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: mehuldamani/qwen-base-verifier-sft-v1
+library_name: transformers
+model_name: big-math-digits-v2-brier
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for big-math-digits-v2-brier
+
+This model is a fine-tuned version of [mehuldamani/qwen-base-verifier-sft-v1](https://huggingface.co/mehuldamani/qwen-base-verifier-sft-v1).
+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-brier", 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/lsp5z7k5) 
+
+
+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 +1,31 @@
+{
+  "_name_or_path": "mehuldamani/qwen-base-verifier-sft-v1",
+  "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,
+  "pad_token_id": 151647,
+  "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 sha256:1bd4f2475391cb46e81e959aa2ba3a71e17aa6f1d6fab488b3633e307a300469
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1424c4559fcbb10cb89c8900b1a6a5d9d84ecdc7dc8d658195e2f0d74455458d
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5716b3d9c19beaf3762b69442c6cf792400fba773aaf6c9ab3631c57dbb49aec
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:197ca509b87d841115e317b7143069cf056765dab4bf770e6270f5013719df77
+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": "<|object_ref_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94a4bd93feb237e711dbe18b039f5614fa36b21f115621ade2ca27edc119f976
+size 11422068

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": "<|object_ref_end|>",
+  "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": 0.04618055555555556,
+      "completions/max_length": 4000.2,
+      "completions/max_terminated_length": 4000.2,
+      "completions/mean_length": 995.653466796875,
+      "completions/mean_terminated_length": 1043.9063598632813,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 223.4,
+      "epoch": 0.011999850001874977,
+      "grad_norm": 0.001468590460717678,
+      "learning_rate": 2.2727272727272728e-06,
+      "loss": -0.0262,
+      "num_tokens": 14584136.0,
+      "reward": 0.8028841495513916,
+      "reward_std": 0.5060957491397857,
+      "rewards/accuracy_reward": 0.35407986044883727,
+      "rewards/brier_reward": 0.5074836075305938,
+      "rewards/confidence_one_or_zero": 0.4384548604488373,
+      "rewards/format_reward": 0.7441840171813965,
+      "rewards/mean_confidence_reward": 0.6029745936393738,
+      "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": 0.03776041666666665,
+      "completions/max_length": 3788.0,
+      "completions/max_terminated_length": 3788.0,
+      "completions/mean_length": 952.0879516601562,
+      "completions/mean_terminated_length": 989.9261596679687,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 233.0,
+      "epoch": 0.023999700003749954,
+      "grad_norm": 0.000640683458186686,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": -0.0367,
+      "num_tokens": 28634909.0,
+      "reward": 1.0157596111297607,
+      "reward_std": 0.3558866620063782,
+      "rewards/accuracy_reward": 0.4484375,
+      "rewards/brier_reward": 0.6547639966011047,
+      "rewards/confidence_one_or_zero": 0.42048611044883727,
+      "rewards/format_reward": 0.9282986044883728,
+      "rewards/mean_confidence_reward": 0.5301635503768921,
+      "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": 0.030295138888888885,
+      "completions/max_length": 3773.6,
+      "completions/max_terminated_length": 3773.6,
+      "completions/mean_length": 968.6600708007812,
+      "completions/mean_terminated_length": 999.1074096679688,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 320.6,
+      "epoch": 0.03599955000562493,
+      "grad_norm": 0.0007433110731653869,
+      "learning_rate": 4.898477157360406e-06,
+      "loss": -0.033,
+      "num_tokens": 42895857.0,
+      "reward": 1.0568380117416383,
+      "reward_std": 0.24810748398303986,
+      "rewards/accuracy_reward": 0.4456597208976746,
+      "rewards/brier_reward": 0.7031617760658264,
+      "rewards/confidence_one_or_zero": 0.1889756962656975,
+      "rewards/format_reward": 0.9648437380790711,
+      "rewards/mean_confidence_reward": 0.34892988204956055,
+      "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": 0.030642361111111092,
+      "completions/max_length": 3860.2,
+      "completions/max_terminated_length": 3860.2,
+      "completions/mean_length": 888.786279296875,
+      "completions/mean_terminated_length": 917.262744140625,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 294.2,
+      "epoch": 0.04799940000749991,
+      "grad_norm": 0.0007100884104147553,
+      "learning_rate": 4.771573604060914e-06,
+      "loss": -0.0317,
+      "num_tokens": 56248371.0,
+      "reward": 1.1035695791244506,
+      "reward_std": 0.2411518782377243,
+      "rewards/accuracy_reward": 0.4994791686534882,
+      "rewards/brier_reward": 0.7392470240592957,
+      "rewards/confidence_one_or_zero": 0.004427083267364651,
+      "rewards/format_reward": 0.9684027791023254,
+      "rewards/mean_confidence_reward": 0.5068701922893524,
+      "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": 0.027517361111111117,
+      "completions/max_length": 3753.2,
+      "completions/max_terminated_length": 3753.2,
+      "completions/mean_length": 845.354345703125,
