Training in progress, step 159, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-159/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-159/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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-159/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-159/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.51.3"
+}

checkpoint-159/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:147562d92bd4f62efa1700e20c50a82d6f85ef2a25110c22a1053c920c507ce0
+size 4902257696

checkpoint-159/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f9c949463ce4ebddfe186611191cefe8025455f53c8b3cf9719e928c129e4b5
+size 4915960368

checkpoint-159/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ebb25703be2e8e9210a539154b0a1804b4f3586ba57c1df8a2cd6d7f64dc212
+size 4983068496

checkpoint-159/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1486b2971df48432890f1fed159df773d6b2a2d5d37821244df4256588192739
+size 1580230264

checkpoint-159/model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 16381470720
+  },
+  "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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "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_norm.weight": "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.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-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_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.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_norm.weight": "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_norm.weight": "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.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "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_norm.weight": "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.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-00001-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_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-159/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48502ab18cfe87c1272411bc37f6e4be1fcfa98f275e6daf6e8be7cc5f2c9e5b
+size 16637925292

checkpoint-159/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e2010a01db67d9a5a7d71f395859654334844f890d83931a09da17ec1cd1ab1
+size 14512

checkpoint-159/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:305dc5a67afe9b6699a059d8c540b05e90e64fdceb539aa95425b71c657404a2
+size 14512

checkpoint-159/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7b05922ae5de37d3fb4f560e867b14eb60da9ae6826373538a0afb28d178133
+size 1064

checkpoint-159/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-159/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-159/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\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    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-159/trainer_state.json

@@ -0,0 +1,1211 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9953051643192489,
+  "eval_steps": 20,
+  "global_step": 159,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006259780907668232,
+      "grad_norm": 24.0,
+      "learning_rate": 0.0,
+      "loss": 2.4351,
+      "step": 1
+    },
+    {
+      "epoch": 0.006259780907668232,
+      "eval_loss": 2.856199264526367,
+      "eval_runtime": 34.38,
+      "eval_samples_per_second": 33.711,
+      "eval_steps_per_second": 8.435,
+      "step": 1
+    },
+    {
+      "epoch": 0.012519561815336464,
+      "grad_norm": 23.875,
+      "learning_rate": 6.666666666666667e-07,
+      "loss": 2.4681,
+      "step": 2
+    },
+    {
+      "epoch": 0.018779342723004695,
+      "grad_norm": 23.75,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 2.3337,
+      "step": 3
+    },
+    {
+      "epoch": 0.025039123630672927,
+      "grad_norm": 25.25,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 2.4301,
+      "step": 4
+    },
+    {
+      "epoch": 0.03129890453834116,
+      "grad_norm": 23.375,
