "loss": 0.0013,
+      "reward": 2.480277806520462,
+      "reward_std": 0.2194257613737136,
+      "rewards/answer_quality_reward_func": 0.6174478959292173,
+      "rewards/format_reward_func": 0.9600955620408058,
+      "rewards/think_quality_reward_func": 0.9027343578636646,
+      "step": 222
+    },
+    {
+      "completion_length": 363.9140625,
+      "epoch": 1.5351629502572899,
+      "grad_norm": 0.19768597185611725,
+      "kl": 0.130950927734375,
+      "learning_rate": 1.4965269896332884e-07,
+      "loss": 0.0013,
+      "reward": 2.5544642210006714,
+      "reward_std": 0.1914985307957977,
+      "rewards/answer_quality_reward_func": 0.6604166496545076,
+      "rewards/format_reward_func": 0.9676152318716049,
+      "rewards/think_quality_reward_func": 0.9264322817325592,
+      "step": 224
+    },
+    {
+      "completion_length": 366.671875,
+      "epoch": 1.548885077186964,
+      "grad_norm": 0.18955481052398682,
+      "kl": 0.131744384765625,
+      "learning_rate": 1.411672843813086e-07,
+      "loss": 0.0013,
+      "reward": 2.5522884875535965,
+      "reward_std": 0.2109237532131374,
+      "rewards/answer_quality_reward_func": 0.6624999791383743,
+      "rewards/format_reward_func": 0.973512452095747,
+      "rewards/think_quality_reward_func": 0.9162760190665722,
+      "step": 226
+    },
+    {
+      "completion_length": 362.2890625,
+      "epoch": 1.5626072041166381,
+      "grad_norm": 0.1849583089351654,
+      "kl": 0.131317138671875,
+      "learning_rate": 1.328898154205184e-07,
+      "loss": 0.0013,
+      "reward": 2.501645267009735,
+      "reward_std": 0.2559964486863464,
+      "rewards/answer_quality_reward_func": 0.6380208097398281,
+      "rewards/format_reward_func": 0.9371921829879284,
+      "rewards/think_quality_reward_func": 0.9264322817325592,
+      "step": 228
+    },
+    {
+      "completion_length": 368.3828125,
+      "epoch": 1.5763293310463122,
+      "grad_norm": 0.8596162796020508,
+      "kl": 0.33184814453125,
+      "learning_rate": 1.2482508892179883e-07,
+      "loss": 0.0033,
+      "reward": 2.5707194209098816,
+      "reward_std": 0.18539277534000576,
+      "rewards/answer_quality_reward_func": 0.6834635213017464,
+      "rewards/format_reward_func": 0.9603027924895287,
+      "rewards/think_quality_reward_func": 0.9269531071186066,
+      "step": 230
+    },
+    {
+      "completion_length": 364.9140625,
+      "epoch": 1.5900514579759863,
+      "grad_norm": 0.19076195359230042,
+      "kl": 0.125640869140625,
+      "learning_rate": 1.1697777844051104e-07,
+      "loss": 0.0013,
+      "reward": 2.5863112658262253,
+      "reward_std": 0.18064910732209682,
+      "rewards/answer_quality_reward_func": 0.6923176795244217,
+      "rewards/format_reward_func": 0.9678216651082039,
+      "rewards/think_quality_reward_func": 0.9261718653142452,
+      "step": 232
+    },
+    {
+      "completion_length": 361.25,
+      "epoch": 1.6037735849056602,
+      "grad_norm": 0.18080592155456543,
+      "kl": 0.128326416015625,
+      "learning_rate": 1.0935243153818435e-07,
+      "loss": 0.0013,
+      "reward": 2.5091036558151245,
+      "reward_std": 0.2531751727219671,
+      "rewards/answer_quality_reward_func": 0.6346353907138109,
+      "rewards/format_reward_func": 0.9598849378526211,
+      "rewards/think_quality_reward_func": 0.9145833216607571,
+      "step": 234
+    },
+    {
+      "completion_length": 364.3984375,
+      "epoch": 1.6174957118353346,
+      "grad_norm": 0.1862427294254303,
+      "kl": 0.124542236328125,
+      "learning_rate": 1.0195346714717812e-07,
+      "loss": 0.0012,
+      "reward": 2.602077677845955,
