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: big-math-digits-v2-correctness
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for big-math-digits-v2-correctness
+
+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="mehuldamani/big-math-digits-v2-correctness", 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/mehuldamani/grpo/runs/826vknbv) 
+
+
+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: 3.6.0
+- Tokenizers: 0.21.1
+
+## 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:eb27fc97f7e2c8c8ad0d58ecd1de79df820a77d8012b66d23c446d58059c4a58
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a4ce7965c63c321d50e131e2bc9dbf2c9dd12ca669252d52779b938c8603ecf
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d6d7ba7bb1ead4d638d394fc82c266a4f6232cfc04bd5c596a309b0b87a02ec
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8cb7b844c73e01a224e6f47e4580fc9b7727d4731f86be4451731385348329a
+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 +1,1261 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.49919376007799904,
+  "eval_steps": 50,
+  "global_step": 208,
+  "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": 0.02065972222222221,
+      "completions/max_length": 4047.0,
+      "completions/max_terminated_length": 4047.0,
+      "completions/mean_length": 495.66493530273436,
+      "completions/mean_terminated_length": 506.1021301269531,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 2.4,
+      "epoch": 0.011999850001874977,
+      "grad_norm": 0.47694680094718933,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": 0.0099,
+      "num_tokens": 7626188.0,
+      "reward": 0.4157118022441864,
+      "reward_std": 0.35606788396835326,
+      "rewards/accuracy_reward": 0.25520833134651183,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.5762152791023254,
+      "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": 0.01171875,
+      "completions/max_length": 3730.2,
+      "completions/max_terminated_length": 3730.2,
+      "completions/mean_length": 371.2526123046875,
+      "completions/mean_terminated_length": 375.78693237304685,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 19.4,
+      "epoch": 0.023999700003749954,
+      "grad_norm": 0.0010379819432273507,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": -0.0026,
+      "num_tokens": 13787658.0,
+      "reward": 0.6760850787162781,
+      "reward_std": 0.2362564116716385,
+      "rewards/accuracy_reward": 0.4039930462837219,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9481770873069764,
+      "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": 0.013975694444444442,
+      "completions/max_length": 4018.4,
+      "completions/max_terminated_length": 4018.4,
+      "completions/mean_length": 464.33099365234375,
+      "completions/mean_terminated_length": 471.20233764648435,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 54.6,
+      "epoch": 0.03599955000562493,
+      "grad_norm": 0.0006205081008374691,
+      "learning_rate": 4.898477157360406e-06,
+      "loss": -0.0066,
+      "num_tokens": 21040655.0,
+      "reward": 0.7481770992279053,
+      "reward_std": 0.18966231644153594,
+      "rewards/accuracy_reward": 0.5131944417953491,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9831597328186035,
+      "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": 0.01649305555555556,
+      "completions/max_length": 3962.2,
+      "completions/max_terminated_length": 3962.2,
+      "completions/mean_length": 579.791845703125,
+      "completions/mean_terminated_length": 589.5614501953125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 119.6,
+      "epoch": 0.04799940000749991,
+      "grad_norm": 0.00045936586684547365,
+      "learning_rate": 4.771573604060914e-06,
+      "loss": -0.0088,
+      "num_tokens": 29635473.0,
+      "reward": 0.7965711951255798,
+      "reward_std": 0.1594875305891037,
+      "rewards/accuracy_reward": 0.6106770873069763,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9824652791023254,
+      "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": 0.012673611111111094,
+      "completions/max_length": 3394.8,
+      "completions/max_terminated_length": 3394.8,
+      "completions/mean_length": 605.4309936523438,
+      "completions/mean_terminated_length": 613.314404296875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 129.6,
+      "epoch": 0.05999925000937488,
+      "grad_norm": 0.0004269441997166723,
+      "learning_rate": 4.644670050761422e-06,
+      "loss": -0.0069,
