Model save

.gitattributes

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

README.md

@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-7B
+library_name: transformers
+model_name: bandit-log-RLCR-v1
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for bandit-log-RLCR-v1
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="mehuldamani/bandit-log-RLCR-v1", 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/RLCR/runs/qlwkmzz2) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.48.3
+- Pytorch: 2.5.1
+- Datasets: 4.0.0
+- Tokenizers: 0.21.1
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

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

config.json

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

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76000cd66656cfff1af2ab831bc65755ea2aba3be3ef274b8df32b1857937b08
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80b2d806940a74451b832c35b4604072a3ae94700b023c4cf5af9a26b19a5443
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf1219a9a8f1953efdb4cdad4ad7396f6de67a6bfb468e12923fe8bf89a3155
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7325f432ffdea1a4476f2a2533eea5d3f8474caf1b2520a92e4c49511accc35
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1031 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9996190476190476,
+  "eval_steps": 50,
+  "global_step": 164,
+  "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": 0.76337890625,
+      "completions/max_length": 128.0,
+      "completions/max_terminated_length": 128.0,
+      "completions/mean_length": 116.70947265625,
+      "completions/mean_terminated_length": 80.29782409667969,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "epoch": 0.030476190476190476,
+      "grad_norm": 0.48198601603507996,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.3641,
+      "num_tokens": 3784033.0,
+      "reward": 1.6605166435241698,
+      "reward_std": 3.4095802307128906,
+      "rewards/accuracy_reward": 0.03017578125,
+      "rewards/brier_reward": 0.130406653881073,
+      "rewards/confidence_one_or_zero": 0.105078125,
+      "rewards/format_reward": 0.1703125,
+      "rewards/log_2_reward": 1.5602725982666015,
+      "rewards/mean_confidence_reward": 0.10646367371082306,
+      "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": 0.42197265625,
+      "completions/max_length": 128.0,
+      "completions/max_terminated_length": 128.0,
+      "completions/mean_length": 97.47744140625,
+      "completions/mean_terminated_length": 76.52580413818359,
+      "completions/min_length": 5.2,
+      "completions/min_terminated_length": 5.2,
+      "epoch": 0.06095238095238095,
+      "grad_norm": 0.38170281052589417,
+      "learning_rate": 1e-06,
+      "loss": 0.7106,
+      "num_tokens": 7371066.0,
+      "reward": 5.354305839538574,
+      "reward_std": 4.306017875671387,
+      "rewards/accuracy_reward": 0.12158203125,
+      "rewards/brier_reward": 0.41428526639938357,
+      "rewards/confidence_one_or_zero": 0.2091796875,
+      "rewards/format_reward": 0.54599609375,
+      "rewards/log_2_reward": 5.020516633987427,
+      "rewards/mean_confidence_reward": 0.27076671421527865,
+      "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": 0.04169921875,
+      "completions/max_length": 128.0,
+      "completions/max_terminated_length": 124.4,
+      "completions/mean_length": 63.0056640625,
+      "completions/mean_terminated_length": 60.36174392700195,
+      "completions/min_length": 16.4,
+      "completions/min_terminated_length": 16.4,
+      "epoch": 0.09142857142857143,
+      "grad_norm": 0.1799696832895279,
+      "learning_rate": 1e-06,
+      "loss": 0.2204,
+      "num_tokens": 10604244.0,
+      "reward": 9.318659210205078,
+      "reward_std": 2.0989513874053953,
+      "rewards/accuracy_reward": 0.19326171875,
+      "rewards/brier_reward": 0.7086999773979187,
+      "rewards/confidence_one_or_zero": 0.30234375,
+      "rewards/format_reward": 0.95224609375,
+      "rewards/log_2_reward": 8.745905876159668,
+      "rewards/mean_confidence_reward": 0.4371440947055817,
+      "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": 0.000390625,
+      "completions/max_length": 112.0,
+      "completions/max_terminated_length": 99.6,
+      "completions/mean_length": 43.30595703125,
+      "completions/mean_terminated_length": 43.27299423217774,
+      "completions/min_length": 17.6,
+      "completions/min_terminated_length": 17.6,
+      "epoch": 0.1219047619047619,
+      "grad_norm": 0.0386660136282444,
+      "learning_rate": 1e-06,
+      "loss": -0.0043,
+      "num_tokens": 13634321.0,
+      "reward": 10.072226905822754,
+      "reward_std": 0.6315600275993347,
+      "rewards/accuracy_reward": 0.16630859375,
+      "rewards/brier_reward": 0.8290799617767334,
+      "rewards/confidence_one_or_zero": 0.44169921875,
+      "rewards/format_reward": 0.9970703125,
+      "rewards/log_2_reward": 9.490537071228028,
+      "rewards/mean_confidence_reward": 0.31124078631401064,
+      "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": 0.0,
