初始化项目，由ModelHub XC社区提供模型

Model: yarin-shaked/Qwen3-Codeforces-GRPO
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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 +1,70 @@
+---
+base_model: Qwen/Qwen3-0.6B
+datasets: open-r1/codeforces
+library_name: transformers
+model_name: Qwen3-Codeforces-GRPO
+tags:
+- generated_from_trainer
+- open-r1
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen3-Codeforces-GRPO
+
+This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on the [open-r1/codeforces](https://huggingface.co/datasets/open-r1/codeforces) 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="yarin-shaked/Qwen3-Codeforces-GRPO", 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/yarinshaked/open-r1/runs/xdob31ou) 
+
+
+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: 0.18.0
+- Transformers: 4.52.3
+- Pytorch: 2.6.0
+- Datasets: 4.2.0
+- 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 Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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": 0.0,
+    "train_runtime": 1.5617,
+    "train_samples": 16676,
+    "train_samples_per_second": 10.245,
+    "train_steps_per_second": 0.64
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:358366208135d990aa18276f15378bab7ac84d7706c3250f3f1486ddeb1e0bae
+size 1192135096

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 sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
+size 11422821

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.0,
+    "train_runtime": 1.5617,
+    "train_samples": 16676,
+    "train_samples_per_second": 10.245,
+    "train_steps_per_second": 0.64
+}

trainer_state.json

@@ -0,0 +1,907 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 32,
+  "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": -0.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 8050.0,
+      "completions/mean_length": 6862.1875,
+      "completions/mean_terminated_length": 3936.60009765625,
+      "completions/min_length": 1679.0,
+      "completions/min_terminated_length": 1679.0,
+      "epoch": 0.125,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.1540709645657331,
+      "learning_rate": 0.0,
+      "loss": -0.0397,
+      "num_tokens": 31407.0,
+      "reward": -0.699999988079071,
+      "reward_std": 0.125,
+      "rewards/cf_code_reward/mean": -0.699999988079071,
+      "rewards/cf_code_reward/std": 0.46043458580970764,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 1
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.25,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 42723.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 2
+    },
+    {
+      "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": 0.75,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7057.0,
+      "completions/mean_length": 8121.0625,
+      "completions/mean_terminated_length": 7057.0,
+      "completions/min_length": 7057.0,
+      "completions/min_terminated_length": 7057.0,
+      "epoch": 0.375,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.16390367065221123,
+      "learning_rate": 1e-06,
+      "loss": -0.0404,
+      "num_tokens": 62168.0,
+      "reward": -0.9375,
+      "reward_std": 0.125,
+      "rewards/cf_code_reward/mean": -0.9375,
+      "rewards/cf_code_reward/std": 0.25,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 3
+    },
+    {
+      "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": 0.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7780.0,
+      "completions/mean_length": 7816.625,
+      "completions/mean_terminated_length": 6190.0,
+      "completions/min_length": 4315.0,
+      "completions/min_terminated_length": 4315.0,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.2878601922045561,
+      "learning_rate": 1e-06,
+      "loss": -0.0875,
+      "num_tokens": 91526.0,
+      "reward": -0.8125,
+      "reward_std": 0.248746857047081,
+      "rewards/cf_code_reward/mean": -0.8125,
+      "rewards/cf_code_reward/std": 0.5572252869606018,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 4
+    },
+    {
+      "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": -0.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6331.0,
+      "completions/mean_length": 6324.3125,
+      "completions/mean_terminated_length": 2215.400146484375,
+      "completions/min_length": 905.0,
+      "completions/min_terminated_length": 905.0,
+      "epoch": 0.625,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.24502748244021016,
+      "learning_rate": 1e-06,
+      "loss": -0.0402,
+      "num_tokens": 118167.0,
+      "reward": -0.6746212244033813,
+      "reward_std": 0.428866446018219,
+      "rewards/cf_code_reward/mean": -0.6746212244033813,
+      "rewards/cf_code_reward/std": 0.7365784049034119,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 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": -1.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 5359.0,
+      "completions/mean_length": 5666.6875,
+      "completions/mean_terminated_length": 3702.5556640625,
+      "completions/min_length": 1851.0,
+      "completions/min_terminated_length": 1851.0,
+      "epoch": 0.75,
+      "frac_reward_zero_std": 0.25,
+      "grad_norm": 0.21413429634446854,
