Upload folder using huggingface_hub

.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

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
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.10659663751721382,
+    "train_runtime": 145281.9904,
+    "train_samples": 631,
+    "train_samples_per_second": 0.087,
+    "train_steps_per_second": 0.001
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/work/home/liuweichu/Qwen2.5-Math-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": 4096,
+  "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": 10000,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "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": "4.49.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50f97bfc1069218cd448e227bccfe082d45630af674d68df8d555374ac742156
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2c644185c03b21bbcd9aaafdfb2345e83b5948cd5997992fdc97c5f0123689
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65434840cbdc19add497f8260a95fcf19d46ed88df25a2f647f717da80956422
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5d61644122f0f277b1cc88e292b052cb750506cd75abde97b08e2c59d92c8f8
+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 +1,208 @@
+{
+  "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        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\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\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.10659663751721382,
+    "train_runtime": 145281.9904,
+    "train_samples": 631,
+    "train_samples_per_second": 0.087,
+    "train_steps_per_second": 0.001
+}

trainer_state.json

@@ -0,0 +1,1162 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 19.810126582278482,
+  "eval_steps": 500,
+  "global_step": 80,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1317.9442443847656,
+      "epoch": 0.20253164556962025,
+      "grad_norm": 0.15780125558376312,
+      "kl": 0.0,
+      "learning_rate": 3.75e-07,
+      "loss": 0.0571,
+      "reward": 0.24441965110599995,
+      "reward_std": 0.26795641146600246,
+      "rewards/accuracy_reward": 0.20312500791624188,
+      "rewards/format_reward": 0.04129464481957257,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1309.1719398498535,
+      "epoch": 0.4050632911392405,
+      "grad_norm": 0.14830459654331207,
+      "kl": 0.0,
+      "learning_rate": 7.5e-07,
+      "loss": 0.0497,
+      "reward": 0.20312500861473382,
+      "reward_std": 0.2503739036619663,
+      "rewards/accuracy_reward": 0.1551339355064556,
+      "rewards/format_reward": 0.047991073690354824,
+      "step": 2
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1356.9543018341064,
+      "epoch": 0.6075949367088608,
+      "grad_norm": 0.12031414359807968,
+      "kl": 0.00023540854454040527,
+      "learning_rate": 1.125e-06,
+      "loss": 0.0485,
+      "reward": 0.19642858079168946,
+      "reward_std": 0.25526259164325893,
+      "rewards/accuracy_reward": 0.15736607962753624,
+      "rewards/format_reward": 0.03906250209547579,
+      "step": 3
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1246.4500675201416,
+      "epoch": 0.810126582278481,
+      "grad_norm": 0.1266031116247177,
+      "kl": 0.0002713203430175781,
+      "learning_rate": 1.5e-06,
+      "loss": 0.0401,
+      "reward": 0.20424107799772173,
+      "reward_std": 0.24340283521451056,
+      "rewards/accuracy_reward": 0.16294643690343946,
+      "rewards/format_reward": 0.041294645285233855,
+      "step": 4
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1280.3237266540527,
+      "epoch": 1.2025316455696202,
+      "grad_norm": 0.1469860076904297,
+      "kl": 0.00030854344367980957,
+      "learning_rate": 1.875e-06,
+      "loss": 0.0877,
+      "reward": 0.21316965215373784,
+      "reward_std": 0.2447465395089239,
+      "rewards/accuracy_reward": 0.17745536426082253,
+      "rewards/format_reward": 0.03571428754366934,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1362.0257396697998,
+      "epoch": 1.4050632911392404,
+      "grad_norm": 0.10963964462280273,
+      "kl": 0.0003065764904022217,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0574,
+      "reward": 0.21651786682195961,
+      "reward_std": 0.2525859682355076,
+      "rewards/accuracy_reward": 0.18191965203732252,
+      "rewards/format_reward": 0.03459821629803628,
+      "step": 6
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1365.2232837677002,
+      "epoch": 1.6075949367088609,
+      "grad_norm": 0.143161341547966,
+      "kl": 0.0009369254112243652,
+      "learning_rate": 2.6250000000000003e-06,
+      "loss": 0.0556,
+      "reward": 0.22321429511066526,
+      "reward_std": 0.26517220702953637,
+      "rewards/accuracy_reward": 0.1696428646100685,
+      "rewards/format_reward": 0.05357143119908869,