+      "completions/mean_terminated_length": 869.4375122070312,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 275.0,
+      "epoch": 0.05999925000937488,
+      "grad_norm": 0.0007387480000033975,
+      "learning_rate": 4.644670050761422e-06,
+      "loss": -0.0278,
+      "num_tokens": 69111301.0,
+      "reward": 1.1421298265457154,
+      "reward_std": 0.24627233445644378,
+      "rewards/accuracy_reward": 0.5638888835906982,
+      "rewards/brier_reward": 0.7484833002090454,
+      "rewards/confidence_one_or_zero": 0.0007812500058207661,
+      "rewards/format_reward": 0.971875,
+      "rewards/mean_confidence_reward": 0.6265876889228821,
+      "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": 0.03671875,
+      "completions/max_length": 3877.8,
+      "completions/max_terminated_length": 3877.8,
+      "completions/mean_length": 911.8454223632813,
+      "completions/mean_terminated_length": 946.828125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 215.6,
+      "epoch": 0.07199910001124986,
+      "grad_norm": 0.0017544181318953633,
+      "learning_rate": 4.5177664974619295e-06,
+      "loss": -0.0379,
+      "num_tokens": 82725680.0,
+      "reward": 1.1499913215637207,
+      "reward_std": 0.24166221618652345,
+      "rewards/accuracy_reward": 0.5868923664093018,
+      "rewards/brier_reward": 0.7504922270774841,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.9625868082046509,
+      "rewards/mean_confidence_reward": 0.5598831534385681,
+      "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": 0.034895833333333307,
+      "completions/max_length": 3889.6,
+      "completions/max_terminated_length": 3889.6,
+      "completions/mean_length": 903.557470703125,
+      "completions/mean_terminated_length": 936.7724609375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 288.8,
+      "epoch": 0.08399895001312484,
+      "grad_norm": 0.0007147829746827483,
+      "learning_rate": 4.390862944162436e-06,
+      "loss": -0.034,
+      "num_tokens": 96212102.0,
+      "reward": 1.1824100971221925,
+      "reward_std": 0.2268961787223816,
+      "rewards/accuracy_reward": 0.6289930462837219,
+      "rewards/brier_reward": 0.7714917182922363,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9643229246139526,
+      "rewards/mean_confidence_reward": 0.6222647666931153,
+      "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": 0.03116319444444444,
+      "completions/max_length": 3932.8,
+      "completions/max_terminated_length": 3932.8,
+      "completions/mean_length": 823.3291748046875,
+      "completions/mean_terminated_length": 849.9028564453125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 282.8,
+      "epoch": 0.09599880001499982,
+      "grad_norm": 0.0005586285842582583,
+      "learning_rate": 4.263959390862945e-06,
+      "loss": -0.0364,
+      "num_tokens": 108816374.0,
+      "reward": 1.1980676889419555,
+      "reward_std": 0.22116016447544098,
+      "rewards/accuracy_reward": 0.6493055582046509,
+      "rewards/brier_reward": 0.7783258199691773,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9684895873069763,
+      "rewards/mean_confidence_reward": 0.7160234451293945,
+      "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": 0.024565972222222232,
+      "completions/max_length": 3847.6,
+      "completions/max_terminated_length": 3847.6,
+      "completions/mean_length": 782.091845703125,
+      "completions/mean_terminated_length": 801.8463256835937,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 259.0,
+      "epoch": 0.1079986500168748,
+      "grad_norm": 0.0006557401502504945,
+      "learning_rate": 4.137055837563453e-06,
+      "loss": -0.0253,
+      "num_tokens": 120961336.0,
+      "reward": 1.200283408164978,
+      "reward_std": 0.2178070664405823,
+      "rewards/accuracy_reward": 0.6548611164093018,
+      "rewards/brier_reward": 0.7712975144386292,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9743923664093017,
+      "rewards/mean_confidence_reward": 0.7877369880676269,
+      "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": 0.02421875,
+      "completions/max_length": 3791.8,
+      "completions/max_terminated_length": 3791.8,
+      "completions/mean_length": 786.1929809570313,
+      "completions/mean_terminated_length": 805.8355224609375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 240.6,
+      "epoch": 0.11999850001874976,
+      "grad_norm": 0.0006151842535473406,
+      "learning_rate": 4.0101522842639595e-06,
+      "loss": -0.0249,
+      "num_tokens": 133115879.0,
+      "reward": 1.2045230865478516,
+      "reward_std": 0.20249704420566558,
+      "rewards/accuracy_reward": 0.6519965291023254,
+      "rewards/brier_reward": 0.7813406109809875,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9756944417953491,
+      "rewards/mean_confidence_reward": 0.72891925573349,
+      "step": 50
+    },
+    {
+      "epoch": 0.11999850001874976,
+      "eval_completions/clipped_ratio": 0.022569444444444458,
+      "eval_completions/max_length": 2390.1666666666665,
+      "eval_completions/max_terminated_length": 2390.1666666666665,
+      "eval_completions/mean_length": 807.0597432454427,
+      "eval_completions/mean_terminated_length": 825.7537841796875,
+      "eval_completions/min_length": 77.83333333333333,
