Add files using upload-large-folder tool

.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
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "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": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57da7def19a492fa99017d773ad8220d590a2ee1aa1fc89b47115122659bc499
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4bf858940bf2175a405fbb34b64cbfa6574d5b334d298f84ca9ea850db4cb67
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:854d91bd36426340492acf17dc9f3a39175d3a6787a28bfe04361ee36c8d75e6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd49458bf1db5cbf4d5d1a41c6db843ecde6babed7bf5ef35c452bf103580214
+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": "<|im_end|>",
+    "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        {{- 'You are Qwen, created by Alibaba Cloud. 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 Qwen, created by Alibaba Cloud. You 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": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,634 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.3885003885003885,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 748.7643005371094,
+      "epoch": 0.009712509712509712,
+      "grad_norm": 0.3736153689307914,
+      "learning_rate": 1e-06,
+      "loss": -0.0068,
+      "reward": 3.822531852722168,
+      "reward_std": 0.476869178712368,
+      "rewards/agent_reward_func_MC": 0.8567936837673187,
+      "rewards/correctness_reward_func": 1.8019047832489015,
+      "rewards/correctness_reward_func_eval": 0.8142857432365418,
+      "rewards/format_reward_func": 0.3495476073026657,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 836.8619177246094,
+      "epoch": 0.019425019425019424,
+      "grad_norm": 0.3188121982595845,
+      "learning_rate": 1e-06,
+      "loss": -0.0107,
+      "reward": 3.90938099861145,
+      "reward_std": 0.38552937254309655,
+      "rewards/agent_reward_func_MC": 0.8773333775997162,
+      "rewards/correctness_reward_func": 1.8704762172698974,
+      "rewards/correctness_reward_func_eval": 0.812380975484848,
+      "rewards/format_reward_func": 0.3491904670000076,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 973.8400158691406,
+      "epoch": 0.029137529137529136,
+      "grad_norm": 0.27198200236481873,
+      "learning_rate": 1e-06,
+      "loss": -0.0031,
+      "reward": 3.8425635862350465,
+      "reward_std": 0.4346236677467823,
+      "rewards/agent_reward_func_MC": 0.864666701555252,
+      "rewards/correctness_reward_func": 1.8247619271278381,
+      "rewards/correctness_reward_func_eval": 0.8034920811653137,
+      "rewards/format_reward_func": 0.34964284658432004,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1018.5909753417968,
+      "epoch": 0.03885003885003885,
+      "grad_norm": 0.28510359189330664,
+      "learning_rate": 1e-06,
+      "loss": 0.011,
+      "reward": 3.9731746339797973,
+      "reward_std": 0.2720495498180389,
+      "rewards/agent_reward_func_MC": 0.8882857489585877,
+      "rewards/correctness_reward_func": 1.8980952572822571,
+      "rewards/correctness_reward_func_eval": 0.8369841420650482,
+      "rewards/format_reward_func": 0.34980951368808744,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1140.068126220703,
+      "epoch": 0.04856254856254856,
+      "grad_norm": 0.23329425011386498,
+      "learning_rate": 1e-06,
+      "loss": 0.0032,
+      "reward": 3.988293719291687,
+      "reward_std": 0.30129268489778044,
+      "rewards/agent_reward_func_MC": 0.8880000543594361,
+      "rewards/correctness_reward_func": 1.896190493106842,
+      "rewards/correctness_reward_func_eval": 0.8541270065307617,
+      "rewards/format_reward_func": 0.3499761837720871,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1093.8681176757811,
