Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-7B
+library_name: transformers
+model_name: RLVR-hotpot
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for RLVR-hotpot
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B).
+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="Byanka/RLVR-hotpot", 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/wbbbb/RLCR/runs/9x9xyyl8) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.48.3
+- Pytorch: 2.5.1
+- Datasets: 4.0.0
+- Tokenizers: 0.21.4
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.48.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76a62b76dbd9ef20edc205117da313c9c91dba68e4e5bec0e3441ef3d98d157d
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8dc8adf57e6824af6e7e5057c73a15ad9bf2be1beb9e449905c41fae1f4e8414
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f113396c3be23c2629dc8e82e6b334f0de1fb4ebb436401a9c38cd865f02eb78
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06866aeef854fc2fe5aeec6854f2d43c8023f3e96e6de3440d250dd4b4a19474
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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 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 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1874 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 50,
+  "global_step": 312,
+  "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": 0.028125,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1430.2,
+      "completions/mean_length": 166.39462890625,
+      "completions/mean_terminated_length": 126.74219970703125,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "epoch": 0.016,
+      "grad_norm": 0.0278764758259058,
+      "learning_rate": 3.1249999999999997e-07,
+      "loss": 0.0308,
+      "num_tokens": 13404233.0,
+      "reward": 0.435546875,
+      "reward_std": 0.3221697866916656,
+      "rewards/accuracy_reward": 0.2009765625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.6701171875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.02431640625,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1472.4,
+      "completions/mean_length": 162.2275390625,
+      "completions/mean_terminated_length": 128.01040344238282,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "epoch": 0.032,
+      "grad_norm": 0.022988498210906982,
+      "learning_rate": 6.249999999999999e-07,
+      "loss": 0.038,
+      "num_tokens": 27022115.0,
+      "reward": 0.462451171875,
+      "reward_std": 0.3004496514797211,
+      "rewards/accuracy_reward": 0.19091796875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.733984375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00947265625,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1380.6,
+      "completions/mean_length": 117.775,
+      "completions/mean_terminated_length": 104.22791290283203,
+      "completions/min_length": 3.6,
+      "completions/min_terminated_length": 3.6,
+      "epoch": 0.048,
+      "grad_norm": 0.025120964273810387,
+      "learning_rate": 9.374999999999999e-07,
+      "loss": 0.0318,
+      "num_tokens": 40133187.0,
+      "reward": 0.583056640625,
+      "reward_std": 0.2110624998807907,
+      "rewards/accuracy_reward": 0.24814453125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.91796875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0048828125,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 1017.2,
+      "completions/mean_length": 87.47548828125,
+      "completions/mean_terminated_length": 80.37409057617188,
+      "completions/min_length": 8.8,
+      "completions/min_terminated_length": 8.8,
+      "epoch": 0.064,
+      "grad_norm": 0.00622530234977603,
+      "learning_rate": 1e-06,
+      "loss": 0.0215,
+      "num_tokens": 52803656.0,
+      "reward": 0.6568359375,
+      "reward_std": 0.15337491929531097,
+      "rewards/accuracy_reward": 0.3328125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.980859375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0005859375,
+      "completions/max_length": 1171.8,
+      "completions/max_terminated_length": 593.8,
+      "completions/mean_length": 73.31455078125,
+      "completions/mean_terminated_length": 72.45734252929688,
+      "completions/min_length": 13.6,
+      "completions/min_terminated_length": 13.6,
+      "epoch": 0.08,
+      "grad_norm": 0.01711602509021759,
+      "learning_rate": 1e-06,
+      "loss": 0.0012,
+      "num_tokens": 65343869.0,
+      "reward": 0.697216796875,
+      "reward_std": 0.1176684021949768,
+      "rewards/accuracy_reward": 0.39697265625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9974609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00029296875,
+      "completions/max_length": 1257.4,
+      "completions/max_terminated_length": 598.0,
+      "completions/mean_length": 72.3849609375,
+      "completions/mean_terminated_length": 71.9559326171875,
+      "completions/min_length": 18.0,
+      "completions/min_terminated_length": 18.0,
+      "epoch": 0.096,
+      "grad_norm": 0.0022409269586205482,
+      "learning_rate": 1e-06,
+      "loss": 0.0002,
+      "num_tokens": 77986019.0,
+      "reward": 0.699267578125,
+      "reward_std": 0.10926563590765,
+      "rewards/accuracy_reward": 0.4005859375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99794921875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.000390625,
+      "completions/max_length": 1141.6,
+      "completions/max_terminated_length": 687.8,
+      "completions/mean_length": 75.8130859375,
+      "completions/mean_terminated_length": 75.24237976074218,
+      "completions/min_length": 19.8,
+      "completions/min_terminated_length": 19.8,
+      "epoch": 0.112,
+      "grad_norm": 0.002861637622117996,
+      "learning_rate": 1e-06,
+      "loss": 0.0027,
+      "num_tokens": 90728137.0,
+      "reward": 0.71552734375,
+      "reward_std": 0.1081365168094635,
+      "rewards/accuracy_reward": 0.43212890625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99892578125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00048828125,
+      "completions/max_length": 1178.2,
+      "completions/max_terminated_length": 563.4,
+      "completions/mean_length": 79.030859375,
+      "completions/mean_terminated_length": 78.31913757324219,
+      "completions/min_length": 20.8,
+      "completions/min_terminated_length": 20.8,
+      "epoch": 0.128,
+      "grad_norm": 0.0015531065873801708,
+      "learning_rate": 1e-06,
+      "loss": 0.0023,
+      "num_tokens": 103310405.0,
