Upload folder using huggingface_hub

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 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 0.0,
+    "train_loss": 0.6225600397872354,
+    "train_runtime": 17487.6193,
+    "train_samples": 64128,
+    "train_samples_per_second": 3.667,
+    "train_steps_per_second": 0.029
+}

checkpoint-303/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
+}

checkpoint-303/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/GLOBALFS/gznwp_3/qxj/lgzhong/LLaMA-Factory/saves/Qwen2.5-7B-Instruct-SFT-v1.5",
+  "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_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-303/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": "4.43.4"
+}

checkpoint-303/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50c13efa948f45962e05ac5afe2972f782051208a2b3fb899932b4af5855ee84
+size 4877660776

checkpoint-303/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eed25ac99a29df782209770a1c641f09aeea9e6499812e79bda53a9ed45f1b8f
+size 4932751008

checkpoint-303/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7af31c820d0b3249a00aff4c0fae8f97fe939c02fd2f3c1b79698050c351b44
+size 4330865200

checkpoint-303/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32d11d083a3980cdc3a6d760faa64bc20f63bc98f348510e8e203230f021d332
+size 1089994880

checkpoint-303/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"
+  }
+}

checkpoint-303/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
+  }
+}

checkpoint-303/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",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-303/trainer_state.json

@@ -0,0 +1,948 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6047904191616766,
+  "eval_steps": 500,
+  "global_step": 303,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001996007984031936,
+      "grad_norm": 3.4413226850733536,
+      "learning_rate": 5.88235294117647e-09,
+      "logits/chosen": -0.2126132994890213,
+      "logits/rejected": -0.06049485132098198,
+      "logps/chosen": -312.6929931640625,
+      "logps/rejected": -303.399658203125,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.00998003992015968,
+      "grad_norm": 3.5626484310109503,
+      "learning_rate": 2.941176470588235e-08,
+      "logits/chosen": -0.15043149888515472,
+      "logits/rejected": -0.05884423851966858,
+      "logps/chosen": -271.6809387207031,
+      "logps/rejected": -308.14019775390625,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.34375,
+      "rewards/chosen": 0.00032658452983014286,
+      "rewards/margins": -0.00044720349251292646,
+      "rewards/rejected": 0.0007737880805507302,
+      "step": 5
+    },
+    {
+      "epoch": 0.01996007984031936,
+      "grad_norm": 3.444766226961807,
+      "learning_rate": 5.88235294117647e-08,
+      "logits/chosen": -0.04885115846991539,
+      "logits/rejected": 0.02876092866063118,
+      "logps/chosen": -314.44207763671875,
+      "logps/rejected": -324.5089111328125,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.0015638660406693816,
+      "rewards/margins": -0.0018882350996136665,
+      "rewards/rejected": 0.0003243688843213022,
+      "step": 10
+    },
+    {
+      "epoch": 0.029940119760479042,
+      "grad_norm": 3.351776759283806,
+      "learning_rate": 8.823529411764706e-08,
+      "logits/chosen": -0.14645501971244812,
+      "logits/rejected": -0.10253484547138214,
+      "logps/chosen": -325.3197021484375,
+      "logps/rejected": -335.1691589355469,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.3375000059604645,
+      "rewards/chosen": -0.0009325200808234513,
+      "rewards/margins": -0.0027469159103929996,
+      "rewards/rejected": 0.0018143958877772093,
+      "step": 15
+    },
+    {
+      "epoch": 0.03992015968063872,
+      "grad_norm": 3.2486760323756765,
+      "learning_rate": 1.176470588235294e-07,
+      "logits/chosen": -0.17513605952262878,
+      "logits/rejected": -0.14125120639801025,
+      "logps/chosen": -236.529052734375,
+      "logps/rejected": -224.99609375,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.00048039742978289723,
+      "rewards/margins": -0.0017443184042349458,
+      "rewards/rejected": 0.0012639210326597095,
+      "step": 20
+    },
+    {
+      "epoch": 0.0499001996007984,
+      "grad_norm": 3.682895506825886,
+      "learning_rate": 1.4705882352941175e-07,
+      "logits/chosen": 0.02582230605185032,
+      "logits/rejected": -0.026322145015001297,
+      "logps/chosen": -276.4084777832031,
+      "logps/rejected": -271.5510559082031,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.00010870690312003717,
+      "rewards/margins": -2.2810349037172273e-05,
+      "rewards/rejected": -8.589646313339472e-05,
+      "step": 25
+    },
+    {
+      "epoch": 0.059880239520958084,
+      "grad_norm": 3.521568498969969,
+      "learning_rate": 1.764705882352941e-07,
+      "logits/chosen": -0.029633093625307083,
+      "logits/rejected": 0.017462745308876038,
+      "logps/chosen": -241.04345703125,
+      "logps/rejected": -254.0708465576172,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.001156697398982942,
+      "rewards/margins": 0.0012088593794032931,
+      "rewards/rejected": -5.2162260544719175e-05,
+      "step": 30
+    },
+    {
+      "epoch": 0.06986027944111776,
+      "grad_norm": 3.4756100770970852,
+      "learning_rate": 2.0588235294117647e-07,
+      "logits/chosen": -0.09809896349906921,
+      "logits/rejected": -0.12783308327198029,
+      "logps/chosen": -316.04541015625,
+      "logps/rejected": -303.2275085449219,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.0019062187056988478,
+      "rewards/margins": 0.0034712664783000946,
+      "rewards/rejected": -0.0015650471905246377,
+      "step": 35
+    },
+    {
+      "epoch": 0.07984031936127745,
+      "grad_norm": 3.5251485554920383,
+      "learning_rate": 2.352941176470588e-07,
+      "logits/chosen": -0.10866469144821167,
+      "logits/rejected": -0.08842261880636215,
+      "logps/chosen": -300.94866943359375,
+      "logps/rejected": -301.57635498046875,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0005061564734205604,
+      "rewards/margins": 0.0017319575417786837,
+      "rewards/rejected": -0.0012258009519428015,
+      "step": 40
+    },
+    {
+      "epoch": 0.08982035928143713,
+      "grad_norm": 3.562421126179782,
+      "learning_rate": 2.6470588235294114e-07,
+      "logits/chosen": -0.04412439838051796,
+      "logits/rejected": 0.046757772564888,
+      "logps/chosen": -276.1053771972656,
+      "logps/rejected": -299.3190612792969,
+      "loss": 0.692,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.002857887651771307,
+      "rewards/margins": 0.0004688422195613384,
+      "rewards/rejected": -0.003326730104163289,
+      "step": 45
+    },
+    {
+      "epoch": 0.0998003992015968,
+      "grad_norm": 3.174201376940309,
+      "learning_rate": 2.941176470588235e-07,
+      "logits/chosen": -0.08824320137500763,
+      "logits/rejected": -0.043245576322078705,
+      "logps/chosen": -271.13604736328125,
+      "logps/rejected": -272.74102783203125,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.0016361953457817435,
+      "rewards/margins": 0.005965009797364473,
+      "rewards/rejected": -0.007601206190884113,
+      "step": 50
+    },
+    {
+      "epoch": 0.10978043912175649,
+      "grad_norm": 3.3426951285606368,
+      "learning_rate": 2.999415172560531e-07,
+      "logits/chosen": 0.032454706728458405,
+      "logits/rejected": 0.15314094722270966,
+      "logps/chosen": -301.4625244140625,
+      "logps/rejected": -304.8877258300781,
+      "loss": 0.691,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.007659287191927433,
+      "rewards/margins": 0.0023522169794887304,
+      "rewards/rejected": -0.010011503472924232,
+      "step": 55
+    },
+    {
+      "epoch": 0.11976047904191617,
+      "grad_norm": 3.2266501701625283,
+      "learning_rate": 2.997040092642407e-07,
+      "logits/chosen": -0.13825412094593048,
+      "logits/rejected": -0.06802596896886826,
+      "logps/chosen": -273.85198974609375,
+      "logps/rejected": -256.1399841308594,
+      "loss": 0.6905,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.0074735768139362335,
+      "rewards/margins": 0.005476811900734901,
+      "rewards/rejected": -0.012950388714671135,
+      "step": 60
+    },
+    {
+      "epoch": 0.12974051896207583,
+      "grad_norm": 3.129826931598691,
+      "learning_rate": 2.9928410999727467e-07,
+      "logits/chosen": -0.03806266561150551,
+      "logits/rejected": -0.06114925071597099,
+      "logps/chosen": -273.815673828125,
+      "logps/rejected": -257.2196350097656,
+      "loss": 0.6897,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.010186719708144665,
+      "rewards/margins": 0.00584446731954813,
+      "rewards/rejected": -0.016031187027692795,
+      "step": 65
+    },
+    {
+      "epoch": 0.13972055888223553,
+      "grad_norm": 3.2696148017727764,
+      "learning_rate": 2.9868233103773125e-07,
+      "logits/chosen": -0.19126296043395996,
+      "logits/rejected": -0.1384088099002838,
+      "logps/chosen": -289.3074645996094,
+      "logps/rejected": -304.941650390625,
+      "loss": 0.6901,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.012994937598705292,
+      "rewards/margins": 0.006138815078884363,
+      "rewards/rejected": -0.019133752211928368,
+      "step": 70
+    },
+    {
+      "epoch": 0.1497005988023952,
+      "grad_norm": 3.158441752144902,
+      "learning_rate": 2.978994055605757e-07,
+      "logits/chosen": -0.3353852927684784,
+      "logits/rejected": -0.20957405865192413,
+      "logps/chosen": -282.4247131347656,
+      "logps/rejected": -297.1376647949219,
+      "loss": 0.6887,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.013628537766635418,
+      "rewards/margins": 0.012240052223205566,
+      "rewards/rejected": -0.02586858905851841,
+      "step": 75
+    },
+    {
+      "epoch": 0.1596806387225549,
+      "grad_norm": 3.2922551208958932,
+      "learning_rate": 2.9693628743990157e-07,
+      "logits/chosen": -0.2210439145565033,
+      "logits/rejected": -0.13906380534172058,
+      "logps/chosen": -286.2383728027344,
+      "logps/rejected": -284.0565490722656,
+      "loss": 0.6885,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.012788718566298485,
+      "rewards/margins": 0.01518750749528408,
+      "rewards/rejected": -0.027976226061582565,
+      "step": 80
+    },
+    {
+      "epoch": 0.16966067864271456,
+      "grad_norm": 3.143746580193799,
+      "learning_rate": 2.9579415008678196e-07,
+      "logits/chosen": 0.061027251183986664,
+      "logits/rejected": 0.020937766879796982,
+      "logps/chosen": -261.85797119140625,
+      "logps/rejected": -245.4117889404297,
+      "loss": 0.6879,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.020817553624510765,
+      "rewards/margins": 0.01146668754518032,
+      "rewards/rejected": -0.032284241169691086,
+      "step": 85
+    },
+    {
+      "epoch": 0.17964071856287425,
+      "grad_norm": 3.1363791165769634,
+      "learning_rate": 2.944743850196487e-07,
+      "logits/chosen": -0.18295350670814514,
+      "logits/rejected": -0.138901025056839,
+      "logps/chosen": -302.30377197265625,
+      "logps/rejected": -297.4572448730469,
+      "loss": 0.6867,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.022789286449551582,
+      "rewards/margins": 0.014456982724368572,
+      "rewards/rejected": -0.03724626824259758,
+      "step": 90
+    },
+    {
+      "epoch": 0.18962075848303392,
+      "grad_norm": 3.375624228841244,
+      "learning_rate": 2.92978600168942e-07,
+      "logits/chosen": -0.21953599154949188,
+      "logits/rejected": -0.19249823689460754,
+      "logps/chosen": -282.0645446777344,
+      "logps/rejected": -293.2350158691406,
+      "loss": 0.6865,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.028345201164484024,
+      "rewards/margins": 0.015181821770966053,
+      "rewards/rejected": -0.0435270220041275,
+      "step": 95
+    },
+    {
+      "epoch": 0.1996007984031936,
+      "grad_norm": 3.4004680540887673,
+      "learning_rate": 2.913086179180945e-07,
+      "logits/chosen": -0.26934295892715454,
+      "logits/rejected": -0.24918439984321594,
+      "logps/chosen": -267.2822570800781,
+      "logps/rejected": -273.8163757324219,
+      "loss": 0.6847,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.02366602048277855,
+      "rewards/margins": 0.018390221521258354,
+      "rewards/rejected": -0.042056240141391754,
+      "step": 100
+    },
+    {
+      "epoch": 0.20958083832335328,
+      "grad_norm": 3.348944145808141,
+      "learning_rate": 2.894664728832377e-07,
+      "logits/chosen": -0.12691783905029297,
+      "logits/rejected": -0.10880570113658905,
+      "logps/chosen": -306.7061462402344,
+      "logps/rejected": -296.7961120605469,
+      "loss": 0.684,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.02831300161778927,
+      "rewards/margins": 0.024948222562670708,
+      "rewards/rejected": -0.053261227905750275,
+      "step": 105
+    },
+    {
+      "epoch": 0.21956087824351297,
+      "grad_norm": 3.3068624575557677,
+      "learning_rate": 2.8745440943433595e-07,
+      "logits/chosen": -0.39724451303482056,
+      "logits/rejected": -0.3233721852302551,
+      "logps/chosen": -299.71356201171875,
+      "logps/rejected": -307.81011962890625,
+      "loss": 0.6826,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.037553686648607254,
+      "rewards/margins": 0.01620485447347164,
+      "rewards/rejected": -0.053758542984724045,
+      "step": 110
+    },
+    {
+      "epoch": 0.22954091816367264,
+      "grad_norm": 3.5399975333931057,
+      "learning_rate": 2.8527487896076705e-07,
+      "logits/chosen": -0.2971861958503723,
+      "logits/rejected": -0.26923665404319763,
+      "logps/chosen": -323.73760986328125,
+      "logps/rejected": -317.88238525390625,
+      "loss": 0.6812,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.03361167758703232,
+      "rewards/margins": 0.025083836168050766,
+      "rewards/rejected": -0.058695513755083084,
+      "step": 115
+    },
+    {
+      "epoch": 0.23952095808383234,
+      "grad_norm": 3.387251098081717,
+      "learning_rate": 2.829305368846822e-07,
+      "logits/chosen": -0.08930722624063492,
+      "logits/rejected": -0.093043752014637,
+      "logps/chosen": -298.3551330566406,
+      "logps/rejected": -301.565185546875,
+      "loss": 0.6807,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.04334830120205879,
+      "rewards/margins": 0.02416048012673855,
+      "rewards/rejected": -0.06750877946615219,
+      "step": 120
+    },
+    {
+      "epoch": 0.249500998003992,
+      "grad_norm": 3.458206539528906,
+      "learning_rate": 2.8042423942578286e-07,
+      "logits/chosen": -0.06799415498971939,
+      "logits/rejected": 0.05015769600868225,
+      "logps/chosen": -252.72793579101562,
+      "logps/rejected": -279.40631103515625,
+      "loss": 0.6788,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.0386417880654335,
+      "rewards/margins": 0.03730592131614685,
+      "rewards/rejected": -0.07594770938158035,
+      "step": 125
+    },
+    {
+      "epoch": 0.25948103792415167,
+      "grad_norm": 3.4555138461844757,
+      "learning_rate": 2.7775904012145714e-07,
+      "logits/chosen": -0.24486279487609863,
+      "logits/rejected": -0.1943987011909485,
+      "logps/chosen": -326.3341369628906,
+      "logps/rejected": -326.3017272949219,
+      "loss": 0.6792,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.04846924915909767,
+      "rewards/margins": 0.03331124037504196,
+      "rewards/rejected": -0.08178049325942993,
+      "step": 130
+    },
+    {
+      "epoch": 0.2694610778443114,
+      "grad_norm": 3.4103149118409104,
+      "learning_rate": 2.749381861065149e-07,
+      "logits/chosen": -0.11615544557571411,
+      "logits/rejected": -0.02477203868329525,
+      "logps/chosen": -281.5689697265625,
+      "logps/rejected": -289.6168518066406,
+      "loss": 0.6756,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.04677049443125725,
+      "rewards/margins": 0.03843165561556816,
+      "rewards/rejected": -0.085202157497406,
+      "step": 135
+    },
+    {
+      "epoch": 0.27944111776447106,
+      "grad_norm": 3.3294732309430946,
+      "learning_rate": 2.719651141570541e-07,
+      "logits/chosen": -0.07356293499469757,
+      "logits/rejected": 0.01894739270210266,
+      "logps/chosen": -295.6517333984375,
+      "logps/rejected": -294.22064208984375,
+      "loss": 0.6733,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.04726024717092514,
+      "rewards/margins": 0.05050128698348999,
+      "rewards/rejected": -0.09776153415441513,
+      "step": 140
+    },
+    {
+      "epoch": 0.2894211576846307,
+      "grad_norm": 3.335787112423438,
+      "learning_rate": 2.6884344650327857e-07,
+      "logits/chosen": -0.3144836127758026,
+      "logits/rejected": -0.2471332997083664,
+      "logps/chosen": -275.6163635253906,
+      "logps/rejected": -283.7267150878906,
+      "loss": 0.6741,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.06026310846209526,
+      "rewards/margins": 0.03206663206219673,
+      "rewards/rejected": -0.0923297330737114,
+      "step": 145
+    },
+    {
+      "epoch": 0.2994011976047904,
+      "grad_norm": 3.351780879830391,
+      "learning_rate": 2.6557698641636836e-07,
+      "logits/chosen": -0.09479612112045288,
+      "logits/rejected": -0.05155174061655998,