+      "step": 7
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1320.9459075927734,
+      "epoch": 1.810126582278481,
+      "grad_norm": 0.0994948148727417,
+      "kl": 0.002080678939819336,
+      "learning_rate": 3e-06,
+      "loss": 0.0839,
+      "reward": 0.26227679871954024,
+      "reward_std": 0.28934473474510014,
+      "rewards/accuracy_reward": 0.2087053683353588,
+      "rewards/format_reward": 0.053571431897580624,
+      "step": 8
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1262.8661212921143,
+      "epoch": 2.2025316455696204,
+      "grad_norm": 0.8203178644180298,
+      "kl": 0.0046384334564208984,
+      "learning_rate": 2.998572332372787e-06,
+      "loss": 0.0457,
+      "reward": 0.2868303719442338,
+      "reward_std": 0.3498251587152481,
+      "rewards/accuracy_reward": 0.18861608114093542,
+      "rewards/format_reward": 0.09821428963914514,
+      "step": 9
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1360.1105499267578,
+      "epoch": 2.4050632911392404,
+      "grad_norm": 0.1783958524465561,
+      "kl": 0.013251304626464844,
+      "learning_rate": 2.994292047137618e-06,
+      "loss": 0.0292,
+      "reward": 0.26227679825387895,
+      "reward_std": 0.30967882834374905,
+      "rewards/accuracy_reward": 0.15736607799772173,
+      "rewards/format_reward": 0.10491071920841932,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1258.4922485351562,
+      "epoch": 2.607594936708861,
+      "grad_norm": 0.14482943713665009,
+      "kl": 0.01790475845336914,
+      "learning_rate": 2.9871672920607156e-06,
+      "loss": 0.0542,
+      "reward": 0.2879464461002499,
+      "reward_std": 0.36507281148806214,
+      "rewards/accuracy_reward": 0.12723214749712497,
+      "rewards/format_reward": 0.16071429359726608,
+      "step": 11
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1224.5542240142822,
+      "epoch": 2.810126582278481,
+      "grad_norm": 0.18995879590511322,
+      "kl": 0.015253305435180664,
+      "learning_rate": 2.9772116295183124e-06,
+      "loss": 0.0481,
+      "reward": 0.40066965902224183,
+      "reward_std": 0.44980036094784737,
+      "rewards/accuracy_reward": 0.1986607233993709,
+      "rewards/format_reward": 0.20200893806759268,
+      "step": 12
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1317.55810546875,
+      "epoch": 3.2025316455696204,
+      "grad_norm": 0.12641476094722748,
+      "kl": 0.028325557708740234,
+      "learning_rate": 2.9644440106799e-06,
+      "loss": 0.083,
+      "reward": 0.5022321622818708,
+      "reward_std": 0.48967235907912254,
+      "rewards/accuracy_reward": 0.21093750931322575,
+      "rewards/format_reward": 0.29129465599544346,
+      "step": 13
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1256.8672466278076,
+      "epoch": 3.4050632911392404,
+      "grad_norm": 9.634344100952148,
+      "kl": 0.02230978012084961,
+      "learning_rate": 2.9488887394336023e-06,
+      "loss": 0.0578,
+      "reward": 0.5457589533179998,
+      "reward_std": 0.5024354420602322,
+      "rewards/accuracy_reward": 0.16406250861473382,
+      "rewards/format_reward": 0.3816964467987418,
+      "step": 14
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1307.5703716278076,
+      "epoch": 3.607594936708861,
+      "grad_norm": 0.38609325885772705,
+      "kl": 0.02093505859375,
+      "learning_rate": 2.9305754261223403e-06,
+      "loss": 0.0582,
+      "reward": 0.6060268161818385,
+      "reward_std": 0.48538014432415366,
+      "rewards/accuracy_reward": 0.17410715005826205,
+      "rewards/format_reward": 0.4319196632131934,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1322.5646591186523,
+      "epoch": 3.810126582278481,
+      "grad_norm": 0.29984602332115173,
+      "kl": 0.025579452514648438,
+      "learning_rate": 2.9095389311788626e-06,
+      "loss": 0.0647,
+      "reward": 0.6071428805589676,
+      "reward_std": 0.48221714748069644,
+      "rewards/accuracy_reward": 0.12723214947618544,
+      "rewards/format_reward": 0.47991073597222567,
+      "step": 16
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1265.1797485351562,
+      "epoch": 4.2025316455696204,
+      "grad_norm": 0.22652213275432587,
+      "kl": 0.047135353088378906,
+      "learning_rate": 2.88581929876693e-06,
+      "loss": 0.032,
+      "reward": 0.728794677183032,
+      "reward_std": 0.5240897228941321,
+      "rewards/accuracy_reward": 0.17522322153672576,
+      "rewards/format_reward": 0.5535714561119676,
+      "step": 17
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1309.780195236206,
+      "epoch": 4.405063291139241,
+      "grad_norm": 0.16519580781459808,
+      "kl": 0.013474464416503906,
+      "learning_rate": 2.859461680554975e-06,