+      "epoch": 0.05827505827505827,
+      "grad_norm": 0.29946322491146965,
+      "learning_rate": 1e-06,
+      "loss": -0.0109,
+      "reward": 3.977658863067627,
+      "reward_std": 0.32108820773661134,
+      "rewards/agent_reward_func_MC": 0.869904808998108,
+      "rewards/correctness_reward_func": 1.8838095450401307,
+      "rewards/correctness_reward_func_eval": 0.8739682829380035,
+      "rewards/format_reward_func": 0.34997618436813355,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1075.1785949707032,
+      "epoch": 0.06798756798756798,
+      "grad_norm": 0.3040633702971847,
+      "learning_rate": 1e-06,
+      "loss": 0.0037,
+      "reward": 4.008127021789551,
+      "reward_std": 0.3045533967390657,
+      "rewards/agent_reward_func_MC": 0.8873333740234375,
+      "rewards/correctness_reward_func": 1.892380964756012,
+      "rewards/correctness_reward_func_eval": 0.8784127116203309,
+      "rewards/format_reward_func": 0.3499999940395355,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1051.7819262695311,
+      "epoch": 0.0777000777000777,
+      "grad_norm": 0.2654552473631526,
+      "learning_rate": 1e-06,
+      "loss": 0.0047,
+      "reward": 3.9801508474349974,
+      "reward_std": 0.3097702523320913,
+      "rewards/agent_reward_func_MC": 0.8759365463256836,
+      "rewards/correctness_reward_func": 1.8752381134033203,
+      "rewards/correctness_reward_func_eval": 0.8790476399660111,
+      "rewards/format_reward_func": 0.34992856383323667,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 920.3571643066406,
+      "epoch": 0.08741258741258741,
+      "grad_norm": 0.30787656246569944,
+      "learning_rate": 1e-06,
+      "loss": 0.0022,
+      "reward": 4.030627017021179,
+      "reward_std": 0.257388199865818,
+      "rewards/agent_reward_func_MC": 0.9038730561733246,
+      "rewards/correctness_reward_func": 1.8942857313156127,
+      "rewards/correctness_reward_func_eval": 0.8825397026538849,
+      "rewards/format_reward_func": 0.34992856383323667,
+      "step": 45
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 950.1019201660156,
+      "epoch": 0.09712509712509712,
+      "grad_norm": 0.278978790381264,
+      "learning_rate": 1e-06,
+      "loss": 0.0049,
+      "reward": 4.0613808870315555,
+      "reward_std": 0.2030999060533941,
+      "rewards/agent_reward_func_MC": 0.9173016262054443,
+      "rewards/correctness_reward_func": 1.8819047713279724,
+      "rewards/correctness_reward_func_eval": 0.9122222352027893,
+      "rewards/format_reward_func": 0.34995237350463865,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 988.4190625,
+      "epoch": 0.10683760683760683,
+      "grad_norm": 0.28501385265891443,
+      "learning_rate": 1e-06,
+      "loss": 0.0041,
+      "reward": 4.06360315322876,
+      "reward_std": 0.28966286245733497,
+      "rewards/agent_reward_func_MC": 0.9020952671766281,
+      "rewards/correctness_reward_func": 1.896190493106842,
+      "rewards/correctness_reward_func_eval": 0.9155555760860443,
+      "rewards/format_reward_func": 0.34976189851760864,
+      "step": 55
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 988.201923828125,
+      "epoch": 0.11655011655011654,
+      "grad_norm": 0.35841673382474903,
+      "learning_rate": 1e-06,
+      "loss": 0.0082,
+      "reward": 4.126190505027771,
+      "reward_std": 0.24293919634073974,
+      "rewards/agent_reward_func_MC": 0.918984169960022,
+      "rewards/correctness_reward_func": 1.9352381134033203,
+      "rewards/correctness_reward_func_eval": 0.9220635092258453,
+      "rewards/format_reward_func": 0.3499047553539276,
+      "step": 60
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 964.7343017578125,
+      "epoch": 0.12626262626262627,
+      "grad_norm": 0.3255852780092938,
+      "learning_rate": 1e-06,