+      "reward_std": 0.13783499377314,
+      "rewards/answer_quality_reward_func": 0.6990885213017464,
+      "rewards/format_reward_func": 0.9752547778189182,
+      "rewards/think_quality_reward_func": 0.9277343638241291,
+      "step": 236
+    },
+    {
+      "completion_length": 366.9609375,
+      "epoch": 1.6312178387650085,
+      "grad_norm": 0.18392881751060486,
+      "kl": 0.120025634765625,
+      "learning_rate": 9.478517300988559e-08,
+      "loss": 0.0012,
+      "reward": 2.5595516860485077,
+      "reward_std": 0.17690538289025426,
+      "rewards/answer_quality_reward_func": 0.6696614287793636,
+      "rewards/format_reward_func": 0.9812964908778667,
+      "rewards/think_quality_reward_func": 0.9085937328636646,
+      "step": 238
+    },
+    {
+      "completion_length": 357.734375,
+      "epoch": 1.6449399656946828,
+      "grad_norm": 0.19649651646614075,
+      "kl": 0.1282958984375,
+      "learning_rate": 8.785170319396174e-08,
+      "loss": 0.0013,
+      "reward": 2.5774243772029877,
+      "reward_std": 0.21083476941566914,
+      "rewards/answer_quality_reward_func": 0.691536445170641,
+      "rewards/format_reward_func": 0.9608879648149014,
+      "rewards/think_quality_reward_func": 0.9249999858438969,
+      "step": 240
+    },
+    {
+      "completion_length": 360.109375,
+      "epoch": 1.6586620926243567,
+      "grad_norm": 0.20828209817409515,
+      "kl": 0.143646240234375,
+      "learning_rate": 8.115707568501767e-08,
+      "loss": 0.0014,
+      "reward": 2.5289851427078247,
+      "reward_std": 0.21116807917132974,
+      "rewards/answer_quality_reward_func": 0.6630208157002926,
+      "rewards/format_reward_func": 0.9667456112802029,
+      "rewards/think_quality_reward_func": 0.8992187306284904,
+      "step": 242
+    },
+    {
+      "completion_length": 355.0390625,
+      "epoch": 1.6723842195540308,
+      "grad_norm": 0.18950007855892181,
+      "kl": 0.146240234375,
+      "learning_rate": 7.470517005817473e-08,
+      "loss": 0.0015,
+      "reward": 2.4979211688041687,
+      "reward_std": 0.28769278433173895,
+      "rewards/answer_quality_reward_func": 0.6554687283933163,
+      "rewards/format_reward_func": 0.9266972057521343,
+      "rewards/think_quality_reward_func": 0.9157551862299442,
+      "step": 244
+    },
+    {
+      "completion_length": 357.78125,
+      "epoch": 1.686106346483705,
+      "grad_norm": 0.19160950183868408,
+      "kl": 0.13055419921875,
+      "learning_rate": 6.849972522982845e-08,
+      "loss": 0.0013,
+      "reward": 2.562749296426773,
+      "reward_std": 0.17146155866794288,
+      "rewards/answer_quality_reward_func": 0.6764322705566883,
+      "rewards/format_reward_func": 0.9675669968128204,
+      "rewards/think_quality_reward_func": 0.918749988079071,
+      "step": 246
+    },
+    {
+      "completion_length": 360.0390625,
+      "epoch": 1.699828473413379,
+      "grad_norm": 0.19480085372924805,
+      "kl": 0.12933349609375,
+      "learning_rate": 6.254433729092518e-08,
+      "loss": 0.0013,
+      "reward": 2.56176520884037,
+      "reward_std": 0.20834232028573751,
+      "rewards/answer_quality_reward_func": 0.6878906078636646,
+      "rewards/format_reward_func": 0.9599422812461853,
+      "rewards/think_quality_reward_func": 0.9139322750270367,
+      "step": 248
+    },
+    {
+      "completion_length": 357.609375,
+      "epoch": 1.7135506003430532,
+      "grad_norm": 0.18451695144176483,
+      "kl": 0.136260986328125,
+      "learning_rate": 5.684245742300625e-08,
+      "loss": 0.0014,
+      "reward": 2.5442382991313934,
+      "reward_std": 0.21742628375068307,
