Training in progress, step 156, checkpoint

.gitattributes

@@ -37,3 +37,4 @@ tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-39/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-78/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-117/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-156/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-156/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-156/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": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 32768,
+  "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": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-156/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

checkpoint-156/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:878cd7df43f272fe969910e5b804d4836e810c64df8a0820b945ce90d4fbe243
+size 4967215360

checkpoint-156/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de2e2f57390913a10a7c091b0f3b46702faae53b8961d19041018dc4540e7fb
+size 3077766632

checkpoint-156/model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-156/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:193ffde9bd5234f014f21e92a5727db598ee1be545752f9ff1e6a5f4e15ffbee
+size 8172200062

checkpoint-156/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f37c40ce327861a7ca13b719d3aa37510a143368b6e74358bdb14becb3899e1e
+size 14244

checkpoint-156/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f3270b8fe02d2a389fa802dd493d2b2e64312f61b699dd4b4fc141b2ece4e6c
+size 1064

checkpoint-156/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-156/tokenizer.json

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

checkpoint-156/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-156/trainer_state.json

@@ -0,0 +1,1126 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02564102564102564,
+      "grad_norm": 4.75,
+      "learning_rate": 0.0,
+      "loss": 2.8786,
+      "step": 1
+    },
+    {
+      "epoch": 0.05128205128205128,
+      "grad_norm": 8.0625,
+      "learning_rate": 2.5e-06,
+      "loss": 2.9525,
+      "step": 2
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 11.6875,
+      "learning_rate": 5e-06,
+      "loss": 2.7153,
+      "step": 3
+    },
+    {
+      "epoch": 0.10256410256410256,
+      "grad_norm": 12.4375,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 2.5826,
+      "step": 4
+    },
+    {
+      "epoch": 0.1282051282051282,
+      "grad_norm": 10.375,
+      "learning_rate": 1e-05,
+      "loss": 2.5254,
+      "step": 5
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 8.875,
+      "learning_rate": 9.998932083939657e-06,
+      "loss": 2.3523,
+      "step": 6
+    },
+    {
+      "epoch": 0.1794871794871795,
+      "grad_norm": 8.8125,
+      "learning_rate": 9.995728791936505e-06,
+      "loss": 2.2738,
+      "step": 7
+    },
+    {
+      "epoch": 0.20512820512820512,
+      "grad_norm": 7.28125,
+      "learning_rate": 9.990391492329341e-06,
+      "loss": 2.2553,
+      "step": 8
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 6.90625,
+      "learning_rate": 9.98292246503335e-06,
+      "loss": 2.1269,
+      "step": 9
+    },
+    {
+      "epoch": 0.2564102564102564,
+      "grad_norm": 6.875,
+      "learning_rate": 9.973324900566214e-06,
+      "loss": 2.1726,
+      "step": 10
+    },
+    {
+      "epoch": 0.28205128205128205,
+      "grad_norm": 7.25,
+      "learning_rate": 9.961602898685225e-06,