+      "reward": 0.713525390625,
+      "reward_std": 0.09464964717626571,
+      "rewards/accuracy_reward": 0.4279296875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99912109375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00048828125,
+      "completions/max_length": 1106.2,
+      "completions/max_terminated_length": 417.8,
+      "completions/mean_length": 77.76083984375,
+      "completions/mean_terminated_length": 77.0487274169922,
+      "completions/min_length": 17.6,
+      "completions/min_terminated_length": 17.6,
+      "epoch": 0.144,
+      "grad_norm": 0.0022233380004763603,
+      "learning_rate": 1e-06,
+      "loss": 0.0017,
+      "num_tokens": 115913428.0,
+      "reward": 0.76220703125,
+      "reward_std": 0.09807199090719224,
+      "rewards/accuracy_reward": 0.52548828125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99892578125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0001953125,
+      "completions/max_length": 853.4,
+      "completions/max_terminated_length": 390.8,
+      "completions/mean_length": 79.07109375,
+      "completions/mean_terminated_length": 78.78670043945313,
+      "completions/min_length": 23.6,
+      "completions/min_terminated_length": 23.6,
+      "epoch": 0.16,
+      "grad_norm": 0.0017749707913026214,
+      "learning_rate": 1e-06,
+      "loss": 0.001,
+      "num_tokens": 128600364.0,
+      "reward": 0.7380859375,
+      "reward_std": 0.09451625794172287,
+      "rewards/accuracy_reward": 0.4765625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.16,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 232.5,
+      "eval_completions/max_terminated_length": 232.5,
+      "eval_completions/mean_length": 82.95326042175293,
+      "eval_completions/mean_terminated_length": 82.95326042175293,
+      "eval_completions/min_length": 28.25,
+      "eval_completions/min_terminated_length": 28.25,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 128600364.0,
+      "eval_reward": 0.69140625,
+      "eval_reward_std": 0.24272222816944122,
+      "eval_rewards/accuracy_reward": 0.3828125,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 13.311,
+      "eval_samples_per_second": 37.563,
+      "eval_steps_per_second": 0.301,
+      "step": 50
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00029296875,
+      "completions/max_length": 834.6,
+      "completions/max_terminated_length": 366.6,
+      "completions/mean_length": 83.1912109375,
+      "completions/mean_terminated_length": 82.76549530029297,
+      "completions/min_length": 21.0,
+      "completions/min_terminated_length": 21.0,
+      "epoch": 0.176,
+      "grad_norm": 0.0019512384897097945,
+      "learning_rate": 1e-06,
+      "loss": 0.0016,
+      "num_tokens": 141545682.0,
+      "reward": 0.733056640625,
+      "reward_std": 0.095227712392807,
+      "rewards/accuracy_reward": 0.46650390625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00048828125,
+      "completions/max_length": 1311.4,
+      "completions/max_terminated_length": 485.4,
+      "completions/mean_length": 86.99189453125,
+      "completions/mean_terminated_length": 86.28425750732421,
+      "completions/min_length": 22.6,
+      "completions/min_terminated_length": 22.6,
+      "epoch": 0.192,
+      "grad_norm": 0.0016324262833222747,
+      "learning_rate": 1e-06,
+      "loss": 0.0021,
+      "num_tokens": 154107615.0,
+      "reward": 0.74697265625,
+      "reward_std": 0.08921304196119309,
+      "rewards/accuracy_reward": 0.4947265625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99921875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 60
+    },
+    {
+      "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": 0.000390625,
+      "completions/max_length": 1086.2,
+      "completions/max_terminated_length": 592.6,
+      "completions/mean_length": 90.79443359375,
+      "completions/mean_terminated_length": 90.22920989990234,
+      "completions/min_length": 28.2,
+      "completions/min_terminated_length": 28.2,
+      "epoch": 0.208,
+      "grad_norm": 0.0016499038320034742,
+      "learning_rate": 1e-06,
+      "loss": 0.0023,
+      "num_tokens": 166925894.0,
+      "reward": 0.77353515625,
+      "reward_std": 0.08650225400924683,
+      "rewards/accuracy_reward": 0.54765625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9994140625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 65
+    },
+    {
+      "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": 0.0009765625,
+      "completions/max_length": 1338.6,
+      "completions/max_terminated_length": 731.0,
+      "completions/mean_length": 96.20087890625,
+      "completions/mean_terminated_length": 94.7965301513672,
+      "completions/min_length": 28.6,
+      "completions/min_terminated_length": 28.6,
+      "epoch": 0.224,
+      "grad_norm": 0.001517058233730495,
+      "learning_rate": 1e-06,
+      "loss": 0.002,
+      "num_tokens": 179920495.0,
+      "reward": 0.74716796875,
+      "reward_std": 0.08538677096366883,
+      "rewards/accuracy_reward": 0.49560546875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99873046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 70
+    },
+    {
+      "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": 0.00107421875,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 574.4,
+      "completions/mean_length": 97.76240234375,
+      "completions/mean_terminated_length": 96.21627960205078,
+      "completions/min_length": 25.4,
+      "completions/min_terminated_length": 25.4,
+      "epoch": 0.24,
+      "grad_norm": 0.0017738911556079984,
+      "learning_rate": 1e-06,
+      "loss": 0.0028,
+      "num_tokens": 193029582.0,
+      "reward": 0.77578125,
+      "reward_std": 0.09508010596036912,
+      "rewards/accuracy_reward": 0.55283203125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99873046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 75
+    },
+    {
+      "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": 0.0009765625,
+      "completions/max_length": 1319.4,
+      "completions/max_terminated_length": 417.2,
+      "completions/mean_length": 96.47294921875,
+      "completions/mean_terminated_length": 95.06647644042968,
+      "completions/min_length": 30.6,
+      "completions/min_terminated_length": 30.6,
+      "epoch": 0.256,
+      "grad_norm": 0.0015991576947271824,
+      "learning_rate": 1e-06,
+      "loss": 0.0029,
+      "num_tokens": 205928601.0,