+      "rewards/answer_quality_reward_func": 0.6804687194526196,
+      "rewards/format_reward_func": 0.9573893435299397,
+      "rewards/think_quality_reward_func": 0.9063801914453506,
+      "step": 250
+    },
+    {
+      "completion_length": 359.3046875,
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.19356690347194672,
+      "kl": 0.12518310546875,
+      "learning_rate": 5.1397389898229003e-08,
+      "loss": 0.0013,
+      "reward": 2.526460498571396,
+      "reward_std": 0.25330993602983654,
+      "rewards/answer_quality_reward_func": 0.6654947698116302,
+      "rewards/format_reward_func": 0.9613563567399979,
+      "rewards/think_quality_reward_func": 0.899609349668026,
+      "step": 252
+    },
+    {
+      "completion_length": 357.5,
+      "epoch": 1.7409948542024014,
+      "grad_norm": 0.1791919767856598,
+      "kl": 0.12841796875,
+      "learning_rate": 4.621229016452155e-08,
+      "loss": 0.0013,
+      "reward": 2.5491337031126022,
+      "reward_std": 0.19318409776315093,
+      "rewards/answer_quality_reward_func": 0.6712239310145378,
+      "rewards/format_reward_func": 0.96632120013237,
+      "rewards/think_quality_reward_func": 0.9115885272622108,
+      "step": 254
+    },
+    {
+      "completion_length": 356.0703125,
+      "epoch": 1.7547169811320755,
+      "grad_norm": 0.19216229021549225,
+      "kl": 0.129425048828125,
+      "learning_rate": 4.129016301698285e-08,
+      "loss": 0.0013,
+      "reward": 2.5107860416173935,
+      "reward_std": 0.24518050299957395,
+      "rewards/answer_quality_reward_func": 0.6419270690530539,
+      "rewards/format_reward_func": 0.9691193960607052,
+      "rewards/think_quality_reward_func": 0.8997395746409893,
+      "step": 256
+    },
+    {
+      "completion_length": 353.25,
+      "epoch": 1.7684391080617496,
+      "grad_norm": 0.1873447746038437,
+      "kl": 0.130950927734375,
+      "learning_rate": 3.663386085658693e-08,
+      "loss": 0.0013,
+      "reward": 2.559653639793396,
+      "reward_std": 0.24428889504633844,
+      "rewards/answer_quality_reward_func": 0.6865885220468044,
+      "rewards/format_reward_func": 0.9601744785904884,
+      "rewards/think_quality_reward_func": 0.9128906019032001,
+      "step": 258
+    },
+    {
+      "completion_length": 365.8828125,
+      "epoch": 1.7821612349914235,
+      "grad_norm": 0.1755881905555725,
+      "kl": 0.12396240234375,
+      "learning_rate": 3.2246082037199526e-08,
+      "loss": 0.0012,
+      "reward": 2.532922700047493,
+      "reward_std": 0.21777902520261705,
+      "rewards/answer_quality_reward_func": 0.6352864466607571,
+      "rewards/format_reward_func": 0.9744591377675533,
+      "rewards/think_quality_reward_func": 0.9231770634651184,
+      "step": 260
+    },
+    {
+      "completion_length": 366.859375,
+      "epoch": 1.7958833619210979,
+      "grad_norm": 0.18515096604824066,
+      "kl": 0.121734619140625,
+      "learning_rate": 2.8129369301866877e-08,
+      "loss": 0.0012,
+      "reward": 2.510231152176857,
+      "reward_std": 0.3017300651408732,
+      "rewards/answer_quality_reward_func": 0.6789062321186066,
+      "rewards/format_reward_func": 0.9211686924099922,
+      "rewards/think_quality_reward_func": 0.9101562425494194,
+      "step": 262
+    },
+    {
+      "completion_length": 361.6953125,
+      "epoch": 1.8096054888507718,
+      "grad_norm": 0.1807563304901123,
+      "kl": 0.122406005859375,
+      "learning_rate": 2.4286108309281515e-08,
+      "loss": 0.0012,
+      "reward": 2.5208630114793777,
+      "reward_std": 0.24535474996082485,
+      "rewards/answer_quality_reward_func": 0.6476562321186066,