+      "num_tokens": 38536406.0,
+      "reward": 0.8223090291023254,
+      "reward_std": 0.13588928282260895,
+      "rewards/accuracy_reward": 0.6580729246139526,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9865451455116272,
+      "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": 0.017361111111111115,
+      "completions/max_length": 3280.8,
+      "completions/max_terminated_length": 3280.8,
+      "completions/mean_length": 605.2468017578125,
+      "completions/mean_terminated_length": 616.0807861328125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 123.0,
+      "epoch": 0.07199910001124986,
+      "grad_norm": 0.000590955838561058,
+      "learning_rate": 4.5177664974619295e-06,
+      "loss": -0.0102,
+      "num_tokens": 47420689.0,
+      "reward": 0.8153645873069764,
+      "reward_std": 0.14741556644439696,
+      "rewards/accuracy_reward": 0.6482638835906982,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9824652791023254,
+      "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": 0.02178819444444442,
+      "completions/max_length": 3437.4,
+      "completions/max_terminated_length": 3437.4,
+      "completions/mean_length": 595.20625,
+      "completions/mean_terminated_length": 608.612451171875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 141.2,
+      "epoch": 0.08399895001312484,
+      "grad_norm": 0.0004463954537641257,
+      "learning_rate": 4.390862944162436e-06,
+      "loss": -0.013,
+      "num_tokens": 56156825.0,
+      "reward": 0.8129774451255798,
+      "reward_std": 0.13939182609319686,
+      "rewards/accuracy_reward": 0.6477430462837219,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9782117962837219,
+      "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": 0.025954861111111116,
+      "completions/max_length": 3589.0,
+      "completions/max_terminated_length": 3589.0,
+      "completions/mean_length": 608.2237060546875,
+      "completions/mean_terminated_length": 624.4381469726562,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 144.4,
+      "epoch": 0.09599880001499982,
+      "grad_norm": 0.0005039877141825855,
+      "learning_rate": 4.263959390862945e-06,
+      "loss": -0.0181,
+      "num_tokens": 65085002.0,
+      "reward": 0.8188802123069763,
+      "reward_std": 0.13610992431640626,
+      "rewards/accuracy_reward": 0.6638020873069763,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9739583253860473,
+      "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": 0.024826388888888884,
+      "completions/max_length": 3807.0,
+      "completions/max_terminated_length": 3807.0,
+      "completions/mean_length": 640.9053955078125,
+      "completions/mean_terminated_length": 657.2029418945312,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 145.4,
+      "epoch": 0.1079986500168748,
+      "grad_norm": 0.00040095733129419386,
+      "learning_rate": 4.137055837563453e-06,
+      "loss": -0.0146,
+      "num_tokens": 74405416.0,
+      "reward": 0.8217013955116272,
+      "reward_std": 0.13904002010822297,
+      "rewards/accuracy_reward": 0.6684895753860474,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9749131917953491,
+      "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": 0.02352430555555556,
+      "completions/max_length": 3562.0,
+      "completions/max_terminated_length": 3562.0,
+      "completions/mean_length": 639.3743896484375,
+      "completions/mean_terminated_length": 654.712939453125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 162.4,
+      "epoch": 0.11999850001874976,
+      "grad_norm": 0.0005420144880190492,
+      "learning_rate": 4.0101522842639595e-06,
+      "loss": -0.0162,
+      "num_tokens": 83670529.0,
+      "reward": 0.8127604246139526,
+      "reward_std": 0.13803613781929017,
+      "rewards/accuracy_reward": 0.6490451335906983,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9764756798744202,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.11999850001874976,
+      "eval_completions/clipped_ratio": 0.025868055555555547,
+      "eval_completions/max_length": 2410.0,
+      "eval_completions/max_terminated_length": 2410.0,
+      "eval_completions/mean_length": 618.3784891764323,
+      "eval_completions/mean_terminated_length": 634.7286783854166,
+      "eval_completions/min_length": 0.0,
+      "eval_completions/min_terminated_length": 202.16666666666666,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 83670529.0,
+      "eval_reward": 0.816406269868215,