+      "reward": 0.75869140625,
+      "reward_std": 0.08824991285800934,
+      "rewards/accuracy_reward": 0.518359375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 80
+    },
+    {
+      "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": 0.00087890625,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 459.0,
+      "completions/mean_length": 99.259765625,
+      "completions/mean_terminated_length": 97.99633331298828,
+      "completions/min_length": 31.0,
+      "completions/min_terminated_length": 31.0,
+      "epoch": 0.272,
+      "grad_norm": 0.0014954438665881753,
+      "learning_rate": 1e-06,
+      "loss": 0.0026,
+      "num_tokens": 218767037.0,
+      "reward": 0.7568359375,
+      "reward_std": 0.08405127227306367,
+      "rewards/accuracy_reward": 0.51484375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.998828125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 85
+    },
+    {
+      "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": 0.00068359375,
+      "completions/max_length": 1149.6,
+      "completions/max_terminated_length": 682.4,
+      "completions/mean_length": 94.7064453125,
+      "completions/mean_terminated_length": 93.72140197753906,
+      "completions/min_length": 32.2,
+      "completions/min_terminated_length": 32.2,
+      "epoch": 0.288,
+      "grad_norm": 0.0017134748632088304,
+      "learning_rate": 1e-06,
+      "loss": 0.0026,
+      "num_tokens": 231551327.0,
+      "reward": 0.7654296875,
+      "reward_std": 0.08652912825345993,
+      "rewards/accuracy_reward": 0.53154296875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99931640625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 90
+    },
+    {
+      "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": 0.00078125,
+      "completions/max_length": 1091.0,
+      "completions/max_terminated_length": 413.2,
+      "completions/mean_length": 94.5794921875,
+      "completions/mean_terminated_length": 93.45206604003906,
+      "completions/min_length": 34.4,
+      "completions/min_terminated_length": 34.4,
+      "epoch": 0.304,
+      "grad_norm": 0.002114097587764263,
+      "learning_rate": 1e-06,
+      "loss": 0.0031,
+      "num_tokens": 244306093.0,
+      "reward": 0.762939453125,
+      "reward_std": 0.08613481372594833,
+      "rewards/accuracy_reward": 0.52705078125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.998828125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 95
+    },
+    {
+      "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": 0.0005859375,
+      "completions/max_length": 1399.2,
+      "completions/max_terminated_length": 458.8,
+      "completions/mean_length": 91.70283203125,
+      "completions/mean_terminated_length": 90.85653686523438,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 0.32,
+      "grad_norm": 0.00154271034989506,
+      "learning_rate": 1e-06,
+      "loss": 0.0023,
+      "num_tokens": 257190154.0,
+      "reward": 0.77060546875,
+      "reward_std": 0.06635084152221679,
+      "rewards/accuracy_reward": 0.5419921875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99921875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.32,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 232.5,
+      "eval_completions/max_terminated_length": 232.5,
+      "eval_completions/mean_length": 93.95743560791016,
+      "eval_completions/mean_terminated_length": 93.95743560791016,
+      "eval_completions/min_length": 41.75,
+      "eval_completions/min_terminated_length": 41.75,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 257190154.0,
+      "eval_reward": 0.712890625,
+      "eval_reward_std": 0.2481144778430462,
+      "eval_rewards/accuracy_reward": 0.42578125,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 14.235,
+      "eval_samples_per_second": 35.125,
+      "eval_steps_per_second": 0.281,
+      "step": 100
+    },
+    {
+      "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": 0.00146484375,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 624.2,
+      "completions/mean_length": 94.64306640625,
+      "completions/mean_terminated_length": 92.5290313720703,
+      "completions/min_length": 30.4,
+      "completions/min_terminated_length": 30.4,
+      "epoch": 0.336,
+      "grad_norm": 0.001522217644378543,
+      "learning_rate": 1e-06,
+      "loss": 0.0043,
+      "num_tokens": 269738051.0,
+      "reward": 0.77568359375,
+      "reward_std": 0.07683707624673844,
+      "rewards/accuracy_reward": 0.5529296875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9984375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 105
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.001171875,
+      "completions/max_length": 1307.4,
+      "completions/max_terminated_length": 435.8,
+      "completions/mean_length": 94.1294921875,
+      "completions/mean_terminated_length": 92.43776245117188,
+      "completions/min_length": 21.8,
+      "completions/min_terminated_length": 21.8,
+      "epoch": 0.352,
+      "grad_norm": 0.001526491018012166,
+      "learning_rate": 1e-06,
+      "loss": 0.0039,
+      "num_tokens": 282818673.0,
+      "reward": 0.745751953125,
+      "reward_std": 0.08200332224369049,
+      "rewards/accuracy_reward": 0.49306640625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9984375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 110
+    },
+    {
+      "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": 0.0013671875,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 588.4,
+      "completions/mean_length": 92.6953125,
+      "completions/mean_terminated_length": 90.7186294555664,
+      "completions/min_length": 30.6,
+      "completions/min_terminated_length": 30.6,
+      "epoch": 0.368,
+      "grad_norm": 0.0013903952203691006,
+      "learning_rate": 1e-06,
+      "loss": 0.0039,
+      "num_tokens": 295689665.0,
+      "reward": 0.754443359375,
+      "reward_std": 0.07026491463184356,
+      "rewards/accuracy_reward": 0.5103515625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99853515625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 115
+    },
+    {
+      "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": 0.0009765625,
+      "completions/max_length": 1296.6,
+      "completions/max_terminated_length": 561.2,
+      "completions/mean_length": 91.94736328125,
+      "completions/mean_terminated_length": 90.53576354980468,
+      "completions/min_length": 32.0,
+      "completions/min_terminated_length": 32.0,