+      "loss": 2.087,
+      "step": 11
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 6.8125,
+      "learning_rate": 9.947761466636014e-06,
+      "loss": 2.0203,
+      "step": 12
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 7.03125,
+      "learning_rate": 9.931806517013612e-06,
+      "loss": 2.0242,
+      "step": 13
+    },
+    {
+      "epoch": 0.358974358974359,
+      "grad_norm": 6.53125,
+      "learning_rate": 9.913744865236798e-06,
+      "loss": 1.9997,
+      "step": 14
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 6.34375,
+      "learning_rate": 9.893584226636773e-06,
+      "loss": 1.8334,
+      "step": 15
+    },
+    {
+      "epoch": 0.41025641025641024,
+      "grad_norm": 6.40625,
+      "learning_rate": 9.871333213161438e-06,
+      "loss": 1.9528,
+      "step": 16
+    },
+    {
+      "epoch": 0.4358974358974359,
+      "grad_norm": 6.0,
+      "learning_rate": 9.847001329696653e-06,
+      "loss": 1.8608,
+      "step": 17
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 5.46875,
+      "learning_rate": 9.820598970006068e-06,
+      "loss": 1.8053,
+      "step": 18
+    },
+    {
+      "epoch": 0.48717948717948717,
+      "grad_norm": 5.15625,
+      "learning_rate": 9.792137412291265e-06,
+      "loss": 1.8232,
+      "step": 19
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 5.34375,
+      "learning_rate": 9.761628814374074e-06,
+      "loss": 1.7059,
+      "step": 20
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 5.15625,
+      "learning_rate": 9.729086208503174e-06,
+      "loss": 1.9746,
+      "step": 21
+    },
+    {
+      "epoch": 0.5641025641025641,
+      "grad_norm": 5.21875,
+      "learning_rate": 9.694523495787149e-06,
+      "loss": 1.6262,
+      "step": 22
+    },
+    {
+      "epoch": 0.5897435897435898,
+      "grad_norm": 4.96875,
+      "learning_rate": 9.657955440256396e-06,
+      "loss": 1.8171,
+      "step": 23
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 5.09375,
+      "learning_rate": 9.619397662556434e-06,
+      "loss": 1.7618,
+      "step": 24
+    },
+    {
+      "epoch": 0.6410256410256411,
+      "grad_norm": 5.25,
+      "learning_rate": 9.578866633275289e-06,
+      "loss": 1.711,
+      "step": 25
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 5.03125,
+      "learning_rate": 9.536379665907801e-06,
+      "loss": 1.5066,
+      "step": 26
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 5.625,
+      "learning_rate": 9.491954909459895e-06,
+      "loss": 1.4406,
+      "step": 27
+    },
+    {
+      "epoch": 0.717948717948718,
+      "grad_norm": 5.5,
+      "learning_rate": 9.445611340695926e-06,
+      "loss": 1.558,
+      "step": 28
+    },
+    {
+      "epoch": 0.7435897435897436,
+      "grad_norm": 4.9375,
+      "learning_rate": 9.397368756032445e-06,
+      "loss": 1.4596,
+      "step": 29
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 6.3125,
+      "learning_rate": 9.347247763081834e-06,
+      "loss": 1.6387,
+      "step": 30
+    },
+    {
+      "epoch": 0.7948717948717948,
+      "grad_norm": 8.75,
+      "learning_rate": 9.295269771849426e-06,
+      "loss": 1.5038,
+      "step": 31
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 7.0,
+      "learning_rate": 9.241456985587868e-06,
+      "loss": 2.154,
+      "step": 32
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 6.4375,
+      "learning_rate": 9.185832391312644e-06,