+      "rewards/format_reward_func": 0.9531547091901302,
+      "rewards/think_quality_reward_func": 0.9200520627200603,
+      "step": 264
+    },
+    {
+      "completion_length": 364.3984375,
+      "epoch": 1.823327615780446,
+      "grad_norm": 0.18482524156570435,
+      "kl": 0.127532958984375,
+      "learning_rate": 2.0718526251279344e-08,
+      "loss": 0.0013,
+      "reward": 2.554647773504257,
+      "reward_std": 0.19098084070719779,
+      "rewards/answer_quality_reward_func": 0.6700520515441895,
+      "rewards/format_reward_func": 0.9655852615833282,
+      "rewards/think_quality_reward_func": 0.9190103895962238,
+      "step": 266
+    },
+    {
+      "completion_length": 371.5859375,
+      "epoch": 1.83704974271012,
+      "grad_norm": 0.1782553344964981,
+      "kl": 0.12518310546875,
+      "learning_rate": 1.7428690562169e-08,
+      "loss": 0.0013,
+      "reward": 2.5526810586452484,
+      "reward_std": 0.1757985802832991,
+      "rewards/answer_quality_reward_func": 0.658854141831398,
+      "rewards/format_reward_func": 0.9739050604403019,
+      "rewards/think_quality_reward_func": 0.9199218712747097,
+      "step": 268
+    },
+    {
+      "completion_length": 357.8671875,
+      "epoch": 1.8507718696397941,
+      "grad_norm": 0.19761717319488525,
+      "kl": 0.124725341796875,
+      "learning_rate": 1.4418507720641793e-08,
+      "loss": 0.0012,
+      "reward": 2.535528153181076,
+      "reward_std": 0.2555379909463227,
+      "rewards/answer_quality_reward_func": 0.6736978925764561,
+      "rewards/format_reward_func": 0.9456844069063663,
+      "rewards/think_quality_reward_func": 0.916145820170641,
+      "step": 270
+    },
+    {
+      "completion_length": 355.234375,
+      "epoch": 1.8644939965694682,
+      "grad_norm": 0.19647447764873505,
+      "kl": 0.1353759765625,
+      "learning_rate": 1.168972214495667e-08,
+      "loss": 0.0014,
+      "reward": 2.5135684609413147,
+      "reward_std": 0.22324076062068343,
+      "rewards/answer_quality_reward_func": 0.6335937287658453,
+      "rewards/format_reward_func": 0.9600528627634048,
+      "rewards/think_quality_reward_func": 0.9199218489229679,
+      "step": 272
+    },
+    {
+      "completion_length": 358.5625,
+      "epoch": 1.8782161234991424,
+      "grad_norm": 0.2118876725435257,
+      "kl": 0.130889892578125,
+      "learning_rate": 9.24391518203943e-09,
+      "loss": 0.0013,
+      "reward": 2.5152609050273895,
+      "reward_std": 0.24667337420396507,
+      "rewards/answer_quality_reward_func": 0.6584635209292173,
+      "rewards/format_reward_func": 0.9436463750898838,
+      "rewards/think_quality_reward_func": 0.9131510369479656,
+      "step": 274
+    },
+    {
+      "completion_length": 366.65625,
+      "epoch": 1.8919382504288165,
+      "grad_norm": 0.18235713243484497,
+      "kl": 0.127838134765625,
+      "learning_rate": 7.082504191083416e-09,
+      "loss": 0.0013,
+      "reward": 2.5470276474952698,
+      "reward_std": 0.22138820216059685,
+      "rewards/answer_quality_reward_func": 0.6856770627200603,
+      "rewards/format_reward_func": 0.9509339332580566,
+      "rewards/think_quality_reward_func": 0.9104166477918625,
+      "step": 276
+    },
+    {
+      "completion_length": 354.5078125,
+      "epoch": 1.9056603773584906,
+      "grad_norm": 0.1872020810842514,
+      "kl": 0.121551513671875,
+      "learning_rate": 5.2067417221813844e-09,
+      "loss": 0.0012,
+      "reward": 2.5168375074863434,
+      "reward_std": 0.2121731808874756,
+      "rewards/answer_quality_reward_func": 0.6410156022757292,
+      "rewards/format_reward_func": 0.9677490033209324,