+      "logps/chosen": -273.46527099609375,
+      "logps/rejected": -285.8160095214844,
+      "loss": 0.6719,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.057442475110292435,
+      "rewards/margins": 0.04023780673742294,
+      "rewards/rejected": -0.09768027812242508,
+      "step": 150
+    },
+    {
+      "epoch": 0.3093812375249501,
+      "grad_norm": 3.3953812787691744,
+      "learning_rate": 2.6216971357477977e-07,
+      "logits/chosen": -0.20542898774147034,
+      "logits/rejected": -0.16760793328285217,
+      "logps/chosen": -319.43438720703125,
+      "logps/rejected": -337.89678955078125,
+      "loss": 0.6677,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.0877736285328865,
+      "rewards/margins": 0.05791449546813965,
+      "rewards/rejected": -0.14568811655044556,
+      "step": 155
+    },
+    {
+      "epoch": 0.3193612774451098,
+      "grad_norm": 3.7295101426966957,
+      "learning_rate": 2.5862577921562015e-07,
+      "logits/chosen": -0.26064497232437134,
+      "logits/rejected": -0.1645033359527588,
+      "logps/chosen": -292.02484130859375,
+      "logps/rejected": -300.4161376953125,
+      "loss": 0.665,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.08468987792730331,
+      "rewards/margins": 0.062365107238292694,
+      "rewards/rejected": -0.1470550000667572,
+      "step": 160
+    },
+    {
+      "epoch": 0.32934131736526945,
+      "grad_norm": 3.5278102635310775,
+      "learning_rate": 2.549495010770048e-07,
+      "logits/chosen": -0.2758394777774811,
+      "logits/rejected": -0.20927894115447998,
+      "logps/chosen": -288.8243713378906,
+      "logps/rejected": -291.8514404296875,
+      "loss": 0.6655,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.10788210481405258,
+      "rewards/margins": 0.06151789426803589,
+      "rewards/rejected": -0.16940000653266907,
+      "step": 165
+    },
+    {
+      "epoch": 0.3393213572854291,
+      "grad_norm": 3.512512373193113,
+      "learning_rate": 2.511453581375585e-07,
+      "logits/chosen": -0.39803841710090637,
+      "logits/rejected": -0.3213597238063812,
+      "logps/chosen": -258.41326904296875,
+      "logps/rejected": -263.5000915527344,
+      "loss": 0.6625,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.10974812507629395,
+      "rewards/margins": 0.04202640801668167,
+      "rewards/rejected": -0.15177452564239502,
+      "step": 170
+    },
+    {
+      "epoch": 0.34930139720558884,
+      "grad_norm": 3.7824536020137383,
+      "learning_rate": 2.4721798515946963e-07,
+      "logits/chosen": -0.2360338717699051,
+      "logits/rejected": -0.17899933457374573,
+      "logps/chosen": -274.8690185546875,
+      "logps/rejected": -291.98419189453125,
+      "loss": 0.6587,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.1216902956366539,
+      "rewards/margins": 0.0732160434126854,
+      "rewards/rejected": -0.1949063539505005,
+      "step": 175
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "grad_norm": 3.6570477679381033,
+      "learning_rate": 2.4317216704174655e-07,
+      "logits/chosen": -0.2678098976612091,
+      "logits/rejected": -0.22654588520526886,
+      "logps/chosen": -285.76885986328125,
+      "logps/rejected": -300.3975524902344,
+      "loss": 0.6575,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.13574646413326263,
+      "rewards/margins": 0.06750482320785522,
+      "rewards/rejected": -0.20325128734111786,
+      "step": 180
+    },
+    {
+      "epoch": 0.36926147704590817,
+      "grad_norm": 3.705774667801494,
+      "learning_rate": 2.3901283299055524e-07,
+      "logits/chosen": -0.4732998013496399,
+      "logits/rejected": -0.39881661534309387,
+      "logps/chosen": -321.14984130859375,
+      "logps/rejected": -326.15032958984375,
+      "loss": 0.6514,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.17002463340759277,
+      "rewards/margins": 0.08681143075227737,
+      "rewards/rejected": -0.25683605670928955,
+      "step": 185
+    },
+    {
+      "epoch": 0.37924151696606784,
+      "grad_norm": 3.4125215861302176,
+      "learning_rate": 2.3474505051374067e-07,
+      "logits/chosen": -0.34785977005958557,
+      "logits/rejected": -0.24581901729106903,
+      "logps/chosen": -323.81732177734375,
+      "logps/rejected": -328.8360900878906,
+      "loss": 0.6496,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.20683076977729797,
+      "rewards/margins": 0.07259462773799896,
+      "rewards/rejected": -0.2794254422187805,
+      "step": 190
+    },
+    {
+      "epoch": 0.38922155688622756,
+      "grad_norm": 3.6035947439545715,
+      "learning_rate": 2.3037401924684947e-07,
+      "logits/chosen": -0.2815292775630951,
+      "logits/rejected": -0.2620851397514343,
+      "logps/chosen": -319.5675048828125,
+      "logps/rejected": -332.9228210449219,
+      "loss": 0.6501,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.2412305772304535,
+      "rewards/margins": 0.09057402610778809,
+      "rewards/rejected": -0.3318046033382416,
+      "step": 195
+    },
+    {
+      "epoch": 0.3992015968063872,
+      "grad_norm": 3.6822468215438624,
+      "learning_rate": 2.2590506461817452e-07,
+      "logits/chosen": -0.259944349527359,
+      "logits/rejected": -0.20725861191749573,
+      "logps/chosen": -298.30303955078125,
+      "logps/rejected": -305.5474548339844,
+      "loss": 0.6419,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.24381069839000702,
+      "rewards/margins": 0.11996382474899292,
+      "rewards/rejected": -0.36377447843551636,
+      "step": 200
+    },
+    {
+      "epoch": 0.4091816367265469,
+      "grad_norm": 3.7132773714988927,
+      "learning_rate": 2.213436313605413e-07,
+      "logits/chosen": -0.5560285449028015,
+      "logits/rejected": -0.49163347482681274,
+      "logps/chosen": -387.44171142578125,
+      "logps/rejected": -402.449462890625,
+      "loss": 0.6434,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.3169836699962616,
+      "rewards/margins": 0.07618891447782516,
+      "rewards/rejected": -0.39317259192466736,
+      "step": 205
+    },
+    {
+      "epoch": 0.41916167664670656,
+      "grad_norm": 3.775451248470663,
+      "learning_rate": 2.166952768777391e-07,
+      "logits/chosen": -0.2941240966320038,
+      "logits/rejected": -0.3131045997142792,
+      "logps/chosen": -303.090087890625,
+      "logps/rejected": -298.85699462890625,
+      "loss": 0.6404,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.2724608778953552,
+      "rewards/margins": 0.1073354110121727,
+      "rewards/rejected": -0.3797963261604309,
+      "step": 210
+    },
+    {
+      "epoch": 0.4291417165668663,
+      "grad_norm": 3.7925188623151422,
+      "learning_rate": 2.1196566447368126e-07,
+      "logits/chosen": -0.26538053154945374,
+      "logits/rejected": -0.25145062804222107,
+      "logps/chosen": -334.455078125,
+      "logps/rejected": -356.2786865234375,
+      "loss": 0.6355,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.34816819429397583,
+      "rewards/margins": 0.12635044753551483,
+      "rewards/rejected": -0.4745185971260071,
+      "step": 215
+    },
+    {
+      "epoch": 0.43912175648702595,
+      "grad_norm": 3.8981243362393565,
+      "learning_rate": 2.0716055645254113e-07,
+      "logits/chosen": -0.46777939796447754,
+      "logits/rejected": -0.4300519824028015,
+      "logps/chosen": -325.1937255859375,
+      "logps/rejected": -333.54022216796875,
+      "loss": 0.641,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.4105430245399475,
+      "rewards/margins": 0.10119415819644928,
+      "rewards/rejected": -0.5117372274398804,
+      "step": 220
+    },
+    {
+      "epoch": 0.4491017964071856,
+      "grad_norm": 3.7392987472200354,
+      "learning_rate": 2.0228580709827226e-07,
+      "logits/chosen": -0.5368104577064514,
+      "logits/rejected": -0.45491117238998413,
+      "logps/chosen": -349.7928771972656,
+      "logps/rejected": -371.95050048828125,
+      "loss": 0.6326,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3743346631526947,
+      "rewards/margins": 0.1426324099302292,
+      "rewards/rejected": -0.5169671177864075,
+      "step": 225
+    },
+    {
+      "epoch": 0.4590818363273453,
+      "grad_norm": 3.6974655152807174,
+      "learning_rate": 1.9734735554206537e-07,
+      "logits/chosen": -0.31408676505088806,
+      "logits/rejected": -0.2642524242401123,
+      "logps/chosen": -349.4893798828125,
+      "logps/rejected": -369.08990478515625,
+      "loss": 0.6238,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.47439342737197876,
+      "rewards/margins": 0.15798419713974,
+      "rewards/rejected": -0.632377564907074,
+      "step": 230
+    },
+    {
+      "epoch": 0.469061876247505,
+      "grad_norm": 3.9074441662298662,
+      "learning_rate": 1.9235121852643148e-07,
+      "logits/chosen": -0.4889460504055023,
+      "logits/rejected": -0.48752936720848083,
+      "logps/chosen": -331.08624267578125,
+      "logps/rejected": -348.8202819824219,
+      "loss": 0.6259,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.41649022698402405,
+      "rewards/margins": 0.1930549144744873,
+      "rewards/rejected": -0.609545111656189,
+      "step": 235
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 3.7710978575315757,
+      "learning_rate": 1.8730348307472826e-07,
+      "logits/chosen": -0.4119279384613037,
+      "logits/rejected": -0.444758802652359,
+      "logps/chosen": -348.2624206542969,
+      "logps/rejected": -369.9598083496094,
+      "loss": 0.6249,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.5225319862365723,
+      "rewards/margins": 0.13163016736507416,
+      "rewards/rejected": -0.6541622281074524,
+      "step": 240
+    },
+    {
+      "epoch": 0.48902195608782434,
+      "grad_norm": 4.08348789093204,
+      "learning_rate": 1.822102990750595e-07,
+      "logits/chosen": -0.5410420298576355,
+      "logits/rejected": -0.4581461548805237,
+      "logps/chosen": -300.3963317871094,
+      "logps/rejected": -326.97357177734375,
+      "loss": 0.6205,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.4268406927585602,
+      "rewards/margins": 0.17870576679706573,
+      "rewards/rejected": -0.6055464744567871,
+      "step": 245
+    },
+    {
+      "epoch": 0.499001996007984,
+      "grad_norm": 3.8249633059365977,
+      "learning_rate": 1.7707787178758402e-07,
+      "logits/chosen": -0.5376532673835754,
+      "logits/rejected": -0.5166374444961548,
+      "logps/chosen": -334.3974609375,
+      "logps/rejected": -363.59832763671875,
+      "loss": 0.6097,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.5467029809951782,
+      "rewards/margins": 0.219395712018013,
+      "rewards/rejected": -0.7660986185073853,
+      "step": 250
+    },
+    {
+      "epoch": 0.5089820359281437,
+      "grad_norm": 4.084608415013939,
+      "learning_rate": 1.7191245428436176e-07,
+      "logits/chosen": -0.6120297908782959,
+      "logits/rejected": -0.5665668249130249,
+      "logps/chosen": -388.49237060546875,
+      "logps/rejected": -404.17913818359375,
+      "loss": 0.6066,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.5541552305221558,
+      "rewards/margins": 0.18654166162014008,
+      "rewards/rejected": -0.7406969666481018,
+      "step": 255
+    },
+    {
+      "epoch": 0.5189620758483033,
+      "grad_norm": 4.127013078261958,
+      "learning_rate": 1.667203398309488e-07,
+      "logits/chosen": -0.602649450302124,
+      "logits/rejected": -0.47091540694236755,
+      "logps/chosen": -342.5652770996094,
+      "logps/rejected": -363.1390380859375,
+      "loss": 0.6099,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.5999665260314941,
+      "rewards/margins": 0.22458717226982117,
+      "rewards/rejected": -0.8245537877082825,
+      "step": 260
+    },
+    {
+      "epoch": 0.5289421157684631,
+      "grad_norm": 4.181662944251744,
+      "learning_rate": 1.6150785421902278e-07,
+      "logits/chosen": -0.49136123061180115,
+      "logits/rejected": -0.4355231821537018,
+      "logps/chosen": -355.0814514160156,
+      "logps/rejected": -400.48486328125,
+      "loss": 0.6027,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.6992485523223877,
+      "rewards/margins": 0.2647705674171448,
+      "rewards/rejected": -0.9640190005302429,
+      "step": 265
+    },
+    {
+      "epoch": 0.5389221556886228,
+      "grad_norm": 4.187328944312369,
+      "learning_rate": 1.5628134805937993e-07,
+      "logits/chosen": -0.6901322603225708,
+      "logits/rejected": -0.7155795693397522,
+      "logps/chosen": -338.4058532714844,
+      "logps/rejected": -357.05145263671875,
+      "loss": 0.6044,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.6499531865119934,
+      "rewards/margins": 0.2078942060470581,
+      "rewards/rejected": -0.8578473329544067,
+      "step": 270
+    },
+    {
+      "epoch": 0.5489021956087824,
+      "grad_norm": 4.480820141822546,
+      "learning_rate": 1.5104718904469424e-07,
+      "logits/chosen": -0.49210062623023987,
+      "logits/rejected": -0.4995419979095459,
+      "logps/chosen": -362.78936767578125,
+      "logps/rejected": -376.6024475097656,
+      "loss": 0.6022,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.684400200843811,
+      "rewards/margins": 0.22897310554981232,
+      "rewards/rejected": -0.9133733510971069,
+      "step": 275
+    },
+    {
+      "epoch": 0.5588822355289421,
+      "grad_norm": 4.335560690928003,
+      "learning_rate": 1.458117541914647e-07,
+      "logits/chosen": -0.6205674409866333,
+      "logits/rejected": -0.5415416955947876,
+      "logps/chosen": -363.15484619140625,
+      "logps/rejected": -380.423828125,
+      "loss": 0.601,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.7319628000259399,
+      "rewards/margins": 0.22972945868968964,
+      "rewards/rejected": -0.9616923332214355,
+      "step": 280
+    },
+    {
+      "epoch": 0.5688622754491018,
+      "grad_norm": 4.236266469806635,
+      "learning_rate": 1.4058142207060298e-07,
+      "logits/chosen": -0.5227392315864563,
+      "logits/rejected": -0.44109734892845154,
+      "logps/chosen": -350.81268310546875,
+      "logps/rejected": -387.339111328125,
+      "loss": 0.599,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.7962437272071838,
+      "rewards/margins": 0.2677839994430542,
+      "rewards/rejected": -1.0640277862548828,
+      "step": 285
+    },
+    {
+      "epoch": 0.5788423153692615,
+      "grad_norm": 4.1859368563558546,
+      "learning_rate": 1.353625650361276e-07,
+      "logits/chosen": -0.4567599296569824,
+      "logits/rejected": -0.37081751227378845,
+      "logps/chosen": -292.90582275390625,
+      "logps/rejected": -351.08428955078125,
+      "loss": 0.5976,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.7117597460746765,
+      "rewards/margins": 0.23347418010234833,
+      "rewards/rejected": -0.9452340006828308,
+      "step": 290
+    },
+    {
+      "epoch": 0.5888223552894212,
+      "grad_norm": 4.963202872238042,
+      "learning_rate": 1.301615414614316e-07,
+      "logits/chosen": -0.5814245939254761,
+      "logits/rejected": -0.477074533700943,
+      "logps/chosen": -359.9764404296875,
+      "logps/rejected": -408.649169921875,
+      "loss": 0.5854,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.8252065777778625,
+      "rewards/margins": 0.3438906669616699,
+      "rewards/rejected": -1.1690973043441772,
+      "step": 295
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "grad_norm": 4.522965998928778,
+      "learning_rate": 1.2498468799258466e-07,
+      "logits/chosen": -0.6931585669517517,
+      "logits/rejected": -0.6726911067962646,
+      "logps/chosen": -447.56134033203125,
+      "logps/rejected": -467.0315856933594,
+      "loss": 0.5951,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.0262882709503174,
+      "rewards/margins": 0.3147868514060974,
+      "rewards/rejected": -1.3410751819610596,
+      "step": 300
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 501,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 101,
+  "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-303/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2062bff810c3be97f9dc215093b5dad2b48711e0862036888bf785c22f9a23
+size 7544

checkpoint-404/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
+}

checkpoint-404/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/GLOBALFS/gznwp_3/qxj/lgzhong/LLaMA-Factory/saves/Qwen2.5-7B-Instruct-SFT-v1.5",
+  "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_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-404/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": "4.43.4"
+}

checkpoint-404/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97b2b692f3c9c5b5db1e24de775197758a1e5e3fa94054c839fb791e4145033d
+size 4877660776

checkpoint-404/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92ae08845fcd6464d344a06dd1d04e5a3fb685f7b494ed57c0672eead7b34c6c
+size 4932751008

checkpoint-404/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f90b756ff997561d7e9417189be24926d28b180627029e8440dd19e0617e386
+size 4330865200

checkpoint-404/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0099342202fbba8fbec3763e6fa28ea58cd15a074b9b8e294f0a1e2e14ad7983
+size 1089994880

checkpoint-404/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"
+  }
+}

checkpoint-404/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
+  }
+}

checkpoint-404/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",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-404/trainer_state.json