+      "loss": 0.003,
+      "reward": 4.03707145690918,
+      "reward_std": 0.2535955292731524,
+      "rewards/agent_reward_func_MC": 0.9001587682962418,
+      "rewards/correctness_reward_func": 1.8800000143051148,
+      "rewards/correctness_reward_func_eval": 0.9069841504096985,
+      "rewards/format_reward_func": 0.34992856442928316,
+      "step": 65
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1023.8019348144531,
+      "epoch": 0.13597513597513597,
+      "grad_norm": 0.258258613758542,
+      "learning_rate": 1e-06,
+      "loss": 0.0021,
+      "reward": 4.010547647476196,
+      "reward_std": 0.30033121041953564,
+      "rewards/agent_reward_func_MC": 0.8870794075727463,
+      "rewards/correctness_reward_func": 1.867619068622589,
+      "rewards/correctness_reward_func_eval": 0.9058730411529541,
+      "rewards/format_reward_func": 0.34997618436813355,
+      "step": 70
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1049.6647875976562,
+      "epoch": 0.1456876456876457,
+      "grad_norm": 0.2868301098892232,
+      "learning_rate": 1e-06,
+      "loss": 0.0083,
+      "reward": 4.163015942573548,
+      "reward_std": 0.19761438958346844,
+      "rewards/agent_reward_func_MC": 0.936666705608368,
+      "rewards/correctness_reward_func": 1.9514285826683044,
+      "rewards/correctness_reward_func_eval": 0.9249206626415253,
+      "rewards/format_reward_func": 0.3499999940395355,
+      "step": 75
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1131.1047875976562,
+      "epoch": 0.1554001554001554,
+      "grad_norm": 0.22388105570487274,
+      "learning_rate": 1e-06,
+      "loss": 0.007,
+      "reward": 3.9448730325698853,
+      "reward_std": 0.26593201816082,
+      "rewards/agent_reward_func_MC": 0.8765079736709595,
+      "rewards/correctness_reward_func": 1.839047634601593,
+      "rewards/correctness_reward_func_eval": 0.879365097284317,
+      "rewards/format_reward_func": 0.34995237410068514,
+      "step": 80
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1176.7590686035155,
+      "epoch": 0.16511266511266512,
+      "grad_norm": 0.2821630374549152,
+      "learning_rate": 1e-06,
+      "loss": 0.0177,
+      "reward": 3.8298174810409544,
+      "reward_std": 0.25791051633656026,
+      "rewards/agent_reward_func_MC": 0.8357143165171146,
+      "rewards/correctness_reward_func": 1.7523809648305178,
+      "rewards/correctness_reward_func_eval": 0.8917460405826568,
+      "rewards/format_reward_func": 0.3499761837720871,
+      "step": 85
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1018.4166821289062,
+      "epoch": 0.17482517482517482,
+      "grad_norm": 0.29273821007360346,
+      "learning_rate": 1e-06,
+      "loss": 0.0077,
+      "reward": 4.071373038291931,
+      "reward_std": 0.18497788973152637,
+      "rewards/agent_reward_func_MC": 0.9020317900180816,
+      "rewards/correctness_reward_func": 1.8876190567016602,
+      "rewards/correctness_reward_func_eval": 0.9317460560798645,
+      "rewards/format_reward_func": 0.3499761837720871,
+      "step": 90
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1005.7043090820313,
+      "epoch": 0.18453768453768454,
+      "grad_norm": 0.24921090330226142,
+      "learning_rate": 1e-06,
+      "loss": 0.0056,
+      "reward": 4.00266664981842,
+      "reward_std": 0.22064166717231273,
+      "rewards/agent_reward_func_MC": 0.8949206686019897,
+      "rewards/correctness_reward_func": 1.849523823261261,
+      "rewards/correctness_reward_func_eval": 0.9084127140045166,
+      "rewards/format_reward_func": 0.3498095166683197,
+      "step": 95
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 943.940966796875,
+      "epoch": 0.19425019425019424,
+      "grad_norm": 0.255215749280062,
+      "learning_rate": 1e-06,
+      "loss": -0.0096,