+      "loss": 0.0598,
+      "reward": 0.7276786109432578,
+      "reward_std": 0.5046426299959421,
+      "rewards/accuracy_reward": 0.1540178640279919,
+      "rewards/format_reward": 0.5736607434228063,
+      "step": 18
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1320.1898040771484,
+      "epoch": 4.6075949367088604,
+      "grad_norm": 0.13712696731090546,
+      "kl": 0.01743030548095703,
+      "learning_rate": 2.8305162497673325e-06,
+      "loss": 0.074,
+      "reward": 0.7343750400468707,
+      "reward_std": 0.5123187024146318,
+      "rewards/accuracy_reward": 0.15513393573928624,
+      "rewards/format_reward": 0.5792410988360643,
+      "step": 19
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1219.2167301177979,
+      "epoch": 4.810126582278481,
+      "grad_norm": 0.13668957352638245,
+      "kl": 0.014723777770996094,
+      "learning_rate": 2.7990381056766585e-06,
+      "loss": 0.0726,
+      "reward": 0.8549107480794191,
+      "reward_std": 0.45913853123784065,
+      "rewards/accuracy_reward": 0.18303572200238705,
+      "rewards/format_reward": 0.6718750316649675,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1226.5603199005127,
+      "epoch": 5.2025316455696204,
+      "grad_norm": 0.13830004632472992,
+      "kl": 0.0236053466796875,
+      "learning_rate": 2.765087168719329e-06,
+      "loss": 0.021,
+      "reward": 0.8816964756697416,
+      "reward_std": 0.5056763701140881,
+      "rewards/accuracy_reward": 0.20424108230508864,
+      "rewards/format_reward": 0.6774553898721933,
+      "step": 21
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1145.9241542816162,
+      "epoch": 5.405063291139241,
+      "grad_norm": 0.21640558540821075,
+      "kl": 0.021097183227539062,
+      "learning_rate": 2.728728066433488e-06,
+      "loss": 0.0532,
+      "reward": 0.8839286137372255,
+      "reward_std": 0.43036860041320324,
+      "rewards/accuracy_reward": 0.18861608009319752,
+      "rewards/format_reward": 0.6953125363215804,
+      "step": 22
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1197.8103218078613,
+      "epoch": 5.6075949367088604,
+      "grad_norm": 0.1460823118686676,
+      "kl": 0.0402984619140625,
+      "learning_rate": 2.690030010436853e-06,
+      "loss": 0.0818,
+      "reward": 0.8895089738070965,
+      "reward_std": 0.4404608942568302,
+      "rewards/accuracy_reward": 0.14732143667060882,
+      "rewards/format_reward": 0.7421875428408384,
+      "step": 23
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1357.7104873657227,
+      "epoch": 5.810126582278481,
+      "grad_norm": 0.27858996391296387,
+      "kl": 0.045017242431640625,
+      "learning_rate": 2.649066664678467e-06,
+      "loss": 0.0808,
+      "reward": 0.8839286100119352,
+      "reward_std": 0.4558837213553488,
+      "rewards/accuracy_reward": 0.16183036426082253,
+      "rewards/format_reward": 0.7220982499420643,
+      "step": 24
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1194.8192462921143,
+      "epoch": 6.2025316455696204,
+      "grad_norm": 0.14784154295921326,
+      "kl": 0.016931533813476562,
+      "learning_rate": 2.605916005215186e-06,
+      "loss": 0.0616,
+      "reward": 0.9006696790456772,
+      "reward_std": 0.436885382514447,
+      "rewards/accuracy_reward": 0.15290179336443543,
+      "rewards/format_reward": 0.7477678973227739,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1149.721025466919,
+      "epoch": 6.405063291139241,
+      "grad_norm": 0.12463140487670898,
+      "kl": 0.01778697967529297,
+      "learning_rate": 2.5606601717798212e-06,
+      "loss": 0.0871,
+      "reward": 0.9709821846336126,
+      "reward_std": 0.43305877037346363,
+      "rewards/accuracy_reward": 0.16294643736910075,
+      "rewards/format_reward": 0.8080357536673546,
+      "step": 26
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1091.338228225708,
+      "epoch": 6.6075949367088604,
+      "grad_norm": 0.16402533650398254,
+      "kl": 0.028328895568847656,
+      "learning_rate": 2.5133853114234908e-06,
+      "loss": 0.0804,
+      "reward": 1.0167411249130964,
+      "reward_std": 0.4595717927441001,
+      "rewards/accuracy_reward": 0.23772322584409267,
+      "rewards/format_reward": 0.7790178991854191,
+      "step": 27
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1120.704236984253,
+      "epoch": 6.810126582278481,
+      "grad_norm": 0.152034193277359,
+      "kl": 0.01720428466796875,
+      "learning_rate": 2.464181414529809e-06,
+      "loss": 0.0649,
+      "reward": 0.9787946827709675,
+      "reward_std": 0.40247320383787155,
+      "rewards/accuracy_reward": 0.17299107660073787,
+      "rewards/format_reward": 0.8058036062866449,
+      "step": 28
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1154.484426498413,