+      "learning_rate": 2.666666666666667e-06,
+      "loss": 2.4849,
+      "step": 5
+    },
+    {
+      "epoch": 0.03755868544600939,
+      "grad_norm": 20.375,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 2.4069,
+      "step": 6
+    },
+    {
+      "epoch": 0.04381846635367762,
+      "grad_norm": 18.75,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 2.3702,
+      "step": 7
+    },
+    {
+      "epoch": 0.050078247261345854,
+      "grad_norm": 16.0,
+      "learning_rate": 4.666666666666667e-06,
+      "loss": 2.233,
+      "step": 8
+    },
+    {
+      "epoch": 0.056338028169014086,
+      "grad_norm": 12.75,
+      "learning_rate": 5.333333333333334e-06,
+      "loss": 2.254,
+      "step": 9
+    },
+    {
+      "epoch": 0.06259780907668232,
+      "grad_norm": 9.75,
+      "learning_rate": 6e-06,
+      "loss": 2.1663,
+      "step": 10
+    },
+    {
+      "epoch": 0.06885758998435054,
+      "grad_norm": 8.1875,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 2.0993,
+      "step": 11
+    },
+    {
+      "epoch": 0.07511737089201878,
+      "grad_norm": 6.03125,
+      "learning_rate": 7.333333333333333e-06,
+      "loss": 2.0805,
+      "step": 12
+    },
+    {
+      "epoch": 0.081377151799687,
+      "grad_norm": 5.09375,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 2.0682,
+      "step": 13
+    },
+    {
+      "epoch": 0.08763693270735524,
+      "grad_norm": 3.75,
+      "learning_rate": 8.666666666666668e-06,
+      "loss": 2.0658,
+      "step": 14
+    },
+    {
+      "epoch": 0.09389671361502347,
+      "grad_norm": 2.703125,
+      "learning_rate": 9.333333333333334e-06,
+      "loss": 2.0055,
+      "step": 15
+    },
+    {
+      "epoch": 0.10015649452269171,
+      "grad_norm": 2.140625,
+      "learning_rate": 1e-05,
+      "loss": 1.971,
+      "step": 16
+    },
+    {
+      "epoch": 0.10641627543035993,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.999731248679734e-06,
+      "loss": 2.0593,
+      "step": 17
+    },
+    {
+      "epoch": 0.11267605633802817,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.99892502360984e-06,
+      "loss": 1.9322,
+      "step": 18
+    },
+    {
+      "epoch": 0.1189358372456964,
+      "grad_norm": 1.6796875,
+      "learning_rate": 9.99758141145994e-06,
+      "loss": 1.8955,
+      "step": 19
+    },
+    {
+      "epoch": 0.12519561815336464,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.995700556669052e-06,
+      "loss": 1.8937,
+      "step": 20
+    },
+    {
+      "epoch": 0.12519561815336464,
+      "eval_loss": 2.1415202617645264,
+      "eval_runtime": 32.3427,
+      "eval_samples_per_second": 35.835,
+      "eval_steps_per_second": 8.966,
+      "step": 20
+    },
+    {
+      "epoch": 0.13145539906103287,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.993282661430058e-06,
+      "loss": 2.0143,
+      "step": 21
+    },
+    {
+      "epoch": 0.13771517996870108,
+      "grad_norm": 1.25,
+      "learning_rate": 9.990327985667972e-06,
+      "loss": 1.8491,
+      "step": 22
+    },
+    {
+      "epoch": 0.14397496087636932,
+      "grad_norm": 1.265625,
+      "learning_rate": 9.986836847012001e-06,
+      "loss": 1.8292,
+      "step": 23
+    },
+    {
+      "epoch": 0.15023474178403756,
+      "grad_norm": 1.1640625,
+      "learning_rate": 9.98280962076139e-06,
+      "loss": 1.8565,
+      "step": 24
+    },
+    {
+      "epoch": 0.1564945226917058,
+      "grad_norm": 1.0625,
+      "learning_rate": 9.978246739845095e-06,
+      "loss": 1.8344,
+      "step": 25
+    },
+    {
+      "epoch": 0.162754303599374,
+      "grad_norm": 0.95703125,
+      "learning_rate": 9.973148694775217e-06,
+      "loss": 1.8407,
+      "step": 26
+    },
+    {
+      "epoch": 0.16901408450704225,
+      "grad_norm": 0.9765625,
+      "learning_rate": 9.967516033594295e-06,
+      "loss": 1.9214,
+      "step": 27
+    },
+    {
+      "epoch": 0.1752738654147105,
+      "grad_norm": 0.89453125,