+      "loss": 1.9146,
+      "step": 33
+    },
+    {
+      "epoch": 0.8717948717948718,
+      "grad_norm": 6.8125,
+      "learning_rate": 9.12841974998278e-06,
+      "loss": 2.3066,
+      "step": 34
+    },
+    {
+      "epoch": 0.8974358974358975,
+      "grad_norm": 7.0,
+      "learning_rate": 9.069243586350976e-06,
+      "loss": 2.2234,
+      "step": 35
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 8.4375,
+      "learning_rate": 9.008329178487442e-06,
+      "loss": 2.9886,
+      "step": 36
+    },
+    {
+      "epoch": 0.9487179487179487,
+      "grad_norm": 9.5,
+      "learning_rate": 8.94570254698197e-06,
+      "loss": 4.0233,
+      "step": 37
+    },
+    {
+      "epoch": 0.9743589743589743,
+      "grad_norm": 13.1875,
+      "learning_rate": 8.881390443828788e-06,
+      "loss": 4.4944,
+      "step": 38
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 45.75,
+      "learning_rate": 8.815420340999034e-06,
+      "loss": 6.7771,
+      "step": 39
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 4.03125,
+      "learning_rate": 8.747820418705632e-06,
+      "loss": 2.741,
+      "step": 40
+    },
+    {
+      "epoch": 1.0512820512820513,
+      "grad_norm": 23.75,
+      "learning_rate": 8.67861955336566e-06,
+      "loss": 2.7361,
+      "step": 41
+    },
+    {
+      "epoch": 1.0769230769230769,
+      "grad_norm": 41.25,
+      "learning_rate": 8.607847305265312e-06,
+      "loss": 2.4577,
+      "step": 42
+    },
+    {
+      "epoch": 1.1025641025641026,
+      "grad_norm": 36.5,
+      "learning_rate": 8.535533905932739e-06,
+      "loss": 2.0977,
+      "step": 43
+    },
+    {
+      "epoch": 1.1282051282051282,
+      "grad_norm": 11.625,
+      "learning_rate": 8.461710245224149e-06,
+      "loss": 2.0235,
+      "step": 44
+    },
+    {
+      "epoch": 1.1538461538461537,
+      "grad_norm": 12.4375,
+      "learning_rate": 8.386407858128707e-06,
+      "loss": 1.8987,
+      "step": 45
+    },
+    {
+      "epoch": 1.1794871794871795,
+      "grad_norm": 11.3125,
+      "learning_rate": 8.309658911297833e-06,
+      "loss": 1.7952,
+      "step": 46
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 7.0,
+      "learning_rate": 8.231496189304704e-06,
+      "loss": 1.8796,
+      "step": 47
+    },
+    {
+      "epoch": 1.2307692307692308,
+      "grad_norm": 5.5,
+      "learning_rate": 8.151953080639777e-06,
+      "loss": 1.8016,
+      "step": 48
+    },
+    {
+      "epoch": 1.2564102564102564,
+      "grad_norm": 5.875,
+      "learning_rate": 8.071063563448341e-06,
+      "loss": 1.8173,
+      "step": 49
+    },
+    {
+      "epoch": 1.282051282051282,
+      "grad_norm": 5.125,
+      "learning_rate": 7.988862191016204e-06,
+      "loss": 1.8295,
+      "step": 50
+    },
+    {
+      "epoch": 1.3076923076923077,
+      "grad_norm": 4.96875,
+      "learning_rate": 7.905384077009693e-06,
+      "loss": 1.7912,
+      "step": 51
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 4.84375,
+      "learning_rate": 7.820664880476257e-06,
+      "loss": 1.7695,
+      "step": 52
+    },
+    {
+      "epoch": 1.358974358974359,
+      "grad_norm": 4.5625,
+      "learning_rate": 7.734740790612137e-06,
+      "loss": 1.7942,
+      "step": 53
+    },
+    {
+      "epoch": 1.3846153846153846,
+      "grad_norm": 4.59375,
+      "learning_rate": 7.647648511303545e-06,
+      "loss": 1.7302,