+      "completions/max_length": 90.0,
+      "completions/max_terminated_length": 90.0,
+      "completions/mean_length": 42.37373046875,
+      "completions/mean_terminated_length": 42.37373046875,
+      "completions/min_length": 22.0,
+      "completions/min_terminated_length": 22.0,
+      "epoch": 0.1523809523809524,
+      "grad_norm": 0.013290881179273129,
+      "learning_rate": 1e-06,
+      "loss": -0.001,
+      "num_tokens": 16657508.0,
+      "reward": 10.345937538146973,
+      "reward_std": 0.27599466145038604,
+      "rewards/accuracy_reward": 0.11845703125,
+      "rewards/brier_reward": 0.9262194037437439,
+      "rewards/confidence_one_or_zero": 0.70439453125,
+      "rewards/format_reward": 0.99912109375,
+      "rewards/log_2_reward": 9.787148475646973,
+      "rewards/mean_confidence_reward": 0.13568951636552812,
+      "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": 0.0,
+      "completions/max_length": 77.6,
+      "completions/max_terminated_length": 77.6,
+      "completions/mean_length": 40.87314453125,
+      "completions/mean_terminated_length": 40.87314453125,
+      "completions/min_length": 24.0,
+      "completions/min_terminated_length": 24.0,
+      "epoch": 0.18285714285714286,
+      "grad_norm": 0.01713799685239792,
+      "learning_rate": 1e-06,
+      "loss": 0.0003,
+      "num_tokens": 19663153.0,
+      "reward": 10.48781967163086,
+      "reward_std": 0.0398749703541398,
+      "rewards/accuracy_reward": 0.00849609375,
+      "rewards/brier_reward": 0.9944719195365905,
+      "rewards/confidence_one_or_zero": 0.98203125,
+      "rewards/format_reward": 0.9998046875,
+      "rewards/log_2_reward": 9.98366928100586,
+      "rewards/mean_confidence_reward": 0.005668945552315563,
+      "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": 0.0,
+      "completions/max_length": 60.6,
+      "completions/max_terminated_length": 60.6,
+      "completions/mean_length": 40.10283203125,
+      "completions/mean_terminated_length": 40.10283203125,
+      "completions/min_length": 24.2,
+      "completions/min_terminated_length": 24.2,
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 22658990.0,
+      "reward": 10.499842834472656,
+      "reward_std": 0.0008906088653020561,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.9999728918075561,
+      "rewards/confidence_one_or_zero": 0.99912109375,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.999842834472656,
+      "rewards/mean_confidence_reward": 0.00014160156424622983,
+      "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": 0.0,
+      "completions/max_length": 60.4,
+      "completions/max_terminated_length": 60.4,
+      "completions/mean_length": 39.8552734375,
+      "completions/mean_terminated_length": 39.8552734375,
+      "completions/min_length": 25.8,
+      "completions/min_terminated_length": 25.8,
+      "epoch": 0.2438095238095238,
+      "grad_norm": 9.549452079227194e-05,
+      "learning_rate": 1e-06,
+      "loss": 0.0001,
+      "num_tokens": 25658020.0,
+      "reward": 10.498812484741212,
+      "reward_std": 0.006671252334490419,
+      "rewards/accuracy_reward": 9.765625e-05,
+      "rewards/brier_reward": 0.9998310446739197,
+      "rewards/confidence_one_or_zero": 0.999609375,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.998812484741212,
+      "rewards/mean_confidence_reward": 6.83593752910383e-05,
+      "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": 0.0,
+      "completions/max_length": 58.2,
+      "completions/max_terminated_length": 58.2,
+      "completions/mean_length": 39.4888671875,
+      "completions/mean_terminated_length": 39.4888671875,
+      "completions/min_length": 26.2,
+      "completions/min_terminated_length": 26.2,
+      "epoch": 0.2742857142857143,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": -0.0001,
+      "num_tokens": 28652306.0,
+      "reward": 10.498974609375,
+      "reward_std": 0.005800485238432884,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.99990234375,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.9990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 56.6,
+      "completions/max_terminated_length": 56.6,
+      "completions/mean_length": 39.37822265625,
+      "completions/mean_terminated_length": 39.37822265625,
+      "completions/min_length": 26.6,
+      "completions/min_terminated_length": 26.6,
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 31639059.0,
+      "reward": 10.498974609375,
+      "reward_std": 0.005800485238432884,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.99990234375,
+      "rewards/confidence_one_or_zero": 0.99990234375,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.9990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 48.25,
+      "eval_completions/max_terminated_length": 48.25,
+      "eval_completions/mean_length": 39.21484375,
+      "eval_completions/mean_terminated_length": 39.21484375,
+      "eval_completions/min_length": 29.25,