+      "epoch": 7.2025316455696204,
+      "grad_norm": 0.13842816650867462,
+      "kl": 0.03877449035644531,
+      "learning_rate": 2.4131421435130812e-06,
+      "loss": 0.0955,
+      "reward": 0.9866071864962578,
+      "reward_std": 0.47181375650689006,
+      "rewards/accuracy_reward": 0.19642858125735074,
+      "rewards/format_reward": 0.7901786081492901,
+      "step": 29
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1082.405179977417,
+      "epoch": 7.405063291139241,
+      "grad_norm": 0.14722459018230438,
+      "kl": 0.04826545715332031,
+      "learning_rate": 2.3603646545265692e-06,
+      "loss": 0.0519,
+      "reward": 1.0546875447034836,
+      "reward_std": 0.4271851107478142,
+      "rewards/accuracy_reward": 0.21428572619333863,
+      "rewards/format_reward": 0.8404018338769674,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1093.8527278900146,
+      "epoch": 7.6075949367088604,
+      "grad_norm": 0.1317053586244583,
+      "kl": 0.01566791534423828,
+      "learning_rate": 2.305949412520236e-06,
+      "loss": 0.0803,
+      "reward": 1.0401786137372255,
+      "reward_std": 0.3743963772431016,
+      "rewards/accuracy_reward": 0.19196429441217333,
+      "rewards/format_reward": 0.8482143301516771,
+      "step": 31
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1086.0333862304688,
+      "epoch": 7.810126582278481,
+      "grad_norm": 0.11714313179254532,
+      "kl": 0.020026206970214844,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0793,
+      "reward": 1.056919701397419,
+      "reward_std": 0.37524981633760035,
+      "rewards/accuracy_reward": 0.2187500090803951,
+      "rewards/format_reward": 0.8381696902215481,
+      "step": 32
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1113.4855403900146,
+      "epoch": 8.20253164556962,
+      "grad_norm": 0.13244719803333282,
+      "kl": 0.017362594604492188,
+      "learning_rate": 2.192622919852551e-06,
+      "loss": 0.0644,
+      "reward": 1.0312500484287739,
+      "reward_std": 0.36712014535441995,
+      "rewards/accuracy_reward": 0.1886160805588588,
+      "rewards/format_reward": 0.8426339719444513,
+      "step": 33
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1150.787992477417,
+      "epoch": 8.405063291139241,
+      "grad_norm": 0.11223872005939484,
+      "kl": 0.02086639404296875,
+      "learning_rate": 2.1339273926110494e-06,
+      "loss": 0.0693,
+      "reward": 1.0625000447034836,
+      "reward_std": 0.3789821336977184,
+      "rewards/accuracy_reward": 0.21651786437723786,
+      "rewards/format_reward": 0.8459821864962578,
+      "step": 34
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1145.8158931732178,
+      "epoch": 8.60759493670886,
+      "grad_norm": 0.18010753393173218,
+      "kl": 0.021386146545410156,
+      "learning_rate": 2.074025148547635e-06,
+      "loss": 0.0767,
+      "reward": 1.0558036286383867,
+      "reward_std": 0.38298405637033284,
+      "rewards/accuracy_reward": 0.1941964360885322,
+      "rewards/format_reward": 0.8616071809083223,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1208.060474395752,
+      "epoch": 8.810126582278482,
+      "grad_norm": 0.18328261375427246,
+      "kl": 0.01535797119140625,
+      "learning_rate": 2.0130302149885033e-06,
+      "loss": 0.0796,
+      "reward": 1.027901828289032,
+      "reward_std": 0.3823082959279418,
+      "rewards/accuracy_reward": 0.17410715273581445,
+      "rewards/format_reward": 0.8537946827709675,
+      "step": 36
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1159.372817993164,
+      "epoch": 9.20253164556962,
+      "grad_norm": 0.12609297037124634,
+      "kl": 0.013571739196777344,
+      "learning_rate": 1.9510586992564096e-06,
+      "loss": 0.0778,
+      "reward": 1.0636161137372255,
+      "reward_std": 0.3645266597159207,
+      "rewards/accuracy_reward": 0.19308036612346768,
+      "rewards/format_reward": 0.8705357536673546,
+      "step": 37
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1254.4621124267578,
+      "epoch": 9.405063291139241,
+      "grad_norm": 0.14299969375133514,
+      "kl": 0.013241767883300781,
+      "learning_rate": 1.888228567653781e-06,
+      "loss": 0.0773,
+      "reward": 1.053571479395032,
+      "reward_std": 0.37696896330453455,
+      "rewards/accuracy_reward": 0.1975446525029838,
+      "rewards/format_reward": 0.856026828289032,
+      "step": 38
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1183.1540699005127,
+      "epoch": 9.60759493670886,
+      "grad_norm": 0.11042484641075134,
+      "kl": 0.01685810089111328,
+      "learning_rate": 1.8246594209071543e-06,
+      "loss": 0.0612,
+      "reward": 1.068080399185419,
+      "reward_std": 0.375900273444131,