+      "reward": 3.9010079383850096,
+      "reward_std": 0.26742793841287493,
+      "rewards/agent_reward_func_MC": 0.8706984454393387,
+      "rewards/correctness_reward_func": 1.796190493106842,
+      "rewards/correctness_reward_func_eval": 0.8842857277393341,
+      "rewards/format_reward_func": 0.3498333257436752,
+      "step": 100
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1131.998592529297,
+      "epoch": 0.20396270396270397,
+      "grad_norm": 0.24196861235641634,
+      "learning_rate": 1e-06,
+      "loss": 0.0061,
+      "reward": 3.9897142422199248,
+      "reward_std": 0.2609097701497376,
+      "rewards/agent_reward_func_MC": 0.8956508328020573,
+      "rewards/correctness_reward_func": 1.8285714424401522,
+      "rewards/correctness_reward_func_eval": 0.9158730319142342,
+      "rewards/format_reward_func": 0.34961903989315035,
+      "step": 105
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1269.4943090820314,
+      "epoch": 0.21367521367521367,
+      "grad_norm": 0.22055070432080545,
+      "learning_rate": 1e-06,
+      "loss": 0.0059,
+      "reward": 3.955634880065918,
+      "reward_std": 0.2273477977141738,
+      "rewards/agent_reward_func_MC": 0.8830476495623588,
+      "rewards/correctness_reward_func": 1.8095238244533538,
+      "rewards/correctness_reward_func_eval": 0.9134920847415924,
+      "rewards/format_reward_func": 0.3495714205503464,
+      "step": 110
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1250.7200256347655,
+      "epoch": 0.2233877233877234,
+      "grad_norm": 0.28987017976023693,
+      "learning_rate": 1e-06,
+      "loss": -0.0021,
+      "reward": 4.0416190052032475,
+      "reward_std": 0.20220871651545166,
+      "rewards/agent_reward_func_MC": 0.8979682916402817,
+      "rewards/correctness_reward_func": 1.8542857229709626,
+      "rewards/correctness_reward_func_eval": 0.9393650984764099,
+      "rewards/format_reward_func": 0.3499999940395355,
+      "step": 115
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1257.4157287597657,
+      "epoch": 0.2331002331002331,
+      "grad_norm": 0.19555680054474148,
+      "learning_rate": 1e-06,
+      "loss": 0.008,
+      "reward": 3.912722191810608,
+      "reward_std": 0.22784368658438325,
+      "rewards/agent_reward_func_MC": 0.869650827050209,
+      "rewards/correctness_reward_func": 1.796190493106842,
+      "rewards/correctness_reward_func_eval": 0.897142875790596,
+      "rewards/format_reward_func": 0.3497380870580673,
+      "step": 120
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1272.7885961914062,
+      "epoch": 0.24281274281274282,
+      "grad_norm": 0.18255389452293974,
+      "learning_rate": 1e-06,
+      "loss": -0.0106,
+      "reward": 3.8947618293762205,
+      "reward_std": 0.20762850038707256,
+      "rewards/agent_reward_func_MC": 0.8573016184568405,
+      "rewards/correctness_reward_func": 1.773333351612091,
+      "rewards/correctness_reward_func_eval": 0.9141269952058793,
+      "rewards/format_reward_func": 0.3499999940395355,
+      "step": 125
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1440.9728833007812,
+      "epoch": 0.25252525252525254,
+      "grad_norm": 0.2547576435452318,
+      "learning_rate": 1e-06,
+      "loss": 0.0119,
+      "reward": 3.864793620109558,
+      "reward_std": 0.29515512300655244,
+      "rewards/agent_reward_func_MC": 0.8445079725980759,
+      "rewards/correctness_reward_func": 1.7628571581840515,
+      "rewards/correctness_reward_func_eval": 0.9076190626621247,
+      "rewards/format_reward_func": 0.34980951607227323,
+      "step": 130
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1441.5447827148437,
+      "epoch": 0.26223776223776224,
+      "grad_norm": 0.24563201564074505,
+      "learning_rate": 1e-06,
+      "loss": 0.0135,