+      "eval_completions/min_terminated_length": 29.25,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 31639059.0,
+      "eval_reward": 10.5,
+      "eval_reward_std": 0.0,
+      "eval_rewards/accuracy_reward": 0.0,
+      "eval_rewards/brier_reward": 1.0,
+      "eval_rewards/confidence_one_or_zero": 1.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/log_2_reward": 10.0,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 7.2463,
+      "eval_samples_per_second": 69.001,
+      "eval_steps_per_second": 0.552,
+      "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": 0.0,
+      "completions/max_length": 55.0,
+      "completions/max_terminated_length": 55.0,
+      "completions/mean_length": 39.50654296875,
+      "completions/mean_terminated_length": 39.50654296875,
+      "completions/min_length": 26.0,
+      "completions/min_terminated_length": 26.0,
+      "epoch": 0.3352380952380952,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 34630902.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 55.4,
+      "completions/max_terminated_length": 55.4,
+      "completions/mean_length": 39.666015625,
+      "completions/mean_terminated_length": 39.666015625,
+      "completions/min_length": 26.8,
+      "completions/min_terminated_length": 26.8,
+      "epoch": 0.3657142857142857,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 37627098.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 60
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 55.4,
+      "completions/max_terminated_length": 55.4,
+      "completions/mean_length": 39.70166015625,
+      "completions/mean_terminated_length": 39.70166015625,
+      "completions/min_length": 25.0,
+      "completions/min_terminated_length": 25.0,
+      "epoch": 0.3961904761904762,
+      "grad_norm": 0.004820019006729126,
+      "learning_rate": 1e-06,
+      "loss": 0.0002,
+      "num_tokens": 40622155.0,
+      "reward": 10.498974609375,
+      "reward_std": 0.005800485238432884,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.99990234375,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.9990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 65
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 56.2,
+      "completions/max_terminated_length": 56.2,
+      "completions/mean_length": 39.75986328125,
+      "completions/mean_terminated_length": 39.75986328125,
+      "completions/min_length": 25.2,
+      "completions/min_terminated_length": 25.2,
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 43618960.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 70
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 57.2,
+      "completions/max_terminated_length": 57.2,
+      "completions/mean_length": 39.5822265625,
+      "completions/mean_terminated_length": 39.5822265625,
+      "completions/min_length": 25.2,
+      "completions/min_terminated_length": 25.2,
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": -0.0002,
+      "num_tokens": 46609594.0,
+      "reward": 10.498974609375,
+      "reward_std": 0.005800485238432884,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.99990234375,
+      "rewards/confidence_one_or_zero": 0.99990234375,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.9990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 75
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 55.2,
+      "completions/max_terminated_length": 55.2,
+      "completions/mean_length": 39.87529296875,
+      "completions/mean_terminated_length": 39.87529296875,
+      "completions/min_length": 27.0,
+      "completions/min_terminated_length": 27.0,
+      "epoch": 0.4876190476190476,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0001,
+      "num_tokens": 49602237.0,
+      "reward": 10.498974609375,
+      "reward_std": 0.005800485238432884,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.99990234375,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.9990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 80
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 59.0,
+      "completions/max_terminated_length": 59.0,
+      "completions/mean_length": 40.1205078125,
+      "completions/mean_terminated_length": 40.1205078125,
+      "completions/min_length": 27.2,
+      "completions/min_terminated_length": 27.2,
+      "epoch": 0.518095238095238,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 52598607.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 85
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 59.2,
+      "completions/max_terminated_length": 59.2,
+      "completions/mean_length": 40.13505859375,
+      "completions/mean_terminated_length": 40.13505859375,
+      "completions/min_length": 25.8,
+      "completions/min_terminated_length": 25.8,
+      "epoch": 0.5485714285714286,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 55596438.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 90
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 56.8,
+      "completions/max_terminated_length": 56.8,
+      "completions/mean_length": 40.24052734375,