+      "eval_reward_std": 0.2650855928659439,
+      "eval_rewards/accuracy_reward": 0.6588541666666666,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 0.9739583233992258,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 317.036,
+      "eval_samples_per_second": 3.154,
+      "eval_steps_per_second": 0.019,
+      "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": 0.0265625,
+      "completions/max_length": 3296.0,
+      "completions/max_terminated_length": 3296.0,
+      "completions/mean_length": 634.9600708007813,
+      "completions/mean_terminated_length": 652.637939453125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 145.6,
+      "epoch": 0.13199835002062474,
+      "grad_norm": 0.0007147942669689655,
+      "learning_rate": 3.883248730964467e-06,
+      "loss": -0.0147,
+      "num_tokens": 92867765.0,
+      "reward": 0.8098524332046508,
+      "reward_std": 0.13919124156236648,
+      "rewards/accuracy_reward": 0.6467013835906983,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9730034708976746,
+      "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": 0.020486111111111115,
+      "completions/max_length": 3785.2,
+      "completions/max_terminated_length": 3785.2,
+      "completions/mean_length": 638.7587768554688,
+      "completions/mean_terminated_length": 652.251123046875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 149.0,
+      "epoch": 0.14399820002249972,
+      "grad_norm": 0.0006786566809751093,
+      "learning_rate": 3.756345177664975e-06,
+      "loss": -0.0139,
+      "num_tokens": 102124762.0,
+      "reward": 0.8063802123069763,
+      "reward_std": 0.13464951664209365,
+      "rewards/accuracy_reward": 0.63359375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9791666626930237,
+      "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": 0.015364583333333326,
+      "completions/max_length": 3440.2,
+      "completions/max_terminated_length": 3440.2,
+      "completions/mean_length": 628.39228515625,
+      "completions/mean_terminated_length": 638.17490234375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 141.6,
+      "epoch": 0.1559980500243747,
+      "grad_norm": 0.0004710310895461589,
+      "learning_rate": 3.629441624365482e-06,
+      "loss": -0.0085,
+      "num_tokens": 111259809.0,
+      "reward": 0.8261718869209289,
+      "reward_std": 0.11869495064020157,
+      "rewards/accuracy_reward": 0.6677951335906982,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9845486164093018,
+      "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": 0.02109375,
+      "completions/max_length": 3541.8,
+      "completions/max_terminated_length": 3541.8,
+      "completions/mean_length": 620.9056396484375,
+      "completions/mean_terminated_length": 634.306201171875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 114.4,
+      "epoch": 0.16799790002624967,
+      "grad_norm": 0.0005915550282225013,
+      "learning_rate": 3.5025380710659903e-06,
+      "loss": -0.0141,
+      "num_tokens": 120292706.0,
+      "reward": 0.8110677123069763,
+      "reward_std": 0.12359137833118439,
+      "rewards/accuracy_reward": 0.6433159708976746,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9788194417953491,
+      "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": 0.013368055555555558,
+      "completions/max_length": 2899.0,
+      "completions/max_terminated_length": 2899.0,
+      "completions/mean_length": 608.4648559570312,
+      "completions/mean_terminated_length": 616.763671875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 150.4,
+      "epoch": 0.17999775002812465,
+      "grad_norm": 0.00045338328345678747,
+      "learning_rate": 3.375634517766498e-06,
+      "loss": -0.008,
+      "num_tokens": 129169037.0,
+      "reward": 0.8407552123069764,
+      "reward_std": 0.11922919005155563,
+      "rewards/accuracy_reward": 0.6949652910232544,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9865451335906983,
+      "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": 0.023177083333333327,
+      "completions/max_length": 3817.4,
+      "completions/max_terminated_length": 3817.4,
+      "completions/mean_length": 648.0177368164062,
+      "completions/mean_terminated_length": 663.47724609375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 127.4,
+      "epoch": 0.19199760002999963,
+      "grad_norm": 0.00041271100053563714,
+      "learning_rate": 3.2487309644670053e-06,
+      "loss": -0.0138,
+      "num_tokens": 138489401.0,
+      "reward": 0.8135850667953491,