+      "learning_rate": 9.961349361816384e-06,
+      "loss": 1.9058,
+      "step": 28
+    },
+    {
+      "epoch": 0.18153364632237873,
+      "grad_norm": 0.8984375,
+      "learning_rate": 9.954649342361952e-06,
+      "loss": 1.9187,
+      "step": 29
+    },
+    {
+      "epoch": 0.18779342723004694,
+      "grad_norm": 0.87109375,
+      "learning_rate": 9.947416695486633e-06,
+      "loss": 1.8439,
+      "step": 30
+    },
+    {
+      "epoch": 0.19405320813771518,
+      "grad_norm": 0.9453125,
+      "learning_rate": 9.939652198703785e-06,
+      "loss": 1.9411,
+      "step": 31
+    },
+    {
+      "epoch": 0.20031298904538342,
+      "grad_norm": 0.90625,
+      "learning_rate": 9.93135668670091e-06,
+      "loss": 1.9375,
+      "step": 32
+    },
+    {
+      "epoch": 0.20657276995305165,
+      "grad_norm": 0.921875,
+      "learning_rate": 9.92253105124993e-06,
+      "loss": 1.8445,
+      "step": 33
+    },
+    {
+      "epoch": 0.21283255086071987,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.91317624111132e-06,
+      "loss": 1.8388,
+      "step": 34
+    },
+    {
+      "epoch": 0.2190923317683881,
+      "grad_norm": 0.765625,
+      "learning_rate": 9.903293261932106e-06,
+      "loss": 1.87,
+      "step": 35
+    },
+    {
+      "epoch": 0.22535211267605634,
+      "grad_norm": 0.8984375,
+      "learning_rate": 9.89288317613777e-06,
+      "loss": 1.8586,
+      "step": 36
+    },
+    {
+      "epoch": 0.23161189358372458,
+      "grad_norm": 0.7734375,
+      "learning_rate": 9.881947102818036e-06,
+      "loss": 1.7725,
+      "step": 37
+    },
+    {
+      "epoch": 0.2378716744913928,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.870486217606557e-06,
+      "loss": 1.8729,
+      "step": 38
+    },
+    {
+      "epoch": 0.24413145539906103,
+      "grad_norm": 0.71875,
+      "learning_rate": 9.858501752554548e-06,
+      "loss": 1.7154,
+      "step": 39
+    },
+    {
+      "epoch": 0.25039123630672927,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.845994995998332e-06,
+      "loss": 1.7026,
+      "step": 40
+    },
+    {
+      "epoch": 0.25039123630672927,
+      "eval_loss": 2.0947954654693604,
+      "eval_runtime": 31.845,
+      "eval_samples_per_second": 36.395,
+      "eval_steps_per_second": 9.107,
+      "step": 40
+    },
+    {
+      "epoch": 0.2566510172143975,
+      "grad_norm": 0.7578125,
+      "learning_rate": 9.83296729242084e-06,
+      "loss": 1.8626,
+      "step": 41
+    },
+    {
+      "epoch": 0.26291079812206575,
+      "grad_norm": 0.7734375,
+      "learning_rate": 9.819420042307091e-06,
+      "loss": 1.8422,
+      "step": 42
+    },
+    {
+      "epoch": 0.26917057902973396,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.805354701993624e-06,
+      "loss": 1.9615,
+      "step": 43
+    },
+    {
+      "epoch": 0.27543035993740217,
+      "grad_norm": 0.8125,
+      "learning_rate": 9.79077278351195e-06,
+      "loss": 1.7841,
+      "step": 44
+    },
+    {
+      "epoch": 0.28169014084507044,
+      "grad_norm": 0.703125,
+      "learning_rate": 9.77567585442601e-06,
+      "loss": 1.8549,
+      "step": 45
+    },
+    {
+      "epoch": 0.28794992175273865,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.76006553766365e-06,
+      "loss": 1.8915,
+      "step": 46
+    },
+    {
+      "epoch": 0.2942097026604069,
+      "grad_norm": 0.71484375,
+      "learning_rate": 9.743943511342168e-06,
+      "loss": 1.7428,
+      "step": 47
+    },
+    {
+      "epoch": 0.3004694835680751,
+      "grad_norm": 0.70703125,
+      "learning_rate": 9.727311508587907e-06,
+      "loss": 1.7938,
+      "step": 48
+    },
+    {
+      "epoch": 0.30672926447574334,
+      "grad_norm": 0.85546875,
+      "learning_rate": 9.710171317349946e-06,
+      "loss": 1.8441,
+      "step": 49
+    },
+    {
+      "epoch": 0.3129890453834116,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.692524780207897e-06,
+      "loss": 1.8148,