+      "epoch": 0.384,
+      "grad_norm": 0.0018187090754508972,
+      "learning_rate": 1e-06,
+      "loss": 0.0033,
+      "num_tokens": 308344038.0,
+      "reward": 0.7708984375,
+      "reward_std": 0.07117158472537995,
+      "rewards/accuracy_reward": 0.54296875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.998828125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 120
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.001171875,
+      "completions/max_length": 1305.0,
+      "completions/max_terminated_length": 520.2,
+      "completions/mean_length": 89.5787109375,
+      "completions/mean_terminated_length": 87.88221435546875,
+      "completions/min_length": 29.4,
+      "completions/min_terminated_length": 29.4,
+      "epoch": 0.4,
+      "grad_norm": 0.0016340231522917747,
+      "learning_rate": 1e-06,
+      "loss": 0.0038,
+      "num_tokens": 321154092.0,
+      "reward": 0.76103515625,
+      "reward_std": 0.07767283618450165,
+      "rewards/accuracy_reward": 0.52333984375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99873046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 125
+    },
+    {
+      "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": 0.00068359375,
+      "completions/max_length": 1244.4,
+      "completions/max_terminated_length": 590.0,
+      "completions/mean_length": 89.6955078125,
+      "completions/mean_terminated_length": 88.70513153076172,
+      "completions/min_length": 31.8,
+      "completions/min_terminated_length": 31.8,
+      "epoch": 0.416,
+      "grad_norm": 0.0015821981942281127,
+      "learning_rate": 1e-06,
+      "loss": 0.0019,
+      "num_tokens": 333810078.0,
+      "reward": 0.764208984375,
+      "reward_std": 0.06756853386759758,
+      "rewards/accuracy_reward": 0.5291015625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99931640625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 130
+    },
+    {
+      "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": 0.00048828125,
+      "completions/max_length": 1174.4,
+      "completions/max_terminated_length": 537.0,
+      "completions/mean_length": 90.36181640625,
+      "completions/mean_terminated_length": 89.65568542480469,
+      "completions/min_length": 35.0,
+      "completions/min_terminated_length": 35.0,
+      "epoch": 0.432,
+      "grad_norm": 0.0014525202568620443,
+      "learning_rate": 1e-06,
+      "loss": 0.0025,
+      "num_tokens": 346606039.0,
+      "reward": 0.7806640625,
+      "reward_std": 0.06507465690374374,
+      "rewards/accuracy_reward": 0.56181640625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99951171875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 135
+    },
+    {
+      "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": 0.00068359375,
+      "completions/max_length": 1301.0,
+      "completions/max_terminated_length": 503.6,
+      "completions/mean_length": 94.90302734375,
+      "completions/mean_terminated_length": 93.91733856201172,
+      "completions/min_length": 42.2,
+      "completions/min_terminated_length": 42.2,
+      "epoch": 0.448,
+      "grad_norm": 0.0015080425655469298,
+      "learning_rate": 1e-06,
+      "loss": 0.0023,
+      "num_tokens": 359386966.0,
+      "reward": 0.76650390625,
+      "reward_std": 0.069513601064682,
+      "rewards/accuracy_reward": 0.53369140625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99931640625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 140
+    },
+    {
+      "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": 0.00185546875,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 541.6,
+      "completions/mean_length": 99.85595703125,
+      "completions/mean_terminated_length": 97.19031372070313,
+      "completions/min_length": 40.8,
+      "completions/min_terminated_length": 40.8,
+      "epoch": 0.464,
+      "grad_norm": 0.0010223939316347241,
+      "learning_rate": 1e-06,
+      "loss": 0.0047,
+      "num_tokens": 372436627.0,
+      "reward": 0.7345703125,
+      "reward_std": 0.05768234580755234,
+      "rewards/accuracy_reward": 0.47109375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.998046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 145
+    },
+    {
+      "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": 0.00068359375,
+      "completions/max_length": 1303.2,
+      "completions/max_terminated_length": 405.6,
+      "completions/mean_length": 98.14833984375,
+      "completions/mean_terminated_length": 97.16446533203126,
+      "completions/min_length": 43.8,
+      "completions/min_terminated_length": 43.8,
+      "epoch": 0.48,
+      "grad_norm": 0.0016905076336115599,
+      "learning_rate": 1e-06,
+      "loss": 0.0023,
+      "num_tokens": 385346018.0,
+      "reward": 0.769873046875,
+      "reward_std": 0.07736360728740692,
+      "rewards/accuracy_reward": 0.5408203125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99892578125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.48,
+      "eval_completions/clipped_ratio": 0.001953125,
+      "eval_completions/max_length": 582.5,
+      "eval_completions/max_terminated_length": 264.0,
+      "eval_completions/mean_length": 101.61126136779785,
+      "eval_completions/mean_terminated_length": 98.80445098876953,
+      "eval_completions/min_length": 51.25,
+      "eval_completions/min_terminated_length": 51.25,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 385346018.0,
+      "eval_reward": 0.7265625,
+      "eval_reward_std": 0.2514254078269005,
+      "eval_rewards/accuracy_reward": 0.455078125,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 0.998046875,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 24.3286,
+      "eval_samples_per_second": 20.552,
+      "eval_steps_per_second": 0.164,
+      "step": 150
+    },
+    {
+      "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": 0.00078125,
+      "completions/max_length": 1536.0,
+      "completions/max_terminated_length": 386.0,
+      "completions/mean_length": 97.898046875,
+      "completions/mean_terminated_length": 96.7735092163086,
+      "completions/min_length": 40.2,
+      "completions/min_terminated_length": 40.2,
+      "epoch": 0.496,
+      "grad_norm": 0.001528796274214983,
+      "learning_rate": 1e-06,
+      "loss": 0.0029,
+      "num_tokens": 398512654.0,
+      "reward": 0.7744140625,
+      "reward_std": 0.0720748171210289,