+      "reward_std": 0.12409738302230836,
+      "rewards/accuracy_reward": 0.6503472208976746,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9768229126930237,
+      "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": 0.025868055555555537,
+      "completions/max_length": 3501.2,
+      "completions/max_terminated_length": 3501.2,
+      "completions/mean_length": 654.8557373046875,
+      "completions/mean_terminated_length": 672.3203979492188,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 166.8,
+      "epoch": 0.2039974500318746,
+      "grad_norm": 0.00039561674930155277,
+      "learning_rate": 3.121827411167513e-06,
+      "loss": -0.0162,
+      "num_tokens": 147922459.0,
+      "reward": 0.8282986283302307,
+      "reward_std": 0.13599332869052888,
+      "rewards/accuracy_reward": 0.6832465171813965,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9733506917953492,
+      "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": 0.02430555555555558,
+      "completions/max_length": 3750.8,
+      "completions/max_terminated_length": 3750.8,
+      "completions/mean_length": 626.2822875976562,
+      "completions/mean_terminated_length": 641.9483764648437,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 136.6,
+      "epoch": 0.2159973000337496,
+      "grad_norm": 0.00046881154412403703,
+      "learning_rate": 2.9949238578680207e-06,
+      "loss": -0.0153,
+      "num_tokens": 157007823.0,
+      "reward": 0.8209635376930237,
+      "reward_std": 0.13299919813871383,
+      "rewards/accuracy_reward": 0.6667534708976746,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9751736164093018,
+      "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": 0.018923611111111092,
+      "completions/max_length": 3614.2,
+      "completions/max_terminated_length": 3614.2,
+      "completions/mean_length": 643.94228515625,
+      "completions/mean_terminated_length": 656.3934814453125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 131.2,
+      "epoch": 0.22799715003562457,
+      "grad_norm": 0.0003850593639072031,
+      "learning_rate": 2.8680203045685284e-06,
+      "loss": -0.0103,
+      "num_tokens": 166319638.0,
+      "reward": 0.8210069537162781,
+      "reward_std": 0.11787589490413666,
+      "rewards/accuracy_reward": 0.6611979007720947,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9808159828186035,
+      "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": 0.025347222222222233,
+      "completions/max_length": 3307.0,
+      "completions/max_terminated_length": 3307.0,
+      "completions/mean_length": 667.9455932617187,
+      "completions/mean_terminated_length": 685.2820556640625,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 149.2,
+      "epoch": 0.23999700003749952,
+      "grad_norm": 0.000390661385608837,
+      "learning_rate": 2.7411167512690357e-06,
+      "loss": -0.0161,
+      "num_tokens": 175915363.0,
+      "reward": 0.8228298664093018,
+      "reward_std": 0.127268485724926,
+      "rewards/accuracy_reward": 0.6711805582046508,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9744791626930237,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.23999700003749952,
+      "eval_completions/clipped_ratio": 0.018923611111111127,
+      "eval_completions/max_length": 2499.1666666666665,
+      "eval_completions/max_terminated_length": 2499.1666666666665,
+      "eval_completions/mean_length": 652.9295349121094,
+      "eval_completions/mean_terminated_length": 665.5544128417969,
+      "eval_completions/min_length": 0.0,
+      "eval_completions/min_terminated_length": 209.0,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 175915363.0,
+      "eval_reward": 0.8289930721124014,
+      "eval_reward_std": 0.2512400249640147,
+      "eval_rewards/accuracy_reward": 0.6744791666666666,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 0.9835069477558136,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 315.8521,
+      "eval_samples_per_second": 3.166,
+      "eval_steps_per_second": 0.019,
+      "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": 0.021267361111111115,
+      "completions/max_length": 3450.8,
+      "completions/max_terminated_length": 3450.8,
+      "completions/mean_length": 657.2955810546875,
+      "completions/mean_terminated_length": 671.5618774414063,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 130.6,
+      "epoch": 0.2519968500393745,
+      "grad_norm": 0.0004644222208298743,
+      "learning_rate": 2.6142131979695434e-06,