+      "step": 50
+    },
+    {
+      "epoch": 0.3192488262910798,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.674373794173818e-06,
+      "loss": 1.7628,
+      "step": 51
+    },
+    {
+      "epoch": 0.325508607198748,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.655720310488298e-06,
+      "loss": 1.8734,
+      "step": 52
+    },
+    {
+      "epoch": 0.3317683881064163,
+      "grad_norm": 0.80859375,
+      "learning_rate": 9.636566334410682e-06,
+      "loss": 1.8551,
+      "step": 53
+    },
+    {
+      "epoch": 0.3380281690140845,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.616913925003514e-06,
+      "loss": 1.9247,
+      "step": 54
+    },
+    {
+      "epoch": 0.3442879499217527,
+      "grad_norm": 0.73828125,
+      "learning_rate": 9.596765194911182e-06,
+      "loss": 1.8792,
+      "step": 55
+    },
+    {
+      "epoch": 0.350547730829421,
+      "grad_norm": 0.87109375,
+      "learning_rate": 9.576122310132814e-06,
+      "loss": 1.8499,
+      "step": 56
+    },
+    {
+      "epoch": 0.3568075117370892,
+      "grad_norm": 0.7890625,
+      "learning_rate": 9.554987489789426e-06,
+      "loss": 1.8316,
+      "step": 57
+    },
+    {
+      "epoch": 0.36306729264475746,
+      "grad_norm": 0.765625,
+      "learning_rate": 9.533363005885362e-06,
+      "loss": 1.8628,
+      "step": 58
+    },
+    {
+      "epoch": 0.36932707355242567,
+      "grad_norm": 0.796875,
+      "learning_rate": 9.511251183064068e-06,
+      "loss": 1.8859,
+      "step": 59
+    },
+    {
+      "epoch": 0.3755868544600939,
+      "grad_norm": 0.78125,
+      "learning_rate": 9.48865439835817e-06,
+      "loss": 1.8667,
+      "step": 60
+    },
+    {
+      "epoch": 0.3755868544600939,
+      "eval_loss": 2.089089870452881,
+      "eval_runtime": 31.7863,
+      "eval_samples_per_second": 36.462,
+      "eval_steps_per_second": 9.123,
+      "step": 60
+    },
+    {
+      "epoch": 0.38184663536776214,
+      "grad_norm": 0.77734375,
+      "learning_rate": 9.465575080933959e-06,
+      "loss": 1.9035,
+      "step": 61
+    },
+    {
+      "epoch": 0.38810641627543035,
+      "grad_norm": 0.78125,
+      "learning_rate": 9.442015711830246e-06,
+      "loss": 1.8529,
+      "step": 62
+    },
+    {
+      "epoch": 0.39436619718309857,
+      "grad_norm": 0.7578125,
+      "learning_rate": 9.417978823691652e-06,
+      "loss": 1.9195,
+      "step": 63
+    },
+    {
+      "epoch": 0.40062597809076683,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.393467000496345e-06,
+      "loss": 1.7397,
+      "step": 64
+    },
+    {
+      "epoch": 0.40688575899843504,
+      "grad_norm": 0.7421875,
+      "learning_rate": 9.368482877278264e-06,
+      "loss": 1.7112,
+      "step": 65
+    },
+    {
+      "epoch": 0.4131455399061033,
+      "grad_norm": 0.75390625,
+      "learning_rate": 9.34302913984385e-06,
+      "loss": 1.8223,
+      "step": 66
+    },
+    {
+      "epoch": 0.4194053208137715,
+      "grad_norm": 1.3203125,
+      "learning_rate": 9.317108524483319e-06,
+      "loss": 1.8934,
+      "step": 67
+    },
+    {
+      "epoch": 0.42566510172143973,
+      "grad_norm": 0.765625,
+      "learning_rate": 9.29072381767651e-06,
+      "loss": 1.8963,
+      "step": 68
+    },
+    {
+      "epoch": 0.431924882629108,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.26387785579334e-06,
+      "loss": 1.9008,
+      "step": 69
+    },
+    {
+      "epoch": 0.4381846635367762,
+      "grad_norm": 0.9140625,
+      "learning_rate": 9.236573524788888e-06,
+      "loss": 1.7498,
+      "step": 70
+    },
+    {
+      "epoch": 0.4444444444444444,
+      "grad_norm": 0.765625,
+      "learning_rate": 9.208813759893158e-06,
+      "loss": 1.8538,
+      "step": 71
+    },
+    {
+      "epoch": 0.4507042253521127,
+      "grad_norm": 0.78515625,
+      "learning_rate": 9.180601545295535e-06,
+      "loss": 1.9173,
+      "step": 72
+    },
+    {
+      "epoch": 0.4569640062597809,