+      "step": 54
+    },
+    {
+      "epoch": 1.4102564102564101,
+      "grad_norm": 4.53125,
+      "learning_rate": 7.559425245448006e-06,
+      "loss": 1.6814,
+      "step": 55
+    },
+    {
+      "epoch": 1.435897435897436,
+      "grad_norm": 4.4375,
+      "learning_rate": 7.470108679062521e-06,
+      "loss": 1.6977,
+      "step": 56
+    },
+    {
+      "epoch": 1.4615384615384617,
+      "grad_norm": 4.34375,
+      "learning_rate": 7.379736965185369e-06,
+      "loss": 1.6699,
+      "step": 57
+    },
+    {
+      "epoch": 1.4871794871794872,
+      "grad_norm": 4.6875,
+      "learning_rate": 7.288348707578409e-06,
+      "loss": 1.6252,
+      "step": 58
+    },
+    {
+      "epoch": 1.5128205128205128,
+      "grad_norm": 4.6875,
+      "learning_rate": 7.195982944236853e-06,
+      "loss": 1.5826,
+      "step": 59
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 4.4375,
+      "learning_rate": 7.102679130713538e-06,
+      "loss": 1.7134,
+      "step": 60
+    },
+    {
+      "epoch": 1.564102564102564,
+      "grad_norm": 4.8125,
+      "learning_rate": 7.008477123264849e-06,
+      "loss": 1.5422,
+      "step": 61
+    },
+    {
+      "epoch": 1.5897435897435899,
+      "grad_norm": 4.40625,
+      "learning_rate": 6.913417161825449e-06,
+      "loss": 1.6654,
+      "step": 62
+    },
+    {
+      "epoch": 1.6153846153846154,
+      "grad_norm": 4.8125,
+      "learning_rate": 6.817539852819149e-06,
+      "loss": 1.7428,
+      "step": 63
+    },
+    {
+      "epoch": 1.641025641025641,
+      "grad_norm": 5.0625,
+      "learning_rate": 6.720886151813194e-06,
+      "loss": 1.5221,
+      "step": 64
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 4.5625,
+      "learning_rate": 6.6234973460234184e-06,
+      "loss": 1.4163,
+      "step": 65
+    },
+    {
+      "epoch": 1.6923076923076923,
+      "grad_norm": 4.96875,
+      "learning_rate": 6.525415036677745e-06,
+      "loss": 1.3288,
+      "step": 66
+    },
+    {
+      "epoch": 1.717948717948718,
+      "grad_norm": 5.09375,
+      "learning_rate": 6.426681121245527e-06,
+      "loss": 1.3884,
+      "step": 67
+    },
+    {
+      "epoch": 1.7435897435897436,
+      "grad_norm": 5.40625,
+      "learning_rate": 6.327337775540362e-06,
+      "loss": 1.4421,
+      "step": 68
+    },
+    {
+      "epoch": 1.7692307692307692,
+      "grad_norm": 4.9375,
+      "learning_rate": 6.227427435703997e-06,
+      "loss": 1.5454,
+      "step": 69
+    },
+    {
+      "epoch": 1.7948717948717947,
+      "grad_norm": 4.875,
+      "learning_rate": 6.126992780079032e-06,
+      "loss": 1.5869,
+      "step": 70
+    },
+    {
+      "epoch": 1.8205128205128205,
+      "grad_norm": 5.09375,
+      "learning_rate": 6.026076710978172e-06,
+      "loss": 2.0383,
+      "step": 71
+    },
+    {
+      "epoch": 1.8461538461538463,
+      "grad_norm": 5.5,
+      "learning_rate": 5.924722336357793e-06,
+      "loss": 1.7922,
+      "step": 72
+    },
+    {
+      "epoch": 1.8717948717948718,
+      "grad_norm": 6.75,
+      "learning_rate": 5.82297295140367e-06,
+      "loss": 2.1761,
+      "step": 73
+    },
+    {
+      "epoch": 1.8974358974358974,
+      "grad_norm": 6.375,
+      "learning_rate": 5.720872020036734e-06,
+      "loss": 2.1503,
+      "step": 74
+    },
+    {
+      "epoch": 1.9230769230769231,
+      "grad_norm": 6.96875,
+      "learning_rate": 5.61846315634674e-06,