@@ -0,0 +1,1248 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8063872255489022,
+  "eval_steps": 500,
+  "global_step": 404,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001996007984031936,
+      "grad_norm": 3.4413226850733536,
+      "learning_rate": 5.88235294117647e-09,
+      "logits/chosen": -0.2126132994890213,
+      "logits/rejected": -0.06049485132098198,
+      "logps/chosen": -312.6929931640625,
+      "logps/rejected": -303.399658203125,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.00998003992015968,
+      "grad_norm": 3.5626484310109503,
+      "learning_rate": 2.941176470588235e-08,
+      "logits/chosen": -0.15043149888515472,
+      "logits/rejected": -0.05884423851966858,
+      "logps/chosen": -271.6809387207031,
+      "logps/rejected": -308.14019775390625,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.34375,
+      "rewards/chosen": 0.00032658452983014286,
+      "rewards/margins": -0.00044720349251292646,
+      "rewards/rejected": 0.0007737880805507302,
+      "step": 5
+    },
+    {
+      "epoch": 0.01996007984031936,
+      "grad_norm": 3.444766226961807,
+      "learning_rate": 5.88235294117647e-08,
+      "logits/chosen": -0.04885115846991539,
+      "logits/rejected": 0.02876092866063118,
+      "logps/chosen": -314.44207763671875,
+      "logps/rejected": -324.5089111328125,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.0015638660406693816,
+      "rewards/margins": -0.0018882350996136665,
+      "rewards/rejected": 0.0003243688843213022,
+      "step": 10
+    },
+    {
+      "epoch": 0.029940119760479042,
+      "grad_norm": 3.351776759283806,
+      "learning_rate": 8.823529411764706e-08,
+      "logits/chosen": -0.14645501971244812,
+      "logits/rejected": -0.10253484547138214,
+      "logps/chosen": -325.3197021484375,
+      "logps/rejected": -335.1691589355469,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.3375000059604645,
+      "rewards/chosen": -0.0009325200808234513,
+      "rewards/margins": -0.0027469159103929996,
+      "rewards/rejected": 0.0018143958877772093,
+      "step": 15
+    },
+    {
+      "epoch": 0.03992015968063872,
+      "grad_norm": 3.2486760323756765,
+      "learning_rate": 1.176470588235294e-07,
+      "logits/chosen": -0.17513605952262878,
+      "logits/rejected": -0.14125120639801025,
+      "logps/chosen": -236.529052734375,
+      "logps/rejected": -224.99609375,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.00048039742978289723,
+      "rewards/margins": -0.0017443184042349458,
+      "rewards/rejected": 0.0012639210326597095,
+      "step": 20
+    },
+    {
+      "epoch": 0.0499001996007984,
+      "grad_norm": 3.682895506825886,
+      "learning_rate": 1.4705882352941175e-07,
+      "logits/chosen": 0.02582230605185032,
+      "logits/rejected": -0.026322145015001297,
+      "logps/chosen": -276.4084777832031,
+      "logps/rejected": -271.5510559082031,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.00010870690312003717,
+      "rewards/margins": -2.2810349037172273e-05,
+      "rewards/rejected": -8.589646313339472e-05,
+      "step": 25
+    },
+    {
+      "epoch": 0.059880239520958084,
+      "grad_norm": 3.521568498969969,
+      "learning_rate": 1.764705882352941e-07,
+      "logits/chosen": -0.029633093625307083,
+      "logits/rejected": 0.017462745308876038,
+      "logps/chosen": -241.04345703125,
+      "logps/rejected": -254.0708465576172,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.001156697398982942,
+      "rewards/margins": 0.0012088593794032931,
+      "rewards/rejected": -5.2162260544719175e-05,
+      "step": 30
+    },
+    {
+      "epoch": 0.06986027944111776,
+      "grad_norm": 3.4756100770970852,
+      "learning_rate": 2.0588235294117647e-07,
+      "logits/chosen": -0.09809896349906921,
+      "logits/rejected": -0.12783308327198029,
+      "logps/chosen": -316.04541015625,
+      "logps/rejected": -303.2275085449219,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.0019062187056988478,
+      "rewards/margins": 0.0034712664783000946,
+      "rewards/rejected": -0.0015650471905246377,
+      "step": 35
+    },
+    {
+      "epoch": 0.07984031936127745,
+      "grad_norm": 3.5251485554920383,
+      "learning_rate": 2.352941176470588e-07,
+      "logits/chosen": -0.10866469144821167,
+      "logits/rejected": -0.08842261880636215,
+      "logps/chosen": -300.94866943359375,
+      "logps/rejected": -301.57635498046875,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0005061564734205604,
+      "rewards/margins": 0.0017319575417786837,
+      "rewards/rejected": -0.0012258009519428015,
+      "step": 40
+    },
+    {
+      "epoch": 0.08982035928143713,
+      "grad_norm": 3.562421126179782,
+      "learning_rate": 2.6470588235294114e-07,
+      "logits/chosen": -0.04412439838051796,
+      "logits/rejected": 0.046757772564888,
+      "logps/chosen": -276.1053771972656,
+      "logps/rejected": -299.3190612792969,
+      "loss": 0.692,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.002857887651771307,
+      "rewards/margins": 0.0004688422195613384,
+      "rewards/rejected": -0.003326730104163289,
+      "step": 45
+    },
+    {
+      "epoch": 0.0998003992015968,
+      "grad_norm": 3.174201376940309,
+      "learning_rate": 2.941176470588235e-07,
+      "logits/chosen": -0.08824320137500763,
+      "logits/rejected": -0.043245576322078705,
+      "logps/chosen": -271.13604736328125,
+      "logps/rejected": -272.74102783203125,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.0016361953457817435,
+      "rewards/margins": 0.005965009797364473,
+      "rewards/rejected": -0.007601206190884113,
+      "step": 50
+    },
+    {
+      "epoch": 0.10978043912175649,
+      "grad_norm": 3.3426951285606368,
+      "learning_rate": 2.999415172560531e-07,
+      "logits/chosen": 0.032454706728458405,
+      "logits/rejected": 0.15314094722270966,
+      "logps/chosen": -301.4625244140625,
+      "logps/rejected": -304.8877258300781,
+      "loss": 0.691,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.007659287191927433,
+      "rewards/margins": 0.0023522169794887304,
+      "rewards/rejected": -0.010011503472924232,
+      "step": 55
+    },
+    {
+      "epoch": 0.11976047904191617,
+      "grad_norm": 3.2266501701625283,
+      "learning_rate": 2.997040092642407e-07,
+      "logits/chosen": -0.13825412094593048,
+      "logits/rejected": -0.06802596896886826,
+      "logps/chosen": -273.85198974609375,
+      "logps/rejected": -256.1399841308594,
+      "loss": 0.6905,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.0074735768139362335,
+      "rewards/margins": 0.005476811900734901,
+      "rewards/rejected": -0.012950388714671135,
+      "step": 60
+    },
+    {
+      "epoch": 0.12974051896207583,
+      "grad_norm": 3.129826931598691,
+      "learning_rate": 2.9928410999727467e-07,
+      "logits/chosen": -0.03806266561150551,
+      "logits/rejected": -0.06114925071597099,
+      "logps/chosen": -273.815673828125,
+      "logps/rejected": -257.2196350097656,
+      "loss": 0.6897,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.010186719708144665,
+      "rewards/margins": 0.00584446731954813,
+      "rewards/rejected": -0.016031187027692795,
+      "step": 65
+    },
+    {
+      "epoch": 0.13972055888223553,
+      "grad_norm": 3.2696148017727764,
+      "learning_rate": 2.9868233103773125e-07,
+      "logits/chosen": -0.19126296043395996,
+      "logits/rejected": -0.1384088099002838,
+      "logps/chosen": -289.3074645996094,
+      "logps/rejected": -304.941650390625,
+      "loss": 0.6901,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.012994937598705292,
+      "rewards/margins": 0.006138815078884363,
+      "rewards/rejected": -0.019133752211928368,
+      "step": 70
+    },
+    {
+      "epoch": 0.1497005988023952,
+      "grad_norm": 3.158441752144902,
+      "learning_rate": 2.978994055605757e-07,
+      "logits/chosen": -0.3353852927684784,
+      "logits/rejected": -0.20957405865192413,
+      "logps/chosen": -282.4247131347656,
+      "logps/rejected": -297.1376647949219,
+      "loss": 0.6887,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.013628537766635418,
+      "rewards/margins": 0.012240052223205566,
+      "rewards/rejected": -0.02586858905851841,
+      "step": 75
+    },
+    {
+      "epoch": 0.1596806387225549,
+      "grad_norm": 3.2922551208958932,
+      "learning_rate": 2.9693628743990157e-07,
+      "logits/chosen": -0.2210439145565033,
+      "logits/rejected": -0.13906380534172058,
+      "logps/chosen": -286.2383728027344,
+      "logps/rejected": -284.0565490722656,
+      "loss": 0.6885,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.012788718566298485,
+      "rewards/margins": 0.01518750749528408,
+      "rewards/rejected": -0.027976226061582565,
+      "step": 80
+    },
+    {
+      "epoch": 0.16966067864271456,
+      "grad_norm": 3.143746580193799,
+      "learning_rate": 2.9579415008678196e-07,
+      "logits/chosen": 0.061027251183986664,
+      "logits/rejected": 0.020937766879796982,
+      "logps/chosen": -261.85797119140625,
+      "logps/rejected": -245.4117889404297,
+      "loss": 0.6879,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.020817553624510765,
+      "rewards/margins": 0.01146668754518032,
+      "rewards/rejected": -0.032284241169691086,
+      "step": 85
+    },
+    {
+      "epoch": 0.17964071856287425,
+      "grad_norm": 3.1363791165769634,
+      "learning_rate": 2.944743850196487e-07,
+      "logits/chosen": -0.18295350670814514,
+      "logits/rejected": -0.138901025056839,
+      "logps/chosen": -302.30377197265625,
+      "logps/rejected": -297.4572448730469,
+      "loss": 0.6867,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.022789286449551582,
+      "rewards/margins": 0.014456982724368572,
+      "rewards/rejected": -0.03724626824259758,
+      "step": 90
+    },
+    {
+      "epoch": 0.18962075848303392,
+      "grad_norm": 3.375624228841244,
+      "learning_rate": 2.92978600168942e-07,
+      "logits/chosen": -0.21953599154949188,
+      "logits/rejected": -0.19249823689460754,
+      "logps/chosen": -282.0645446777344,
+      "logps/rejected": -293.2350158691406,
+      "loss": 0.6865,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.028345201164484024,
+      "rewards/margins": 0.015181821770966053,
+      "rewards/rejected": -0.0435270220041275,
+      "step": 95
+    },
+    {
+      "epoch": 0.1996007984031936,
+      "grad_norm": 3.4004680540887673,
+      "learning_rate": 2.913086179180945e-07,
+      "logits/chosen": -0.26934295892715454,
+      "logits/rejected": -0.24918439984321594,
+      "logps/chosen": -267.2822570800781,
+      "logps/rejected": -273.8163757324219,
+      "loss": 0.6847,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.02366602048277855,
+      "rewards/margins": 0.018390221521258354,
+      "rewards/rejected": -0.042056240141391754,
+      "step": 100
+    },
+    {
+      "epoch": 0.20958083832335328,
+      "grad_norm": 3.348944145808141,
+      "learning_rate": 2.894664728832377e-07,
+      "logits/chosen": -0.12691783905029297,
+      "logits/rejected": -0.10880570113658905,
+      "logps/chosen": -306.7061462402344,
+      "logps/rejected": -296.7961120605469,
+      "loss": 0.684,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.02831300161778927,
+      "rewards/margins": 0.024948222562670708,
+      "rewards/rejected": -0.053261227905750275,
+      "step": 105
+    },
+    {
+      "epoch": 0.21956087824351297,
+      "grad_norm": 3.3068624575557677,
+      "learning_rate": 2.8745440943433595e-07,
+      "logits/chosen": -0.39724451303482056,
+      "logits/rejected": -0.3233721852302551,
+      "logps/chosen": -299.71356201171875,
+      "logps/rejected": -307.81011962890625,
+      "loss": 0.6826,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.037553686648607254,
+      "rewards/margins": 0.01620485447347164,
+      "rewards/rejected": -0.053758542984724045,
+      "step": 110
+    },
+    {
+      "epoch": 0.22954091816367264,
+      "grad_norm": 3.5399975333931057,
+      "learning_rate": 2.8527487896076705e-07,
+      "logits/chosen": -0.2971861958503723,
+      "logits/rejected": -0.26923665404319763,
+      "logps/chosen": -323.73760986328125,
+      "logps/rejected": -317.88238525390625,
+      "loss": 0.6812,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.03361167758703232,
+      "rewards/margins": 0.025083836168050766,
+      "rewards/rejected": -0.058695513755083084,
+      "step": 115
+    },
+    {
+      "epoch": 0.23952095808383234,
+      "grad_norm": 3.387251098081717,
+      "learning_rate": 2.829305368846822e-07,
+      "logits/chosen": -0.08930722624063492,
+      "logits/rejected": -0.093043752014637,
+      "logps/chosen": -298.3551330566406,
+      "logps/rejected": -301.565185546875,
+      "loss": 0.6807,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.04334830120205879,
+      "rewards/margins": 0.02416048012673855,
+      "rewards/rejected": -0.06750877946615219,
+      "step": 120
+    },
+    {
+      "epoch": 0.249500998003992,
+      "grad_norm": 3.458206539528906,
+      "learning_rate": 2.8042423942578286e-07,
+      "logits/chosen": -0.06799415498971939,
+      "logits/rejected": 0.05015769600868225,
+      "logps/chosen": -252.72793579101562,
+      "logps/rejected": -279.40631103515625,
+      "loss": 0.6788,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.0386417880654335,
+      "rewards/margins": 0.03730592131614685,
+      "rewards/rejected": -0.07594770938158035,
+      "step": 125
+    },
+    {
+      "epoch": 0.25948103792415167,
+      "grad_norm": 3.4555138461844757,
+      "learning_rate": 2.7775904012145714e-07,
+      "logits/chosen": -0.24486279487609863,
+      "logits/rejected": -0.1943987011909485,
+      "logps/chosen": -326.3341369628906,
+      "logps/rejected": -326.3017272949219,
+      "loss": 0.6792,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.04846924915909767,
+      "rewards/margins": 0.03331124037504196,
+      "rewards/rejected": -0.08178049325942993,
+      "step": 130
+    },
+    {
+      "epoch": 0.2694610778443114,
+      "grad_norm": 3.4103149118409104,