+      "grad_norm": 0.85546875,
+      "learning_rate": 9.151939913823988e-06,
+      "loss": 1.9062,
+      "step": 73
+    },
+    {
+      "epoch": 0.46322378716744916,
+      "grad_norm": 0.76171875,
+      "learning_rate": 9.122831946619038e-06,
+      "loss": 1.8574,
+      "step": 74
+    },
+    {
+      "epoch": 0.4694835680751174,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.093280772802527e-06,
+      "loss": 1.8464,
+      "step": 75
+    },
+    {
+      "epoch": 0.4757433489827856,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.063289569141251e-06,
+      "loss": 1.8025,
+      "step": 76
+    },
+    {
+      "epoch": 0.48200312989045385,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.032861559705442e-06,
+      "loss": 1.7934,
+      "step": 77
+    },
+    {
+      "epoch": 0.48826291079812206,
+      "grad_norm": 0.76953125,
+      "learning_rate": 9.002000015522182e-06,
+      "loss": 1.834,
+      "step": 78
+    },
+    {
+      "epoch": 0.4945226917057903,
+      "grad_norm": 0.79296875,
+      "learning_rate": 8.970708254223768e-06,
+      "loss": 1.9787,
+      "step": 79
+    },
+    {
+      "epoch": 0.5007824726134585,
+      "grad_norm": 0.7578125,
+      "learning_rate": 8.938989639691068e-06,
+      "loss": 1.8841,
+      "step": 80
+    },
+    {
+      "epoch": 0.5007824726134585,
+      "eval_loss": 2.083742618560791,
+      "eval_runtime": 32.0915,
+      "eval_samples_per_second": 36.115,
+      "eval_steps_per_second": 9.037,
+      "step": 80
+    },
+    {
+      "epoch": 0.5070422535211268,
+      "grad_norm": 0.765625,
+      "learning_rate": 8.90684758169189e-06,
+      "loss": 1.7598,
+      "step": 81
+    },
+    {
+      "epoch": 0.513302034428795,
+      "grad_norm": 0.88671875,
+      "learning_rate": 8.87428553551445e-06,
+      "loss": 1.8376,
+      "step": 82
+    },
+    {
+      "epoch": 0.5195618153364632,
+      "grad_norm": 0.79296875,
+      "learning_rate": 8.841307001595904e-06,
+      "loss": 1.8295,
+      "step": 83
+    },
+    {
+      "epoch": 0.5258215962441315,
+      "grad_norm": 0.78125,
+      "learning_rate": 8.807915525146065e-06,
+      "loss": 1.7782,
+      "step": 84
+    },
+    {
+      "epoch": 0.5320813771517997,
+      "grad_norm": 0.8828125,
+      "learning_rate": 8.774114695766286e-06,
+      "loss": 1.8151,
+      "step": 85
+    },
+    {
+      "epoch": 0.5383411580594679,
+      "grad_norm": 0.88671875,
+      "learning_rate": 8.739908147063576e-06,
+      "loss": 1.8271,
+      "step": 86
+    },
+    {
+      "epoch": 0.5446009389671361,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.705299556259986e-06,
+      "loss": 1.8576,
+      "step": 87
+    },
+    {
+      "epoch": 0.5508607198748043,
+      "grad_norm": 0.92578125,
+      "learning_rate": 8.670292643797302e-06,
+      "loss": 1.8252,
+      "step": 88
+    },
+    {
+      "epoch": 0.5571205007824727,
+      "grad_norm": 0.8046875,
+      "learning_rate": 8.634891172937102e-06,
+      "loss": 1.7893,
+      "step": 89
+    },
+    {
+      "epoch": 0.5633802816901409,
+      "grad_norm": 1.0546875,
+      "learning_rate": 8.599098949356201e-06,
+      "loss": 1.7345,
+      "step": 90
+    },
+    {
+      "epoch": 0.5696400625978091,
+      "grad_norm": 0.875,
+      "learning_rate": 8.562919820737537e-06,
+      "loss": 1.8542,
+      "step": 91
+    },
+    {
+      "epoch": 0.5758998435054773,
+      "grad_norm": 0.859375,
+      "learning_rate": 8.526357676356538e-06,
+      "loss": 1.9353,
+      "step": 92
+    },
+    {
+      "epoch": 0.5821596244131455,
+      "grad_norm": 0.94140625,
+      "learning_rate": 8.489416446663037e-06,
+      "loss": 1.8938,
+      "step": 93
+    },
+    {
+      "epoch": 0.5884194053208138,
+      "grad_norm": 0.89453125,
+      "learning_rate": 8.452100102858734e-06,
+      "loss": 1.811,
+      "step": 94
+    },
+    {
+      "epoch": 0.594679186228482,
+      "grad_norm": 0.90234375,