+      "loss": 2.8915,
+      "step": 75
+    },
+    {
+      "epoch": 1.9487179487179487,
+      "grad_norm": 7.25,
+      "learning_rate": 5.515790105961785e-06,
+      "loss": 3.8878,
+      "step": 76
+    },
+    {
+      "epoch": 1.9743589743589745,
+      "grad_norm": 11.125,
+      "learning_rate": 5.412896727361663e-06,
+      "loss": 4.3157,
+      "step": 77
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 38.5,
+      "learning_rate": 5.309826973142974e-06,
+      "loss": 6.2624,
+      "step": 78
+    },
+    {
+      "epoch": 2.0256410256410255,
+      "grad_norm": 4.34375,
+      "learning_rate": 5.206624871244066e-06,
+      "loss": 2.6988,
+      "step": 79
+    },
+    {
+      "epoch": 2.051282051282051,
+      "grad_norm": 16.125,
+      "learning_rate": 5.103334506137773e-06,
+      "loss": 2.6872,
+      "step": 80
+    },
+    {
+      "epoch": 2.076923076923077,
+      "grad_norm": 27.0,
+      "learning_rate": 5e-06,
+      "loss": 2.3881,
+      "step": 81
+    },
+    {
+      "epoch": 2.1025641025641026,
+      "grad_norm": 29.0,
+      "learning_rate": 4.89666549386223e-06,
+      "loss": 2.1485,
+      "step": 82
+    },
+    {
+      "epoch": 2.128205128205128,
+      "grad_norm": 23.75,
+      "learning_rate": 4.793375128755934e-06,
+      "loss": 2.1047,
+      "step": 83
+    },
+    {
+      "epoch": 2.1538461538461537,
+      "grad_norm": 19.375,
+      "learning_rate": 4.690173026857028e-06,
+      "loss": 1.9177,
+      "step": 84
+    },
+    {
+      "epoch": 2.1794871794871793,
+      "grad_norm": 14.0,
+      "learning_rate": 4.587103272638339e-06,
+      "loss": 1.7993,
+      "step": 85
+    },
+    {
+      "epoch": 2.2051282051282053,
+      "grad_norm": 7.625,
+      "learning_rate": 4.4842098940382155e-06,
+      "loss": 1.8896,
+      "step": 86
+    },
+    {
+      "epoch": 2.230769230769231,
+      "grad_norm": 7.21875,
+      "learning_rate": 4.381536843653262e-06,
+      "loss": 1.761,
+      "step": 87
+    },
+    {
+      "epoch": 2.2564102564102564,
+      "grad_norm": 7.9375,
+      "learning_rate": 4.279127979963266e-06,
+      "loss": 1.8078,
+      "step": 88
+    },
+    {
+      "epoch": 2.282051282051282,
+      "grad_norm": 7.84375,
+      "learning_rate": 4.17702704859633e-06,
+      "loss": 1.7515,
+      "step": 89
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 7.0625,
+      "learning_rate": 4.075277663642208e-06,
+      "loss": 1.7459,
+      "step": 90
+    },
+    {
+      "epoch": 2.3333333333333335,
+      "grad_norm": 6.34375,
+      "learning_rate": 3.973923289021829e-06,
+      "loss": 1.6839,
+      "step": 91
+    },
+    {
+      "epoch": 2.358974358974359,
+      "grad_norm": 5.59375,
+      "learning_rate": 3.8730072199209705e-06,
+      "loss": 1.7688,
+      "step": 92
+    },
+    {
+      "epoch": 2.3846153846153846,
+      "grad_norm": 5.53125,
+      "learning_rate": 3.7725725642960047e-06,
+      "loss": 1.6122,
+      "step": 93
+    },
+    {
+      "epoch": 2.41025641025641,
+      "grad_norm": 5.21875,
+      "learning_rate": 3.67266222445964e-06,
+      "loss": 1.7193,
+      "step": 94
+    },
+    {
+      "epoch": 2.435897435897436,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.573318878754475e-06,
+      "loss": 1.6538,
+      "step": 95
+    },
+    {
+      "epoch": 2.4615384615384617,
+      "grad_norm": 4.6875,
+      "learning_rate": 3.4745849633222566e-06,
+      "loss": 1.622,