+      "eval_completions/min_terminated_length": 333.6666666666667,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 133115879.0,
+      "eval_reward": 1.2035881280899048,
+      "eval_reward_std": 0.3418561766544978,
+      "eval_rewards/accuracy_reward": 0.6475694378217062,
+      "eval_rewards/brier_reward": 0.7847678065299988,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 0.9748263955116272,
+      "eval_rewards/mean_confidence_reward": 0.623480906089147,
+      "eval_runtime": 325.6138,
+      "eval_samples_per_second": 3.071,
+      "eval_steps_per_second": 0.018,
+      "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": 0.029861111111111095,
+      "completions/max_length": 3624.8,
+      "completions/max_terminated_length": 3624.8,
+      "completions/mean_length": 839.8423828125,
+      "completions/mean_terminated_length": 866.0277465820312,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 262.4,
+      "epoch": 0.13199835002062474,
+      "grad_norm": 0.0006012032390572131,
+      "learning_rate": 3.883248730964467e-06,
+      "loss": -0.0267,
+      "num_tokens": 145871439.0,
+      "reward": 1.1937550544738769,
+      "reward_std": 0.18426936566829683,
+      "rewards/accuracy_reward": 0.647656238079071,
+      "rewards/brier_reward": 0.7702242016792298,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9696180582046509,
+      "rewards/mean_confidence_reward": 0.5814600586891174,
+      "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": 0.023611111111111093,
+      "completions/max_length": 3906.2,
+      "completions/max_terminated_length": 3906.2,
+      "completions/mean_length": 821.8163940429688,
+      "completions/mean_terminated_length": 841.79453125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 273.2,
+      "epoch": 0.14399820002249972,
+      "grad_norm": 0.0006839183042757213,
+      "learning_rate": 3.756345177664975e-06,
+      "loss": -0.0259,
+      "num_tokens": 158435340.0,
+      "reward": 1.1945719718933105,
+      "reward_std": 0.1913407564163208,
+      "rewards/accuracy_reward": 0.6302083373069763,
+      "rewards/brier_reward": 0.7827078938484192,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9762152791023254,
+      "rewards/mean_confidence_reward": 0.619076383113861,
+      "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": 0.019357638888888907,
+      "completions/max_length": 3618.6,
+      "completions/max_terminated_length": 3618.6,
+      "completions/mean_length": 749.66796875,
+      "completions/mean_terminated_length": 764.5959350585938,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 192.4,
+      "epoch": 0.1559980500243747,
+      "grad_norm": 0.0007240342674776912,
+      "learning_rate": 3.629441624365482e-06,
+      "loss": -0.0186,
+      "num_tokens": 170165563.0,
+      "reward": 1.2224555015563965,
+      "reward_std": 0.18082822263240814,
+      "rewards/accuracy_reward": 0.6611111164093018,
+      "rewards/brier_reward": 0.8033169031143188,
+      "rewards/confidence_one_or_zero": 0.0006076388992369175,
+      "rewards/format_reward": 0.9804687619209289,
+      "rewards/mean_confidence_reward": 0.7073316097259521,
+      "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": 0.024392361111111115,
+      "completions/max_length": 3395.4,
+      "completions/max_terminated_length": 3395.4,
+      "completions/mean_length": 733.86416015625,
+      "completions/mean_terminated_length": 752.2443115234375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 192.8,
+      "epoch": 0.16799790002624967,
+      "grad_norm": 0.0005545295425690711,
+      "learning_rate": 3.5025380710659903e-06,
+      "loss": -0.0235,
+      "num_tokens": 181697822.0,
+      "reward": 1.2054958105087281,
+      "reward_std": 0.18330176770687104,
+      "rewards/accuracy_reward": 0.6433159589767456,
+      "rewards/brier_reward": 0.7922271609306335,
+      "rewards/confidence_one_or_zero": 0.007031250232830644,
+      "rewards/format_reward": 0.9754340291023255,
+      "rewards/mean_confidence_reward": 0.7130208492279053,
+      "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": 0.018055555555555537,
+      "completions/max_length": 3356.2,
+      "completions/max_terminated_length": 3356.2,
+      "completions/mean_length": 770.8174438476562,
+      "completions/mean_terminated_length": 785.1328491210937,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 255.8,
+      "epoch": 0.17999775002812465,
+      "grad_norm": 0.00040936042205430567,
+      "learning_rate": 3.375634517766498e-06,
+      "loss": -0.0181,
+      "num_tokens": 193642535.0,
+      "reward": 1.244530153274536,
+      "reward_std": 0.1650351107120514,
+      "rewards/accuracy_reward": 0.7009548544883728,
+      "rewards/brier_reward": 0.8063218355178833,
+      "rewards/confidence_one_or_zero": 0.011805555410683155,
+      "rewards/format_reward": 0.9817708373069763,
+      "rewards/mean_confidence_reward": 0.6228342056274414,
+      "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": 0.01788194444444442,
+      "completions/max_length": 3750.2,
+      "completions/max_terminated_length": 3750.2,
+      "completions/mean_length": 820.3263061523437,
+      "completions/mean_terminated_length": 835.380224609375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 227.0,
+      "epoch": 0.19199760002999963,