+      "learning_rate": 8.414412656470297e-06,
+      "loss": 1.8387,
+      "step": 95
+    },
+    {
+      "epoch": 0.6009389671361502,
+      "grad_norm": 0.87890625,
+      "learning_rate": 8.376358158918114e-06,
+      "loss": 1.83,
+      "step": 96
+    },
+    {
+      "epoch": 0.6071987480438185,
+      "grad_norm": 0.82421875,
+      "learning_rate": 8.33794070108077e-06,
+      "loss": 1.8087,
+      "step": 97
+    },
+    {
+      "epoch": 0.6134585289514867,
+      "grad_norm": 0.90625,
+      "learning_rate": 8.299164412855268e-06,
+      "loss": 1.8735,
+      "step": 98
+    },
+    {
+      "epoch": 0.6197183098591549,
+      "grad_norm": 0.84765625,
+      "learning_rate": 8.260033462713073e-06,
+      "loss": 1.8415,
+      "step": 99
+    },
+    {
+      "epoch": 0.6259780907668232,
+      "grad_norm": 0.9609375,
+      "learning_rate": 8.22055205725199e-06,
+      "loss": 1.7648,
+      "step": 100
+    },
+    {
+      "epoch": 0.6259780907668232,
+      "eval_loss": 2.081907272338867,
+      "eval_runtime": 32.2169,
+      "eval_samples_per_second": 35.975,
+      "eval_steps_per_second": 9.001,
+      "step": 100
+    },
+    {
+      "epoch": 0.6322378716744914,
+      "grad_norm": 0.921875,
+      "learning_rate": 8.180724440743957e-06,
+      "loss": 1.7488,
+      "step": 101
+    },
+    {
+      "epoch": 0.6384976525821596,
+      "grad_norm": 0.9140625,
+      "learning_rate": 8.14055489467878e-06,
+      "loss": 1.8555,
+      "step": 102
+    },
+    {
+      "epoch": 0.6447574334898278,
+      "grad_norm": 0.8671875,
+      "learning_rate": 8.100047737303877e-06,
+      "loss": 1.7153,
+      "step": 103
+    },
+    {
+      "epoch": 0.651017214397496,
+      "grad_norm": 0.8203125,
+      "learning_rate": 8.059207323160057e-06,
+      "loss": 1.8374,
+      "step": 104
+    },
+    {
+      "epoch": 0.6572769953051644,
+      "grad_norm": 0.84765625,
+      "learning_rate": 8.018038042613407e-06,
+      "loss": 1.7978,
+      "step": 105
+    },
+    {
+      "epoch": 0.6635367762128326,
+      "grad_norm": 0.9453125,
+      "learning_rate": 7.97654432138333e-06,
+      "loss": 1.8959,
+      "step": 106
+    },
+    {
+      "epoch": 0.6697965571205008,
+      "grad_norm": 0.9296875,
+      "learning_rate": 7.93473062006677e-06,
+      "loss": 1.8987,
+      "step": 107
+    },
+    {
+      "epoch": 0.676056338028169,
+      "grad_norm": 0.91796875,
+      "learning_rate": 7.892601433658705e-06,
+      "loss": 1.8158,
+      "step": 108
+    },
+    {
+      "epoch": 0.6823161189358372,
+      "grad_norm": 0.87890625,
+      "learning_rate": 7.850161291068915e-06,
+      "loss": 1.7846,
+      "step": 109
+    },
+    {
+      "epoch": 0.6885758998435054,
+      "grad_norm": 0.859375,
+      "learning_rate": 7.807414754635145e-06,
+      "loss": 1.7181,
+      "step": 110
+    },
+    {
+      "epoch": 0.6948356807511737,
+      "grad_norm": 0.88671875,
+      "learning_rate": 7.764366419632636e-06,
+      "loss": 1.8185,
+      "step": 111
+    },
+    {
+      "epoch": 0.701095461658842,
+      "grad_norm": 0.94140625,
+      "learning_rate": 7.721020913780137e-06,
+      "loss": 1.8794,
+      "step": 112
+    },
+    {
+      "epoch": 0.7073552425665102,
+      "grad_norm": 0.89453125,
+      "learning_rate": 7.677382896742417e-06,
+      "loss": 1.8333,
+      "step": 113
+    },
+    {
+      "epoch": 0.7136150234741784,
+      "grad_norm": 0.88671875,
+      "learning_rate": 7.63345705962935e-06,
+      "loss": 1.765,
+      "step": 114
+    },
+    {
+      "epoch": 0.7198748043818466,
+      "grad_norm": 0.921875,
+      "learning_rate": 7.589248124491627e-06,
+      "loss": 1.7885,
+      "step": 115
+    },
+    {
+      "epoch": 0.7261345852895149,
+      "grad_norm": 0.88671875,
+      "learning_rate": 7.544760843813122e-06,
+      "loss": 1.8512,
+      "step": 116
+    },
+    {
+      "epoch": 0.7323943661971831,
+      "grad_norm": 0.890625,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 1.8184,