+      "step": 96
+    },
+    {
+      "epoch": 2.4871794871794872,
+      "grad_norm": 4.875,
+      "learning_rate": 3.3765026539765832e-06,
+      "loss": 1.5624,
+      "step": 97
+    },
+    {
+      "epoch": 2.5128205128205128,
+      "grad_norm": 4.625,
+      "learning_rate": 3.2791138481868084e-06,
+      "loss": 1.552,
+      "step": 98
+    },
+    {
+      "epoch": 2.5384615384615383,
+      "grad_norm": 4.75,
+      "learning_rate": 3.1824601471808504e-06,
+      "loss": 1.6924,
+      "step": 99
+    },
+    {
+      "epoch": 2.564102564102564,
+      "grad_norm": 5.0,
+      "learning_rate": 3.0865828381745515e-06,
+      "loss": 1.4784,
+      "step": 100
+    },
+    {
+      "epoch": 2.58974358974359,
+      "grad_norm": 4.5625,
+      "learning_rate": 2.991522876735154e-06,
+      "loss": 1.6101,
+      "step": 101
+    },
+    {
+      "epoch": 2.6153846153846154,
+      "grad_norm": 4.875,
+      "learning_rate": 2.8973208692864623e-06,
+      "loss": 1.6149,
+      "step": 102
+    },
+    {
+      "epoch": 2.641025641025641,
+      "grad_norm": 4.96875,
+      "learning_rate": 2.804017055763149e-06,
+      "loss": 1.5607,
+      "step": 103
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 4.59375,
+      "learning_rate": 2.711651292421593e-06,
+      "loss": 1.3517,
+      "step": 104
+    },
+    {
+      "epoch": 2.6923076923076925,
+      "grad_norm": 4.78125,
+      "learning_rate": 2.6202630348146323e-06,
+      "loss": 1.362,
+      "step": 105
+    },
+    {
+      "epoch": 2.717948717948718,
+      "grad_norm": 5.125,
+      "learning_rate": 2.529891320937481e-06,
+      "loss": 1.232,
+      "step": 106
+    },
+    {
+      "epoch": 2.7435897435897436,
+      "grad_norm": 5.25,
+      "learning_rate": 2.4405747545519966e-06,
+      "loss": 1.5141,
+      "step": 107
+    },
+    {
+      "epoch": 2.769230769230769,
+      "grad_norm": 5.28125,
+      "learning_rate": 2.352351488696457e-06,
+      "loss": 1.4774,
+      "step": 108
+    },
+    {
+      "epoch": 2.7948717948717947,
+      "grad_norm": 5.5625,
+      "learning_rate": 2.265259209387867e-06,
+      "loss": 1.6229,
+      "step": 109
+    },
+    {
+      "epoch": 2.8205128205128203,
+      "grad_norm": 5.875,
+      "learning_rate": 2.179335119523745e-06,
+      "loss": 1.9325,
+      "step": 110
+    },
+    {
+      "epoch": 2.8461538461538463,
+      "grad_norm": 6.6875,
+      "learning_rate": 2.094615922990309e-06,
+      "loss": 1.8139,
+      "step": 111
+    },
+    {
+      "epoch": 2.871794871794872,
+      "grad_norm": 8.3125,
+      "learning_rate": 2.0111378089837958e-06,
+      "loss": 2.1465,
+      "step": 112
+    },
+    {
+      "epoch": 2.8974358974358974,
+      "grad_norm": 9.6875,
+      "learning_rate": 1.928936436551661e-06,
+      "loss": 2.1325,
+      "step": 113
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "grad_norm": 9.1875,
+      "learning_rate": 1.848046919360225e-06,
+      "loss": 2.9035,
+      "step": 114
+    },
+    {
+      "epoch": 2.948717948717949,
+      "grad_norm": 7.3125,
+      "learning_rate": 1.7685038106952952e-06,
+      "loss": 3.8152,
+      "step": 115
+    },
+    {
+      "epoch": 2.9743589743589745,
+      "grad_norm": 11.1875,
+      "learning_rate": 1.6903410887021676e-06,
+      "loss": 4.2236,
+      "step": 116
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 38.25,
+      "learning_rate": 1.6135921418712959e-06,