+      "learning_rate": 2.749381861065149e-07,
+      "logits/chosen": -0.11615544557571411,
+      "logits/rejected": -0.02477203868329525,
+      "logps/chosen": -281.5689697265625,
+      "logps/rejected": -289.6168518066406,
+      "loss": 0.6756,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.04677049443125725,
+      "rewards/margins": 0.03843165561556816,
+      "rewards/rejected": -0.085202157497406,
+      "step": 135
+    },
+    {
+      "epoch": 0.27944111776447106,
+      "grad_norm": 3.3294732309430946,
+      "learning_rate": 2.719651141570541e-07,
+      "logits/chosen": -0.07356293499469757,
+      "logits/rejected": 0.01894739270210266,
+      "logps/chosen": -295.6517333984375,
+      "logps/rejected": -294.22064208984375,
+      "loss": 0.6733,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.04726024717092514,
+      "rewards/margins": 0.05050128698348999,
+      "rewards/rejected": -0.09776153415441513,
+      "step": 140
+    },
+    {
+      "epoch": 0.2894211576846307,
+      "grad_norm": 3.335787112423438,
+      "learning_rate": 2.6884344650327857e-07,
+      "logits/chosen": -0.3144836127758026,
+      "logits/rejected": -0.2471332997083664,
+      "logps/chosen": -275.6163635253906,
+      "logps/rejected": -283.7267150878906,
+      "loss": 0.6741,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.06026310846209526,
+      "rewards/margins": 0.03206663206219673,
+      "rewards/rejected": -0.0923297330737114,
+      "step": 145
+    },
+    {
+      "epoch": 0.2994011976047904,
+      "grad_norm": 3.351780879830391,
+      "learning_rate": 2.6557698641636836e-07,
+      "logits/chosen": -0.09479612112045288,
+      "logits/rejected": -0.05155174061655998,
+      "logps/chosen": -273.46527099609375,
+      "logps/rejected": -285.8160095214844,
+      "loss": 0.6719,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.057442475110292435,
+      "rewards/margins": 0.04023780673742294,
+      "rewards/rejected": -0.09768027812242508,
+      "step": 150
+    },
+    {
+      "epoch": 0.3093812375249501,
+      "grad_norm": 3.3953812787691744,
+      "learning_rate": 2.6216971357477977e-07,
+      "logits/chosen": -0.20542898774147034,
+      "logits/rejected": -0.16760793328285217,
+      "logps/chosen": -319.43438720703125,
+      "logps/rejected": -337.89678955078125,
+      "loss": 0.6677,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.0877736285328865,
+      "rewards/margins": 0.05791449546813965,
+      "rewards/rejected": -0.14568811655044556,
+      "step": 155
+    },
+    {
+      "epoch": 0.3193612774451098,
+      "grad_norm": 3.7295101426966957,
+      "learning_rate": 2.5862577921562015e-07,
+      "logits/chosen": -0.26064497232437134,
+      "logits/rejected": -0.1645033359527588,
+      "logps/chosen": -292.02484130859375,
+      "logps/rejected": -300.4161376953125,
+      "loss": 0.665,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.08468987792730331,
+      "rewards/margins": 0.062365107238292694,
+      "rewards/rejected": -0.1470550000667572,
+      "step": 160
+    },
+    {
+      "epoch": 0.32934131736526945,
+      "grad_norm": 3.5278102635310775,
+      "learning_rate": 2.549495010770048e-07,
+      "logits/chosen": -0.2758394777774811,
+      "logits/rejected": -0.20927894115447998,
+      "logps/chosen": -288.8243713378906,
+      "logps/rejected": -291.8514404296875,
+      "loss": 0.6655,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.10788210481405258,
+      "rewards/margins": 0.06151789426803589,
+      "rewards/rejected": -0.16940000653266907,
+      "step": 165
+    },
+    {
+      "epoch": 0.3393213572854291,
+      "grad_norm": 3.512512373193113,
+      "learning_rate": 2.511453581375585e-07,
+      "logits/chosen": -0.39803841710090637,
+      "logits/rejected": -0.3213597238063812,
+      "logps/chosen": -258.41326904296875,
+      "logps/rejected": -263.5000915527344,
+      "loss": 0.6625,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.10974812507629395,
+      "rewards/margins": 0.04202640801668167,
+      "rewards/rejected": -0.15177452564239502,
+      "step": 170
+    },
+    {
+      "epoch": 0.34930139720558884,
+      "grad_norm": 3.7824536020137383,
+      "learning_rate": 2.4721798515946963e-07,
+      "logits/chosen": -0.2360338717699051,
+      "logits/rejected": -0.17899933457374573,
+      "logps/chosen": -274.8690185546875,
+      "logps/rejected": -291.98419189453125,
+      "loss": 0.6587,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.1216902956366539,
+      "rewards/margins": 0.0732160434126854,
+      "rewards/rejected": -0.1949063539505005,
+      "step": 175
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "grad_norm": 3.6570477679381033,
+      "learning_rate": 2.4317216704174655e-07,
+      "logits/chosen": -0.2678098976612091,
+      "logits/rejected": -0.22654588520526886,
+      "logps/chosen": -285.76885986328125,
+      "logps/rejected": -300.3975524902344,
+      "loss": 0.6575,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.13574646413326263,
+      "rewards/margins": 0.06750482320785522,
+      "rewards/rejected": -0.20325128734111786,
+      "step": 180
+    },
+    {
+      "epoch": 0.36926147704590817,
+      "grad_norm": 3.705774667801494,
+      "learning_rate": 2.3901283299055524e-07,
+      "logits/chosen": -0.4732998013496399,
+      "logits/rejected": -0.39881661534309387,
+      "logps/chosen": -321.14984130859375,
+      "logps/rejected": -326.15032958984375,
+      "loss": 0.6514,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.17002463340759277,
+      "rewards/margins": 0.08681143075227737,
+      "rewards/rejected": -0.25683605670928955,
+      "step": 185
+    },
+    {
+      "epoch": 0.37924151696606784,
+      "grad_norm": 3.4125215861302176,
+      "learning_rate": 2.3474505051374067e-07,
+      "logits/chosen": -0.34785977005958557,
+      "logits/rejected": -0.24581901729106903,
+      "logps/chosen": -323.81732177734375,
+      "logps/rejected": -328.8360900878906,
+      "loss": 0.6496,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.20683076977729797,
+      "rewards/margins": 0.07259462773799896,
+      "rewards/rejected": -0.2794254422187805,
+      "step": 190
+    },
+    {
+      "epoch": 0.38922155688622756,
+      "grad_norm": 3.6035947439545715,
+      "learning_rate": 2.3037401924684947e-07,
+      "logits/chosen": -0.2815292775630951,
+      "logits/rejected": -0.2620851397514343,
+      "logps/chosen": -319.5675048828125,
+      "logps/rejected": -332.9228210449219,
+      "loss": 0.6501,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.2412305772304535,
+      "rewards/margins": 0.09057402610778809,
+      "rewards/rejected": -0.3318046033382416,
+      "step": 195
+    },
+    {
+      "epoch": 0.3992015968063872,
+      "grad_norm": 3.6822468215438624,
+      "learning_rate": 2.2590506461817452e-07,
+      "logits/chosen": -0.259944349527359,
+      "logits/rejected": -0.20725861191749573,
+      "logps/chosen": -298.30303955078125,
+      "logps/rejected": -305.5474548339844,
+      "loss": 0.6419,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.24381069839000702,
+      "rewards/margins": 0.11996382474899292,
+      "rewards/rejected": -0.36377447843551636,
+      "step": 200
+    },
+    {
+      "epoch": 0.4091816367265469,
+      "grad_norm": 3.7132773714988927,
+      "learning_rate": 2.213436313605413e-07,
+      "logits/chosen": -0.5560285449028015,
+      "logits/rejected": -0.49163347482681274,
+      "logps/chosen": -387.44171142578125,
+      "logps/rejected": -402.449462890625,
+      "loss": 0.6434,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.3169836699962616,
+      "rewards/margins": 0.07618891447782516,
+      "rewards/rejected": -0.39317259192466736,
+      "step": 205
+    },
+    {
+      "epoch": 0.41916167664670656,
+      "grad_norm": 3.775451248470663,
+      "learning_rate": 2.166952768777391e-07,
+      "logits/chosen": -0.2941240966320038,
+      "logits/rejected": -0.3131045997142792,
+      "logps/chosen": -303.090087890625,
+      "logps/rejected": -298.85699462890625,
+      "loss": 0.6404,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.2724608778953552,
+      "rewards/margins": 0.1073354110121727,
+      "rewards/rejected": -0.3797963261604309,
+      "step": 210
+    },
+    {
+      "epoch": 0.4291417165668663,
+      "grad_norm": 3.7925188623151422,
+      "learning_rate": 2.1196566447368126e-07,
+      "logits/chosen": -0.26538053154945374,
+      "logits/rejected": -0.25145062804222107,
+      "logps/chosen": -334.455078125,
+      "logps/rejected": -356.2786865234375,
+      "loss": 0.6355,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.34816819429397583,
+      "rewards/margins": 0.12635044753551483,
+      "rewards/rejected": -0.4745185971260071,
+      "step": 215
+    },
+    {
+      "epoch": 0.43912175648702595,
+      "grad_norm": 3.8981243362393565,
+      "learning_rate": 2.0716055645254113e-07,
+      "logits/chosen": -0.46777939796447754,
+      "logits/rejected": -0.4300519824028015,
+      "logps/chosen": -325.1937255859375,
+      "logps/rejected": -333.54022216796875,
+      "loss": 0.641,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.4105430245399475,
+      "rewards/margins": 0.10119415819644928,
+      "rewards/rejected": -0.5117372274398804,
+      "step": 220
+    },
+    {
+      "epoch": 0.4491017964071856,
+      "grad_norm": 3.7392987472200354,
+      "learning_rate": 2.0228580709827226e-07,
+      "logits/chosen": -0.5368104577064514,
+      "logits/rejected": -0.45491117238998413,
+      "logps/chosen": -349.7928771972656,
+      "logps/rejected": -371.95050048828125,
+      "loss": 0.6326,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3743346631526947,
+      "rewards/margins": 0.1426324099302292,
+      "rewards/rejected": -0.5169671177864075,
+      "step": 225
+    },
+    {
+      "epoch": 0.4590818363273453,
+      "grad_norm": 3.6974655152807174,
+      "learning_rate": 1.9734735554206537e-07,
+      "logits/chosen": -0.31408676505088806,
+      "logits/rejected": -0.2642524242401123,
+      "logps/chosen": -349.4893798828125,
+      "logps/rejected": -369.08990478515625,
+      "loss": 0.6238,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.47439342737197876,
+      "rewards/margins": 0.15798419713974,
+      "rewards/rejected": -0.632377564907074,
+      "step": 230
+    },
+    {
+      "epoch": 0.469061876247505,
+      "grad_norm": 3.9074441662298662,
+      "learning_rate": 1.9235121852643148e-07,
+      "logits/chosen": -0.4889460504055023,
+      "logits/rejected": -0.48752936720848083,
+      "logps/chosen": -331.08624267578125,
+      "logps/rejected": -348.8202819824219,
+      "loss": 0.6259,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.41649022698402405,
+      "rewards/margins": 0.1930549144744873,
+      "rewards/rejected": -0.609545111656189,
+      "step": 235
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 3.7710978575315757,
+      "learning_rate": 1.8730348307472826e-07,
+      "logits/chosen": -0.4119279384613037,
+      "logits/rejected": -0.444758802652359,
+      "logps/chosen": -348.2624206542969,
+      "logps/rejected": -369.9598083496094,
+      "loss": 0.6249,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.5225319862365723,
+      "rewards/margins": 0.13163016736507416,
+      "rewards/rejected": -0.6541622281074524,
+      "step": 240
+    },
+    {
+      "epoch": 0.48902195608782434,
+      "grad_norm": 4.08348789093204,
+      "learning_rate": 1.822102990750595e-07,
+      "logits/chosen": -0.5410420298576355,
+      "logits/rejected": -0.4581461548805237,
+      "logps/chosen": -300.3963317871094,
+      "logps/rejected": -326.97357177734375,
+      "loss": 0.6205,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.4268406927585602,
+      "rewards/margins": 0.17870576679706573,
+      "rewards/rejected": -0.6055464744567871,
+      "step": 245
+    },
+    {
+      "epoch": 0.499001996007984,
+      "grad_norm": 3.8249633059365977,
+      "learning_rate": 1.7707787178758402e-07,
+      "logits/chosen": -0.5376532673835754,
+      "logits/rejected": -0.5166374444961548,
+      "logps/chosen": -334.3974609375,
+      "logps/rejected": -363.59832763671875,
+      "loss": 0.6097,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.5467029809951782,
+      "rewards/margins": 0.219395712018013,
+      "rewards/rejected": -0.7660986185073853,
+      "step": 250
+    },
+    {
+      "epoch": 0.5089820359281437,
+      "grad_norm": 4.084608415013939,
+      "learning_rate": 1.7191245428436176e-07,
+      "logits/chosen": -0.6120297908782959,
+      "logits/rejected": -0.5665668249130249,
+      "logps/chosen": -388.49237060546875,
+      "logps/rejected": -404.17913818359375,
+      "loss": 0.6066,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.5541552305221558,
+      "rewards/margins": 0.18654166162014008,
+      "rewards/rejected": -0.7406969666481018,
+      "step": 255
+    },
+    {
+      "epoch": 0.5189620758483033,
+      "grad_norm": 4.127013078261958,
+      "learning_rate": 1.667203398309488e-07,
+      "logits/chosen": -0.602649450302124,
+      "logits/rejected": -0.47091540694236755,
+      "logps/chosen": -342.5652770996094,
+      "logps/rejected": -363.1390380859375,
+      "loss": 0.6099,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.5999665260314941,
+      "rewards/margins": 0.22458717226982117,
+      "rewards/rejected": -0.8245537877082825,
+      "step": 260
+    },
+    {
+      "epoch": 0.5289421157684631,
+      "grad_norm": 4.181662944251744,
+      "learning_rate": 1.6150785421902278e-07,
+      "logits/chosen": -0.49136123061180115,
+      "logits/rejected": -0.4355231821537018,
+      "logps/chosen": -355.0814514160156,
+      "logps/rejected": -400.48486328125,
+      "loss": 0.6027,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.6992485523223877,
+      "rewards/margins": 0.2647705674171448,
+      "rewards/rejected": -0.9640190005302429,
+      "step": 265
+    },
+    {
+      "epoch": 0.5389221556886228,
+      "grad_norm": 4.187328944312369,
+      "learning_rate": 1.5628134805937993e-07,