+      "loss": -0.0128,
+      "num_tokens": 185366192.0,
+      "reward": 0.8306857705116272,
+      "reward_std": 0.11819785684347153,
+      "rewards/accuracy_reward": 0.6831597328186035,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9782118082046509,
+      "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": 0.01675347222222221,
+      "completions/max_length": 3521.8,
+      "completions/max_terminated_length": 3521.8,
+      "completions/mean_length": 664.1182495117188,
+      "completions/mean_terminated_length": 675.5516235351563,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 157.8,
+      "epoch": 0.2639967000412495,
+      "grad_norm": 0.0004074091266375035,
+      "learning_rate": 2.487309644670051e-06,
+      "loss": -0.0095,
+      "num_tokens": 194927202.0,
+      "reward": 0.8493489623069763,
+      "reward_std": 0.11185714602470398,
+      "rewards/accuracy_reward": 0.7157986283302307,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9828993082046509,
+      "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": 0.019010416666666675,
+      "completions/max_length": 3542.0,
+      "completions/max_terminated_length": 3542.0,
+      "completions/mean_length": 662.1376831054688,
+      "completions/mean_terminated_length": 675.0173706054687,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 163.2,
+      "epoch": 0.27599655004312446,
+      "grad_norm": 0.0004749298677779734,
+      "learning_rate": 2.3604060913705588e-06,
+      "loss": -0.0124,
+      "num_tokens": 204436148.0,
+      "reward": 0.831163203716278,
+      "reward_std": 0.11646707653999329,
+      "rewards/accuracy_reward": 0.6817708373069763,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9805555701255798,
+      "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": 0.014322916666666652,
+      "completions/max_length": 3572.0,
+      "completions/max_terminated_length": 3572.0,
+      "completions/mean_length": 650.0963623046875,
+      "completions/mean_terminated_length": 659.4545166015625,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 141.6,
+      "epoch": 0.28799640004499943,
+      "grad_norm": 0.0003820126294158399,
+      "learning_rate": 2.233502538071066e-06,
+      "loss": -0.0093,
+      "num_tokens": 213809034.0,
+      "reward": 0.8375434041023254,
+      "reward_std": 0.11465604901313782,
+      "rewards/accuracy_reward": 0.68984375,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.985243046283722,
+      "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": 0.013107638888888884,
+      "completions/max_length": 3326.0,
+      "completions/max_terminated_length": 3326.0,
+      "completions/mean_length": 648.654345703125,
+      "completions/mean_terminated_length": 657.3896240234375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 160.8,
+      "epoch": 0.2999962500468744,
+      "grad_norm": 0.0004972605383954942,
+      "learning_rate": 2.1065989847715737e-06,
+      "loss": -0.0084,
+      "num_tokens": 223201116.0,
+      "reward": 0.8411892294883728,
+      "reward_std": 0.11022633463144302,
+      "rewards/accuracy_reward": 0.6955729126930237,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9868055701255798,
+      "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": 0.017447916666666653,
+      "completions/max_length": 3507.8,
+      "completions/max_terminated_length": 3507.8,
+      "completions/mean_length": 680.4585205078125,
+      "completions/mean_terminated_length": 692.4925903320312,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 150.8,
+      "epoch": 0.3119961000487494,
+      "grad_norm": 0.0004750330117531121,
+      "learning_rate": 1.9796954314720814e-06,
+      "loss": -0.0107,
+      "num_tokens": 232966718.0,
+      "reward": 0.8265190958976746,
+      "reward_std": 0.12254964411258698,
+      "rewards/accuracy_reward": 0.6706597208976746,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9823784708976746,
+      "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": 0.01128472222222221,
+      "completions/max_length": 3688.2,
+      "completions/max_terminated_length": 3688.2,
+      "completions/mean_length": 672.9379272460938,
+      "completions/mean_terminated_length": 680.5967041015625,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 150.8,
+      "epoch": 0.32399595005062437,
+      "grad_norm": 0.0005158277926966548,
+      "learning_rate": 1.852791878172589e-06,
+      "loss": -0.006,
+      "num_tokens": 242613907.0,
+      "reward": 0.8388889074325562,