+      "rewards/accuracy_reward": 0.549609375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99921875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 155
+    },
+    {
+      "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": 0.00048828125,
+      "completions/max_length": 1317.0,
+      "completions/max_terminated_length": 399.8,
+      "completions/mean_length": 95.37158203125,
+      "completions/mean_terminated_length": 94.66787719726562,
+      "completions/min_length": 40.8,
+      "completions/min_terminated_length": 40.8,
+      "epoch": 0.512,
+      "grad_norm": 0.00132983538787812,
+      "learning_rate": 1e-06,
+      "loss": 0.0025,
+      "num_tokens": 411491243.0,
+      "reward": 0.779931640625,
+      "reward_std": 0.06670133695006371,
+      "rewards/accuracy_reward": 0.56044921875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9994140625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 160
+    },
+    {
+      "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": 0.0009765625,
+      "completions/max_length": 1341.4,
+      "completions/max_terminated_length": 662.8,
+      "completions/mean_length": 96.72470703125,
+      "completions/mean_terminated_length": 95.31717834472656,
+      "completions/min_length": 42.0,
+      "completions/min_terminated_length": 42.0,
+      "epoch": 0.528,
+      "grad_norm": 0.001326797646470368,
+      "learning_rate": 1e-06,
+      "loss": 0.0037,
+      "num_tokens": 424367560.0,
+      "reward": 0.77578125,
+      "reward_std": 0.06582950651645661,
+      "rewards/accuracy_reward": 0.5525390625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 165
+    },
+    {
+      "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": 0.0001953125,
+      "completions/max_length": 699.4,
+      "completions/max_terminated_length": 456.6,
+      "completions/mean_length": 93.36513671875,
+      "completions/mean_terminated_length": 93.0830810546875,
+      "completions/min_length": 34.2,
+      "completions/min_terminated_length": 34.2,
+      "epoch": 0.544,
+      "grad_norm": 0.0017570438794791698,
+      "learning_rate": 1e-06,
+      "loss": 0.0018,
+      "num_tokens": 437343523.0,
+      "reward": 0.796533203125,
+      "reward_std": 0.07356481105089188,
+      "rewards/accuracy_reward": 0.593359375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99970703125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 170
+    },
+    {
+      "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": 444.8,
+      "completions/max_terminated_length": 444.8,
+      "completions/mean_length": 91.45390625,
+      "completions/mean_terminated_length": 91.45390625,
+      "completions/min_length": 41.8,
+      "completions/min_terminated_length": 41.8,
+      "epoch": 0.56,
+      "grad_norm": 0.0014896654756739736,
+      "learning_rate": 1e-06,
+      "loss": 0.0009,
+      "num_tokens": 449957739.0,
+      "reward": 0.76611328125,
+      "reward_std": 0.060523012280464174,
+      "rewards/accuracy_reward": 0.53232421875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 175
+    },
+    {
+      "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": 0.000390625,
+      "completions/max_length": 1289.4,
+      "completions/max_terminated_length": 382.2,
+      "completions/mean_length": 90.7419921875,
+      "completions/mean_terminated_length": 90.17736206054687,
+      "completions/min_length": 43.0,
+      "completions/min_terminated_length": 43.0,
+      "epoch": 0.576,
+      "grad_norm": 0.0016016842564567924,
+      "learning_rate": 1e-06,
+      "loss": 0.0008,
+      "num_tokens": 462929881.0,
+      "reward": 0.764111328125,
+      "reward_std": 0.05608753189444542,
+      "rewards/accuracy_reward": 0.52861328125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 180
+    },
+    {
+      "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": 9.765625e-05,
+      "completions/max_length": 603.8,
+      "completions/max_terminated_length": 356.0,
+      "completions/mean_length": 91.03701171875,
+      "completions/mean_terminated_length": 90.8958251953125,
+      "completions/min_length": 42.6,
+      "completions/min_terminated_length": 42.6,
+      "epoch": 0.592,
+      "grad_norm": 0.0013300231657922268,
+      "learning_rate": 1e-06,
+      "loss": 0.0014,
+      "num_tokens": 475886132.0,
+      "reward": 0.763671875,
+      "reward_std": 0.06121245920658112,
+      "rewards/accuracy_reward": 0.52744140625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 185
+    },
+    {
+      "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": 0.00029296875,
+      "completions/max_length": 831.0,
+      "completions/max_terminated_length": 363.8,
+      "completions/mean_length": 94.77607421875,
+      "completions/mean_terminated_length": 94.35356140136719,
+      "completions/min_length": 42.6,
+      "completions/min_terminated_length": 42.6,
+      "epoch": 0.608,
+      "grad_norm": 0.001449022558517754,
+      "learning_rate": 1e-06,
+      "loss": 0.0015,
+      "num_tokens": 488712447.0,
+      "reward": 0.776220703125,
+      "reward_std": 0.055175574868917464,
+      "rewards/accuracy_reward": 0.55283203125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 190
+    },
+    {
+      "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": 9.765625e-05,
+      "completions/max_length": 719.8,
+      "completions/max_terminated_length": 511.4,
+      "completions/mean_length": 95.49326171875,
+      "completions/mean_terminated_length": 95.3530044555664,
+      "completions/min_length": 42.2,
+      "completions/min_terminated_length": 42.2,
+      "epoch": 0.624,
+      "grad_norm": 0.0016013348940759897,
+      "learning_rate": 1e-06,
+      "loss": 0.0005,
+      "num_tokens": 501890522.0,
+      "reward": 0.770703125,
+      "reward_std": 0.06375713348388672,
+      "rewards/accuracy_reward": 0.54150390625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 195
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.001171875,
+      "completions/max_length": 1310.4,
+      "completions/max_terminated_length": 450.2,
+      "completions/mean_length": 97.82939453125,
+      "completions/mean_terminated_length": 96.14148406982422,
+      "completions/min_length": 43.8,
+      "completions/min_terminated_length": 43.8,
+      "epoch": 0.64,
+      "grad_norm": 0.00144854630343616,
+      "learning_rate": 1e-06,
+      "loss": 0.0031,
+      "num_tokens": 515091303.0,
+      "reward": 0.79462890625,
+      "reward_std": 0.05500866025686264,