+      "logits/chosen": -0.6901322603225708,
+      "logits/rejected": -0.7155795693397522,
+      "logps/chosen": -338.4058532714844,
+      "logps/rejected": -357.05145263671875,
+      "loss": 0.6044,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.6499531865119934,
+      "rewards/margins": 0.2078942060470581,
+      "rewards/rejected": -0.8578473329544067,
+      "step": 270
+    },
+    {
+      "epoch": 0.5489021956087824,
+      "grad_norm": 4.480820141822546,
+      "learning_rate": 1.5104718904469424e-07,
+      "logits/chosen": -0.49210062623023987,
+      "logits/rejected": -0.4995419979095459,
+      "logps/chosen": -362.78936767578125,
+      "logps/rejected": -376.6024475097656,
+      "loss": 0.6022,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.684400200843811,
+      "rewards/margins": 0.22897310554981232,
+      "rewards/rejected": -0.9133733510971069,
+      "step": 275
+    },
+    {
+      "epoch": 0.5588822355289421,
+      "grad_norm": 4.335560690928003,
+      "learning_rate": 1.458117541914647e-07,
+      "logits/chosen": -0.6205674409866333,
+      "logits/rejected": -0.5415416955947876,
+      "logps/chosen": -363.15484619140625,
+      "logps/rejected": -380.423828125,
+      "loss": 0.601,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.7319628000259399,
+      "rewards/margins": 0.22972945868968964,
+      "rewards/rejected": -0.9616923332214355,
+      "step": 280
+    },
+    {
+      "epoch": 0.5688622754491018,
+      "grad_norm": 4.236266469806635,
+      "learning_rate": 1.4058142207060298e-07,
+      "logits/chosen": -0.5227392315864563,
+      "logits/rejected": -0.44109734892845154,
+      "logps/chosen": -350.81268310546875,
+      "logps/rejected": -387.339111328125,
+      "loss": 0.599,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.7962437272071838,
+      "rewards/margins": 0.2677839994430542,
+      "rewards/rejected": -1.0640277862548828,
+      "step": 285
+    },
+    {
+      "epoch": 0.5788423153692615,
+      "grad_norm": 4.1859368563558546,
+      "learning_rate": 1.353625650361276e-07,
+      "logits/chosen": -0.4567599296569824,
+      "logits/rejected": -0.37081751227378845,
+      "logps/chosen": -292.90582275390625,
+      "logps/rejected": -351.08428955078125,
+      "loss": 0.5976,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.7117597460746765,
+      "rewards/margins": 0.23347418010234833,
+      "rewards/rejected": -0.9452340006828308,
+      "step": 290
+    },
+    {
+      "epoch": 0.5888223552894212,
+      "grad_norm": 4.963202872238042,
+      "learning_rate": 1.301615414614316e-07,
+      "logits/chosen": -0.5814245939254761,
+      "logits/rejected": -0.477074533700943,
+      "logps/chosen": -359.9764404296875,
+      "logps/rejected": -408.649169921875,
+      "loss": 0.5854,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.8252065777778625,
+      "rewards/margins": 0.3438906669616699,
+      "rewards/rejected": -1.1690973043441772,
+      "step": 295
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "grad_norm": 4.522965998928778,
+      "learning_rate": 1.2498468799258466e-07,
+      "logits/chosen": -0.6931585669517517,
+      "logits/rejected": -0.6726911067962646,
+      "logps/chosen": -447.56134033203125,
+      "logps/rejected": -467.0315856933594,
+      "loss": 0.5951,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.0262882709503174,
+      "rewards/margins": 0.3147868514060974,
+      "rewards/rejected": -1.3410751819610596,
+      "step": 300
+    },
+    {
+      "epoch": 0.6087824351297405,
+      "grad_norm": 4.334372580127937,
+      "learning_rate": 1.1983831182810532e-07,
+      "logits/chosen": -0.7098149657249451,
+      "logits/rejected": -0.6338291764259338,
+      "logps/chosen": -370.42584228515625,
+      "logps/rejected": -416.33673095703125,
+      "loss": 0.5741,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.9695831537246704,
+      "rewards/margins": 0.28274181485176086,
+      "rewards/rejected": -1.2523248195648193,
+      "step": 305
+    },
+    {
+      "epoch": 0.6187624750499002,
+      "grad_norm": 4.645155562753339,
+      "learning_rate": 1.147286830346115e-07,
+      "logits/chosen": -0.7523954510688782,
+      "logits/rejected": -0.6753584146499634,
+      "logps/chosen": -415.63629150390625,
+      "logps/rejected": -454.6825256347656,
+      "loss": 0.5819,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.1591014862060547,
+      "rewards/margins": 0.3371506929397583,
+      "rewards/rejected": -1.496252179145813,
+      "step": 310
+    },
+    {
+      "epoch": 0.6287425149700598,
+      "grad_norm": 4.669200509826971,
+      "learning_rate": 1.0966202690771015e-07,
+      "logits/chosen": -0.668272852897644,
+      "logits/rejected": -0.5711073875427246,
+      "logps/chosen": -412.66424560546875,
+      "logps/rejected": -463.01971435546875,
+      "loss": 0.5802,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.1411970853805542,
+      "rewards/margins": 0.34684187173843384,
+      "rewards/rejected": -1.4880390167236328,
+      "step": 315
+    },
+    {
+      "epoch": 0.6387225548902196,
+      "grad_norm": 4.60028355094582,
+      "learning_rate": 1.0464451638743333e-07,
+      "logits/chosen": -0.720443606376648,
+      "logits/rejected": -0.633614182472229,
+      "logps/chosen": -381.11358642578125,
+      "logps/rejected": -422.4686584472656,
+      "loss": 0.5803,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.1198880672454834,
+      "rewards/margins": 0.3332558274269104,
+      "rewards/rejected": -1.4531439542770386,
+      "step": 320
+    },
+    {
+      "epoch": 0.6487025948103793,
+      "grad_norm": 4.7117497209054315,
+      "learning_rate": 9.968226453746175e-08,
+      "logits/chosen": -0.6728391647338867,
+      "logits/rejected": -0.6361491084098816,
+      "logps/chosen": -388.78375244140625,
+      "logps/rejected": -422.4482421875,
+      "loss": 0.5744,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.175586462020874,
+      "rewards/margins": 0.2871216833591461,
+      "rewards/rejected": -1.4627082347869873,
+      "step": 325
+    },
+    {
+      "epoch": 0.6586826347305389,
+      "grad_norm": 4.348227355176717,
+      "learning_rate": 9.478131709729831e-08,
+      "logits/chosen": -0.7032121419906616,
+      "logits/rejected": -0.6237956285476685,
+      "logps/chosen": -377.9942321777344,
+      "logps/rejected": -404.4933166503906,
+      "loss": 0.5795,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.1823105812072754,
+      "rewards/margins": 0.23070795834064484,
+      "rewards/rejected": -1.4130184650421143,
+      "step": 330
+    },
+    {
+      "epoch": 0.6686626746506986,
+      "grad_norm": 4.567093235085812,
+      "learning_rate": 8.994764511646577e-08,
+      "logits/chosen": -0.696010410785675,
+      "logits/rejected": -0.6754131317138672,
+      "logps/chosen": -400.3501892089844,
+      "logps/rejected": -406.4004821777344,
+      "loss": 0.5887,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.2299916744232178,
+      "rewards/margins": 0.2420133799314499,
+      "rewards/rejected": -1.4720051288604736,
+      "step": 335
+    },
+    {
+      "epoch": 0.6786427145708582,
+      "grad_norm": 5.005664260886447,
+      "learning_rate": 8.518713767970262e-08,
+      "logits/chosen": -0.7765355706214905,
+      "logits/rejected": -0.7291234135627747,
+      "logps/chosen": -440.3502502441406,
+      "logps/rejected": -463.7428283691406,
+      "loss": 0.5654,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -1.2532676458358765,
+      "rewards/margins": 0.2593846023082733,
+      "rewards/rejected": -1.5126522779464722,
+      "step": 340
+    },
+    {
+      "epoch": 0.688622754491018,
+      "grad_norm": 5.103097065108184,
+      "learning_rate": 8.050559473202076e-08,
+      "logits/chosen": -0.5867692232131958,
+      "logits/rejected": -0.5882567167282104,
+      "logps/chosen": -486.0328063964844,
+      "logps/rejected": -492.4873046875,
+      "loss": 0.5909,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.4522783756256104,
+      "rewards/margins": 0.20934677124023438,
+      "rewards/rejected": -1.6616249084472656,
+      "step": 345
+    },
+    {
+      "epoch": 0.6986027944111777,
+      "grad_norm": 4.912813992114836,
+      "learning_rate": 7.590872001236538e-08,
+      "logits/chosen": -0.7335643768310547,
+      "logits/rejected": -0.6834427714347839,
+      "logps/chosen": -402.9820861816406,
+      "logps/rejected": -425.92156982421875,
+      "loss": 0.5716,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.3429086208343506,
+      "rewards/margins": 0.27442997694015503,
+      "rewards/rejected": -1.6173385381698608,
+      "step": 350
+    },
+    {
+      "epoch": 0.7085828343313373,
+      "grad_norm": 5.102923641063365,
+      "learning_rate": 7.140211410448815e-08,
+      "logits/chosen": -0.721831202507019,
+      "logits/rejected": -0.61592036485672,
+      "logps/chosen": -370.572265625,
+      "logps/rejected": -414.7581481933594,
+      "loss": 0.5721,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.2241812944412231,
+      "rewards/margins": 0.3305676281452179,
+      "rewards/rejected": -1.554748773574829,
+      "step": 355
+    },
+    {
+      "epoch": 0.718562874251497,
+      "grad_norm": 5.015860169175414,
+      "learning_rate": 6.69912676134984e-08,
+      "logits/chosen": -0.7092261910438538,
+      "logits/rejected": -0.6547318696975708,
+      "logps/chosen": -440.85711669921875,
+      "logps/rejected": -457.0215759277344,
+      "loss": 0.5707,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.397318720817566,
+      "rewards/margins": 0.24624857306480408,
+      "rewards/rejected": -1.6435673236846924,
+      "step": 360
+    },
+    {
+      "epoch": 0.7285429141716567,
+      "grad_norm": 4.774816172341646,
+      "learning_rate": 6.26815544764066e-08,
+      "logits/chosen": -0.8451409339904785,
+      "logits/rejected": -0.7582667469978333,
+      "logps/chosen": -390.70233154296875,
+      "logps/rejected": -433.895263671875,
+      "loss": 0.5661,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -1.2642087936401367,
+      "rewards/margins": 0.3393135070800781,
+      "rewards/rejected": -1.6035223007202148,
+      "step": 365
+    },
+    {
+      "epoch": 0.7385229540918163,
+      "grad_norm": 4.965964761489328,
+      "learning_rate": 5.847822541480985e-08,
+      "logits/chosen": -0.6884382963180542,
+      "logits/rejected": -0.6832146644592285,
+      "logps/chosen": -505.1039123535156,
+      "logps/rejected": -543.939697265625,
+      "loss": 0.5737,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.5997720956802368,
+      "rewards/margins": 0.34007787704467773,
+      "rewards/rejected": -1.939850091934204,
+      "step": 370
+    },
+    {
+      "epoch": 0.7485029940119761,
+      "grad_norm": 5.257593216933955,
+      "learning_rate": 5.4386401537696535e-08,
+      "logits/chosen": -0.654364287853241,
+      "logits/rejected": -0.618787407875061,
+      "logps/chosen": -424.26031494140625,
+      "logps/rejected": -464.0692443847656,
+      "loss": 0.5656,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.4769487380981445,
+      "rewards/margins": 0.3530046045780182,
+      "rewards/rejected": -1.8299534320831299,
+      "step": 375
+    },
+    {
+      "epoch": 0.7584830339321357,
+      "grad_norm": 5.018164548165559,
+      "learning_rate": 5.0411068102163756e-08,
+      "logits/chosen": -0.7129963636398315,
+      "logits/rejected": -0.6934917569160461,
+      "logps/chosen": -338.116943359375,
+      "logps/rejected": -385.53192138671875,
+      "loss": 0.5812,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.1324220895767212,
+      "rewards/margins": 0.3832218050956726,
+      "rewards/rejected": -1.515643835067749,
+      "step": 380
+    },
+    {
+      "epoch": 0.7684630738522954,
+      "grad_norm": 4.842940867729204,
+      "learning_rate": 4.6557068439649526e-08,
+      "logits/chosen": -0.6886343955993652,
+      "logits/rejected": -0.6565831303596497,
+      "logps/chosen": -475.0184631347656,
+      "logps/rejected": -506.1280212402344,
+      "loss": 0.5773,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.5225403308868408,
+      "rewards/margins": 0.3815816044807434,
+      "rewards/rejected": -1.90412175655365,
+      "step": 385
+    },
+    {
+      "epoch": 0.7784431137724551,
+      "grad_norm": 4.981718868828084,
+      "learning_rate": 4.2829098055079526e-08,
+      "logits/chosen": -0.8457885980606079,
+      "logits/rejected": -0.8267861604690552,
+      "logps/chosen": -402.27032470703125,
+      "logps/rejected": -441.7845153808594,
+      "loss": 0.5706,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.30136239528656,
+      "rewards/margins": 0.37314456701278687,
+      "rewards/rejected": -1.6745071411132812,
+      "step": 390
+    },
+    {
+      "epoch": 0.7884231536926147,
+      "grad_norm": 4.76229443747579,
+      "learning_rate": 3.923169890611741e-08,
+      "logits/chosen": -0.7744909524917603,
+      "logits/rejected": -0.7276748418807983,
+      "logps/chosen": -407.0968322753906,
+      "logps/rejected": -451.7494201660156,
+      "loss": 0.5605,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.4497464895248413,
+      "rewards/margins": 0.40129631757736206,
+      "rewards/rejected": -1.8510427474975586,
+      "step": 395
+    },
+    {
+      "epoch": 0.7984031936127745,
+      "grad_norm": 4.572364850180581,
+      "learning_rate": 3.576925386948951e-08,
+      "logits/chosen": -0.9308286905288696,
+      "logits/rejected": -0.8524009585380554,
+      "logps/chosen": -406.74578857421875,
+      "logps/rejected": -458.7312927246094,
+      "loss": 0.5563,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.3046013116836548,
+      "rewards/margins": 0.4329892098903656,
+      "rewards/rejected": -1.7375905513763428,
+      "step": 400
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 501,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 101,
+  "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-404/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2062bff810c3be97f9dc215093b5dad2b48711e0862036888bf785c22f9a23
+size 7544