+      "reward": 3.883611145019531,
+      "reward_std": 0.2823502243310213,
+      "rewards/agent_reward_func_MC": 0.8565397095680237,
+      "rewards/correctness_reward_func": 1.7819047725200654,
+      "rewards/correctness_reward_func_eval": 0.8952381134033203,
+      "rewards/format_reward_func": 0.34992856562137603,
+      "step": 135
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1483.5781201171876,
+      "epoch": 0.27195027195027194,
+      "grad_norm": 0.22800872368606584,
+      "learning_rate": 1e-06,
+      "loss": 0.018,
+      "reward": 3.8423254334926606,
+      "reward_std": 0.2927846448868513,
+      "rewards/agent_reward_func_MC": 0.836825436502695,
+      "rewards/correctness_reward_func": 1.755238108932972,
+      "rewards/correctness_reward_func_eval": 0.900476205945015,
+      "rewards/format_reward_func": 0.34978570640087125,
+      "step": 140
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1435.1005004882813,
+      "epoch": 0.28166278166278164,
+      "grad_norm": 0.1789329116748729,
+      "learning_rate": 1e-06,
+      "loss": 0.0029,
+      "reward": 3.8026666712760924,
+      "reward_std": 0.2736345401033759,
+      "rewards/agent_reward_func_MC": 0.8252063795924187,
+      "rewards/correctness_reward_func": 1.7352381092309952,
+      "rewards/correctness_reward_func_eval": 0.8922222399711609,
+      "rewards/format_reward_func": 0.3499999940395355,
+      "step": 145
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1238.4776416015625,
+      "epoch": 0.2913752913752914,
+      "grad_norm": 0.25524578153777566,
+      "learning_rate": 1e-06,
+      "loss": 0.0066,
+      "reward": 3.9930158853530884,
+      "reward_std": 0.2553951171413064,
+      "rewards/agent_reward_func_MC": 0.876190505027771,
+      "rewards/correctness_reward_func": 1.8361904859542846,
+      "rewards/correctness_reward_func_eval": 0.9306349349021912,
+      "rewards/format_reward_func": 0.3499999940395355,
+      "step": 150
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1195.0243041992187,
+      "epoch": 0.3010878010878011,
+      "grad_norm": 0.23520669203586708,
+      "learning_rate": 1e-06,
+      "loss": 0.0052,
+      "reward": 4.016698341369629,
+      "reward_std": 0.281817892305553,
+      "rewards/agent_reward_func_MC": 0.9011428928375245,
+      "rewards/correctness_reward_func": 1.8390476369857789,
+      "rewards/correctness_reward_func_eval": 0.9265079569816589,
+      "rewards/format_reward_func": 0.3499999940395355,
+      "step": 155
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1184.551446533203,
+      "epoch": 0.3108003108003108,
+      "grad_norm": 0.23613211319734428,
+      "learning_rate": 1e-06,
+      "loss": 0.0083,
+      "reward": 3.7817697978019713,
+      "reward_std": 0.32593878942541776,
+      "rewards/agent_reward_func_MC": 0.8337143290042878,
+      "rewards/correctness_reward_func": 1.715238115787506,
+      "rewards/correctness_reward_func_eval": 0.8831746190786361,
+      "rewards/format_reward_func": 0.34964285016059876,
+      "step": 160
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1244.0347839355468,
+      "epoch": 0.32051282051282054,
+      "grad_norm": 0.24529652266955448,
+      "learning_rate": 1e-06,
+      "loss": 0.0014,
+      "reward": 3.7896666431427004,
+      "reward_std": 0.3328119495511055,
+      "rewards/agent_reward_func_MC": 0.8448571795225144,
+      "rewards/correctness_reward_func": 1.718095259666443,
+      "rewards/correctness_reward_func_eval": 0.8771428710222244,
+      "rewards/format_reward_func": 0.34957142114639284,
+      "step": 165
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1447.985263671875,
+      "epoch": 0.33022533022533024,
+      "grad_norm": 0.2065211585384318,
+      "learning_rate": 1e-06,
+      "loss": 0.0103,
+      "reward": 3.7185713863372802,