+      "rewards/accuracy_reward": 0.5904296875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.998828125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.64,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 226.5,
+      "eval_completions/max_terminated_length": 226.5,
+      "eval_completions/mean_length": 97.45433807373047,
+      "eval_completions/mean_terminated_length": 97.45433807373047,
+      "eval_completions/min_length": 48.5,
+      "eval_completions/min_terminated_length": 48.5,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 515091303.0,
+      "eval_reward": 0.7216796875,
+      "eval_reward_std": 0.24690637737512589,
+      "eval_rewards/accuracy_reward": 0.443359375,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 14.5533,
+      "eval_samples_per_second": 34.357,
+      "eval_steps_per_second": 0.275,
+      "step": 200
+    },
+    {
+      "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": 0.0001953125,
+      "completions/max_length": 809.0,
+      "completions/max_terminated_length": 348.2,
+      "completions/mean_length": 95.0333984375,
+      "completions/mean_terminated_length": 94.75228271484374,
+      "completions/min_length": 42.4,
+      "completions/min_terminated_length": 42.4,
+      "epoch": 0.656,
+      "grad_norm": 0.0017163316952064633,
+      "learning_rate": 1e-06,
+      "loss": 0.0013,
+      "num_tokens": 527777309.0,
+      "reward": 0.75673828125,
+      "reward_std": 0.060856021195650103,
+      "rewards/accuracy_reward": 0.513671875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9998046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 205
+    },
+    {
+      "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": 0.000390625,
+      "completions/max_length": 828.2,
+      "completions/max_terminated_length": 388.2,
+      "completions/mean_length": 95.4216796875,
+      "completions/mean_terminated_length": 94.85912628173828,
+      "completions/min_length": 41.4,
+      "completions/min_terminated_length": 41.4,
+      "epoch": 0.672,
+      "grad_norm": 0.0013491360004991293,
+      "learning_rate": 1e-06,
+      "loss": 0.0013,
+      "num_tokens": 540524187.0,
+      "reward": 0.768115234375,
+      "reward_std": 0.05722193792462349,
+      "rewards/accuracy_reward": 0.53662109375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 210
+    },
+    {
+      "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": 0.000390625,
+      "completions/max_length": 1050.6,
+      "completions/max_terminated_length": 373.2,
+      "completions/mean_length": 95.3826171875,
+      "completions/mean_terminated_length": 94.82014465332031,
+      "completions/min_length": 43.8,
+      "completions/min_terminated_length": 43.8,
+      "epoch": 0.688,
+      "grad_norm": 0.0017077566590160131,
+      "learning_rate": 1e-06,
+      "loss": 0.0011,
+      "num_tokens": 553311145.0,
+      "reward": 0.779443359375,
+      "reward_std": 0.06311368122696877,
+      "rewards/accuracy_reward": 0.55927734375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 215
+    },
+    {
+      "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": 0.000390625,
+      "completions/max_length": 810.0,
+      "completions/max_terminated_length": 377.8,
+      "completions/mean_length": 90.67568359375,
+      "completions/mean_terminated_length": 90.11159210205078,
+      "completions/min_length": 42.6,
+      "completions/min_terminated_length": 42.6,
+      "epoch": 0.704,
+      "grad_norm": 0.0018953669350594282,
+      "learning_rate": 1e-06,
+      "loss": 0.001,
+      "num_tokens": 565962128.0,
+      "reward": 0.78388671875,
+      "reward_std": 0.05257489308714867,
+      "rewards/accuracy_reward": 0.5681640625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 220
+    },
+    {
+      "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": 0.0005859375,
+      "completions/max_length": 1065.6,
+      "completions/max_terminated_length": 403.6,
+      "completions/mean_length": 91.39638671875,
+      "completions/mean_terminated_length": 90.54814147949219,
+      "completions/min_length": 43.6,
+      "completions/min_terminated_length": 43.6,
+      "epoch": 0.72,
+      "grad_norm": 0.0019243984716013074,
+      "learning_rate": 1e-06,
+      "loss": 0.0025,
+      "num_tokens": 578764203.0,
+      "reward": 0.790576171875,
+      "reward_std": 0.05948638021945953,
+      "rewards/accuracy_reward": 0.58173828125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9994140625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 225
+    },
+    {
+      "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": 0.00078125,
+      "completions/max_length": 1299.8,
+      "completions/max_terminated_length": 342.0,
+      "completions/mean_length": 91.9408203125,
+      "completions/mean_terminated_length": 90.81210021972656,
+      "completions/min_length": 45.0,
+      "completions/min_terminated_length": 45.0,
+      "epoch": 0.736,
+      "grad_norm": 0.0013582052197307348,
+      "learning_rate": 1e-06,
+      "loss": 0.002,
+      "num_tokens": 591501581.0,
+      "reward": 0.79150390625,
+      "reward_std": 0.05623424053192139,
+      "rewards/accuracy_reward": 0.5837890625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99921875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 230
+    },
+    {
+      "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": 0.0001953125,
+      "completions/max_length": 565.0,
+      "completions/max_terminated_length": 327.2,
+      "completions/mean_length": 91.51416015625,
+      "completions/mean_terminated_length": 91.23197326660156,
+      "completions/min_length": 43.8,
+      "completions/min_terminated_length": 43.8,
+      "epoch": 0.752,
+      "grad_norm": 0.0015649450942873955,
+      "learning_rate": 1e-06,
+      "loss": 0.0001,
+      "num_tokens": 604522206.0,
+      "reward": 0.7857421875,
+      "reward_std": 0.05413587838411331,
+      "rewards/accuracy_reward": 0.5716796875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9998046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 235
+    },
+    {
+      "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": 0.000390625,
+      "completions/max_length": 646.2,
+      "completions/max_terminated_length": 607.4,
+      "completions/mean_length": 94.9529296875,
+      "completions/mean_terminated_length": 94.39071350097656,
+      "completions/min_length": 42.4,
+      "completions/min_terminated_length": 42.4,
+      "epoch": 0.768,