+      "rewards/think_quality_reward_func": 0.908072903752327,
+      "step": 278
+    },
+    {
+      "completion_length": 364.9140625,
+      "epoch": 1.9193825042881647,
+      "grad_norm": 0.18977053463459015,
+      "kl": 0.1224365234375,
+      "learning_rate": 3.6177147904655757e-09,
+      "loss": 0.0012,
+      "reward": 2.560437723994255,
+      "reward_std": 0.16596342343837023,
+      "rewards/answer_quality_reward_func": 0.661848939023912,
+      "rewards/format_reward_func": 0.9777554422616959,
+      "rewards/think_quality_reward_func": 0.920833308249712,
+      "step": 280
+    },
+    {
+      "completion_length": 356.1796875,
+      "epoch": 1.9331046312178388,
+      "grad_norm": 0.2080632597208023,
+      "kl": 0.12640380859375,
+      "learning_rate": 2.3163442461766604e-09,
+      "loss": 0.0013,
+      "reward": 2.5427432358264923,
+      "reward_std": 0.19120094063691795,
+      "rewards/answer_quality_reward_func": 0.6494791470468044,
+      "rewards/format_reward_func": 0.9772484712302685,
+      "rewards/think_quality_reward_func": 0.9160156026482582,
+      "step": 282
+    },
+    {
+      "completion_length": 353.5625,
+      "epoch": 1.946826758147513,
+      "grad_norm": 0.1794474720954895,
+      "kl": 0.12701416015625,
+      "learning_rate": 1.3033842410251073e-09,
+      "loss": 0.0013,
+      "reward": 2.554268568754196,
+      "reward_std": 0.2241390033159405,
+      "rewards/answer_quality_reward_func": 0.692317683249712,
+      "rewards/format_reward_func": 0.9537477046251297,
+      "rewards/think_quality_reward_func": 0.9082030989229679,
+      "step": 284
+    },
+    {
+      "completion_length": 363.4140625,
+      "epoch": 1.9605488850771868,
+      "grad_norm": 0.1862979382276535,
+      "kl": 0.12762451171875,
+      "learning_rate": 5.794217911562205e-10,
+      "loss": 0.0013,
+      "reward": 2.5570454448461533,
+      "reward_std": 0.17142929742112756,
+      "rewards/answer_quality_reward_func": 0.6704426892101765,
+      "rewards/format_reward_func": 0.9843892343342304,
+      "rewards/think_quality_reward_func": 0.9022135250270367,
+      "step": 286
+    },
+    {
+      "completion_length": 373.3359375,
+      "epoch": 1.9742710120068612,
+      "grad_norm": 0.18710127472877502,
+      "kl": 0.12957763671875,
+      "learning_rate": 1.4487643697103092e-10,
+      "loss": 0.0013,
+      "reward": 2.549387887120247,
+      "reward_std": 0.18045868794433773,
+      "rewards/answer_quality_reward_func": 0.6738281100988388,
+      "rewards/format_reward_func": 0.9591534696519375,
+      "rewards/think_quality_reward_func": 0.9164062328636646,
+      "step": 288
+    },
+    {
+      "completion_length": 357.3125,
+      "epoch": 1.987993138936535,
+      "grad_norm": 0.1937878131866455,
+      "kl": 0.124114990234375,
+      "learning_rate": 0.0,
+      "loss": 0.0012,
+      "reward": 2.493483319878578,
+      "reward_std": 0.21149947750382125,
+      "rewards/answer_quality_reward_func": 0.620182266458869,
+      "rewards/format_reward_func": 0.9647073000669479,
+      "rewards/think_quality_reward_func": 0.9085937440395355,
+      "step": 290
+    },
+    {
+      "epoch": 1.987993138936535,
+      "step": 290,
+      "total_flos": 0.0,
+      "train_loss": 0.0009153305456556123,
+      "train_runtime": 28649.5238,
+      "train_samples_per_second": 0.081,
+      "train_steps_per_second": 0.01
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 290,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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 sha256:32a488a9882c85642f7e99baa28594ea39d0d6fd147789548d30385b56231b3a
+size 7224