+      "step": 117
+    },
+    {
+      "epoch": 0.7386541471048513,
+      "grad_norm": 0.90234375,
+      "learning_rate": 7.454970404866612e-06,
+      "loss": 1.7486,
+      "step": 118
+    },
+    {
+      "epoch": 0.7449139280125195,
+      "grad_norm": 0.92578125,
+      "learning_rate": 7.409676899118213e-06,
+      "loss": 1.8205,
+      "step": 119
+    },
+    {
+      "epoch": 0.7511737089201878,
+      "grad_norm": 0.8203125,
+      "learning_rate": 7.3641243518305915e-06,
+      "loss": 1.8661,
+      "step": 120
+    },
+    {
+      "epoch": 0.7511737089201878,
+      "eval_loss": 2.0777387619018555,
+      "eval_runtime": 31.941,
+      "eval_samples_per_second": 36.286,
+      "eval_steps_per_second": 9.079,
+      "step": 120
+    },
+    {
+      "epoch": 0.7574334898278561,
+      "grad_norm": 0.87109375,
+      "learning_rate": 7.318317659926637e-06,
+      "loss": 1.8764,
+      "step": 121
+    },
+    {
+      "epoch": 0.7636932707355243,
+      "grad_norm": 0.96484375,
+      "learning_rate": 7.272261747649922e-06,
+      "loss": 1.7789,
+      "step": 122
+    },
+    {
+      "epoch": 0.7699530516431925,
+      "grad_norm": 0.8984375,
+      "learning_rate": 7.225961566035335e-06,
+      "loss": 1.8548,
+      "step": 123
+    },
+    {
+      "epoch": 0.7762128325508607,
+      "grad_norm": 0.96875,
+      "learning_rate": 7.179422092376856e-06,
+      "loss": 1.8024,
+      "step": 124
+    },
+    {
+      "epoch": 0.7824726134585289,
+      "grad_norm": 0.84375,
+      "learning_rate": 7.132648329692478e-06,
+      "loss": 1.8377,
+      "step": 125
+    },
+    {
+      "epoch": 0.7887323943661971,
+      "grad_norm": 0.9140625,
+      "learning_rate": 7.085645306186391e-06,
+      "loss": 1.7966,
+      "step": 126
+    },
+    {
+      "epoch": 0.7949921752738655,
+      "grad_norm": 0.8515625,
+      "learning_rate": 7.038418074708444e-06,
+      "loss": 1.8284,
+      "step": 127
+    },
+    {
+      "epoch": 0.8012519561815337,
+      "grad_norm": 0.953125,
+      "learning_rate": 6.990971712210966e-06,
+      "loss": 1.8473,
+      "step": 128
+    },
+    {
+      "epoch": 0.8075117370892019,
+      "grad_norm": 0.91796875,
+      "learning_rate": 6.943311319202976e-06,
+      "loss": 1.7937,
+      "step": 129
+    },
+    {
+      "epoch": 0.8137715179968701,
+      "grad_norm": 0.88671875,
+      "learning_rate": 6.895442019201898e-06,
+      "loss": 1.8041,
+      "step": 130
+    },
+    {
+      "epoch": 0.8200312989045383,
+      "grad_norm": 0.88671875,
+      "learning_rate": 6.8473689581827585e-06,
+      "loss": 1.804,
+      "step": 131
+    },
+    {
+      "epoch": 0.8262910798122066,
+      "grad_norm": 0.8828125,
+      "learning_rate": 6.7990973040250055e-06,
+      "loss": 1.7166,
+      "step": 132
+    },
+    {
+      "epoch": 0.8325508607198748,
+      "grad_norm": 1.015625,
+      "learning_rate": 6.750632245956954e-06,
+      "loss": 1.8674,
+      "step": 133
+    },
+    {
+      "epoch": 0.838810641627543,
+      "grad_norm": 0.87109375,
+      "learning_rate": 6.701978993997942e-06,
+      "loss": 1.8183,
+      "step": 134
+    },
+    {
+      "epoch": 0.8450704225352113,
+      "grad_norm": 0.890625,
+      "learning_rate": 6.653142778398247e-06,
+      "loss": 1.8159,
+      "step": 135
+    },
+    {
+      "epoch": 0.8513302034428795,
+      "grad_norm": 0.9453125,
+      "learning_rate": 6.6041288490768385e-06,
+      "loss": 1.9359,
+      "step": 136
+    },
+    {
+      "epoch": 0.8575899843505478,
+      "grad_norm": 0.9296875,
+      "learning_rate": 6.554942475057003e-06,
+      "loss": 1.839,
+      "step": 137
+    },
+    {
+      "epoch": 0.863849765258216,
+      "grad_norm": 0.859375,
+      "learning_rate": 6.505588943899923e-06,
+      "loss": 1.7049,
+      "step": 138
+    },
+    {
+      "epoch": 0.8701095461658842,
+      "grad_norm": 0.87890625,
+      "learning_rate": 6.456073561136261e-06,
+      "loss": 1.8681,
+      "step": 139