+      "rewards/accuracy_reward": 0.19419643899891526,
+      "rewards/format_reward": 0.873883968219161,
+      "step": 39
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1185.3604793548584,
+      "epoch": 9.810126582278482,
+      "grad_norm": 0.11164165288209915,
+      "kl": 0.01548004150390625,
+      "learning_rate": 1.7604722665003958e-06,
+      "loss": 0.0371,
+      "reward": 1.061383979395032,
+      "reward_std": 0.34133189218118787,
+      "rewards/accuracy_reward": 0.17299107869621366,
+      "rewards/format_reward": 0.8883928935974836,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1076.3594131469727,
+      "epoch": 10.20253164556962,
+      "grad_norm": 0.16031011939048767,
+      "kl": 0.01823902130126953,
+      "learning_rate": 1.6957892883300778e-06,
+      "loss": 0.0584,
+      "reward": 1.1026786230504513,
+      "reward_std": 0.3611738483887166,
+      "rewards/accuracy_reward": 0.2131696519209072,
+      "rewards/format_reward": 0.8895089663565159,
+      "step": 41
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1139.5413455963135,
+      "epoch": 10.405063291139241,
+      "grad_norm": 0.1290842443704605,
+      "kl": 0.015422821044921875,
+      "learning_rate": 1.6307336141214877e-06,
+      "loss": 0.0619,
+      "reward": 1.0714286230504513,
+      "reward_std": 0.308660123962909,
+      "rewards/accuracy_reward": 0.18191965122241527,
+      "rewards/format_reward": 0.889508968219161,
+      "step": 42
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1171.5971488952637,
+      "epoch": 10.60759493670886,
+      "grad_norm": 0.18351688981056213,
+      "kl": 0.016489028930664062,
+      "learning_rate": 1.5654290810480041e-06,
+      "loss": 0.0774,
+      "reward": 1.1361607685685158,
+      "reward_std": 0.3446261656936258,
+      "rewards/accuracy_reward": 0.23325893853325397,
+      "rewards/format_reward": 0.9029018245637417,
+      "step": 43
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1160.4833908081055,
+      "epoch": 10.810126582278482,
+      "grad_norm": 0.19561266899108887,
+      "kl": 0.013916015625,
+      "learning_rate": 1.5e-06,
+      "loss": 0.059,
+      "reward": 1.0591518338769674,
+      "reward_std": 0.3170809505973011,
+      "rewards/accuracy_reward": 0.16071429196745157,
+      "rewards/format_reward": 0.8984375353902578,
+      "step": 44
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1271.4141178131104,
+      "epoch": 11.20253164556962,
+      "grad_norm": 0.12841616570949554,
+      "kl": 0.016252517700195312,
+      "learning_rate": 1.4345709189519962e-06,
+      "loss": 0.0853,
+      "reward": 1.0993304047733545,
+      "reward_std": 0.3096196516416967,
+      "rewards/accuracy_reward": 0.20535715261939913,
+      "rewards/format_reward": 0.8939732499420643,
+      "step": 45
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1125.301383972168,
+      "epoch": 11.405063291139241,
+      "grad_norm": 0.4378478229045868,
+      "kl": 0.020122528076171875,
+      "learning_rate": 1.3692663858785126e-06,
+      "loss": 0.0546,
+      "reward": 1.0714286211878061,
+      "reward_std": 0.34814802813343704,
+      "rewards/accuracy_reward": 0.18191965098958462,
+      "rewards/format_reward": 0.889508968219161,
+      "step": 46
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1158.8650093078613,
+      "epoch": 11.60759493670886,
+      "grad_norm": 0.10889195650815964,
+      "kl": 0.016626358032226562,
+      "learning_rate": 1.304210711669923e-06,
+      "loss": 0.0547,
+      "reward": 1.0825893394649029,
+      "reward_std": 0.3138458870816976,
+      "rewards/accuracy_reward": 0.16629465005826205,
+      "rewards/format_reward": 0.916294677183032,
+      "step": 47
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1108.9167308807373,
+      "epoch": 11.810126582278482,
+      "grad_norm": 0.14371342957019806,
+      "kl": 0.015249252319335938,
+      "learning_rate": 1.2395277334996047e-06,
+      "loss": 0.0269,
+      "reward": 1.1517857667058706,
+      "reward_std": 0.3139377860352397,
+      "rewards/accuracy_reward": 0.22433036961592734,
+      "rewards/format_reward": 0.9274553880095482,
+      "step": 48
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1162.2154502868652,
+      "epoch": 12.20253164556962,
+      "grad_norm": 0.1115531250834465,
+      "kl": 0.013177871704101562,
+      "learning_rate": 1.1753405790928457e-06,
+      "loss": 0.0628,
+      "reward": 1.1294643320143223,
+      "reward_std": 0.2925685364753008,
+      "rewards/accuracy_reward": 0.18191964994184673,
+      "rewards/format_reward": 0.9475446660071611,
+      "step": 49
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1243.0078659057617,
+      "epoch": 12.405063291139241,
+      "grad_norm": 0.10767732560634613,