+      "reward_std": 0.11086668223142623,
+      "rewards/accuracy_reward": 0.6890625,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9887152671813965,
+      "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": 0.012847222222222232,
+      "completions/max_length": 3413.0,
+      "completions/max_terminated_length": 3413.0,
+      "completions/mean_length": 675.3115478515625,
+      "completions/mean_terminated_length": 684.0101196289063,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 173.6,
+      "epoch": 0.33599580005249935,
+      "grad_norm": 0.00046416957047767937,
+      "learning_rate": 1.7258883248730964e-06,
+      "loss": -0.0076,
+      "num_tokens": 252299640.0,
+      "reward": 0.8318142294883728,
+      "reward_std": 0.11125441938638687,
+      "rewards/accuracy_reward": 0.6766493082046509,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9869791626930237,
+      "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": 0.01015625,
+      "completions/max_length": 3253.2,
+      "completions/max_terminated_length": 3253.2,
+      "completions/mean_length": 660.1990600585938,
+      "completions/mean_terminated_length": 667.0159423828125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 176.2,
+      "epoch": 0.34799565005437433,
+      "grad_norm": 0.00041169917676597834,
+      "learning_rate": 1.5989847715736043e-06,
+      "loss": -0.0057,
+      "num_tokens": 261771661.0,
+      "reward": 0.8521701455116272,
+      "reward_std": 0.10130168348550797,
+      "rewards/accuracy_reward": 0.7144965410232544,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9898437619209289,
+      "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": 0.01050347222222221,
+      "completions/max_length": 3546.8,
+      "completions/max_terminated_length": 3546.8,
+      "completions/mean_length": 725.4683227539062,
+      "completions/mean_terminated_length": 733.1369995117187,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 173.0,
+      "epoch": 0.3599955000562493,
+      "grad_norm": 0.0005442510009743273,
+      "learning_rate": 1.4720812182741118e-06,
+      "loss": -0.0055,
+      "num_tokens": 272041312.0,
+      "reward": 0.8391059041023254,
+      "reward_std": 0.11063261181116105,
+      "rewards/accuracy_reward": 0.6887152671813965,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9894965291023254,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.3599955000562493,
+      "eval_completions/clipped_ratio": 0.009548611111111105,
+      "eval_completions/max_length": 2648.6666666666665,
+      "eval_completions/max_terminated_length": 2648.6666666666665,
+      "eval_completions/mean_length": 697.2899576822916,
+      "eval_completions/mean_terminated_length": 704.1798807779948,
+      "eval_completions/min_length": 77.83333333333333,
+      "eval_completions/min_terminated_length": 218.5,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 272041312.0,
+      "eval_reward": 0.8424479365348816,
+      "eval_reward_std": 0.24290807793537775,
+      "eval_rewards/accuracy_reward": 0.6953125,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 0.9895833333333334,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 335.7366,
+      "eval_samples_per_second": 2.979,
+      "eval_steps_per_second": 0.018,
+      "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": 0.008246527777777768,
+      "completions/max_length": 3176.0,
+      "completions/max_terminated_length": 3176.0,
+      "completions/mean_length": 681.7713500976563,
+      "completions/mean_terminated_length": 687.5726318359375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 186.8,
+      "epoch": 0.3719953500581243,
+      "grad_norm": 0.0005200021550990641,
+      "learning_rate": 1.3451776649746193e-06,
+      "loss": -0.0046,
+      "num_tokens": 281804950.0,
+      "reward": 0.8654947876930237,
+      "reward_std": 0.10751536339521409,
+      "rewards/accuracy_reward": 0.7392361164093018,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9917534828186035,
+      "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": 0.013975694444444419,
+      "completions/max_length": 3486.4,
+      "completions/max_terminated_length": 3486.4,
+      "completions/mean_length": 683.7095581054688,
+      "completions/mean_terminated_length": 693.3710571289063,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 169.2,
+      "epoch": 0.38399520005999926,
+      "grad_norm": 0.00048736194730736315,
+      "learning_rate": 1.218274111675127e-06,