+      "loss": 6.2164,
+      "step": 117
+    },
+    {
+      "epoch": 3.0256410256410255,
+      "grad_norm": 3.875,
+      "learning_rate": 1.5382897547758513e-06,
+      "loss": 2.6836,
+      "step": 118
+    },
+    {
+      "epoch": 3.051282051282051,
+      "grad_norm": 5.71875,
+      "learning_rate": 1.4644660940672628e-06,
+      "loss": 2.5084,
+      "step": 119
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 8.125,
+      "learning_rate": 1.3921526947346902e-06,
+      "loss": 2.0748,
+      "step": 120
+    },
+    {
+      "epoch": 3.1025641025641026,
+      "grad_norm": 6.9375,
+      "learning_rate": 1.321380446634342e-06,
+      "loss": 1.8859,
+      "step": 121
+    },
+    {
+      "epoch": 3.128205128205128,
+      "grad_norm": 7.25,
+      "learning_rate": 1.2521795812943704e-06,
+      "loss": 1.9025,
+      "step": 122
+    },
+    {
+      "epoch": 3.1538461538461537,
+      "grad_norm": 6.375,
+      "learning_rate": 1.1845796590009684e-06,
+      "loss": 1.7788,
+      "step": 123
+    },
+    {
+      "epoch": 3.1794871794871793,
+      "grad_norm": 7.28125,
+      "learning_rate": 1.118609556171213e-06,
+      "loss": 1.727,
+      "step": 124
+    },
+    {
+      "epoch": 3.2051282051282053,
+      "grad_norm": 5.65625,
+      "learning_rate": 1.0542974530180327e-06,
+      "loss": 1.7812,
+      "step": 125
+    },
+    {
+      "epoch": 3.230769230769231,
+      "grad_norm": 7.375,
+      "learning_rate": 9.916708215125586e-07,
+      "loss": 1.7469,
+      "step": 126
+    },
+    {
+      "epoch": 3.2564102564102564,
+      "grad_norm": 5.78125,
+      "learning_rate": 9.307564136490255e-07,
+      "loss": 1.7702,
+      "step": 127
+    },
+    {
+      "epoch": 3.282051282051282,
+      "grad_norm": 5.65625,
+      "learning_rate": 8.715802500172215e-07,
+      "loss": 1.7148,
+      "step": 128
+    },
+    {
+      "epoch": 3.3076923076923075,
+      "grad_norm": 5.65625,
+      "learning_rate": 8.141676086873574e-07,
+      "loss": 1.7481,
+      "step": 129
+    },
+    {
+      "epoch": 3.3333333333333335,
+      "grad_norm": 5.03125,
+      "learning_rate": 7.585430144121319e-07,
+      "loss": 1.6527,
+      "step": 130
+    },
+    {
+      "epoch": 3.358974358974359,
+      "grad_norm": 4.375,
+      "learning_rate": 7.047302281505735e-07,
+      "loss": 1.7278,
+      "step": 131
+    },
+    {
+      "epoch": 3.3846153846153846,
+      "grad_norm": 4.625,
+      "learning_rate": 6.527522369181655e-07,
+      "loss": 1.6841,
+      "step": 132
+    },
+    {
+      "epoch": 3.41025641025641,
+      "grad_norm": 4.875,
+      "learning_rate": 6.026312439675553e-07,
+      "loss": 1.6241,
+      "step": 133
+    },
+    {
+      "epoch": 3.435897435897436,
+      "grad_norm": 4.59375,
+      "learning_rate": 5.543886593040737e-07,
+      "loss": 1.6332,
+      "step": 134
+    },
+    {
+      "epoch": 3.4615384615384617,
+      "grad_norm": 4.375,
+      "learning_rate": 5.080450905401057e-07,
+      "loss": 1.587,
+      "step": 135
+    },
+    {
+      "epoch": 3.4871794871794872,
+      "grad_norm": 4.5625,
+      "learning_rate": 4.6362033409220077e-07,
+      "loss": 1.6122,
+      "step": 136
+    },
+    {
+      "epoch": 3.5128205128205128,
+      "grad_norm": 4.84375,
+      "learning_rate": 4.211333667247125e-07,
+      "loss": 1.5133,
+      "step": 137
+    },
+    {
+      "epoch": 3.5384615384615383,
+      "grad_norm": 4.53125,