+      "learning_rate": 1e-06,
+      "loss": -0.0416,
+      "num_tokens": 161958.0,
+      "reward": -0.5037499666213989,
+      "reward_std": 0.39220669865608215,
+      "rewards/cf_code_reward/mean": -0.5037499666213989,
+      "rewards/cf_code_reward/std": 0.6423693299293518,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 6
+    },
+    {
+      "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": 0.75,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7498.0,
+      "completions/mean_length": 8148.625,
+      "completions/mean_terminated_length": 7498.0,
+      "completions/min_length": 7498.0,
+      "completions/min_terminated_length": 7498.0,
+      "epoch": 0.875,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.15542675545894089,
+      "learning_rate": 1e-06,
+      "loss": -0.0386,
+      "num_tokens": 182668.0,
+      "reward": -0.9437500238418579,
+      "reward_std": 0.11249999701976776,
+      "rewards/cf_code_reward/mean": -0.9437500238418579,
+      "rewards/cf_code_reward/std": 0.22499999403953552,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 7
+    },
+    {
+      "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": 0.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7341.0,
+      "completions/mean_length": 7525.6875,
+      "completions/mean_terminated_length": 4638.33349609375,
+      "completions/min_length": 2906.0,
+      "completions/min_terminated_length": 2906.0,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.17998151407614052,
+      "learning_rate": 1e-06,
+      "loss": -0.0646,
+      "num_tokens": 209383.0,
+      "reward": -0.8104166984558105,
+      "reward_std": 0.2664600610733032,
+      "rewards/cf_code_reward/mean": -0.8104166984558105,
+      "rewards/cf_code_reward/std": 0.4091035723686218,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 8
+    },
+    {
+      "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": 0.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7326.0,
+      "completions/mean_length": 7806.75,
+      "completions/mean_terminated_length": 6137.33349609375,
+      "completions/min_length": 4799.0,
+      "completions/min_terminated_length": 4799.0,
+      "epoch": 0.28125,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2669470114797714,
+      "learning_rate": 1e-06,
+      "loss": -0.1097,
+      "num_tokens": 237667.0,
+      "reward": -0.8180555105209351,
+      "reward_std": 0.3918065130710602,
+      "rewards/cf_code_reward/mean": -0.8180555105209351,
+      "rewards/cf_code_reward/std": 0.39180654287338257,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 9
+    },
+    {
+      "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": 0.75,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7539.0,
+      "completions/mean_length": 8151.1875,
+      "completions/mean_terminated_length": 7539.0,
+      "completions/min_length": 7539.0,
+      "completions/min_terminated_length": 7539.0,
+      "epoch": 0.3125,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.20723698042342187,
+      "learning_rate": 1e-06,
+      "loss": -0.0539,
+      "num_tokens": 266246.0,
+      "reward": -0.9375,
+      "reward_std": 0.25,
+      "rewards/cf_code_reward/mean": -0.9375,
+      "rewards/cf_code_reward/std": 0.25,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.34375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 275446.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 11
+    },
+    {
+      "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": 0.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7984.0,
+      "completions/mean_length": 7683.0,
+      "completions/mean_terminated_length": 5477.33349609375,
+      "completions/min_length": 4031.0,
+      "completions/min_terminated_length": 4031.0,
+      "epoch": 0.375,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2634279160052341,
+      "learning_rate": 1e-06,
+      "loss": -0.0997,
+      "num_tokens": 301318.0,
+      "reward": -0.817991316318512,
+      "reward_std": 0.39194566011428833,
+      "rewards/cf_code_reward/mean": -0.817991316318512,
+      "rewards/cf_code_reward/std": 0.39194566011428833,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 12
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.40625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 310774.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 13
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.4375,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 319062.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 14
+    },
+    {
+      "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": 0.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6720.0,
+      "completions/mean_length": 7516.6875,
+      "completions/mean_terminated_length": 4590.33349609375,
+      "completions/min_length": 2107.0,
+      "completions/min_terminated_length": 2107.0,
+      "epoch": 0.46875,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.31248865871350523,
+      "learning_rate": 1e-06,
+      "loss": -0.0589,
+      "num_tokens": 343457.0,
+      "reward": -0.8062499761581421,
+      "reward_std": 0.5662375688552856,
+      "rewards/cf_code_reward/mean": -0.8062499761581421,