+      "completions/mean_terminated_length": 40.24052734375,
+      "completions/min_length": 27.8,
+      "completions/min_terminated_length": 27.8,
+      "epoch": 0.579047619047619,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 58594133.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 95
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 56.6,
+      "completions/max_terminated_length": 56.6,
+      "completions/mean_length": 40.23056640625,
+      "completions/mean_terminated_length": 40.23056640625,
+      "completions/min_length": 26.0,
+      "completions/min_terminated_length": 26.0,
+      "epoch": 0.6095238095238096,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 61594062.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 50.75,
+      "eval_completions/max_terminated_length": 50.75,
+      "eval_completions/mean_length": 40.36058712005615,
+      "eval_completions/mean_terminated_length": 40.36058712005615,
+      "eval_completions/min_length": 29.5,
+      "eval_completions/min_terminated_length": 29.5,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 61594062.0,
+      "eval_reward": 10.5,
+      "eval_reward_std": 0.0,
+      "eval_rewards/accuracy_reward": 0.0,
+      "eval_rewards/brier_reward": 1.0,
+      "eval_rewards/confidence_one_or_zero": 1.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/log_2_reward": 10.0,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 7.5851,
+      "eval_samples_per_second": 65.919,
+      "eval_steps_per_second": 0.527,
+      "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": 0.0,
+      "completions/max_length": 58.0,
+      "completions/max_terminated_length": 58.0,
+      "completions/mean_length": 40.31025390625,
+      "completions/mean_terminated_length": 40.31025390625,
+      "completions/min_length": 27.4,
+      "completions/min_terminated_length": 27.4,
+      "epoch": 0.64,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 64598391.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 105
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 57.2,
+      "completions/max_terminated_length": 57.2,
+      "completions/mean_length": 40.2923828125,
+      "completions/mean_terminated_length": 40.2923828125,
+      "completions/min_length": 27.4,
+      "completions/min_terminated_length": 27.4,
+      "epoch": 0.6704761904761904,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 67599081.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 110
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 58.2,
+      "completions/max_terminated_length": 58.2,
+      "completions/mean_length": 40.179296875,
+      "completions/mean_terminated_length": 40.179296875,
+      "completions/min_length": 27.4,
+      "completions/min_terminated_length": 27.4,
+      "epoch": 0.700952380952381,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 70597301.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 115
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 57.2,
+      "completions/max_terminated_length": 57.2,
+      "completions/mean_length": 40.3193359375,
+      "completions/mean_terminated_length": 40.3193359375,
+      "completions/min_length": 26.8,
+      "completions/min_terminated_length": 26.8,
+      "epoch": 0.7314285714285714,
+      "grad_norm": 0.024884896352887154,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 73598459.0,
+      "reward": 10.498974609375,
+      "reward_std": 0.005800485238432884,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.99990234375,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.9990234375,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 120
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 55.2,
+      "completions/max_terminated_length": 55.2,
+      "completions/mean_length": 40.234375,
+      "completions/mean_terminated_length": 40.234375,
+      "completions/min_length": 26.0,
+      "completions/min_terminated_length": 26.0,
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 76599483.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 125
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 53.8,
+      "completions/max_terminated_length": 53.8,
+      "completions/mean_length": 40.09111328125,
+      "completions/mean_terminated_length": 40.09111328125,
+      "completions/min_length": 27.2,
+      "completions/min_terminated_length": 27.2,
+      "epoch": 0.7923809523809524,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 79599104.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 130
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 54.8,
+      "completions/max_terminated_length": 54.8,
+      "completions/mean_length": 39.84951171875,
+      "completions/mean_terminated_length": 39.84951171875,
+      "completions/min_length": 25.8,
+      "completions/min_terminated_length": 25.8,
+      "epoch": 0.8228571428571428,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 82590299.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 135
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 56.2,