+      "kl": 0.013563156127929688,
+      "learning_rate": 1.1117714323462188e-06,
+      "loss": 0.0732,
+      "reward": 1.110491119325161,
+      "reward_std": 0.3003906770609319,
+      "rewards/accuracy_reward": 0.18415179511066526,
+      "rewards/format_reward": 0.9263393171131611,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1244.2746181488037,
+      "epoch": 12.60759493670886,
+      "grad_norm": 0.09185539186000824,
+      "kl": 0.03409385681152344,
+      "learning_rate": 1.0489413007435905e-06,
+      "loss": 0.0717,
+      "reward": 1.11049110814929,
+      "reward_std": 0.308702711481601,
+      "rewards/accuracy_reward": 0.18973215168807656,
+      "rewards/format_reward": 0.9207589607685804,
+      "step": 51
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1158.5021438598633,
+      "epoch": 12.810126582278482,
+      "grad_norm": 0.18302814662456512,
+      "kl": 0.02344512939453125,
+      "learning_rate": 9.86969785011497e-07,
+      "loss": 0.0387,
+      "reward": 1.1562500428408384,
+      "reward_std": 0.3003106499090791,
+      "rewards/accuracy_reward": 0.22767858230508864,
+      "rewards/format_reward": 0.9285714570432901,
+      "step": 52
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1237.9732666015625,
+      "epoch": 13.20253164556962,
+      "grad_norm": 0.11227720230817795,
+      "kl": 0.016330718994140625,
+      "learning_rate": 9.259748514523654e-07,
+      "loss": 0.0601,
+      "reward": 1.1171875558793545,
+      "reward_std": 0.359636815963313,
+      "rewards/accuracy_reward": 0.20758929557632655,
+      "rewards/format_reward": 0.9095982518047094,
+      "step": 53
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1117.2076396942139,
+      "epoch": 13.405063291139241,
+      "grad_norm": 0.1859021931886673,
+      "kl": 0.0164947509765625,
+      "learning_rate": 8.660726073889511e-07,
+      "loss": 0.0416,
+      "reward": 1.1428571790456772,
+      "reward_std": 0.2875336476135999,
+      "rewards/accuracy_reward": 0.20424108090810478,
+      "rewards/format_reward": 0.9386161006987095,
+      "step": 54
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1236.578176498413,
+      "epoch": 13.60759493670886,
+      "grad_norm": 0.3497838079929352,
+      "kl": 0.01940155029296875,
+      "learning_rate": 8.073770801474494e-07,
+      "loss": 0.0805,
+      "reward": 1.1495536267757416,
+      "reward_std": 0.3257214743643999,
+      "rewards/accuracy_reward": 0.22433036705479026,
+      "rewards/format_reward": 0.9252232424914837,
+      "step": 55
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1211.5646495819092,
+      "epoch": 13.810126582278482,
+      "grad_norm": 0.19044233858585358,
+      "kl": 0.01702880859375,
+      "learning_rate": 7.500000000000003e-07,
+      "loss": 0.0655,
+      "reward": 1.1183036211878061,
+      "reward_std": 0.298118500970304,
+      "rewards/accuracy_reward": 0.19196429604198784,
+      "rewards/format_reward": 0.9263393171131611,
+      "step": 56
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1143.214334487915,
+      "epoch": 14.20253164556962,
+      "grad_norm": 1.5419952869415283,
+      "kl": 0.035312652587890625,
+      "learning_rate": 6.94050587479764e-07,
+      "loss": 0.0659,
+      "reward": 1.1439732648432255,
+      "reward_std": 0.3306191167794168,
+      "rewards/accuracy_reward": 0.22879465378355235,
+      "rewards/format_reward": 0.9151786025613546,
+      "step": 57
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1238.2567501068115,
+      "epoch": 14.405063291139241,
+      "grad_norm": 0.15846788883209229,
+      "kl": 0.016237258911132812,
+      "learning_rate": 6.396353454734313e-07,
+      "loss": 0.0613,
+      "reward": 1.1305804066359997,
+      "reward_std": 0.2859719139523804,
+      "rewards/accuracy_reward": 0.1941964365541935,
+      "rewards/format_reward": 0.9363839570432901,
+      "step": 58
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1179.9319820404053,
+      "epoch": 14.60759493670886,
+      "grad_norm": 0.2593388855457306,
+      "kl": 0.014705657958984375,
+      "learning_rate": 5.868578564869191e-07,
+      "loss": 0.0796,
+      "reward": 1.1138393357396126,
+      "reward_std": 0.30559679167345166,
+      "rewards/accuracy_reward": 0.17075893632136285,
+      "rewards/format_reward": 0.9430803842842579,
+      "step": 59
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1276.8438034057617,
+      "epoch": 14.810126582278482,
+      "grad_norm": 134161.59375,
+      "kl": 46.516122817993164,
+      "learning_rate": 5.358185854701909e-07,
+      "loss": 3.7375,
+      "reward": 1.1573661230504513,
+      "reward_std": 0.30025100195780396,
+      "rewards/accuracy_reward": 0.21316965157166123,
+      "rewards/format_reward": 0.944196455180645,