+      "rewards/cf_code_reward/std": 0.5662376284599304,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 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": -1.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6767.0,
+      "completions/mean_length": 6238.25,
+      "completions/mean_terminated_length": 4718.66650390625,
+      "completions/min_length": 3229.0,
+      "completions/min_terminated_length": 3229.0,
+      "epoch": 0.5,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.44442560969386563,
+      "learning_rate": 1e-06,
+      "loss": -0.1683,
+      "num_tokens": 400709.0,
+      "reward": -0.38749998807907104,
+      "reward_std": 0.732916533946991,
+      "rewards/cf_code_reward/mean": -0.38749998807907104,
+      "rewards/cf_code_reward/std": 0.7329164743423462,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 16
+    },
+    {
+      "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": -3.0,
+      "completions/max_length": 1425.0,
+      "completions/max_terminated_length": 1425.0,
+      "completions/mean_length": 1088.0625,
+      "completions/mean_terminated_length": 1088.0625,
+      "completions/min_length": 753.0,
+      "completions/min_terminated_length": 753.0,
+      "epoch": 0.53125,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.3425692374871352,
+      "learning_rate": 1e-06,
+      "loss": -0.0026,
+      "num_tokens": 424198.0,
+      "reward": -0.2874999940395355,
+      "reward_std": 0.9912113547325134,
+      "rewards/cf_code_reward/mean": -0.2874999940395355,
+      "rewards/cf_code_reward/std": 0.991211473941803,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 17
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.5625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 444422.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 18
+    },
+    {
+      "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": 0.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6500.0,
+      "completions/mean_length": 7518.4375,
+      "completions/mean_terminated_length": 4599.6669921875,
+      "completions/min_length": 2613.0,
+      "completions/min_terminated_length": 2613.0,
+      "epoch": 0.59375,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2247292061728764,
+      "learning_rate": 1e-06,
+      "loss": -0.0863,
+      "num_tokens": 467501.0,
+      "reward": -0.8107954263687134,
+      "reward_std": 0.4067820608615875,
+      "rewards/cf_code_reward/mean": -0.8107954263687134,
+      "rewards/cf_code_reward/std": 0.4067820906639099,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 19
+    },
+    {
+      "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": 0.75,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 5671.0,
+      "completions/mean_length": 8034.4375,
+      "completions/mean_terminated_length": 5671.0,
+      "completions/min_length": 5671.0,
+      "completions/min_terminated_length": 5671.0,
+      "epoch": 0.625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 499844.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 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": -2.5,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 6850.0,
+      "completions/mean_length": 4564.25,
+      "completions/mean_terminated_length": 4046.000244140625,
+      "completions/min_length": 1360.0,
+      "completions/min_terminated_length": 1360.0,
+      "epoch": 0.65625,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.08550363834268984,
+      "learning_rate": 1e-06,
+      "loss": -0.055,
+      "num_tokens": 564616.0,
+      "reward": -0.13437500596046448,
+      "reward_std": 0.3423832058906555,
+      "rewards/cf_code_reward/mean": -0.13437500596046448,
+      "rewards/cf_code_reward/std": 0.3423832058906555,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 21
+    },
+    {
+      "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": -3.0,
+      "completions/max_length": 5018.0,
+      "completions/max_terminated_length": 5018.0,
+      "completions/mean_length": 3474.8125,
+      "completions/mean_terminated_length": 3474.8125,
+      "completions/min_length": 2417.0,
+      "completions/min_terminated_length": 2417.0,
+      "epoch": 0.6875,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.28546210458938714,
+      "learning_rate": 1e-06,
+      "loss": 0.0211,
+      "num_tokens": 630053.0,
+      "reward": 0.7673437595367432,
+      "reward_std": 0.5111241936683655,
+      "rewards/cf_code_reward/mean": 0.7673437595367432,
+      "rewards/cf_code_reward/std": 0.5111241936683655,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 22
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.71875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 641525.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 23
+    },
+    {
+      "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": -1.5,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7788.0,
+      "completions/mean_length": 6242.4375,
+      "completions/mean_terminated_length": 5072.7001953125,
+      "completions/min_length": 2712.0,
+      "completions/min_terminated_length": 2712.0,
+      "epoch": 0.75,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2722849336489413,