+      "reward_std": 0.3374773776344955,
+      "rewards/agent_reward_func_MC": 0.8139047813415528,
+      "rewards/correctness_reward_func": 1.686666680574417,
+      "rewards/correctness_reward_func_eval": 0.8680952602624893,
+      "rewards/format_reward_func": 0.3499047553539276,
+      "step": 170
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1459.0500244140626,
+      "epoch": 0.33993783993783994,
+      "grad_norm": 0.21734053290147362,
+      "learning_rate": 1e-06,
+      "loss": 0.0124,
+      "reward": 3.979817385673523,
+      "reward_std": 0.31312828628346323,
+      "rewards/agent_reward_func_MC": 0.8849206674098968,
+      "rewards/correctness_reward_func": 1.8247619199752807,
+      "rewards/correctness_reward_func_eval": 0.9206349372863769,
+      "rewards/format_reward_func": 0.34949999272823334,
+      "step": 175
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1425.19859375,
+      "epoch": 0.34965034965034963,
+      "grad_norm": 0.2907016194013063,
+      "learning_rate": 1e-06,
+      "loss": 0.0084,
+      "reward": 3.65442857503891,
+      "reward_std": 0.3651884417142719,
+      "rewards/agent_reward_func_MC": 0.785936538875103,
+      "rewards/correctness_reward_func": 1.647619072496891,
+      "rewards/correctness_reward_func_eval": 0.8711111295223236,
+      "rewards/format_reward_func": 0.3497618967294693,
+      "step": 180
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1544.9428930664062,
+      "epoch": 0.3593628593628594,
+      "grad_norm": 0.20955445164203745,
+      "learning_rate": 1e-06,
+      "loss": 0.0074,
+      "reward": 3.2816984033584595,
+      "reward_std": 0.4594585011713207,
+      "rewards/agent_reward_func_MC": 0.6978095433861017,
+      "rewards/correctness_reward_func": 1.4428571613132954,
+      "rewards/correctness_reward_func_eval": 0.7912698584794998,
+      "rewards/format_reward_func": 0.3497618967294693,
+      "step": 185
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1710.9262353515626,
+      "epoch": 0.3690753690753691,
+      "grad_norm": 0.22177847546734317,
+      "learning_rate": 1e-06,
+      "loss": 0.0104,
+      "reward": 3.5176428842544554,
+      "reward_std": 0.38553844563663003,
+      "rewards/agent_reward_func_MC": 0.7493016171455383,
+      "rewards/correctness_reward_func": 1.5676190626621247,
+      "rewards/correctness_reward_func_eval": 0.8507936751842499,
+      "rewards/format_reward_func": 0.34992856562137603,
+      "step": 190
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1679.4776538085937,
+      "epoch": 0.3787878787878788,
+      "grad_norm": 0.2779597660638594,
+      "learning_rate": 1e-06,
+      "loss": 0.0073,
+      "reward": 3.700857148170471,
+      "reward_std": 0.40202371578663587,
+      "rewards/agent_reward_func_MC": 0.7945079684257508,
+      "rewards/correctness_reward_func": 1.682857164144516,
+      "rewards/correctness_reward_func_eval": 0.8734920841455459,
+      "rewards/format_reward_func": 0.3499999940395355,
+      "step": 195
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 1529.8266943359374,
+      "epoch": 0.3885003885003885,
+      "grad_norm": 0.24354444168029116,
+      "learning_rate": 1e-06,
+      "loss": 0.0098,
+      "reward": 3.8641825485229493,
+      "reward_std": 0.3314341966807842,
+      "rewards/agent_reward_func_MC": 0.8359365397691727,
+      "rewards/correctness_reward_func": 1.7533333575725556,
+      "rewards/correctness_reward_func_eval": 0.9250793838500977,
+      "rewards/format_reward_func": 0.34983332693576813,
+      "step": 200
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 514,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 6,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9afe936b932f1f6491e3245eed49768936dd4bbad6a8e1500943c35c90bb9d32
+size 7480