+      "grad_norm": 0.0017648260109126568,
+      "learning_rate": 1e-06,
+      "loss": 0.0017,
+      "num_tokens": 617283548.0,
+      "reward": 0.761279296875,
+      "reward_std": 0.057571640610694884,
+      "rewards/accuracy_reward": 0.52294921875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 240
+    },
+    {
+      "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": 413.6,
+      "completions/max_terminated_length": 413.6,
+      "completions/mean_length": 93.616015625,
+      "completions/mean_terminated_length": 93.616015625,
+      "completions/min_length": 43.8,
+      "completions/min_terminated_length": 43.8,
+      "epoch": 0.784,
+      "grad_norm": 0.0011762650683522224,
+      "learning_rate": 1e-06,
+      "loss": 0.0006,
+      "num_tokens": 630272864.0,
+      "reward": 0.7892578125,
+      "reward_std": 0.05626345500349998,
+      "rewards/accuracy_reward": 0.578515625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 245
+    },
+    {
+      "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": 326.8,
+      "completions/max_terminated_length": 326.8,
+      "completions/mean_length": 92.14990234375,
+      "completions/mean_terminated_length": 92.14990234375,
+      "completions/min_length": 44.6,
+      "completions/min_terminated_length": 44.6,
+      "epoch": 0.8,
+      "grad_norm": 0.0013073732843622565,
+      "learning_rate": 1e-06,
+      "loss": 0.0002,
+      "num_tokens": 643083359.0,
+      "reward": 0.804052734375,
+      "reward_std": 0.05071377567946911,
+      "rewards/accuracy_reward": 0.60810546875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.8,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 236.75,
+      "eval_completions/max_terminated_length": 236.75,
+      "eval_completions/mean_length": 91.57341003417969,
+      "eval_completions/mean_terminated_length": 91.57341003417969,
+      "eval_completions/min_length": 49.5,
+      "eval_completions/min_terminated_length": 49.5,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 643083359.0,
+      "eval_reward": 0.7265625,
+      "eval_reward_std": 0.24742106348276138,
+      "eval_rewards/accuracy_reward": 0.453125,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 14.2768,
+      "eval_samples_per_second": 35.022,
+      "eval_steps_per_second": 0.28,
+      "step": 250
+    },
+    {
+      "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": 0.0001953125,
+      "completions/max_length": 588.8,
+      "completions/max_terminated_length": 456.2,
+      "completions/mean_length": 89.20595703125,
+      "completions/mean_terminated_length": 88.92289428710937,
+      "completions/min_length": 43.2,
+      "completions/min_terminated_length": 43.2,
+      "epoch": 0.816,
+      "grad_norm": 0.0019169868901371956,
+      "learning_rate": 1e-06,
+      "loss": 0.0008,
+      "num_tokens": 655952316.0,
+      "reward": 0.805029296875,
+      "reward_std": 0.054716046899557114,
+      "rewards/accuracy_reward": 0.61025390625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9998046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 255
+    },
+    {
+      "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": 462.6,
+      "completions/max_terminated_length": 462.6,
+      "completions/mean_length": 91.78896484375,
+      "completions/mean_terminated_length": 91.78896484375,
+      "completions/min_length": 42.0,
+      "completions/min_terminated_length": 42.0,
+      "epoch": 0.832,
+      "grad_norm": 0.0014281836338341236,
+      "learning_rate": 1e-06,
+      "loss": 0.0002,
+      "num_tokens": 668756907.0,
+      "reward": 0.790087890625,
+      "reward_std": 0.0539084292948246,
+      "rewards/accuracy_reward": 0.58017578125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 260
+    },
+    {
+      "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": 9.765625e-05,
+      "completions/max_length": 663.6,
+      "completions/max_terminated_length": 417.8,
+      "completions/mean_length": 91.91787109375,
+      "completions/mean_terminated_length": 91.77665557861329,
+      "completions/min_length": 45.4,
+      "completions/min_terminated_length": 45.4,
+      "epoch": 0.848,
+      "grad_norm": 0.001417965511791408,
+      "learning_rate": 1e-06,
+      "loss": 0.0009,
+      "num_tokens": 681568834.0,
+      "reward": 0.77236328125,
+      "reward_std": 0.0536438025534153,
+      "rewards/accuracy_reward": 0.54482421875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 265
+    },
+    {
+      "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": 0.000390625,
+      "completions/max_length": 1059.4,
+      "completions/max_terminated_length": 416.2,
+      "completions/mean_length": 94.8748046875,
+      "completions/mean_terminated_length": 94.31214294433593,
+      "completions/min_length": 42.8,
+      "completions/min_terminated_length": 42.8,
+      "epoch": 0.864,
+      "grad_norm": 0.0025267351884394884,
+      "learning_rate": 1e-06,
+      "loss": 0.0014,
+      "num_tokens": 694383488.0,
+      "reward": 0.809716796875,
+      "reward_std": 0.05303701683878899,
+      "rewards/accuracy_reward": 0.61982421875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999609375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 270
+    },
+    {
+      "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": 9.765625e-05,
+      "completions/max_length": 592.0,
+      "completions/max_terminated_length": 383.0,
+      "completions/mean_length": 94.92939453125,
+      "completions/mean_terminated_length": 94.78859100341796,
+      "completions/min_length": 45.4,
+      "completions/min_terminated_length": 45.4,
+      "epoch": 0.88,
+      "grad_norm": 0.001522132777608931,
+      "learning_rate": 1e-06,
+      "loss": 0.0011,
+      "num_tokens": 707358957.0,
+      "reward": 0.760546875,
+      "reward_std": 0.055512601137161256,
+      "rewards/accuracy_reward": 0.52119140625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 275
+    },
+    {
+      "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": 9.765625e-05,
+      "completions/max_length": 572.6,
+      "completions/max_terminated_length": 337.0,
+      "completions/mean_length": 97.50546875,
+      "completions/mean_terminated_length": 97.36535034179687,
+      "completions/min_length": 44.0,
+      "completions/min_terminated_length": 44.0,
+      "epoch": 0.896,
+      "grad_norm": 0.0011945873266085982,
+      "learning_rate": 1e-06,
+      "loss": 0.001,