checkpoint-501/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
+}

checkpoint-501/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/GLOBALFS/gznwp_3/qxj/lgzhong/LLaMA-Factory/saves/Qwen2.5-7B-Instruct-SFT-v1.5",
+  "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_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

checkpoint-501/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": "4.43.4"
+}

checkpoint-501/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a225753e92dd848195937eca7428c9f9ceae13cc2c20f0f2c5784fe411567050
+size 4877660776

checkpoint-501/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f834bc79ecfcdb1030896071513fe7f21efd2ab60c7f3b3f5f5fbbff9d6d2151
+size 4932751008

checkpoint-501/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfac9b108ed2fb3816971f8bb68c3a3efba0a9667d172fdfaff1773c447a6a92
+size 4330865200

checkpoint-501/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65069d22b1bc30af9cdb9d286b713ba0ba4168b2ec1279ab1f3cbd8f288ad8fa
+size 1089994880

checkpoint-501/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"
+  }
+}

checkpoint-501/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
+  }
+}

checkpoint-501/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",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-501/trainer_state.json

@@ -0,0 +1,1548 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 501,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001996007984031936,
+      "grad_norm": 3.4413226850733536,
+      "learning_rate": 5.88235294117647e-09,
+      "logits/chosen": -0.2126132994890213,
+      "logits/rejected": -0.06049485132098198,
+      "logps/chosen": -312.6929931640625,
+      "logps/rejected": -303.399658203125,
+      "loss": 0.6931,
+      "rewards/accuracies": 0.0,
+      "rewards/chosen": 0.0,
+      "rewards/margins": 0.0,
+      "rewards/rejected": 0.0,
+      "step": 1
+    },
+    {
+      "epoch": 0.00998003992015968,
+      "grad_norm": 3.5626484310109503,
+      "learning_rate": 2.941176470588235e-08,
+      "logits/chosen": -0.15043149888515472,
+      "logits/rejected": -0.05884423851966858,
+      "logps/chosen": -271.6809387207031,
+      "logps/rejected": -308.14019775390625,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.34375,
+      "rewards/chosen": 0.00032658452983014286,
+      "rewards/margins": -0.00044720349251292646,
+      "rewards/rejected": 0.0007737880805507302,
+      "step": 5
+    },
+    {
+      "epoch": 0.01996007984031936,
+      "grad_norm": 3.444766226961807,
+      "learning_rate": 5.88235294117647e-08,
+      "logits/chosen": -0.04885115846991539,
+      "logits/rejected": 0.02876092866063118,
+      "logps/chosen": -314.44207763671875,
+      "logps/rejected": -324.5089111328125,
+      "loss": 0.6935,
+      "rewards/accuracies": 0.4124999940395355,
+      "rewards/chosen": -0.0015638660406693816,
+      "rewards/margins": -0.0018882350996136665,
+      "rewards/rejected": 0.0003243688843213022,
+      "step": 10
+    },
+    {
+      "epoch": 0.029940119760479042,
+      "grad_norm": 3.351776759283806,
+      "learning_rate": 8.823529411764706e-08,
+      "logits/chosen": -0.14645501971244812,
+      "logits/rejected": -0.10253484547138214,
+      "logps/chosen": -325.3197021484375,
+      "logps/rejected": -335.1691589355469,
+      "loss": 0.6937,
+      "rewards/accuracies": 0.3375000059604645,
+      "rewards/chosen": -0.0009325200808234513,
+      "rewards/margins": -0.0027469159103929996,
+      "rewards/rejected": 0.0018143958877772093,
+      "step": 15
+    },
+    {
+      "epoch": 0.03992015968063872,
+      "grad_norm": 3.2486760323756765,
+      "learning_rate": 1.176470588235294e-07,
+      "logits/chosen": -0.17513605952262878,
+      "logits/rejected": -0.14125120639801025,
+      "logps/chosen": -236.529052734375,
+      "logps/rejected": -224.99609375,
+      "loss": 0.6932,
+      "rewards/accuracies": 0.44999998807907104,
+      "rewards/chosen": -0.00048039742978289723,
+      "rewards/margins": -0.0017443184042349458,
+      "rewards/rejected": 0.0012639210326597095,
+      "step": 20
+    },
+    {
+      "epoch": 0.0499001996007984,
+      "grad_norm": 3.682895506825886,
+      "learning_rate": 1.4705882352941175e-07,
+      "logits/chosen": 0.02582230605185032,
+      "logits/rejected": -0.026322145015001297,
+      "logps/chosen": -276.4084777832031,
+      "logps/rejected": -271.5510559082031,
+      "loss": 0.6928,
+      "rewards/accuracies": 0.5375000238418579,
+      "rewards/chosen": -0.00010870690312003717,
+      "rewards/margins": -2.2810349037172273e-05,
+      "rewards/rejected": -8.589646313339472e-05,
+      "step": 25
+    },
+    {
+      "epoch": 0.059880239520958084,
+      "grad_norm": 3.521568498969969,
+      "learning_rate": 1.764705882352941e-07,
+      "logits/chosen": -0.029633093625307083,
+      "logits/rejected": 0.017462745308876038,
+      "logps/chosen": -241.04345703125,
+      "logps/rejected": -254.0708465576172,
+      "loss": 0.6929,
+      "rewards/accuracies": 0.5,
+      "rewards/chosen": 0.001156697398982942,
+      "rewards/margins": 0.0012088593794032931,
+      "rewards/rejected": -5.2162260544719175e-05,
+      "step": 30
+    },
+    {
+      "epoch": 0.06986027944111776,
+      "grad_norm": 3.4756100770970852,
+      "learning_rate": 2.0588235294117647e-07,
+      "logits/chosen": -0.09809896349906921,
+      "logits/rejected": -0.12783308327198029,
+      "logps/chosen": -316.04541015625,
+      "logps/rejected": -303.2275085449219,
+      "loss": 0.6926,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": 0.0019062187056988478,
+      "rewards/margins": 0.0034712664783000946,
+      "rewards/rejected": -0.0015650471905246377,
+      "step": 35
+    },
+    {
+      "epoch": 0.07984031936127745,
+      "grad_norm": 3.5251485554920383,
+      "learning_rate": 2.352941176470588e-07,
+      "logits/chosen": -0.10866469144821167,
+      "logits/rejected": -0.08842261880636215,
+      "logps/chosen": -300.94866943359375,
+      "logps/rejected": -301.57635498046875,
+      "loss": 0.6927,
+      "rewards/accuracies": 0.48750001192092896,
+      "rewards/chosen": 0.0005061564734205604,
+      "rewards/margins": 0.0017319575417786837,
+      "rewards/rejected": -0.0012258009519428015,
+      "step": 40
+    },
+    {
+      "epoch": 0.08982035928143713,
+      "grad_norm": 3.562421126179782,
+      "learning_rate": 2.6470588235294114e-07,
+      "logits/chosen": -0.04412439838051796,
+      "logits/rejected": 0.046757772564888,
+      "logps/chosen": -276.1053771972656,
+      "logps/rejected": -299.3190612792969,
+      "loss": 0.692,
+      "rewards/accuracies": 0.574999988079071,
+      "rewards/chosen": -0.002857887651771307,
+      "rewards/margins": 0.0004688422195613384,
+      "rewards/rejected": -0.003326730104163289,
+      "step": 45
+    },
+    {
+      "epoch": 0.0998003992015968,
+      "grad_norm": 3.174201376940309,
+      "learning_rate": 2.941176470588235e-07,
+      "logits/chosen": -0.08824320137500763,
+      "logits/rejected": -0.043245576322078705,
+      "logps/chosen": -271.13604736328125,
+      "logps/rejected": -272.74102783203125,
+      "loss": 0.6914,
+      "rewards/accuracies": 0.6000000238418579,
+      "rewards/chosen": -0.0016361953457817435,
+      "rewards/margins": 0.005965009797364473,
+      "rewards/rejected": -0.007601206190884113,
+      "step": 50
+    },
+    {
+      "epoch": 0.10978043912175649,
+      "grad_norm": 3.3426951285606368,
+      "learning_rate": 2.999415172560531e-07,
+      "logits/chosen": 0.032454706728458405,
+      "logits/rejected": 0.15314094722270966,
+      "logps/chosen": -301.4625244140625,
+      "logps/rejected": -304.8877258300781,
+      "loss": 0.691,
+      "rewards/accuracies": 0.612500011920929,
+      "rewards/chosen": -0.007659287191927433,
+      "rewards/margins": 0.0023522169794887304,
+      "rewards/rejected": -0.010011503472924232,
+      "step": 55
+    },
+    {
+      "epoch": 0.11976047904191617,
+      "grad_norm": 3.2266501701625283,
+      "learning_rate": 2.997040092642407e-07,
+      "logits/chosen": -0.13825412094593048,
+      "logits/rejected": -0.06802596896886826,
+      "logps/chosen": -273.85198974609375,
+      "logps/rejected": -256.1399841308594,
+      "loss": 0.6905,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.0074735768139362335,
+      "rewards/margins": 0.005476811900734901,
+      "rewards/rejected": -0.012950388714671135,
+      "step": 60
+    },
+    {
+      "epoch": 0.12974051896207583,
+      "grad_norm": 3.129826931598691,
+      "learning_rate": 2.9928410999727467e-07,
+      "logits/chosen": -0.03806266561150551,
+      "logits/rejected": -0.06114925071597099,
+      "logps/chosen": -273.815673828125,
+      "logps/rejected": -257.2196350097656,
+      "loss": 0.6897,
+      "rewards/accuracies": 0.6625000238418579,
+      "rewards/chosen": -0.010186719708144665,
+      "rewards/margins": 0.00584446731954813,
+      "rewards/rejected": -0.016031187027692795,
+      "step": 65
+    },
+    {
+      "epoch": 0.13972055888223553,
+      "grad_norm": 3.2696148017727764,
+      "learning_rate": 2.9868233103773125e-07,
+      "logits/chosen": -0.19126296043395996,
+      "logits/rejected": -0.1384088099002838,
+      "logps/chosen": -289.3074645996094,
+      "logps/rejected": -304.941650390625,
+      "loss": 0.6901,
+      "rewards/accuracies": 0.6499999761581421,
+      "rewards/chosen": -0.012994937598705292,
+      "rewards/margins": 0.006138815078884363,
+      "rewards/rejected": -0.019133752211928368,
+      "step": 70
+    },
+    {
+      "epoch": 0.1497005988023952,
+      "grad_norm": 3.158441752144902,
+      "learning_rate": 2.978994055605757e-07,
+      "logits/chosen": -0.3353852927684784,
+      "logits/rejected": -0.20957405865192413,
+      "logps/chosen": -282.4247131347656,
+      "logps/rejected": -297.1376647949219,
+      "loss": 0.6887,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.013628537766635418,
+      "rewards/margins": 0.012240052223205566,
+      "rewards/rejected": -0.02586858905851841,
+      "step": 75
+    },
+    {
+      "epoch": 0.1596806387225549,
+      "grad_norm": 3.2922551208958932,
+      "learning_rate": 2.9693628743990157e-07,
+      "logits/chosen": -0.2210439145565033,
+      "logits/rejected": -0.13906380534172058,
+      "logps/chosen": -286.2383728027344,
+      "logps/rejected": -284.0565490722656,
+      "loss": 0.6885,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.012788718566298485,
+      "rewards/margins": 0.01518750749528408,
+      "rewards/rejected": -0.027976226061582565,
+      "step": 80
+    },
+    {
+      "epoch": 0.16966067864271456,
+      "grad_norm": 3.143746580193799,
+      "learning_rate": 2.9579415008678196e-07,
+      "logits/chosen": 0.061027251183986664,
+      "logits/rejected": 0.020937766879796982,
+      "logps/chosen": -261.85797119140625,
+      "logps/rejected": -245.4117889404297,
+      "loss": 0.6879,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.020817553624510765,
+      "rewards/margins": 0.01146668754518032,
+      "rewards/rejected": -0.032284241169691086,
+      "step": 85
+    },
+    {
+      "epoch": 0.17964071856287425,
+      "grad_norm": 3.1363791165769634,
+      "learning_rate": 2.944743850196487e-07,
+      "logits/chosen": -0.18295350670814514,
+      "logits/rejected": -0.138901025056839,
+      "logps/chosen": -302.30377197265625,
+      "logps/rejected": -297.4572448730469,
+      "loss": 0.6867,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.022789286449551582,
+      "rewards/margins": 0.014456982724368572,
+      "rewards/rejected": -0.03724626824259758,
+      "step": 90
+    },
+    {
+      "epoch": 0.18962075848303392,
+      "grad_norm": 3.375624228841244,
+      "learning_rate": 2.92978600168942e-07,
+      "logits/chosen": -0.21953599154949188,
+      "logits/rejected": -0.19249823689460754,
+      "logps/chosen": -282.0645446777344,
+      "logps/rejected": -293.2350158691406,
+      "loss": 0.6865,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -0.028345201164484024,
+      "rewards/margins": 0.015181821770966053,
+      "rewards/rejected": -0.0435270220041275,
+      "step": 95
+    },
+    {
+      "epoch": 0.1996007984031936,
+      "grad_norm": 3.4004680540887673,
+      "learning_rate": 2.913086179180945e-07,
+      "logits/chosen": -0.26934295892715454,
+      "logits/rejected": -0.24918439984321594,
+      "logps/chosen": -267.2822570800781,
+      "logps/rejected": -273.8163757324219,
+      "loss": 0.6847,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.02366602048277855,
+      "rewards/margins": 0.018390221521258354,
+      "rewards/rejected": -0.042056240141391754,
+      "step": 100
+    },
+    {
+      "epoch": 0.20958083832335328,
+      "grad_norm": 3.348944145808141,
+      "learning_rate": 2.894664728832377e-07,
+      "logits/chosen": -0.12691783905029297,
+      "logits/rejected": -0.10880570113658905,
+      "logps/chosen": -306.7061462402344,
+      "logps/rejected": -296.7961120605469,
+      "loss": 0.684,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.02831300161778927,
+      "rewards/margins": 0.024948222562670708,
+      "rewards/rejected": -0.053261227905750275,
+      "step": 105
+    },
+    {
+      "epoch": 0.21956087824351297,
+      "grad_norm": 3.3068624575557677,
+      "learning_rate": 2.8745440943433595e-07,
+      "logits/chosen": -0.39724451303482056,
+      "logits/rejected": -0.3233721852302551,
+      "logps/chosen": -299.71356201171875,
+      "logps/rejected": -307.81011962890625,
+      "loss": 0.6826,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -0.037553686648607254,
+      "rewards/margins": 0.01620485447347164,
+      "rewards/rejected": -0.053758542984724045,
+      "step": 110
+    },
+    {
+      "epoch": 0.22954091816367264,
+      "grad_norm": 3.5399975333931057,
+      "learning_rate": 2.8527487896076705e-07,
+      "logits/chosen": -0.2971861958503723,
+      "logits/rejected": -0.26923665404319763,
+      "logps/chosen": -323.73760986328125,
+      "logps/rejected": -317.88238525390625,
+      "loss": 0.6812,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.03361167758703232,
+      "rewards/margins": 0.025083836168050766,
+      "rewards/rejected": -0.058695513755083084,
+      "step": 115
+    },
+    {
+      "epoch": 0.23952095808383234,
+      "grad_norm": 3.387251098081717,
+      "learning_rate": 2.829305368846822e-07,
+      "logits/chosen": -0.08930722624063492,
+      "logits/rejected": -0.093043752014637,
+      "logps/chosen": -298.3551330566406,
+      "logps/rejected": -301.565185546875,
+      "loss": 0.6807,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.04334830120205879,
+      "rewards/margins": 0.02416048012673855,
+      "rewards/rejected": -0.06750877946615219,
+      "step": 120
+    },
+    {
+      "epoch": 0.249500998003992,
+      "grad_norm": 3.458206539528906,
+      "learning_rate": 2.8042423942578286e-07,
+      "logits/chosen": -0.06799415498971939,
+      "logits/rejected": 0.05015769600868225,
+      "logps/chosen": -252.72793579101562,
+      "logps/rejected": -279.40631103515625,
+      "loss": 0.6788,
+      "rewards/accuracies": 0.887499988079071,
+      "rewards/chosen": -0.0386417880654335,
+      "rewards/margins": 0.03730592131614685,
+      "rewards/rejected": -0.07594770938158035,
+      "step": 125
+    },
+    {
+      "epoch": 0.25948103792415167,
+      "grad_norm": 3.4555138461844757,
+      "learning_rate": 2.7775904012145714e-07,
+      "logits/chosen": -0.24486279487609863,
+      "logits/rejected": -0.1943987011909485,
+      "logps/chosen": -326.3341369628906,
+      "logps/rejected": -326.3017272949219,
+      "loss": 0.6792,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.04846924915909767,
+      "rewards/margins": 0.03331124037504196,
+      "rewards/rejected": -0.08178049325942993,
+      "step": 130
+    },
+    {
+      "epoch": 0.2694610778443114,
+      "grad_norm": 3.4103149118409104,
+      "learning_rate": 2.749381861065149e-07,
+      "logits/chosen": -0.11615544557571411,
+      "logits/rejected": -0.02477203868329525,
+      "logps/chosen": -281.5689697265625,
+      "logps/rejected": -289.6168518066406,
+      "loss": 0.6756,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.04677049443125725,
+      "rewards/margins": 0.03843165561556816,
+      "rewards/rejected": -0.085202157497406,
+      "step": 135
+    },
+    {
+      "epoch": 0.27944111776447106,
+      "grad_norm": 3.3294732309430946,
+      "learning_rate": 2.719651141570541e-07,
+      "logits/chosen": -0.07356293499469757,
+      "logits/rejected": 0.01894739270210266,
+      "logps/chosen": -295.6517333984375,
+      "logps/rejected": -294.22064208984375,
+      "loss": 0.6733,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.04726024717092514,
+      "rewards/margins": 0.05050128698348999,
+      "rewards/rejected": -0.09776153415441513,
+      "step": 140
+    },
+    {
+      "epoch": 0.2894211576846307,
+      "grad_norm": 3.335787112423438,
+      "learning_rate": 2.6884344650327857e-07,
+      "logits/chosen": -0.3144836127758026,
+      "logits/rejected": -0.2471332997083664,
+      "logps/chosen": -275.6163635253906,
+      "logps/rejected": -283.7267150878906,
+      "loss": 0.6741,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.06026310846209526,
+      "rewards/margins": 0.03206663206219673,
+      "rewards/rejected": -0.0923297330737114,
+      "step": 145
+    },
+    {
+      "epoch": 0.2994011976047904,
+      "grad_norm": 3.351780879830391,
+      "learning_rate": 2.6557698641636836e-07,
+      "logits/chosen": -0.09479612112045288,
+      "logits/rejected": -0.05155174061655998,
+      "logps/chosen": -273.46527099609375,
+      "logps/rejected": -285.8160095214844,
+      "loss": 0.6719,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.057442475110292435,
+      "rewards/margins": 0.04023780673742294,
+      "rewards/rejected": -0.09768027812242508,
+      "step": 150
+    },
+    {
+      "epoch": 0.3093812375249501,
+      "grad_norm": 3.3953812787691744,
+      "learning_rate": 2.6216971357477977e-07,
+      "logits/chosen": -0.20542898774147034,
+      "logits/rejected": -0.16760793328285217,
+      "logps/chosen": -319.43438720703125,
+      "logps/rejected": -337.89678955078125,
+      "loss": 0.6677,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -0.0877736285328865,
+      "rewards/margins": 0.05791449546813965,