+      "step": 60
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1248.2243881225586,
+      "epoch": 15.20253164556962,
+      "grad_norm": 0.1083560436964035,
+      "kl": 0.022684097290039062,
+      "learning_rate": 4.866146885765096e-07,
+      "loss": 0.0465,
+      "reward": 1.081473272293806,
+      "reward_std": 0.2627506146673113,
+      "rewards/accuracy_reward": 0.15401786530856043,
+      "rewards/format_reward": 0.9274553898721933,
+      "step": 61
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1141.5882091522217,
+      "epoch": 15.405063291139241,
+      "grad_norm": 0.13774190843105316,
+      "kl": 0.023365020751953125,
+      "learning_rate": 4.3933982822017883e-07,
+      "loss": 0.0737,
+      "reward": 1.1640625558793545,
+      "reward_std": 0.30663056182675064,
+      "rewards/accuracy_reward": 0.22544643806759268,
+      "rewards/format_reward": 0.9386161006987095,
+      "step": 62
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1172.7221584320068,
+      "epoch": 15.60759493670886,
+      "grad_norm": 0.17014561593532562,
+      "kl": 0.018375396728515625,
+      "learning_rate": 3.9408399478481406e-07,
+      "loss": 0.0651,
+      "reward": 1.1718750577419996,
+      "reward_std": 0.31751804961822927,
+      "rewards/accuracy_reward": 0.23549108125735074,
+      "rewards/format_reward": 0.9363839570432901,
+      "step": 63
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1135.0229759216309,
+      "epoch": 15.810126582278482,
+      "grad_norm": 0.15105918049812317,
+      "kl": 0.018392562866210938,
+      "learning_rate": 3.5093333532153313e-07,
+      "loss": 0.0429,
+      "reward": 1.1841518245637417,
+      "reward_std": 0.29690629336982965,
+      "rewards/accuracy_reward": 0.26004465436562896,
+      "rewards/format_reward": 0.9241071715950966,
+      "step": 64
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1078.2868738174438,
+      "epoch": 16.20253164556962,
+      "grad_norm": 0.13650694489479065,
+      "kl": 0.018194198608398438,
+      "learning_rate": 3.0996998956314745e-07,
+      "loss": 0.0484,
+      "reward": 1.1852679140865803,
+      "reward_std": 0.2528684106655419,
+      "rewards/accuracy_reward": 0.22656250791624188,
+      "rewards/format_reward": 0.9587053749710321,
+      "step": 65
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1191.1630020141602,
+      "epoch": 16.40506329113924,
+      "grad_norm": 0.15124773979187012,
+      "kl": 0.01834869384765625,
+      "learning_rate": 2.7127193356651214e-07,
+      "loss": 0.0597,
+      "reward": 1.1328125484287739,
+      "reward_std": 0.2856026024091989,
+      "rewards/accuracy_reward": 0.18526786810252815,
+      "rewards/format_reward": 0.9475446678698063,
+      "step": 66
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1234.5659103393555,
+      "epoch": 16.60759493670886,
+      "grad_norm": 0.139739990234375,
+      "kl": 0.019105911254882812,
+      "learning_rate": 2.3491283128067176e-07,
+      "loss": 0.0696,
+      "reward": 1.1473214849829674,
+      "reward_std": 0.2781486874446273,
+      "rewards/accuracy_reward": 0.2075892968568951,
+      "rewards/format_reward": 0.9397321715950966,
+      "step": 67
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1205.6500625610352,
+      "epoch": 16.810126582278482,
+      "grad_norm": 0.14179465174674988,
+      "kl": 0.018032073974609375,
+      "learning_rate": 2.0096189432334195e-07,
+      "loss": 0.0426,
+      "reward": 1.1506696976721287,
+      "reward_std": 0.29133763001300395,
+      "rewards/accuracy_reward": 0.21651786845177412,
+      "rewards/format_reward": 0.9341518152505159,
+      "step": 68
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1186.745590209961,
+      "epoch": 17.20253164556962,
+      "grad_norm": 0.13754098117351532,
+      "kl": 0.016582489013671875,
+      "learning_rate": 1.6948375023266743e-07,
+      "loss": 0.0482,
+      "reward": 1.1607143357396126,
+      "reward_std": 0.2897793191950768,
+      "rewards/accuracy_reward": 0.20982143899891526,
+      "rewards/format_reward": 0.9508928786963224,
+      "step": 69
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1208.3125495910645,
+      "epoch": 17.40506329113924,
+      "grad_norm": 0.12631621956825256,
+      "kl": 0.01808929443359375,
+      "learning_rate": 1.405383194450251e-07,
+      "loss": 0.0554,
+      "reward": 1.1183036155998707,
+      "reward_std": 0.26985309086740017,
+      "rewards/accuracy_reward": 0.18191965017467737,
+      "rewards/format_reward": 0.9363839570432901,
+      "step": 70
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1204.0859870910645,
+      "epoch": 17.60759493670886,
+      "grad_norm": 0.12439820170402527,
+      "kl": 0.01674652099609375,