+      "loss": -0.0093,
+      "num_tokens": 291570500.0,
+      "reward": 0.8379774451255798,
+      "reward_std": 0.1071748360991478,
+      "rewards/accuracy_reward": 0.689930546283722,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9860242962837219,
+      "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": 0.014670138888888884,
+      "completions/max_length": 3638.8,
+      "completions/max_terminated_length": 3638.8,
+      "completions/mean_length": 728.8395751953125,
+      "completions/mean_terminated_length": 739.8839111328125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 187.0,
+      "epoch": 0.39599505006187424,
+      "grad_norm": 0.0005984375602565706,
+      "learning_rate": 1.0913705583756345e-06,
+      "loss": -0.0069,
+      "num_tokens": 301907724.0,
+      "reward": 0.8228298664093018,
+      "reward_std": 0.10787203758955002,
+      "rewards/accuracy_reward": 0.6605902791023255,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9850694537162781,
+      "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": 0.011111111111111094,
+      "completions/max_length": 3545.2,
+      "completions/max_terminated_length": 3545.2,
+      "completions/mean_length": 690.5397583007813,
+      "completions/mean_terminated_length": 698.257373046875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 167.2,
+      "epoch": 0.4079949000637492,
+      "grad_norm": 0.0004480788193177432,
+      "learning_rate": 9.644670050761422e-07,
+      "loss": -0.0055,
+      "num_tokens": 311753846.0,
+      "reward": 0.8578559160232544,
+      "reward_std": 0.10318245440721512,
+      "rewards/accuracy_reward": 0.7269097208976746,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9888020753860474,
+      "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": 0.010243055555555557,
+      "completions/max_length": 3369.0,
+      "completions/max_terminated_length": 3369.0,
+      "completions/mean_length": 729.870068359375,
+      "completions/mean_terminated_length": 737.4661865234375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 162.2,
+      "epoch": 0.4199947500656242,
+      "grad_norm": 0.00047758789150975645,
+      "learning_rate": 8.375634517766498e-07,
+      "loss": -0.0068,
+      "num_tokens": 322071837.0,
+      "reward": 0.8517795085906983,
+      "reward_std": 0.11207419633865356,
+      "rewards/accuracy_reward": 0.7139756917953491,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9895833253860473,
+      "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": 0.011111111111111094,
+      "completions/max_length": 3660.4,
+      "completions/max_terminated_length": 3660.4,
+      "completions/mean_length": 702.6620727539063,
+      "completions/mean_terminated_length": 710.5470703125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 178.4,
+      "epoch": 0.4319946000674992,
+      "grad_norm": 0.0006071230163797736,
+      "learning_rate": 7.106598984771574e-07,
+      "loss": -0.0065,
+      "num_tokens": 332068392.0,
+      "reward": 0.8521267414093018,
+      "reward_std": 0.10839989632368088,
+      "rewards/accuracy_reward": 0.7157986164093018,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9884548544883728,
+      "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": 0.014149305555555557,
+      "completions/max_length": 3151.4,
+      "completions/max_terminated_length": 3151.4,
+      "completions/mean_length": 697.1512329101563,
+      "completions/mean_terminated_length": 707.2808837890625,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 163.8,
+      "epoch": 0.44399445006937416,
+      "grad_norm": 0.000985562102869153,
+      "learning_rate": 5.83756345177665e-07,
+      "loss": -0.0069,
+      "num_tokens": 341991542.0,
+      "reward": 0.8358941197395324,
+      "reward_std": 0.11062836647033691,
+      "rewards/accuracy_reward": 0.6860243082046509,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9857638835906982,
+      "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": 0.010763888888888884,
+      "completions/max_length": 3502.8,
+      "completions/max_terminated_length": 3502.8,
+      "completions/mean_length": 693.5631103515625,
+      "completions/mean_terminated_length": 701.1261474609375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 167.0,
+      "epoch": 0.45599430007124914,
+      "grad_norm": 0.00046821607975289226,
+      "learning_rate": 4.568527918781726e-07,
+      "loss": -0.0062,
+      "num_tokens": 351866253.0,
+      "reward": 0.8616753458976746,