+      "grad_norm": 0.0005090378108434379,
+      "learning_rate": 3.2487309644670053e-06,
+      "loss": -0.0183,
+      "num_tokens": 206145974.0,
+      "reward": 1.2273483753204346,
+      "reward_std": 0.17248319387435912,
+      "rewards/accuracy_reward": 0.6702256798744202,
+      "rewards/brier_reward": 0.8026000380516052,
+      "rewards/confidence_one_or_zero": 0.04418402835726738,
+      "rewards/format_reward": 0.9818576455116272,
+      "rewards/mean_confidence_reward": 0.6209765553474427,
+      "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": 0.019357638888888862,
+      "completions/max_length": 3891.0,
+      "completions/max_terminated_length": 3891.0,
+      "completions/mean_length": 804.060595703125,
+      "completions/mean_terminated_length": 820.0193115234375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 287.4,
+      "epoch": 0.2039974500318746,
+      "grad_norm": 0.0005799650680273771,
+      "learning_rate": 3.121827411167513e-06,
+      "loss": -0.0182,
+      "num_tokens": 218495952.0,
+      "reward": 1.2420600414276124,
+      "reward_std": 0.1854027807712555,
+      "rewards/accuracy_reward": 0.6829861044883728,
+      "rewards/brier_reward": 0.8210820078849792,
+      "rewards/confidence_one_or_zero": 0.1517361119389534,
+      "rewards/format_reward": 0.9800347328186035,
+      "rewards/mean_confidence_reward": 0.7053038239479065,
+      "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": 0.02152777777777779,
+      "completions/max_length": 3442.0,
+      "completions/max_terminated_length": 3442.0,
+      "completions/mean_length": 785.1589477539062,
+      "completions/mean_terminated_length": 802.4694091796875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 251.8,
+      "epoch": 0.2159973000337496,
+      "grad_norm": 0.0006302814581431448,
+      "learning_rate": 2.9949238578680207e-06,
+      "loss": -0.0238,
+      "num_tokens": 230609655.0,
+      "reward": 1.239054799079895,
+      "reward_std": 0.1893111288547516,
+      "rewards/accuracy_reward": 0.6869791626930237,
+      "rewards/brier_reward": 0.812728750705719,
+      "rewards/confidence_one_or_zero": 0.07578125055879355,
+      "rewards/format_reward": 0.9783854126930237,
+      "rewards/mean_confidence_reward": 0.7320529341697692,
+      "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": 0.01640625,
+      "completions/max_length": 3389.6,
+      "completions/max_terminated_length": 3389.6,
+      "completions/mean_length": 803.64306640625,
+      "completions/mean_terminated_length": 817.1105712890625,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 249.6,
+      "epoch": 0.22799715003562457,
+      "grad_norm": 0.0005609573563560843,
+      "learning_rate": 2.8680203045685284e-06,
+      "loss": -0.0168,
+      "num_tokens": 242959303.0,
+      "reward": 1.235309100151062,
+      "reward_std": 0.17818428277969361,
+      "rewards/accuracy_reward": 0.6747395753860473,
+      "rewards/brier_reward": 0.812617826461792,
+      "rewards/confidence_one_or_zero": 0.003298611124046147,
+      "rewards/format_reward": 0.9832465291023255,
+      "rewards/mean_confidence_reward": 0.7121918439865113,
+      "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": 0.01901041666666665,
+      "completions/max_length": 3287.0,
+      "completions/max_terminated_length": 3287.0,
+      "completions/mean_length": 840.3250122070312,
+      "completions/mean_terminated_length": 856.58330078125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 301.4,
+      "epoch": 0.23999700003749952,
+      "grad_norm": 0.0004377439618110657,
+      "learning_rate": 2.7411167512690357e-06,
+      "loss": -0.0176,
+      "num_tokens": 255738919.0,
+      "reward": 1.248662257194519,
+      "reward_std": 0.1747280478477478,
+      "rewards/accuracy_reward": 0.6919270873069763,
+      "rewards/brier_reward": 0.8243943214416504,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.9809895873069763,
+      "rewards/mean_confidence_reward": 0.6675564289093018,
+      "step": 100
+    },
+    {
+      "epoch": 0.23999700003749952,
+      "eval_completions/clipped_ratio": 0.014756944444444456,
+      "eval_completions/max_length": 2268.0,
+      "eval_completions/max_terminated_length": 2268.0,
+      "eval_completions/mean_length": 831.62744140625,
+      "eval_completions/mean_terminated_length": 844.1648966471354,
+      "eval_completions/min_length": 63.833333333333336,
+      "eval_completions/min_terminated_length": 332.5,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 255738919.0,
+      "eval_reward": 1.2433301011721294,
+      "eval_reward_std": 0.3282207002242406,
+      "eval_rewards/accuracy_reward": 0.6788194378217062,
+      "eval_rewards/brier_reward": 0.8243207434813181,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 0.9835069477558136,
+      "eval_rewards/mean_confidence_reward": 0.649522582689921,
+      "eval_runtime": 322.2356,
+      "eval_samples_per_second": 3.103,
+      "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": 0.01571180555555558,
+      "completions/max_length": 3524.2,
+      "completions/max_terminated_length": 3524.2,
+      "completions/mean_length": 841.7855102539063,
+      "completions/mean_terminated_length": 855.2962036132812,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 271.2,