+      "learning_rate": 1e-06,
+      "loss": -0.1274,
+      "num_tokens": 704684.0,
+      "reward": -0.5212500095367432,
+      "reward_std": 0.4962508976459503,
+      "rewards/cf_code_reward/mean": -0.5212500095367432,
+      "rewards/cf_code_reward/std": 0.4962509572505951,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 24
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.78125,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 719116.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 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": 0.25,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 8087.0,
+      "completions/mean_length": 8041.8125,
+      "completions/mean_terminated_length": 7391.0,
+      "completions/min_length": 6356.0,
+      "completions/min_terminated_length": 6356.0,
+      "epoch": 0.8125,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.2942398936933423,
+      "learning_rate": 1e-06,
+      "loss": -0.1398,
+      "num_tokens": 752985.0,
+      "reward": -0.8091517686843872,
+      "reward_std": 0.4103502035140991,
+      "rewards/cf_code_reward/mean": -0.8091517686843872,
+      "rewards/cf_code_reward/std": 0.4103502035140991,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 26
+    },
+    {
+      "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": 0.75,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7620.0,
+      "completions/mean_length": 8156.25,
+      "completions/mean_terminated_length": 7620.0,
+      "completions/min_length": 7620.0,
+      "completions/min_terminated_length": 7620.0,
+      "epoch": 0.84375,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.19931649636776574,
+      "learning_rate": 1e-06,
+      "loss": -0.0491,
+      "num_tokens": 771469.0,
+      "reward": -0.9437500238418579,
+      "reward_std": 0.22500000894069672,
+      "rewards/cf_code_reward/mean": -0.9437500238418579,
+      "rewards/cf_code_reward/std": 0.22499999403953552,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 27
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.875,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 787325.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 28
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 0.90625,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 801389.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 29
+    },
+    {
+      "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": 0.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 7262.0,
+      "completions/mean_length": 7653.6875,
+      "completions/mean_terminated_length": 6038.75,
+      "completions/min_length": 3702.0,
+      "completions/min_terminated_length": 3702.0,
+      "epoch": 0.9375,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.32699225578745883,
+      "learning_rate": 1e-06,
+      "loss": -0.1449,
+      "num_tokens": 834456.0,
+      "reward": -0.737500011920929,
+      "reward_std": 0.4698108732700348,
+      "rewards/cf_code_reward/mean": -0.737500011920929,
+      "rewards/cf_code_reward/std": 0.4698108732700348,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 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": 0.5,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 4795.0,
+      "completions/mean_length": 7756.4375,
+      "completions/mean_terminated_length": 4707.5,
+      "completions/min_length": 4620.0,
+      "completions/min_terminated_length": 4620.0,
+      "epoch": 0.96875,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 0.331766382104726,
+      "learning_rate": 1e-06,
+      "loss": -0.0646,
+      "num_tokens": 854271.0,
+      "reward": -0.8687499761581421,
+      "reward_std": 0.5249999165534973,
+      "rewards/cf_code_reward/mean": -0.8687499761581421,
+      "rewards/cf_code_reward/std": 0.5250000357627869,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 31
+    },
+    {
+      "clip_ratio/high_max": NaN,
+      "clip_ratio/high_mean": NaN,
+      "clip_ratio/low_mean": NaN,
+      "clip_ratio/low_min": NaN,
+      "clip_ratio/region_mean": NaN,
+      "completions/clipped_ratio": 1.0,
+      "completions/max_length": 8192.0,
+      "completions/max_terminated_length": 0.0,
+      "completions/mean_length": 8192.0,
+      "completions/mean_terminated_length": 0.0,
+      "completions/min_length": 8192.0,
+      "completions/min_terminated_length": 0.0,
+      "epoch": 1.0,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 872095.0,
+      "reward": -1.0,
+      "reward_std": 0.0,
+      "rewards/cf_code_reward/mean": -1.0,
+      "rewards/cf_code_reward/std": 0.0,
+      "rewards/code_format_reward/mean": 0.0,
+      "rewards/code_format_reward/std": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 1.0,
+      "step": 32,
+      "total_flos": 0.0,
+      "train_loss": 0.0,
+      "train_runtime": 1.5617,
+      "train_samples_per_second": 10.245,
+      "train_steps_per_second": 0.64
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 1,
+  "num_input_tokens_seen": 872095,
+  "num_train_epochs": 1,
+  "save_steps": 1,
+  "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": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a76cd0f0a0a542d437e71f48eaa024c3104d61547c601f48353a74ee11c1fb5f
+size 8568