+      "learning_rate": 1.141807012330699e-07,
+      "loss": 0.061,
+      "reward": 1.10267860814929,
+      "reward_std": 0.30230870423838496,
+      "rewards/accuracy_reward": 0.16406250756699592,
+      "rewards/format_reward": 0.9386160988360643,
+      "step": 71
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1168.6833896636963,
+      "epoch": 17.810126582278482,
+      "grad_norm": 0.11665742844343185,
+      "kl": 0.025030136108398438,
+      "learning_rate": 9.046106882113752e-08,
+      "loss": 0.051,
+      "reward": 1.1763393394649029,
+      "reward_std": 0.32615134259685874,
+      "rewards/accuracy_reward": 0.23995536949951202,
+      "rewards/format_reward": 0.9363839589059353,
+      "step": 72
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1177.4955806732178,
+      "epoch": 18.20253164556962,
+      "grad_norm": 0.1363748013973236,
+      "kl": 0.018270492553710938,
+      "learning_rate": 6.942457387765977e-08,
+      "loss": 0.0674,
+      "reward": 1.1439732611179352,
+      "reward_std": 0.2613161935005337,
+      "rewards/accuracy_reward": 0.19754465110599995,
+      "rewards/format_reward": 0.946428595110774,
+      "step": 73
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1190.054738998413,
+      "epoch": 18.40506329113924,
+      "grad_norm": 0.12824372947216034,
+      "kl": 0.018024444580078125,
+      "learning_rate": 5.11112605663977e-08,
+      "loss": 0.0457,
+      "reward": 1.1283482611179352,
+      "reward_std": 0.2721500853076577,
+      "rewards/accuracy_reward": 0.1919642947614193,
+      "rewards/format_reward": 0.9363839570432901,
+      "step": 74
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1171.8717079162598,
+      "epoch": 18.60759493670886,
+      "grad_norm": 0.9167880415916443,
+      "kl": 0.0291290283203125,
+      "learning_rate": 3.5555989320099955e-08,
+      "loss": 0.0824,
+      "reward": 1.1261161230504513,
+      "reward_std": 0.2760429719928652,
+      "rewards/accuracy_reward": 0.1953125084983185,
+      "rewards/format_reward": 0.9308036025613546,
+      "step": 75
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1209.302146911621,
+      "epoch": 18.810126582278482,
+      "grad_norm": 0.09688866138458252,
+      "kl": 0.017160415649414062,
+      "learning_rate": 2.278837048168797e-08,
+      "loss": 0.0286,
+      "reward": 1.1729911025613546,
+      "reward_std": 0.2933972212485969,
+      "rewards/accuracy_reward": 0.23102679941803217,
+      "rewards/format_reward": 0.9419643096625805,
+      "step": 76
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1140.1205825805664,
+      "epoch": 19.20253164556962,
+      "grad_norm": 0.12310791015625,
+      "kl": 0.024255752563476562,
+      "learning_rate": 1.2832707939284426e-08,
+      "loss": 0.0368,
+      "reward": 1.1975446920841932,
+      "reward_std": 0.29775712732225657,
+      "rewards/accuracy_reward": 0.2533482244471088,
+      "rewards/format_reward": 0.9441964514553547,
+      "step": 77
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1153.5368843078613,
+      "epoch": 19.40506329113924,
+      "grad_norm": 0.15291966497898102,
+      "kl": 0.01901531219482422,
+      "learning_rate": 5.707952862381682e-09,
+      "loss": 0.054,
+      "reward": 1.099330399185419,
+      "reward_std": 0.2274289857596159,
+      "rewards/accuracy_reward": 0.14285714621655643,
+      "rewards/format_reward": 0.9564732350409031,
+      "step": 78
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1215.3181285858154,
+      "epoch": 19.60759493670886,
+      "grad_norm": 0.11192745715379715,
+      "kl": 0.017858505249023438,
+      "learning_rate": 1.4276676272133026e-09,
+      "loss": 0.0329,
+      "reward": 1.1216518245637417,
+      "reward_std": 0.2780349128879607,
+      "rewards/accuracy_reward": 0.19308036274742335,
+      "rewards/format_reward": 0.9285714607685804,
+      "step": 79
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1280.5479927062988,
+      "epoch": 19.810126582278482,
+      "grad_norm": 0.12247645109891891,
+      "kl": 0.018152236938476562,
+      "learning_rate": 0.0,
+      "loss": 0.0587,
+      "reward": 1.1674107685685158,
+      "reward_std": 0.30244723055511713,
+      "rewards/accuracy_reward": 0.23549108253791928,
+      "rewards/format_reward": 0.9319196753203869,
+      "step": 80
+    },
+    {
+      "epoch": 19.810126582278482,
+      "step": 80,
+      "total_flos": 0.0,
+      "train_loss": 0.10659663751721382,
+      "train_runtime": 145281.9904,
+      "train_samples_per_second": 0.087,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 80,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 20,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eac3eeaaff024929fd363cc09cd0ded01b0b96ceb7501cec487c056c068ae18
+size 8248