+      "epoch": 0.2519968500393745,
+      "grad_norm": 0.0004888804396614432,
+      "learning_rate": 2.6142131979695434e-06,
+      "loss": -0.0165,
+      "num_tokens": 268513152.0,
+      "reward": 1.240246868133545,
+      "reward_std": 0.1666222870349884,
+      "rewards/accuracy_reward": 0.678819453716278,
+      "rewards/brier_reward": 0.817373263835907,
+      "rewards/confidence_one_or_zero": 0.0003472222248092294,
+      "rewards/format_reward": 0.9842881917953491,
+      "rewards/mean_confidence_reward": 0.6420749306678772,
+      "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": 0.011371527777777812,
+      "completions/max_length": 3665.8,
+      "completions/max_terminated_length": 3665.8,
+      "completions/mean_length": 875.26884765625,
+      "completions/mean_terminated_length": 885.443701171875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 288.8,
+      "epoch": 0.2639967000412495,
+      "grad_norm": 0.00047984463162720203,
+      "learning_rate": 2.487309644670051e-06,
+      "loss": -0.0108,
+      "num_tokens": 281704697.0,
+      "reward": 1.263697338104248,
+      "reward_std": 0.14904940724372864,
+      "rewards/accuracy_reward": 0.7070312619209289,
+      "rewards/brier_reward": 0.831721568107605,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9886284708976746,
+      "rewards/mean_confidence_reward": 0.6679644227027893,
+      "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": 0.012413194444444442,
+      "completions/max_length": 3634.6,
+      "completions/max_terminated_length": 3634.6,
+      "completions/mean_length": 873.7130249023437,
+      "completions/mean_terminated_length": 884.7570068359375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 301.0,
+      "epoch": 0.27599655004312446,
+      "grad_norm": 0.00046908314106985927,
+      "learning_rate": 2.3604060913705588e-06,
+      "loss": -0.0118,
+      "num_tokens": 294849071.0,
+      "reward": 1.2401302576065063,
+      "reward_std": 0.16665265560150147,
+      "rewards/accuracy_reward": 0.6732638955116272,
+      "rewards/brier_reward": 0.8193958520889282,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.9875868082046508,
+      "rewards/mean_confidence_reward": 0.6962688088417053,
+      "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": 0.008593750000000022,
+      "completions/max_length": 3546.4,
+      "completions/max_terminated_length": 3546.4,
+      "completions/mean_length": 859.1952270507812,
+      "completions/mean_terminated_length": 866.6294067382812,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 295.2,
+      "epoch": 0.28799640004499943,
+      "grad_norm": 0.00041610386688262224,
+      "learning_rate": 2.233502538071066e-06,
+      "loss": -0.0088,
+      "num_tokens": 307828856.0,
+      "reward": 1.2503829956054688,
+      "reward_std": 0.16349477469921112,
+      "rewards/accuracy_reward": 0.6833333373069763,
+      "rewards/brier_reward": 0.8260988116264343,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9913194417953491,
+      "rewards/mean_confidence_reward": 0.7186678171157836,
+      "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": 0.010243055555555537,
+      "completions/max_length": 3428.6,
+      "completions/max_terminated_length": 3428.6,
+      "completions/mean_length": 866.3007080078125,
+      "completions/mean_terminated_length": 875.3722900390625,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 299.4,
+      "epoch": 0.2999962500468744,
+      "grad_norm": 0.0005037845694459975,
+      "learning_rate": 2.1065989847715737e-06,
+      "loss": -0.0094,
+      "num_tokens": 320926304.0,
+      "reward": 1.2674844026565553,
+      "reward_std": 0.16409001648426055,
+      "rewards/accuracy_reward": 0.7037326455116272,
+      "rewards/brier_reward": 0.8417252659797668,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.9894965410232544,
+      "rewards/mean_confidence_reward": 0.7170399188995361,
+      "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": 0.013107638888888907,
+      "completions/max_length": 3691.0,
+      "completions/max_terminated_length": 3691.0,
+      "completions/mean_length": 922.182470703125,
+      "completions/mean_terminated_length": 934.426708984375,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 310.6,
+      "epoch": 0.3119961000487494,
+      "grad_norm": 0.0004879495536442846,
+      "learning_rate": 1.9796954314720814e-06,
+      "loss": -0.0133,
+      "num_tokens": 334674646.0,
+      "reward": 1.2395371913909912,
+      "reward_std": 0.16301891803741456,
+      "rewards/accuracy_reward": 0.6685763955116272,
+      "rewards/brier_reward": 0.8237658858299255,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.98671875,
+      "rewards/mean_confidence_reward": 0.6686067819595337,
+      "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": 0.013888888888888862,
+      "completions/max_length": 3607.0,
+      "completions/max_terminated_length": 3607.0,
+      "completions/mean_length": 936.2807250976563,
+      "completions/mean_terminated_length": 949.4107055664062,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 306.4,
+      "epoch": 0.32399595005062437,
+      "grad_norm": 0.0004939971258863807,
+      "learning_rate": 1.852791878172589e-06,
+      "loss": -0.0143,