+      "num_tokens": 720324581.0,
+      "reward": 0.784912109375,
+      "reward_std": 0.04334753602743149,
+      "rewards/accuracy_reward": 0.569921875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 280
+    },
+    {
+      "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": 0.0001953125,
+      "completions/max_length": 960.6,
+      "completions/max_terminated_length": 469.8,
+      "completions/mean_length": 97.699609375,
+      "completions/mean_terminated_length": 97.41859893798828,
+      "completions/min_length": 42.0,
+      "completions/min_terminated_length": 42.0,
+      "epoch": 0.912,
+      "grad_norm": 0.0012196388561278582,
+      "learning_rate": 1e-06,
+      "loss": 0.0008,
+      "num_tokens": 733232641.0,
+      "reward": 0.781201171875,
+      "reward_std": 0.0503702849149704,
+      "rewards/accuracy_reward": 0.56259765625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9998046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 285
+    },
+    {
+      "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": 9.765625e-05,
+      "completions/max_length": 527.2,
+      "completions/max_terminated_length": 509.0,
+      "completions/mean_length": 94.194921875,
+      "completions/mean_terminated_length": 94.05436248779297,
+      "completions/min_length": 39.6,
+      "completions/min_terminated_length": 39.6,
+      "epoch": 0.928,
+      "grad_norm": 0.0010627944720909,
+      "learning_rate": 1e-06,
+      "loss": 0.0004,
+      "num_tokens": 746080333.0,
+      "reward": 0.77783203125,
+      "reward_std": 0.0477489285171032,
+      "rewards/accuracy_reward": 0.55576171875,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 290
+    },
+    {
+      "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": 0.0001953125,
+      "completions/max_length": 830.8,
+      "completions/max_terminated_length": 384.8,
+      "completions/mean_length": 96.19130859375,
+      "completions/mean_terminated_length": 95.91045227050782,
+      "completions/min_length": 41.0,
+      "completions/min_terminated_length": 41.0,
+      "epoch": 0.944,
+      "grad_norm": 0.0012808856554329395,
+      "learning_rate": 1e-06,
+      "loss": 0.0014,
+      "num_tokens": 758897076.0,
+      "reward": 0.774853515625,
+      "reward_std": 0.06085398942232132,
+      "rewards/accuracy_reward": 0.54990234375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9998046875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 295
+    },
+    {
+      "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": 9.765625e-05,
+      "completions/max_length": 618.6,
+      "completions/max_terminated_length": 385.6,
+      "completions/mean_length": 95.019921875,
+      "completions/mean_terminated_length": 94.87908020019532,
+      "completions/min_length": 41.6,
+      "completions/min_terminated_length": 41.6,
+      "epoch": 0.96,
+      "grad_norm": 0.001602579141035676,
+      "learning_rate": 1e-06,
+      "loss": 0.0006,
+      "num_tokens": 771666720.0,
+      "reward": 0.77060546875,
+      "reward_std": 0.047741709649562834,
+      "rewards/accuracy_reward": 0.54130859375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.96,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 212.5,
+      "eval_completions/max_terminated_length": 212.5,
+      "eval_completions/mean_length": 94.41190719604492,
+      "eval_completions/mean_terminated_length": 94.41190719604492,
+      "eval_completions/min_length": 51.0,
+      "eval_completions/min_terminated_length": 51.0,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 771666720.0,
+      "eval_reward": 0.7158203125,
+      "eval_reward_std": 0.24653732031583786,
+      "eval_rewards/accuracy_reward": 0.431640625,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 13.6738,
+      "eval_samples_per_second": 36.566,
+      "eval_steps_per_second": 0.293,
+      "step": 300
+    },
+    {
+      "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": 0.0005859375,
+      "completions/max_length": 1112.6,
+      "completions/max_terminated_length": 416.8,
+      "completions/mean_length": 95.6703125,
+      "completions/mean_terminated_length": 94.82695617675782,
+      "completions/min_length": 39.8,
+      "completions/min_terminated_length": 39.8,
+      "epoch": 0.976,
+      "grad_norm": 0.0012756388168781996,
+      "learning_rate": 1e-06,
+      "loss": 0.0017,
+      "num_tokens": 784363824.0,
+      "reward": 0.789599609375,
+      "reward_std": 0.05751314386725426,
+      "rewards/accuracy_reward": 0.57978515625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9994140625,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 305
+    },
+    {
+      "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": 0.00029296875,
+      "completions/max_length": 813.6,
+      "completions/max_terminated_length": 335.2,
+      "completions/mean_length": 93.523046875,
+      "completions/mean_terminated_length": 93.10098266601562,
+      "completions/min_length": 41.8,
+      "completions/min_terminated_length": 41.8,
+      "epoch": 0.992,
+      "grad_norm": 0.0012513543479144573,
+      "learning_rate": 1e-06,
+      "loss": 0.001,
+      "num_tokens": 797306300.0,
+      "reward": 0.778857421875,
+      "reward_std": 0.04584160037338734,
+      "rewards/accuracy_reward": 0.5580078125,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99970703125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 310
+    },
+    {
+      "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": 341.0,
+      "completions/max_terminated_length": 341.0,
+      "completions/mean_length": 92.21929550170898,
+      "completions/mean_terminated_length": 92.21929550170898,
+      "completions/min_length": 40.5,
+      "completions/min_terminated_length": 40.5,
+      "epoch": 0.9984,
+      "num_tokens": 802441496.0,
+      "reward": 0.784912109375,
+      "reward_std": 0.055518221110105515,
+      "rewards/accuracy_reward": 0.570556640625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.999267578125,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 312,
+      "total_flos": 0.0,
+      "train_loss": 0.0036987085283889873,
+      "train_runtime": 71191.4821,
+      "train_samples_per_second": 0.281,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 312,
+  "num_input_tokens_seen": 802441496,
+  "num_train_epochs": 1,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c7e33bc4f64e22fcd26e4e03a26f945b707a599756db6e343c305abbde9e81
+size 7992