+    },
+    {
+      "epoch": 0.8763693270735524,
+      "grad_norm": 0.98046875,
+      "learning_rate": 6.406401649695814e-06,
+      "loss": 1.7907,
+      "step": 140
+    },
+    {
+      "epoch": 0.8763693270735524,
+      "eval_loss": 2.076223373413086,
+      "eval_runtime": 31.8704,
+      "eval_samples_per_second": 36.366,
+      "eval_steps_per_second": 9.099,
+      "step": 140
+    },
+    {
+      "epoch": 0.8826291079812206,
+      "grad_norm": 0.953125,
+      "learning_rate": 6.356578549335295e-06,
+      "loss": 1.8383,
+      "step": 141
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 1.0078125,
+      "learning_rate": 6.306609616064304e-06,
+      "loss": 1.876,
+      "step": 142
+    },
+    {
+      "epoch": 0.8951486697965572,
+      "grad_norm": 0.85546875,
+      "learning_rate": 6.256500221569556e-06,
+      "loss": 1.7715,
+      "step": 143
+    },
+    {
+      "epoch": 0.9014084507042254,
+      "grad_norm": 0.8671875,
+      "learning_rate": 6.2062557526374226e-06,
+      "loss": 1.8248,
+      "step": 144
+    },
+    {
+      "epoch": 0.9076682316118936,
+      "grad_norm": 0.9296875,
+      "learning_rate": 6.15588161057485e-06,
+      "loss": 1.7684,
+      "step": 145
+    },
+    {
+      "epoch": 0.9139280125195618,
+      "grad_norm": 0.8671875,
+      "learning_rate": 6.10538321062871e-06,
+      "loss": 1.8602,
+      "step": 146
+    },
+    {
+      "epoch": 0.92018779342723,
+      "grad_norm": 0.94140625,
+      "learning_rate": 6.0547659814036664e-06,
+      "loss": 1.8974,
+      "step": 147
+    },
+    {
+      "epoch": 0.9264475743348983,
+      "grad_norm": 0.9453125,
+      "learning_rate": 6.004035364278593e-06,
+      "loss": 1.7399,
+      "step": 148
+    },
+    {
+      "epoch": 0.9327073552425665,
+      "grad_norm": 0.8671875,
+      "learning_rate": 5.953196812821622e-06,
+      "loss": 1.8217,
+      "step": 149
+    },
+    {
+      "epoch": 0.9389671361502347,
+      "grad_norm": 0.83984375,
+      "learning_rate": 5.902255792203882e-06,
+      "loss": 1.6971,
+      "step": 150
+    },
+    {
+      "epoch": 0.945226917057903,
+      "grad_norm": 0.89453125,
+      "learning_rate": 5.851217778611994e-06,
+      "loss": 1.8267,
+      "step": 151
+    },
+    {
+      "epoch": 0.9514866979655712,
+      "grad_norm": 1.234375,
+      "learning_rate": 5.800088258659371e-06,
+      "loss": 1.874,
+      "step": 152
+    },
+    {
+      "epoch": 0.9577464788732394,
+      "grad_norm": 0.91015625,
+      "learning_rate": 5.748872728796409e-06,
+      "loss": 1.7611,
+      "step": 153
+    },
+    {
+      "epoch": 0.9640062597809077,
+      "grad_norm": 0.96875,
+      "learning_rate": 5.697576694719616e-06,
+      "loss": 1.7875,
+      "step": 154
+    },
+    {
+      "epoch": 0.9702660406885759,
+      "grad_norm": 0.95703125,
+      "learning_rate": 5.646205670779745e-06,
+      "loss": 1.8012,
+      "step": 155
+    },
+    {
+      "epoch": 0.9765258215962441,
+      "grad_norm": 0.890625,
+      "learning_rate": 5.594765179389003e-06,
+      "loss": 1.7772,
+      "step": 156
+    },
+    {
+      "epoch": 0.9827856025039123,
+      "grad_norm": 0.88671875,
+      "learning_rate": 5.543260750427373e-06,
+      "loss": 1.874,
+      "step": 157
+    },
+    {
+      "epoch": 0.9890453834115805,
+      "grad_norm": 0.87109375,
+      "learning_rate": 5.4916979206481745e-06,
+      "loss": 1.6977,
+      "step": 158
+    },
+    {
+      "epoch": 0.9953051643192489,
+      "grad_norm": 0.9453125,
+      "learning_rate": 5.440082233082837e-06,
+      "loss": 1.8282,
+      "step": 159
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 318,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 159,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8927476215507845e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-159/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b63df2af0ef622d066b78bd86afc567f96ec14323a6fdcf87ba429f6ed5dc8b
+size 10808