+      "num_tokens": 348553624.0,
+      "reward": 1.2485416412353516,
+      "reward_std": 0.16000640988349915,
+      "rewards/accuracy_reward": 0.68359375,
+      "rewards/brier_reward": 0.8275392770767211,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.985937488079071,
+      "rewards/mean_confidence_reward": 0.6367925047874451,
+      "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": 0.013715277777777767,
+      "completions/max_length": 3831.0,
+      "completions/max_terminated_length": 3831.0,
+      "completions/mean_length": 958.5888061523438,
+      "completions/mean_terminated_length": 971.8986938476562,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 361.8,
+      "epoch": 0.33599580005249935,
+      "grad_norm": 0.000400395569158718,
+      "learning_rate": 1.7258883248730964e-06,
+      "loss": -0.014,
+      "num_tokens": 362700791.0,
+      "reward": 1.2510334968566894,
+      "reward_std": 0.15658156871795653,
+      "rewards/accuracy_reward": 0.6869791746139526,
+      "rewards/brier_reward": 0.8289637804031372,
+      "rewards/confidence_one_or_zero": 0.000260416668606922,
+      "rewards/format_reward": 0.9861111164093017,
+      "rewards/mean_confidence_reward": 0.6465494871139527,
+      "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": 0.010763888888888906,
+      "completions/max_length": 3563.0,
+      "completions/max_terminated_length": 3563.0,
+      "completions/mean_length": 965.1240600585937,
+      "completions/mean_terminated_length": 975.6915283203125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 363.2,
+      "epoch": 0.34799565005437433,
+      "grad_norm": 0.00037705147406086326,
+      "learning_rate": 1.5989847715736043e-06,
+      "loss": -0.0103,
+      "num_tokens": 376883628.0,
+      "reward": 1.277334499359131,
+      "reward_std": 0.1482344537973404,
+      "rewards/accuracy_reward": 0.7192708253860474,
+      "rewards/brier_reward": 0.8463218331336975,
+      "rewards/confidence_one_or_zero": 0.0001736111124046147,
+      "rewards/format_reward": 0.9890625,
+      "rewards/mean_confidence_reward": 0.6897005200386047,
+      "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": 0.011458333333333326,
+      "completions/max_length": 3604.0,
+      "completions/max_terminated_length": 3604.0,
+      "completions/mean_length": 1037.48076171875,
+      "completions/mean_terminated_length": 1049.4971313476562,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 386.6,
+      "epoch": 0.3599955000562493,
+      "grad_norm": 0.00044691620860248804,
+      "learning_rate": 1.4720812182741118e-06,
+      "loss": -0.0112,
+      "num_tokens": 391945742.0,
+      "reward": 1.265284013748169,
+      "reward_std": 0.16107824742794036,
+      "rewards/accuracy_reward": 0.7019097208976746,
+      "rewards/brier_reward": 0.8401894569396973,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9884548783302307,
+      "rewards/mean_confidence_reward": 0.7001345157623291,
+      "step": 150
+    },
+    {
+      "epoch": 0.3599955000562493,
+      "eval_completions/clipped_ratio": 0.018923611111111127,
+      "eval_completions/max_length": 2578.1666666666665,
+      "eval_completions/max_terminated_length": 2578.1666666666665,
+      "eval_completions/mean_length": 1002.6307474772135,
+      "eval_completions/mean_terminated_length": 1022.0964050292969,
+      "eval_completions/min_length": 0.0,
+      "eval_completions/min_terminated_length": 426.5,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 391945742.0,
+      "eval_reward": 1.2544946670532227,
+      "eval_reward_std": 0.3295811116695404,
+      "eval_rewards/accuracy_reward": 0.6901041766007742,
+      "eval_rewards/brier_reward": 0.8353646099567413,
+      "eval_rewards/confidence_one_or_zero": 0.0008680555814256271,
+      "eval_rewards/format_reward": 0.9835069477558136,
+      "eval_rewards/mean_confidence_reward": 0.6782117982705435,
+      "eval_runtime": 329.0215,
+      "eval_samples_per_second": 3.039,
+      "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": 0.018489583333333302,
+      "completions/max_length": 3506.6,
+      "completions/max_terminated_length": 3506.6,
+      "completions/mean_length": 990.0326416015625,
+      "completions/mean_terminated_length": 1008.8268432617188,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 392.2,
+      "epoch": 0.3719953500581243,
+      "grad_norm": 0.0004651858762372285,
+      "learning_rate": 1.3451776649746193e-06,
+      "loss": -0.0192,
+      "num_tokens": 406458630.0,
+      "reward": 1.2769456386566163,
+      "reward_std": 0.17086925506591796,
+      "rewards/accuracy_reward": 0.7310763835906983,
+      "rewards/brier_reward": 0.8413774013519287,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.9814236044883728,
+      "rewards/mean_confidence_reward": 0.690551221370697,
+      "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": 0.016666666666666673,
+      "completions/max_length": 3474.8,
+      "completions/max_terminated_length": 3474.8,
+      "completions/mean_length": 1012.5202270507813,
+      "completions/mean_terminated_length": 1029.66376953125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 388.0,
+      "epoch": 0.38399520005999926,
+      "grad_norm": 0.0003789855109062046,