+      "reward_std": 0.11032991707324982,
+      "rewards/accuracy_reward": 0.7342013955116272,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9891493201255799,
+      "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": 0.015017361111111117,
+      "completions/max_length": 3624.0,
+      "completions/max_terminated_length": 3624.0,
+      "completions/mean_length": 707.9368286132812,
+      "completions/mean_terminated_length": 718.9172485351562,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 125.0,
+      "epoch": 0.46799415007312406,
+      "grad_norm": 0.0005199919687584043,
+      "learning_rate": 3.2994923857868026e-07,
+      "loss": -0.0096,
+      "num_tokens": 361904469.0,
+      "reward": 0.8315538167953491,
+      "reward_std": 0.10869046747684478,
+      "rewards/accuracy_reward": 0.6782986164093018,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9848090410232544,
+      "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": 0.008333333333333326,
+      "completions/max_length": 3104.0,
+      "completions/max_terminated_length": 3104.0,
+      "completions/mean_length": 690.364599609375,
+      "completions/mean_terminated_length": 696.1920288085937,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 176.2,
+      "epoch": 0.47999400007499904,
+      "grad_norm": 0.00045739096822217107,
+      "learning_rate": 2.0304568527918783e-07,
+      "loss": -0.0042,
+      "num_tokens": 371727197.0,
+      "reward": 0.8470920085906982,
+      "reward_std": 0.09732583314180374,
+      "rewards/accuracy_reward": 0.7025173544883728,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9916666626930237,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.47999400007499904,
+      "eval_completions/clipped_ratio": 0.006076388888888877,
+      "eval_completions/max_length": 2123.3333333333335,
+      "eval_completions/max_terminated_length": 2123.3333333333335,
+      "eval_completions/mean_length": 704.721201578776,
+      "eval_completions/mean_terminated_length": 708.9297790527344,
+      "eval_completions/min_length": 100.16666666666667,
+      "eval_completions/min_terminated_length": 211.0,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 371727197.0,
+      "eval_reward": 0.8424479365348816,
+      "eval_reward_std": 0.23790805538495383,
+      "eval_rewards/accuracy_reward": 0.691840281089147,
+      "eval_rewards/brier_reward": 0.0,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 0.9930555522441864,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 336.264,
+      "eval_samples_per_second": 2.974,
+      "eval_steps_per_second": 0.018,
+      "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": 0.01128472222222221,
+      "completions/max_length": 3577.6,
+      "completions/max_terminated_length": 3577.6,
+      "completions/mean_length": 705.7981811523438,
+      "completions/mean_terminated_length": 713.82548828125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 167.4,
+      "epoch": 0.491993850076874,
+      "grad_norm": 0.0006899295258335769,
+      "learning_rate": 7.614213197969544e-08,
+      "loss": -0.0061,
+      "num_tokens": 381725864.0,
+      "reward": 0.8680121541023255,
+      "reward_std": 0.10762782245874405,
+      "rewards/accuracy_reward": 0.7473090291023254,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9887152910232544,
+      "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": 0.00795717592592593,
+      "completions/max_length": 3177.3333333333335,
+      "completions/max_terminated_length": 3177.3333333333335,
+      "completions/mean_length": 710.8990478515625,
+      "completions/mean_terminated_length": 716.7127685546875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 147.33333333333334,
+      "epoch": 0.49919376007799904,
+      "num_tokens": 387786798.0,
+      "reward": 0.8449074029922485,
+      "reward_std": 0.10756702721118927,
+      "rewards/accuracy_reward": 0.6977719863255819,
+      "rewards/brier_reward": 0.0,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9920428395271301,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 208,
+      "total_flos": 0.0,
+      "train_loss": -0.00919347727456345,
+      "train_runtime": 75450.0592,
+      "train_samples_per_second": 0.199,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 208,
+  "num_input_tokens_seen": 387786798,
+  "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": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73b4e03e35043b8f349eb1c1fb2a7107a1ab913a9e688a036af6e5c73e54f89a
+size 8312