+      "completions/max_terminated_length": 56.2,
+      "completions/mean_length": 39.871875,
+      "completions/mean_terminated_length": 39.871875,
+      "completions/min_length": 26.8,
+      "completions/min_terminated_length": 26.8,
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 85586203.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 140
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 55.6,
+      "completions/max_terminated_length": 55.6,
+      "completions/mean_length": 40.103125,
+      "completions/mean_terminated_length": 40.103125,
+      "completions/min_length": 27.4,
+      "completions/min_terminated_length": 27.4,
+      "epoch": 0.8838095238095238,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 88590747.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 145
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 55.2,
+      "completions/max_terminated_length": 55.2,
+      "completions/mean_length": 39.84501953125,
+      "completions/mean_terminated_length": 39.84501953125,
+      "completions/min_length": 27.2,
+      "completions/min_terminated_length": 27.2,
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 91584520.0,
+      "reward": 10.5,
+      "reward_std": 0.0,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 1.0,
+      "rewards/confidence_one_or_zero": 1.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 10.0,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 49.75,
+      "eval_completions/max_terminated_length": 49.75,
+      "eval_completions/mean_length": 39.660088539123535,
+      "eval_completions/mean_terminated_length": 39.660088539123535,
+      "eval_completions/min_length": 30.25,
+      "eval_completions/min_terminated_length": 30.25,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 91584520.0,
+      "eval_reward": 10.5,
+      "eval_reward_std": 0.0,
+      "eval_rewards/accuracy_reward": 0.0,
+      "eval_rewards/brier_reward": 1.0,
+      "eval_rewards/confidence_one_or_zero": 1.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/log_2_reward": 10.0,
+      "eval_rewards/mean_confidence_reward": 0.0,
+      "eval_runtime": 7.0368,
+      "eval_samples_per_second": 71.055,
+      "eval_steps_per_second": 0.568,
+      "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": 0.0,
+      "completions/max_length": 54.4,
+      "completions/max_terminated_length": 54.4,
+      "completions/mean_length": 39.9212890625,
+      "completions/mean_terminated_length": 39.9212890625,
+      "completions/min_length": 26.8,
+      "completions/min_terminated_length": 26.8,
+      "epoch": 0.9447619047619048,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 94581058.0,
+      "reward": 10.49995002746582,
+      "reward_std": 0.0002821940928697586,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.9999843716621399,
+      "rewards/confidence_one_or_zero": 0.99990234375,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.99995002746582,
+      "rewards/mean_confidence_reward": 3.906250058207661e-05,
+      "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": 0.0,
+      "completions/max_length": 55.4,
+      "completions/max_terminated_length": 55.4,
+      "completions/mean_length": 39.9310546875,
+      "completions/mean_terminated_length": 39.9310546875,
+      "completions/min_length": 26.6,
+      "completions/min_terminated_length": 26.6,
+      "epoch": 0.9752380952380952,
+      "grad_norm": 0.0,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 97578656.0,
+      "reward": 10.499971961975097,
+      "reward_std": 0.00015892352676019072,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.999993896484375,
+      "rewards/confidence_one_or_zero": 0.99990234375,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.999971961975097,
+      "rewards/mean_confidence_reward": 2.44140625e-05,
+      "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": 0.0,
+      "completions/max_length": 61.25,
+      "completions/max_terminated_length": 61.25,
+      "completions/mean_length": 39.9080171585083,
+      "completions/mean_terminated_length": 39.9080171585083,
+      "completions/min_length": 26.75,
+      "completions/min_terminated_length": 26.75,
+      "epoch": 0.9996190476190476,
+      "num_tokens": 99976491.0,
+      "reward": 10.49871826171875,
+      "reward_std": 0.007250606548041105,
+      "rewards/accuracy_reward": 0.0,
+      "rewards/brier_reward": 0.9998779296875,
+      "rewards/confidence_one_or_zero": 0.9998779296875,
+      "rewards/format_reward": 0.9998779296875,
+      "rewards/log_2_reward": 9.998779296875,
+      "rewards/mean_confidence_reward": 0.0,
+      "step": 164,
+      "total_flos": 0.0,
+      "train_loss": 0.03933636305515481,
+      "train_runtime": 14176.1116,
+      "train_samples_per_second": 0.741,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 164,
+  "num_input_tokens_seen": 99976491,
+  "num_train_epochs": 1,
+  "save_steps": 60,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63d4aa4220126ce39e3c759e942549268b55541cf2f0832d0eb04d0aa957fcdc
+size 8056