+      "learning_rate": 1.218274111675127e-06,
+      "loss": -0.0163,
+      "num_tokens": 421210159.0,
+      "reward": 1.2442054748535156,
+      "reward_std": 0.1634654939174652,
+      "rewards/accuracy_reward": 0.6777777791023254,
+      "rewards/brier_reward": 0.8272862553596496,
+      "rewards/confidence_one_or_zero": 0.0001736111124046147,
+      "rewards/format_reward": 0.9833333373069764,
+      "rewards/mean_confidence_reward": 0.6832248091697692,
+      "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": 0.017013888888888884,
+      "completions/max_length": 3455.6,
+      "completions/max_terminated_length": 3455.6,
+      "completions/mean_length": 1036.8546020507813,
+      "completions/mean_terminated_length": 1054.9498901367188,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 389.8,
+      "epoch": 0.39599505006187424,
+      "grad_norm": 0.0010382012696936727,
+      "learning_rate": 1.0913705583756345e-06,
+      "loss": -0.0158,
+      "num_tokens": 436293796.0,
+      "reward": 1.2380517244338989,
+      "reward_std": 0.15648340582847595,
+      "rewards/accuracy_reward": 0.6625868082046509,
+      "rewards/brier_reward": 0.8305176854133606,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.9829861164093018,
+      "rewards/mean_confidence_reward": 0.6423246383666992,
+      "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": 0.013107638888888861,
+      "completions/max_length": 3402.2,
+      "completions/max_terminated_length": 3402.2,
+      "completions/mean_length": 995.6934814453125,
+      "completions/mean_terminated_length": 1008.8341430664062,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 362.2,
+      "epoch": 0.4079949000637492,
+      "grad_norm": 0.0004276257532183081,
+      "learning_rate": 9.644670050761422e-07,
+      "loss": -0.0126,
+      "num_tokens": 450853369.0,
+      "reward": 1.2728031158447266,
+      "reward_std": 0.15210382044315338,
+      "rewards/accuracy_reward": 0.7168402671813965,
+      "rewards/brier_reward": 0.8419468402862549,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.986805546283722,
+      "rewards/mean_confidence_reward": 0.6786675453186035,
+      "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": 0.01284722222222221,
+      "completions/max_length": 3748.0,
+      "completions/max_terminated_length": 3748.0,
+      "completions/mean_length": 1020.3355224609375,
+      "completions/mean_terminated_length": 1033.6660888671875,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 369.6,
+      "epoch": 0.4199947500656242,
+      "grad_norm": 0.0005423967377282679,
+      "learning_rate": 8.375634517766498e-07,
+      "loss": -0.0116,
+      "num_tokens": 465715602.0,
+      "reward": 1.2671451807022094,
+      "reward_std": 0.16106505692005157,
+      "rewards/accuracy_reward": 0.7060763835906982,
+      "rewards/brier_reward": 0.8413081169128418,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.9868923544883728,
+      "rewards/mean_confidence_reward": 0.6738255381584167,
+      "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": 0.015451388888888907,
+      "completions/max_length": 3535.4,
+      "completions/max_terminated_length": 3535.4,
+      "completions/mean_length": 983.2767578125,
+      "completions/mean_terminated_length": 998.7015869140625,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 373.0,
+      "epoch": 0.4319946000674992,
+      "grad_norm": 0.0004915730678476393,
+      "learning_rate": 7.106598984771574e-07,
+      "loss": -0.0148,
+      "num_tokens": 480142918.0,
+      "reward": 1.2670525074005128,
+      "reward_std": 0.15874242782592773,
+      "rewards/accuracy_reward": 0.7168402791023254,
+      "rewards/brier_reward": 0.8327020764350891,
+      "rewards/confidence_one_or_zero": 0.000260416668606922,
+      "rewards/format_reward": 0.9845486044883728,
+      "rewards/mean_confidence_reward": 0.7012196183204651,
+      "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": 0.012586805555555558,
+      "completions/max_length": 3636.2,
+      "completions/max_terminated_length": 3636.2,
+      "completions/mean_length": 998.0439208984375,
+      "completions/mean_terminated_length": 1010.7783203125,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 346.6,
+      "epoch": 0.44399445006937416,
+      "grad_norm": 0.0005585678154602647,
+      "learning_rate": 5.83756345177665e-07,
+      "loss": -0.012,
+      "num_tokens": 494730432.0,
+      "reward": 1.2518677711486816,
+      "reward_std": 0.16244393587112427,
+      "rewards/accuracy_reward": 0.6817708253860474,
+      "rewards/brier_reward": 0.8345379948616027,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.987413203716278,
+      "rewards/mean_confidence_reward": 0.6762803792953491,
+      "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": 0.010156249999999978,
+      "completions/max_length": 3530.2,
+      "completions/max_terminated_length": 3530.2,
+      "completions/mean_length": 979.3949829101563,
+      "completions/mean_terminated_length": 989.3971069335937,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 395.0,
+      "epoch": 0.45599430007124914,
+      "grad_norm": 0.0004858736938331276,
+      "learning_rate": 4.568527918781726e-07,
+      "loss": -0.0101,
+      "num_tokens": 509096006.0,
+      "reward": 1.276425051689148,