+      "rewards/rejected": -0.14568811655044556,
+      "step": 155
+    },
+    {
+      "epoch": 0.3193612774451098,
+      "grad_norm": 3.7295101426966957,
+      "learning_rate": 2.5862577921562015e-07,
+      "logits/chosen": -0.26064497232437134,
+      "logits/rejected": -0.1645033359527588,
+      "logps/chosen": -292.02484130859375,
+      "logps/rejected": -300.4161376953125,
+      "loss": 0.665,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.08468987792730331,
+      "rewards/margins": 0.062365107238292694,
+      "rewards/rejected": -0.1470550000667572,
+      "step": 160
+    },
+    {
+      "epoch": 0.32934131736526945,
+      "grad_norm": 3.5278102635310775,
+      "learning_rate": 2.549495010770048e-07,
+      "logits/chosen": -0.2758394777774811,
+      "logits/rejected": -0.20927894115447998,
+      "logps/chosen": -288.8243713378906,
+      "logps/rejected": -291.8514404296875,
+      "loss": 0.6655,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.10788210481405258,
+      "rewards/margins": 0.06151789426803589,
+      "rewards/rejected": -0.16940000653266907,
+      "step": 165
+    },
+    {
+      "epoch": 0.3393213572854291,
+      "grad_norm": 3.512512373193113,
+      "learning_rate": 2.511453581375585e-07,
+      "logits/chosen": -0.39803841710090637,
+      "logits/rejected": -0.3213597238063812,
+      "logps/chosen": -258.41326904296875,
+      "logps/rejected": -263.5000915527344,
+      "loss": 0.6625,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.10974812507629395,
+      "rewards/margins": 0.04202640801668167,
+      "rewards/rejected": -0.15177452564239502,
+      "step": 170
+    },
+    {
+      "epoch": 0.34930139720558884,
+      "grad_norm": 3.7824536020137383,
+      "learning_rate": 2.4721798515946963e-07,
+      "logits/chosen": -0.2360338717699051,
+      "logits/rejected": -0.17899933457374573,
+      "logps/chosen": -274.8690185546875,
+      "logps/rejected": -291.98419189453125,
+      "loss": 0.6587,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.1216902956366539,
+      "rewards/margins": 0.0732160434126854,
+      "rewards/rejected": -0.1949063539505005,
+      "step": 175
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "grad_norm": 3.6570477679381033,
+      "learning_rate": 2.4317216704174655e-07,
+      "logits/chosen": -0.2678098976612091,
+      "logits/rejected": -0.22654588520526886,
+      "logps/chosen": -285.76885986328125,
+      "logps/rejected": -300.3975524902344,
+      "loss": 0.6575,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.13574646413326263,
+      "rewards/margins": 0.06750482320785522,
+      "rewards/rejected": -0.20325128734111786,
+      "step": 180
+    },
+    {
+      "epoch": 0.36926147704590817,
+      "grad_norm": 3.705774667801494,
+      "learning_rate": 2.3901283299055524e-07,
+      "logits/chosen": -0.4732998013496399,
+      "logits/rejected": -0.39881661534309387,
+      "logps/chosen": -321.14984130859375,
+      "logps/rejected": -326.15032958984375,
+      "loss": 0.6514,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.17002463340759277,
+      "rewards/margins": 0.08681143075227737,
+      "rewards/rejected": -0.25683605670928955,
+      "step": 185
+    },
+    {
+      "epoch": 0.37924151696606784,
+      "grad_norm": 3.4125215861302176,
+      "learning_rate": 2.3474505051374067e-07,
+      "logits/chosen": -0.34785977005958557,
+      "logits/rejected": -0.24581901729106903,
+      "logps/chosen": -323.81732177734375,
+      "logps/rejected": -328.8360900878906,
+      "loss": 0.6496,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -0.20683076977729797,
+      "rewards/margins": 0.07259462773799896,
+      "rewards/rejected": -0.2794254422187805,
+      "step": 190
+    },
+    {
+      "epoch": 0.38922155688622756,
+      "grad_norm": 3.6035947439545715,
+      "learning_rate": 2.3037401924684947e-07,
+      "logits/chosen": -0.2815292775630951,
+      "logits/rejected": -0.2620851397514343,
+      "logps/chosen": -319.5675048828125,
+      "logps/rejected": -332.9228210449219,
+      "loss": 0.6501,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.2412305772304535,
+      "rewards/margins": 0.09057402610778809,
+      "rewards/rejected": -0.3318046033382416,
+      "step": 195
+    },
+    {
+      "epoch": 0.3992015968063872,
+      "grad_norm": 3.6822468215438624,
+      "learning_rate": 2.2590506461817452e-07,
+      "logits/chosen": -0.259944349527359,
+      "logits/rejected": -0.20725861191749573,
+      "logps/chosen": -298.30303955078125,
+      "logps/rejected": -305.5474548339844,
+      "loss": 0.6419,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.24381069839000702,
+      "rewards/margins": 0.11996382474899292,
+      "rewards/rejected": -0.36377447843551636,
+      "step": 200
+    },
+    {
+      "epoch": 0.4091816367265469,
+      "grad_norm": 3.7132773714988927,
+      "learning_rate": 2.213436313605413e-07,
+      "logits/chosen": -0.5560285449028015,
+      "logits/rejected": -0.49163347482681274,
+      "logps/chosen": -387.44171142578125,
+      "logps/rejected": -402.449462890625,
+      "loss": 0.6434,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.3169836699962616,
+      "rewards/margins": 0.07618891447782516,
+      "rewards/rejected": -0.39317259192466736,
+      "step": 205
+    },
+    {
+      "epoch": 0.41916167664670656,
+      "grad_norm": 3.775451248470663,
+      "learning_rate": 2.166952768777391e-07,
+      "logits/chosen": -0.2941240966320038,
+      "logits/rejected": -0.3131045997142792,
+      "logps/chosen": -303.090087890625,
+      "logps/rejected": -298.85699462890625,
+      "loss": 0.6404,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.2724608778953552,
+      "rewards/margins": 0.1073354110121727,
+      "rewards/rejected": -0.3797963261604309,
+      "step": 210
+    },
+    {
+      "epoch": 0.4291417165668663,
+      "grad_norm": 3.7925188623151422,
+      "learning_rate": 2.1196566447368126e-07,
+      "logits/chosen": -0.26538053154945374,
+      "logits/rejected": -0.25145062804222107,
+      "logps/chosen": -334.455078125,
+      "logps/rejected": -356.2786865234375,
+      "loss": 0.6355,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.34816819429397583,
+      "rewards/margins": 0.12635044753551483,
+      "rewards/rejected": -0.4745185971260071,
+      "step": 215
+    },
+    {
+      "epoch": 0.43912175648702595,
+      "grad_norm": 3.8981243362393565,
+      "learning_rate": 2.0716055645254113e-07,
+      "logits/chosen": -0.46777939796447754,
+      "logits/rejected": -0.4300519824028015,
+      "logps/chosen": -325.1937255859375,
+      "logps/rejected": -333.54022216796875,
+      "loss": 0.641,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -0.4105430245399475,
+      "rewards/margins": 0.10119415819644928,
+      "rewards/rejected": -0.5117372274398804,
+      "step": 220
+    },
+    {
+      "epoch": 0.4491017964071856,
+      "grad_norm": 3.7392987472200354,
+      "learning_rate": 2.0228580709827226e-07,
+      "logits/chosen": -0.5368104577064514,
+      "logits/rejected": -0.45491117238998413,
+      "logps/chosen": -349.7928771972656,
+      "logps/rejected": -371.95050048828125,
+      "loss": 0.6326,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.3743346631526947,
+      "rewards/margins": 0.1426324099302292,
+      "rewards/rejected": -0.5169671177864075,
+      "step": 225
+    },
+    {
+      "epoch": 0.4590818363273453,
+      "grad_norm": 3.6974655152807174,
+      "learning_rate": 1.9734735554206537e-07,
+      "logits/chosen": -0.31408676505088806,
+      "logits/rejected": -0.2642524242401123,
+      "logps/chosen": -349.4893798828125,
+      "logps/rejected": -369.08990478515625,
+      "loss": 0.6238,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -0.47439342737197876,
+      "rewards/margins": 0.15798419713974,
+      "rewards/rejected": -0.632377564907074,
+      "step": 230
+    },
+    {
+      "epoch": 0.469061876247505,
+      "grad_norm": 3.9074441662298662,
+      "learning_rate": 1.9235121852643148e-07,
+      "logits/chosen": -0.4889460504055023,
+      "logits/rejected": -0.48752936720848083,
+      "logps/chosen": -331.08624267578125,
+      "logps/rejected": -348.8202819824219,
+      "loss": 0.6259,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -0.41649022698402405,
+      "rewards/margins": 0.1930549144744873,
+      "rewards/rejected": -0.609545111656189,
+      "step": 235
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 3.7710978575315757,
+      "learning_rate": 1.8730348307472826e-07,
+      "logits/chosen": -0.4119279384613037,
+      "logits/rejected": -0.444758802652359,
+      "logps/chosen": -348.2624206542969,
+      "logps/rejected": -369.9598083496094,
+      "loss": 0.6249,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.5225319862365723,
+      "rewards/margins": 0.13163016736507416,
+      "rewards/rejected": -0.6541622281074524,
+      "step": 240
+    },
+    {
+      "epoch": 0.48902195608782434,
+      "grad_norm": 4.08348789093204,
+      "learning_rate": 1.822102990750595e-07,
+      "logits/chosen": -0.5410420298576355,
+      "logits/rejected": -0.4581461548805237,
+      "logps/chosen": -300.3963317871094,
+      "logps/rejected": -326.97357177734375,
+      "loss": 0.6205,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.4268406927585602,
+      "rewards/margins": 0.17870576679706573,
+      "rewards/rejected": -0.6055464744567871,
+      "step": 245
+    },
+    {
+      "epoch": 0.499001996007984,
+      "grad_norm": 3.8249633059365977,
+      "learning_rate": 1.7707787178758402e-07,
+      "logits/chosen": -0.5376532673835754,
+      "logits/rejected": -0.5166374444961548,
+      "logps/chosen": -334.3974609375,
+      "logps/rejected": -363.59832763671875,
+      "loss": 0.6097,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -0.5467029809951782,
+      "rewards/margins": 0.219395712018013,
+      "rewards/rejected": -0.7660986185073853,
+      "step": 250
+    },
+    {
+      "epoch": 0.5089820359281437,
+      "grad_norm": 4.084608415013939,
+      "learning_rate": 1.7191245428436176e-07,
+      "logits/chosen": -0.6120297908782959,
+      "logits/rejected": -0.5665668249130249,
+      "logps/chosen": -388.49237060546875,
+      "logps/rejected": -404.17913818359375,
+      "loss": 0.6066,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.5541552305221558,
+      "rewards/margins": 0.18654166162014008,
+      "rewards/rejected": -0.7406969666481018,
+      "step": 255
+    },
+    {
+      "epoch": 0.5189620758483033,
+      "grad_norm": 4.127013078261958,
+      "learning_rate": 1.667203398309488e-07,
+      "logits/chosen": -0.602649450302124,
+      "logits/rejected": -0.47091540694236755,
+      "logps/chosen": -342.5652770996094,
+      "logps/rejected": -363.1390380859375,
+      "loss": 0.6099,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.5999665260314941,
+      "rewards/margins": 0.22458717226982117,
+      "rewards/rejected": -0.8245537877082825,
+      "step": 260
+    },
+    {
+      "epoch": 0.5289421157684631,
+      "grad_norm": 4.181662944251744,
+      "learning_rate": 1.6150785421902278e-07,
+      "logits/chosen": -0.49136123061180115,
+      "logits/rejected": -0.4355231821537018,
+      "logps/chosen": -355.0814514160156,
+      "logps/rejected": -400.48486328125,
+      "loss": 0.6027,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.6992485523223877,
+      "rewards/margins": 0.2647705674171448,
+      "rewards/rejected": -0.9640190005302429,
+      "step": 265
+    },
+    {
+      "epoch": 0.5389221556886228,
+      "grad_norm": 4.187328944312369,
+      "learning_rate": 1.5628134805937993e-07,
+      "logits/chosen": -0.6901322603225708,
+      "logits/rejected": -0.7155795693397522,
+      "logps/chosen": -338.4058532714844,
+      "logps/rejected": -357.05145263671875,
+      "loss": 0.6044,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.6499531865119934,
+      "rewards/margins": 0.2078942060470581,
+      "rewards/rejected": -0.8578473329544067,
+      "step": 270
+    },
+    {
+      "epoch": 0.5489021956087824,
+      "grad_norm": 4.480820141822546,
+      "learning_rate": 1.5104718904469424e-07,
+      "logits/chosen": -0.49210062623023987,
+      "logits/rejected": -0.4995419979095459,
+      "logps/chosen": -362.78936767578125,
+      "logps/rejected": -376.6024475097656,
+      "loss": 0.6022,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -0.684400200843811,
+      "rewards/margins": 0.22897310554981232,
+      "rewards/rejected": -0.9133733510971069,
+      "step": 275
+    },
+    {
+      "epoch": 0.5588822355289421,
+      "grad_norm": 4.335560690928003,
+      "learning_rate": 1.458117541914647e-07,
+      "logits/chosen": -0.6205674409866333,
+      "logits/rejected": -0.5415416955947876,
+      "logps/chosen": -363.15484619140625,
+      "logps/rejected": -380.423828125,
+      "loss": 0.601,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -0.7319628000259399,
+      "rewards/margins": 0.22972945868968964,
+      "rewards/rejected": -0.9616923332214355,
+      "step": 280
+    },
+    {
+      "epoch": 0.5688622754491018,
+      "grad_norm": 4.236266469806635,
+      "learning_rate": 1.4058142207060298e-07,
+      "logits/chosen": -0.5227392315864563,
+      "logits/rejected": -0.44109734892845154,
+      "logps/chosen": -350.81268310546875,
+      "logps/rejected": -387.339111328125,
+      "loss": 0.599,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.7962437272071838,
+      "rewards/margins": 0.2677839994430542,
+      "rewards/rejected": -1.0640277862548828,
+      "step": 285
+    },
+    {
+      "epoch": 0.5788423153692615,
+      "grad_norm": 4.1859368563558546,
+      "learning_rate": 1.353625650361276e-07,
+      "logits/chosen": -0.4567599296569824,
+      "logits/rejected": -0.37081751227378845,
+      "logps/chosen": -292.90582275390625,
+      "logps/rejected": -351.08428955078125,
+      "loss": 0.5976,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -0.7117597460746765,
+      "rewards/margins": 0.23347418010234833,
+      "rewards/rejected": -0.9452340006828308,
+      "step": 290
+    },
+    {
+      "epoch": 0.5888223552894212,
+      "grad_norm": 4.963202872238042,
+      "learning_rate": 1.301615414614316e-07,
+      "logits/chosen": -0.5814245939254761,
+      "logits/rejected": -0.477074533700943,
+      "logps/chosen": -359.9764404296875,
+      "logps/rejected": -408.649169921875,
+      "loss": 0.5854,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -0.8252065777778625,
+      "rewards/margins": 0.3438906669616699,
+      "rewards/rejected": -1.1690973043441772,
+      "step": 295
+    },
+    {
+      "epoch": 0.5988023952095808,
+      "grad_norm": 4.522965998928778,
+      "learning_rate": 1.2498468799258466e-07,
+      "logits/chosen": -0.6931585669517517,
+      "logits/rejected": -0.6726911067962646,
+      "logps/chosen": -447.56134033203125,
+      "logps/rejected": -467.0315856933594,
+      "loss": 0.5951,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.0262882709503174,
+      "rewards/margins": 0.3147868514060974,
+      "rewards/rejected": -1.3410751819610596,
+      "step": 300
+    },
+    {
+      "epoch": 0.6087824351297405,
+      "grad_norm": 4.334372580127937,
+      "learning_rate": 1.1983831182810532e-07,
+      "logits/chosen": -0.7098149657249451,
+      "logits/rejected": -0.6338291764259338,
+      "logps/chosen": -370.42584228515625,
+      "logps/rejected": -416.33673095703125,
+      "loss": 0.5741,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -0.9695831537246704,
+      "rewards/margins": 0.28274181485176086,
+      "rewards/rejected": -1.2523248195648193,
+      "step": 305
+    },
+    {
+      "epoch": 0.6187624750499002,
+      "grad_norm": 4.645155562753339,
+      "learning_rate": 1.147286830346115e-07,
+      "logits/chosen": -0.7523954510688782,
+      "logits/rejected": -0.6753584146499634,
+      "logps/chosen": -415.63629150390625,
+      "logps/rejected": -454.6825256347656,
+      "loss": 0.5819,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.1591014862060547,
+      "rewards/margins": 0.3371506929397583,
+      "rewards/rejected": -1.496252179145813,
+      "step": 310
+    },
+    {
+      "epoch": 0.6287425149700598,
+      "grad_norm": 4.669200509826971,
+      "learning_rate": 1.0966202690771015e-07,
+      "logits/chosen": -0.668272852897644,
+      "logits/rejected": -0.5711073875427246,
+      "logps/chosen": -412.66424560546875,
+      "logps/rejected": -463.01971435546875,
+      "loss": 0.5802,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.1411970853805542,
+      "rewards/margins": 0.34684187173843384,
+      "rewards/rejected": -1.4880390167236328,
+      "step": 315
+    },
+    {
+      "epoch": 0.6387225548902196,
+      "grad_norm": 4.60028355094582,
+      "learning_rate": 1.0464451638743333e-07,
+      "logits/chosen": -0.720443606376648,
+      "logits/rejected": -0.633614182472229,
+      "logps/chosen": -381.11358642578125,
+      "logps/rejected": -422.4686584472656,
+      "loss": 0.5803,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.1198880672454834,
+      "rewards/margins": 0.3332558274269104,
+      "rewards/rejected": -1.4531439542770386,
+      "step": 320
+    },
+    {
+      "epoch": 0.6487025948103793,
+      "grad_norm": 4.7117497209054315,
+      "learning_rate": 9.968226453746175e-08,
+      "logits/chosen": -0.6728391647338867,
+      "logits/rejected": -0.6361491084098816,
+      "logps/chosen": -388.78375244140625,
+      "logps/rejected": -422.4482421875,
+      "loss": 0.5744,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.175586462020874,
+      "rewards/margins": 0.2871216833591461,
+      "rewards/rejected": -1.4627082347869873,
+      "step": 325
+    },
+    {
+      "epoch": 0.6586826347305389,
+      "grad_norm": 4.348227355176717,
+      "learning_rate": 9.478131709729831e-08,
+      "logits/chosen": -0.7032121419906616,
+      "logits/rejected": -0.6237956285476685,
+      "logps/chosen": -377.9942321777344,
+      "logps/rejected": -404.4933166503906,
+      "loss": 0.5795,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.1823105812072754,
+      "rewards/margins": 0.23070795834064484,
+      "rewards/rejected": -1.4130184650421143,
+      "step": 330
+    },
+    {
+      "epoch": 0.6686626746506986,
+      "grad_norm": 4.567093235085812,