+      "learning_rate": 3.8060233744356634e-07,
+      "loss": 1.7055,
+      "step": 138
+    },
+    {
+      "epoch": 3.564102564102564,
+      "grad_norm": 4.75,
+      "learning_rate": 3.420445597436056e-07,
+      "loss": 1.4768,
+      "step": 139
+    },
+    {
+      "epoch": 3.58974358974359,
+      "grad_norm": 4.34375,
+      "learning_rate": 3.0547650421285216e-07,
+      "loss": 1.6144,
+      "step": 140
+    },
+    {
+      "epoch": 3.6153846153846154,
+      "grad_norm": 4.59375,
+      "learning_rate": 2.7091379149682683e-07,
+      "loss": 1.6258,
+      "step": 141
+    },
+    {
+      "epoch": 3.641025641025641,
+      "grad_norm": 4.84375,
+      "learning_rate": 2.3837118562592799e-07,
+      "loss": 1.47,
+      "step": 142
+    },
+    {
+      "epoch": 3.6666666666666665,
+      "grad_norm": 4.5,
+      "learning_rate": 2.0786258770873647e-07,
+      "loss": 1.3829,
+      "step": 143
+    },
+    {
+      "epoch": 3.6923076923076925,
+      "grad_norm": 4.8125,
+      "learning_rate": 1.7940102999393194e-07,
+      "loss": 1.3299,
+      "step": 144
+    },
+    {
+      "epoch": 3.717948717948718,
+      "grad_norm": 4.625,
+      "learning_rate": 1.5299867030334815e-07,
+      "loss": 1.4538,
+      "step": 145
+    },
+    {
+      "epoch": 3.7435897435897436,
+      "grad_norm": 4.8125,
+      "learning_rate": 1.286667868385627e-07,
+      "loss": 1.269,
+      "step": 146
+    },
+    {
+      "epoch": 3.769230769230769,
+      "grad_norm": 4.8125,
+      "learning_rate": 1.0641577336322761e-07,
+      "loss": 1.4599,
+      "step": 147
+    },
+    {
+      "epoch": 3.7948717948717947,
+      "grad_norm": 5.25,
+      "learning_rate": 8.625513476320291e-08,
+      "loss": 1.5192,
+      "step": 148
+    },
+    {
+      "epoch": 3.8205128205128203,
+      "grad_norm": 5.1875,
+      "learning_rate": 6.819348298638839e-08,
+      "loss": 1.986,
+      "step": 149
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 6.0,
+      "learning_rate": 5.223853336398632e-08,
+      "loss": 1.8131,
+      "step": 150
+    },
+    {
+      "epoch": 3.871794871794872,
+      "grad_norm": 7.0625,
+      "learning_rate": 3.839710131477492e-08,
+      "loss": 2.138,
+      "step": 151
+    },
+    {
+      "epoch": 3.8974358974358974,
+      "grad_norm": 8.5,
+      "learning_rate": 2.6675099433787212e-08,
+      "loss": 2.1238,
+      "step": 152
+    },
+    {
+      "epoch": 3.9230769230769234,
+      "grad_norm": 8.5,
+      "learning_rate": 1.7077534966650767e-08,
+      "loss": 2.887,
+      "step": 153
+    },
+    {
+      "epoch": 3.948717948717949,
+      "grad_norm": 7.40625,
+      "learning_rate": 9.608507670659239e-09,
+      "loss": 3.8071,
+      "step": 154
+    },
+    {
+      "epoch": 3.9743589743589745,
+      "grad_norm": 11.1875,
+      "learning_rate": 4.2712080634949024e-09,
+      "loss": 4.2345,
+      "step": 155
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 38.0,
+      "learning_rate": 1.0679160603449533e-09,
+      "loss": 6.1763,
+      "step": 156
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 156,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 39,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.786072307381043e+16,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-156/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b330478a4b4bb0bc756e2a18c2c63b7c59c668df63dea20e6d480a74520f29dd
+size 10872