+      "reward_std": 0.152652707695961,
+      "rewards/accuracy_reward": 0.7210069417953491,
+      "rewards/brier_reward": 0.8419852733612061,
+      "rewards/confidence_one_or_zero": 0.0001736111124046147,
+      "rewards/format_reward": 0.989843738079071,
+      "rewards/mean_confidence_reward": 0.7043576240539551,
+      "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": 0.012934027777777768,
+      "completions/max_length": 3613.8,
+      "completions/max_terminated_length": 3613.8,
+      "completions/mean_length": 1004.6217895507813,
+      "completions/mean_terminated_length": 1017.9731323242188,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 351.8,
+      "epoch": 0.46799415007312406,
+      "grad_norm": 0.00045332699664868414,
+      "learning_rate": 3.2994923857868026e-07,
+      "loss": -0.0123,
+      "num_tokens": 523750113.0,
+      "reward": 1.2433192253112793,
+      "reward_std": 0.16497401297092437,
+      "rewards/accuracy_reward": 0.6746527791023255,
+      "rewards/brier_reward": 0.8250796437263489,
+      "rewards/confidence_one_or_zero": 0.000260416668606922,
+      "rewards/format_reward": 0.9868923783302307,
+      "rewards/mean_confidence_reward": 0.6832942724227905,
+      "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": 0.010503472222222232,
+      "completions/max_length": 3605.0,
+      "completions/max_terminated_length": 3605.0,
+      "completions/mean_length": 991.7037475585937,
+      "completions/mean_terminated_length": 1002.2833374023437,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 385.8,
+      "epoch": 0.47999400007499904,
+      "grad_norm": 0.000445247016614303,
+      "learning_rate": 2.0304568527918783e-07,
+      "loss": -0.01,
+      "num_tokens": 538242348.0,
+      "reward": 1.2666230201721191,
+      "reward_std": 0.1489817589521408,
+      "rewards/accuracy_reward": 0.7033854246139526,
+      "rewards/brier_reward": 0.840523874759674,
+      "rewards/confidence_one_or_zero": 0.0001736111124046147,
+      "rewards/format_reward": 0.9893229126930236,
+      "rewards/mean_confidence_reward": 0.6932456612586975,
+      "step": 200
+    },
+    {
+      "epoch": 0.47999400007499904,
+      "eval_completions/clipped_ratio": 0.013020833333333334,
+      "eval_completions/max_length": 2447.0,
+      "eval_completions/max_terminated_length": 2447.0,
+      "eval_completions/mean_length": 982.8340454101562,
+      "eval_completions/mean_terminated_length": 995.8915710449219,
+      "eval_completions/min_length": 85.33333333333333,
+      "eval_completions/min_terminated_length": 435.5,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 538242348.0,
+      "eval_reward": 1.2601836721102397,
+      "eval_reward_std": 0.32464847962061566,
+      "eval_rewards/accuracy_reward": 0.7057291666666666,
+      "eval_rewards/brier_reward": 0.829381505648295,
+      "eval_rewards/confidence_one_or_zero": 0.0008680555814256271,
+      "eval_rewards/format_reward": 0.9852430522441864,
+      "eval_rewards/mean_confidence_reward": 0.6809461911519369,
+      "eval_runtime": 325.5733,
+      "eval_samples_per_second": 3.072,
+      "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": 0.01371527777777779,
+      "completions/max_length": 3609.8,
+      "completions/max_terminated_length": 3609.8,
+      "completions/mean_length": 1008.6137329101563,
+      "completions/mean_terminated_length": 1022.6266235351562,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 371.6,
+      "epoch": 0.491993850076874,
+      "grad_norm": 0.0003949266974814236,
+      "learning_rate": 7.614213197969544e-08,
+      "loss": -0.0132,
+      "num_tokens": 552927530.0,
+      "reward": 1.291322445869446,
+      "reward_std": 0.1527684062719345,
+      "rewards/accuracy_reward": 0.7461805582046509,
+      "rewards/brier_reward": 0.8501658320426941,
+      "rewards/confidence_one_or_zero": 8.680555620230735e-05,
+      "rewards/format_reward": 0.9862847328186035,
+      "rewards/mean_confidence_reward": 0.6899566054344177,
+      "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": 0.008101851851851824,
+      "completions/max_length": 3854.6666666666665,
+      "completions/max_terminated_length": 3854.6666666666665,
+      "completions/mean_length": 1010.2601725260416,
+      "completions/mean_terminated_length": 1018.6278889973959,
+      "completions/min_length": 0.0,
+      "completions/min_terminated_length": 327.3333333333333,
+      "epoch": 0.49919376007799904,
+      "num_tokens": 561776496.0,
+      "reward": 1.2661747137705486,
+      "reward_std": 0.1512370283404986,
+      "rewards/accuracy_reward": 0.7044270833333334,
+      "rewards/brier_reward": 0.8360105156898499,
+      "rewards/confidence_one_or_zero": 0.00028935185400769114,
+      "rewards/format_reward": 0.9918981393178304,
+      "rewards/mean_confidence_reward": 0.6803168257077535,
+      "step": 208,
+      "total_flos": 0.0,
+      "train_loss": -0.019072025002410207,
+      "train_runtime": 90469.3907,
+      "train_samples_per_second": 0.166,
+      "train_steps_per_second": 0.002
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 208,
+  "num_input_tokens_seen": 561776496,
+  "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:c3bb8c95c0097eaf91410d97aef4eee8b11c27a596b073048728e5fcd6d667d1
+size 8312