+      "learning_rate": 8.994764511646577e-08,
+      "logits/chosen": -0.696010410785675,
+      "logits/rejected": -0.6754131317138672,
+      "logps/chosen": -400.3501892089844,
+      "logps/rejected": -406.4004821777344,
+      "loss": 0.5887,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.2299916744232178,
+      "rewards/margins": 0.2420133799314499,
+      "rewards/rejected": -1.4720051288604736,
+      "step": 335
+    },
+    {
+      "epoch": 0.6786427145708582,
+      "grad_norm": 5.005664260886447,
+      "learning_rate": 8.518713767970262e-08,
+      "logits/chosen": -0.7765355706214905,
+      "logits/rejected": -0.7291234135627747,
+      "logps/chosen": -440.3502502441406,
+      "logps/rejected": -463.7428283691406,
+      "loss": 0.5654,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -1.2532676458358765,
+      "rewards/margins": 0.2593846023082733,
+      "rewards/rejected": -1.5126522779464722,
+      "step": 340
+    },
+    {
+      "epoch": 0.688622754491018,
+      "grad_norm": 5.103097065108184,
+      "learning_rate": 8.050559473202076e-08,
+      "logits/chosen": -0.5867692232131958,
+      "logits/rejected": -0.5882567167282104,
+      "logps/chosen": -486.0328063964844,
+      "logps/rejected": -492.4873046875,
+      "loss": 0.5909,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.4522783756256104,
+      "rewards/margins": 0.20934677124023438,
+      "rewards/rejected": -1.6616249084472656,
+      "step": 345
+    },
+    {
+      "epoch": 0.6986027944111777,
+      "grad_norm": 4.912813992114836,
+      "learning_rate": 7.590872001236538e-08,
+      "logits/chosen": -0.7335643768310547,
+      "logits/rejected": -0.6834427714347839,
+      "logps/chosen": -402.9820861816406,
+      "logps/rejected": -425.92156982421875,
+      "loss": 0.5716,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.3429086208343506,
+      "rewards/margins": 0.27442997694015503,
+      "rewards/rejected": -1.6173385381698608,
+      "step": 350
+    },
+    {
+      "epoch": 0.7085828343313373,
+      "grad_norm": 5.102923641063365,
+      "learning_rate": 7.140211410448815e-08,
+      "logits/chosen": -0.721831202507019,
+      "logits/rejected": -0.61592036485672,
+      "logps/chosen": -370.572265625,
+      "logps/rejected": -414.7581481933594,
+      "loss": 0.5721,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.2241812944412231,
+      "rewards/margins": 0.3305676281452179,
+      "rewards/rejected": -1.554748773574829,
+      "step": 355
+    },
+    {
+      "epoch": 0.718562874251497,
+      "grad_norm": 5.015860169175414,
+      "learning_rate": 6.69912676134984e-08,
+      "logits/chosen": -0.7092261910438538,
+      "logits/rejected": -0.6547318696975708,
+      "logps/chosen": -440.85711669921875,
+      "logps/rejected": -457.0215759277344,
+      "loss": 0.5707,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.397318720817566,
+      "rewards/margins": 0.24624857306480408,
+      "rewards/rejected": -1.6435673236846924,
+      "step": 360
+    },
+    {
+      "epoch": 0.7285429141716567,
+      "grad_norm": 4.774816172341646,
+      "learning_rate": 6.26815544764066e-08,
+      "logits/chosen": -0.8451409339904785,
+      "logits/rejected": -0.7582667469978333,
+      "logps/chosen": -390.70233154296875,
+      "logps/rejected": -433.895263671875,
+      "loss": 0.5661,
+      "rewards/accuracies": 0.675000011920929,
+      "rewards/chosen": -1.2642087936401367,
+      "rewards/margins": 0.3393135070800781,
+      "rewards/rejected": -1.6035223007202148,
+      "step": 365
+    },
+    {
+      "epoch": 0.7385229540918163,
+      "grad_norm": 4.965964761489328,
+      "learning_rate": 5.847822541480985e-08,
+      "logits/chosen": -0.6884382963180542,
+      "logits/rejected": -0.6832146644592285,
+      "logps/chosen": -505.1039123535156,
+      "logps/rejected": -543.939697265625,
+      "loss": 0.5737,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.5997720956802368,
+      "rewards/margins": 0.34007787704467773,
+      "rewards/rejected": -1.939850091934204,
+      "step": 370
+    },
+    {
+      "epoch": 0.7485029940119761,
+      "grad_norm": 5.257593216933955,
+      "learning_rate": 5.4386401537696535e-08,
+      "logits/chosen": -0.654364287853241,
+      "logits/rejected": -0.618787407875061,
+      "logps/chosen": -424.26031494140625,
+      "logps/rejected": -464.0692443847656,
+      "loss": 0.5656,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.4769487380981445,
+      "rewards/margins": 0.3530046045780182,
+      "rewards/rejected": -1.8299534320831299,
+      "step": 375
+    },
+    {
+      "epoch": 0.7584830339321357,
+      "grad_norm": 5.018164548165559,
+      "learning_rate": 5.0411068102163756e-08,
+      "logits/chosen": -0.7129963636398315,
+      "logits/rejected": -0.6934917569160461,
+      "logps/chosen": -338.116943359375,
+      "logps/rejected": -385.53192138671875,
+      "loss": 0.5812,
+      "rewards/accuracies": 0.7875000238418579,
+      "rewards/chosen": -1.1324220895767212,
+      "rewards/margins": 0.3832218050956726,
+      "rewards/rejected": -1.515643835067749,
+      "step": 380
+    },
+    {
+      "epoch": 0.7684630738522954,
+      "grad_norm": 4.842940867729204,
+      "learning_rate": 4.6557068439649526e-08,
+      "logits/chosen": -0.6886343955993652,
+      "logits/rejected": -0.6565831303596497,
+      "logps/chosen": -475.0184631347656,
+      "logps/rejected": -506.1280212402344,
+      "loss": 0.5773,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.5225403308868408,
+      "rewards/margins": 0.3815816044807434,
+      "rewards/rejected": -1.90412175655365,
+      "step": 385
+    },
+    {
+      "epoch": 0.7784431137724551,
+      "grad_norm": 4.981718868828084,
+      "learning_rate": 4.2829098055079526e-08,
+      "logits/chosen": -0.8457885980606079,
+      "logits/rejected": -0.8267861604690552,
+      "logps/chosen": -402.27032470703125,
+      "logps/rejected": -441.7845153808594,
+      "loss": 0.5706,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.30136239528656,
+      "rewards/margins": 0.37314456701278687,
+      "rewards/rejected": -1.6745071411132812,
+      "step": 390
+    },
+    {
+      "epoch": 0.7884231536926147,
+      "grad_norm": 4.76229443747579,
+      "learning_rate": 3.923169890611741e-08,
+      "logits/chosen": -0.7744909524917603,
+      "logits/rejected": -0.7276748418807983,
+      "logps/chosen": -407.0968322753906,
+      "logps/rejected": -451.7494201660156,
+      "loss": 0.5605,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.4497464895248413,
+      "rewards/margins": 0.40129631757736206,
+      "rewards/rejected": -1.8510427474975586,
+      "step": 395
+    },
+    {
+      "epoch": 0.7984031936127745,
+      "grad_norm": 4.572364850180581,
+      "learning_rate": 3.576925386948951e-08,
+      "logits/chosen": -0.9308286905288696,
+      "logits/rejected": -0.8524009585380554,
+      "logps/chosen": -406.74578857421875,
+      "logps/rejected": -458.7312927246094,
+      "loss": 0.5563,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.3046013116836548,
+      "rewards/margins": 0.4329892098903656,
+      "rewards/rejected": -1.7375905513763428,
+      "step": 400
+    },
+    {
+      "epoch": 0.8083832335329342,
+      "grad_norm": 4.905353303890107,
+      "learning_rate": 3.244598140112404e-08,
+      "logits/chosen": -0.8015610575675964,
+      "logits/rejected": -0.7380157709121704,
+      "logps/chosen": -399.67218017578125,
+      "logps/rejected": -457.02825927734375,
+      "loss": 0.5685,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.3612743616104126,
+      "rewards/margins": 0.4470387399196625,
+      "rewards/rejected": -1.808313012123108,
+      "step": 405
+    },
+    {
+      "epoch": 0.8183632734530938,
+      "grad_norm": 5.311955246309319,
+      "learning_rate": 2.9265930396612894e-08,
+      "logits/chosen": -0.7535597085952759,
+      "logits/rejected": -0.6952261328697205,
+      "logps/chosen": -399.0675964355469,
+      "logps/rejected": -452.47344970703125,
+      "loss": 0.582,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.2877695560455322,
+      "rewards/margins": 0.3449626564979553,
+      "rewards/rejected": -1.6327321529388428,
+      "step": 410
+    },
+    {
+      "epoch": 0.8283433133732535,
+      "grad_norm": 5.053420598356344,
+      "learning_rate": 2.623297525825574e-08,
+      "logits/chosen": -0.8561833500862122,
+      "logits/rejected": -0.8156620264053345,
+      "logps/chosen": -430.49725341796875,
+      "logps/rejected": -483.80364990234375,
+      "loss": 0.5686,
+      "rewards/accuracies": 0.800000011920929,
+      "rewards/chosen": -1.4236512184143066,
+      "rewards/margins": 0.3616659343242645,
+      "rewards/rejected": -1.7853171825408936,
+      "step": 415
+    },
+    {
+      "epoch": 0.8383233532934131,
+      "grad_norm": 5.004297553699464,
+      "learning_rate": 2.335081117469777e-08,
+      "logits/chosen": -0.8136135339736938,
+      "logits/rejected": -0.7686566114425659,
+      "logps/chosen": -444.23419189453125,
+      "logps/rejected": -508.3873596191406,
+      "loss": 0.5616,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.4251264333724976,
+      "rewards/margins": 0.4452531933784485,
+      "rewards/rejected": -1.8703796863555908,
+      "step": 420
+    },
+    {
+      "epoch": 0.8483033932135728,
+      "grad_norm": 5.171033512433695,
+      "learning_rate": 2.062294961891138e-08,
+      "logits/chosen": -0.9262305498123169,
+      "logits/rejected": -0.8602676391601562,
+      "logps/chosen": -419.66705322265625,
+      "logps/rejected": -458.7422790527344,
+      "loss": 0.5601,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.3270304203033447,
+      "rewards/margins": 0.39937418699264526,
+      "rewards/rejected": -1.7264049053192139,
+      "step": 425
+    },
+    {
+      "epoch": 0.8582834331337326,
+      "grad_norm": 5.325797888088927,
+      "learning_rate": 1.8052714070007545e-08,
+      "logits/chosen": -0.7420898675918579,
+      "logits/rejected": -0.7444819211959839,
+      "logps/chosen": -404.44879150390625,
+      "logps/rejected": -432.81304931640625,
+      "loss": 0.5725,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.3653631210327148,
+      "rewards/margins": 0.33520203828811646,
+      "rewards/rejected": -1.7005650997161865,
+      "step": 430
+    },
+    {
+      "epoch": 0.8682634730538922,
+      "grad_norm": 5.010002107069334,
+      "learning_rate": 1.5643235964088065e-08,
+      "logits/chosen": -0.8383352160453796,
+      "logits/rejected": -0.8191484212875366,
+      "logps/chosen": -455.4537048339844,
+      "logps/rejected": -499.7396545410156,
+      "loss": 0.5761,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.4779622554779053,
+      "rewards/margins": 0.4129580557346344,
+      "rewards/rejected": -1.8909204006195068,
+      "step": 435
+    },
+    {
+      "epoch": 0.8782435129740519,
+      "grad_norm": 4.772084864042891,
+      "learning_rate": 1.3397450879073446e-08,
+      "logits/chosen": -0.8404937982559204,
+      "logits/rejected": -0.8073346018791199,
+      "logps/chosen": -468.2997131347656,
+      "logps/rejected": -504.8995666503906,
+      "loss": 0.5648,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.6386680603027344,
+      "rewards/margins": 0.4446341395378113,
+      "rewards/rejected": -2.0833022594451904,
+      "step": 440
+    },
+    {
+      "epoch": 0.8882235528942116,
+      "grad_norm": 4.956615120474398,
+      "learning_rate": 1.1318094958153047e-08,
+      "logits/chosen": -0.9180776476860046,
+      "logits/rejected": -0.8899502754211426,
+      "logps/chosen": -371.7776794433594,
+      "logps/rejected": -428.5679626464844,
+      "loss": 0.5901,
+      "rewards/accuracies": 0.7250000238418579,
+      "rewards/chosen": -1.327950119972229,
+      "rewards/margins": 0.3467249274253845,
+      "rewards/rejected": -1.6746749877929688,
+      "step": 445
+    },
+    {
+      "epoch": 0.8982035928143712,
+      "grad_norm": 4.788171459453746,
+      "learning_rate": 9.40770157621628e-09,
+      "logits/chosen": -0.7842416167259216,
+      "logits/rejected": -0.7082861661911011,
+      "logps/chosen": -417.77520751953125,
+      "logps/rejected": -457.5712890625,
+      "loss": 0.5593,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.3801639080047607,
+      "rewards/margins": 0.37675610184669495,
+      "rewards/rejected": -1.7569200992584229,
+      "step": 450
+    },
+    {
+      "epoch": 0.908183632734531,
+      "grad_norm": 4.581072227617621,
+      "learning_rate": 7.66859825332552e-09,
+      "logits/chosen": -0.80731201171875,
+      "logits/rejected": -0.7170153856277466,
+      "logps/chosen": -426.0374450683594,
+      "logps/rejected": -491.17724609375,
+      "loss": 0.5684,
+      "rewards/accuracies": 0.762499988079071,
+      "rewards/chosen": -1.4778865575790405,
+      "rewards/margins": 0.48648372292518616,
+      "rewards/rejected": -1.9643701314926147,
+      "step": 455
+    },
+    {
+      "epoch": 0.9181636726546906,
+      "grad_norm": 5.211747811331229,
+      "learning_rate": 6.102903818991373e-09,
+      "logits/chosen": -0.7492889761924744,
+      "logits/rejected": -0.692005455493927,
+      "logps/chosen": -408.1048583984375,
+      "logps/rejected": -465.81072998046875,
+      "loss": 0.5508,
+      "rewards/accuracies": 0.7124999761581421,
+      "rewards/chosen": -1.4337399005889893,
+      "rewards/margins": 0.4602373242378235,
+      "rewards/rejected": -1.893977165222168,
+      "step": 460
+    },
+    {
+      "epoch": 0.9281437125748503,
+      "grad_norm": 4.735277022639165,
+      "learning_rate": 4.712525830705338e-09,
+      "logits/chosen": -0.7876361012458801,
+      "logits/rejected": -0.7164231538772583,
+      "logps/chosen": -456.64654541015625,
+      "logps/rejected": -530.7649536132812,
+      "loss": 0.5495,
+      "rewards/accuracies": 0.8374999761581421,
+      "rewards/chosen": -1.4868801832199097,
+      "rewards/margins": 0.5220947265625,
+      "rewards/rejected": -2.00897479057312,
+      "step": 465
+    },
+    {
+      "epoch": 0.93812375249501,
+      "grad_norm": 5.092880826292085,
+      "learning_rate": 3.4991582498748116e-09,
+      "logits/chosen": -0.7580504417419434,
+      "logits/rejected": -0.7435745000839233,
+      "logps/chosen": -418.53643798828125,
+      "logps/rejected": -443.73016357421875,
+      "loss": 0.5562,
+      "rewards/accuracies": 0.6875,
+      "rewards/chosen": -1.392344355583191,
+      "rewards/margins": 0.26586177945137024,
+      "rewards/rejected": -1.6582062244415283,
+      "step": 470
+    },
+    {
+      "epoch": 0.9481037924151696,
+      "grad_norm": 4.985840092185972,
+      "learning_rate": 2.464279377992129e-09,
+      "logits/chosen": -0.7668736577033997,
+      "logits/rejected": -0.7452988624572754,
+      "logps/chosen": -466.7787170410156,
+      "logps/rejected": -506.02178955078125,
+      "loss": 0.5624,
+      "rewards/accuracies": 0.737500011920929,
+      "rewards/chosen": -1.6175203323364258,
+      "rewards/margins": 0.31748542189598083,
+      "rewards/rejected": -1.9350059032440186,
+      "step": 475
+    },
+    {
+      "epoch": 0.9580838323353293,
+      "grad_norm": 4.967479585965563,
+      "learning_rate": 1.60915005555175e-09,
+      "logits/chosen": -0.8129042387008667,
+      "logits/rejected": -0.739594578742981,
+      "logps/chosen": -447.076171875,
+      "logps/rejected": -484.808349609375,
+      "loss": 0.5671,
+      "rewards/accuracies": 0.824999988079071,
+      "rewards/chosen": -1.4572417736053467,
+      "rewards/margins": 0.46610623598098755,
+      "rewards/rejected": -1.9233481884002686,
+      "step": 480
+    },
+    {
+      "epoch": 0.9680638722554891,
+      "grad_norm": 5.96217808704067,
+      "learning_rate": 9.348121259105446e-10,
+      "logits/chosen": -0.7033708691596985,
+      "logits/rejected": -0.6699236035346985,
+      "logps/chosen": -417.16009521484375,
+      "logps/rejected": -451.69482421875,
+      "loss": 0.5803,
+      "rewards/accuracies": 0.7749999761581421,
+      "rewards/chosen": -1.3706567287445068,
+      "rewards/margins": 0.40733280777931213,
+      "rewards/rejected": -1.777989387512207,
+      "step": 485
+    },
+    {
+      "epoch": 0.9780439121756487,
+      "grad_norm": 5.734111733284475,
+      "learning_rate": 4.4208716596196293e-10,
+      "logits/chosen": -0.6810269951820374,
+      "logits/rejected": -0.6299699544906616,
+      "logps/chosen": -417.22967529296875,
+      "logps/rejected": -446.90447998046875,
+      "loss": 0.5733,
+      "rewards/accuracies": 0.75,
+      "rewards/chosen": -1.4043614864349365,
+      "rewards/margins": 0.3416087031364441,
+      "rewards/rejected": -1.745970368385315,
+      "step": 490
+    },
+    {
+      "epoch": 0.9880239520958084,
+      "grad_norm": 4.812399430304323,
+      "learning_rate": 1.3157548517124251e-10,
+      "logits/chosen": -0.7450631260871887,
+      "logits/rejected": -0.7431787252426147,
+      "logps/chosen": -416.9190979003906,
+      "logps/rejected": -472.78607177734375,
+      "loss": 0.5482,
+      "rewards/accuracies": 0.8125,
+      "rewards/chosen": -1.3006139993667603,
+      "rewards/margins": 0.49053430557250977,
+      "rewards/rejected": -1.7911481857299805,
+      "step": 495
+    },
+    {
+      "epoch": 0.998003992015968,
+      "grad_norm": 4.968518024512937,
+      "learning_rate": 3.6553941907879745e-12,
+      "logits/chosen": -0.765219509601593,
+      "logits/rejected": -0.7625989317893982,
+      "logps/chosen": -421.33843994140625,
+      "logps/rejected": -453.9501037597656,
+      "loss": 0.5756,
+      "rewards/accuracies": 0.699999988079071,
+      "rewards/chosen": -1.4310005903244019,
+      "rewards/margins": 0.3257448077201843,
+      "rewards/rejected": -1.7567455768585205,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 501,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 101,
+  "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-501/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d2062bff810c3be97f9dc215093b5dad2b48711e0862036888bf785c22f9a23
+size 7544

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "/GLOBALFS/gznwp_3/qxj/lgzhong/LLaMA-Factory/saves/Qwen2.5-7B-Instruct-SFT-v1.5",
+  "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_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.43.4",
+  "use_cache": true,
+  "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": "4.43.4"
+}