Uploaded from W&B

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</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
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "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
+}

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"
+}

model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:733d1ad4b591a1e0ea3f24761a4b6d0e99d07f0186201dd2788265b6a256b305
+size 4984780784

model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccdcb7db2051bb04578c15fbc8de0908dc382e2e0c11d12e841a659b060a362
+size 4980892048

model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64e3bf40e26d50d168975db66ec0be143153d22ac74b8dab5ed7bb399b25352f
+size 4928485104

model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd527b82bf98c9aa46042138f842cfcae9ee3f0029cb362d556a8d2344a907a0
+size 4980892112

model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a27920d463f37058f3a01ef15e895935a14b076f65075ce57c76fce4775d593
+size 4928485104

model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bae46196571919129ce0bff9017fd324fa4833a01cb82bd6e1d392fa68c3ad9a
+size 4733130504

model.safetensors.index.json

@@ -0,0 +1,450 @@
+{
+  "metadata": {
+    "total_size": 29536614400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1962 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 27,
+  "global_step": 264,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007575757575757576,
+      "grad_norm": 1.3283417224884033,
+      "learning_rate": 0.0,
+      "loss": 0.4143,
+      "step": 1
+    },
+    {
+      "epoch": 0.007575757575757576,
+      "eval_loss": 0.4484974443912506,
+      "eval_runtime": 4.6204,
+      "eval_samples_per_second": 9.739,
+      "eval_steps_per_second": 0.649,
+      "step": 1
+    },
+    {
+      "epoch": 0.015151515151515152,
+      "grad_norm": 1.3961235284805298,
+      "learning_rate": 3.0000000000000004e-08,
+      "loss": 0.4409,
+      "step": 2
+    },
+    {
+      "epoch": 0.022727272727272728,
+      "grad_norm": 1.449282169342041,
+      "learning_rate": 6.000000000000001e-08,
+      "loss": 0.4237,
+      "step": 3
+    },
+    {
+      "epoch": 0.030303030303030304,
+      "grad_norm": 1.5465986728668213,
+      "learning_rate": 9e-08,
+      "loss": 0.4423,
+      "step": 4
+    },
+    {
+      "epoch": 0.03787878787878788,
+      "grad_norm": 1.4676655530929565,
+      "learning_rate": 1.2000000000000002e-07,
+      "loss": 0.4679,
+      "step": 5
+    },
+    {
+      "epoch": 0.045454545454545456,
+      "grad_norm": 1.4171987771987915,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.4126,
+      "step": 6
+    },
+    {
+      "epoch": 0.05303030303030303,
+      "grad_norm": 1.4400802850723267,
+      "learning_rate": 1.8e-07,
+      "loss": 0.4391,
+      "step": 7
+    },
+    {
+      "epoch": 0.06060606060606061,
+      "grad_norm": 1.304193377494812,
+      "learning_rate": 2.1000000000000003e-07,
+      "loss": 0.4251,
+      "step": 8
+    },
+    {
+      "epoch": 0.06818181818181818,
+      "grad_norm": 1.445847749710083,
+      "learning_rate": 2.4000000000000003e-07,
+      "loss": 0.44,
+      "step": 9
+    },
+    {
+      "epoch": 0.07575757575757576,
+      "grad_norm": 1.390260934829712,
+      "learning_rate": 2.7e-07,
+      "loss": 0.4455,
+      "step": 10
+    },
+    {
+      "epoch": 0.08333333333333333,
+      "grad_norm": 1.4599530696868896,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 0.451,
+      "step": 11
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 1.554587960243225,
+      "learning_rate": 3.3e-07,
+      "loss": 0.4501,
+      "step": 12
+    },
+    {
+      "epoch": 0.09848484848484848,
+      "grad_norm": 1.4988254308700562,
+      "learning_rate": 3.6e-07,
+      "loss": 0.477,
+      "step": 13
+    },
+    {
+      "epoch": 0.10606060606060606,
+      "grad_norm": 1.510806679725647,
+      "learning_rate": 3.9e-07,
+      "loss": 0.4543,
+      "step": 14
+    },
+    {
+      "epoch": 0.11363636363636363,
+      "grad_norm": 1.270984172821045,
+      "learning_rate": 4.2000000000000006e-07,
+      "loss": 0.4268,
+      "step": 15
+    },
+    {
+      "epoch": 0.12121212121212122,
+      "grad_norm": 1.2247107028961182,
+      "learning_rate": 4.5e-07,
+      "loss": 0.3925,
+      "step": 16
+    },
+    {
+      "epoch": 0.12878787878787878,
+      "grad_norm": 1.3379729986190796,
+      "learning_rate": 4.800000000000001e-07,
+      "loss": 0.437,
+      "step": 17
+    },
+    {
+      "epoch": 0.13636363636363635,
+      "grad_norm": 1.2792962789535522,
+      "learning_rate": 5.100000000000001e-07,
+      "loss": 0.4405,
+      "step": 18
+    },
+    {
+      "epoch": 0.14393939393939395,
+      "grad_norm": 1.1307419538497925,
+      "learning_rate": 5.4e-07,
+      "loss": 0.4169,
+      "step": 19
+    },
+    {
+      "epoch": 0.15151515151515152,
+      "grad_norm": 1.1039320230484009,
+      "learning_rate": 5.7e-07,
+      "loss": 0.4004,
+      "step": 20
+    },
+    {
+      "epoch": 0.1590909090909091,
+      "grad_norm": 1.3360621929168701,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.4481,
+      "step": 21
+    },
+    {
+      "epoch": 0.16666666666666666,
+      "grad_norm": 1.1867090463638306,
+      "learning_rate": 6.3e-07,
+      "loss": 0.412,
+      "step": 22
+    },
+    {
+      "epoch": 0.17424242424242425,
+      "grad_norm": 1.1521047353744507,
+      "learning_rate": 6.6e-07,
+      "loss": 0.4452,
+      "step": 23
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 1.0933047533035278,
+      "learning_rate": 6.900000000000001e-07,
+      "loss": 0.4037,
+      "step": 24
+    },
+    {
+      "epoch": 0.1893939393939394,
+      "grad_norm": 0.9085134863853455,
+      "learning_rate": 7.2e-07,
+      "loss": 0.4254,
+      "step": 25
+    },
+    {
+      "epoch": 0.19696969696969696,
+      "grad_norm": 0.8757545351982117,
+      "learning_rate": 7.5e-07,
+      "loss": 0.3814,
+      "step": 26
+    },
+    {
+      "epoch": 0.20454545454545456,
+      "grad_norm": 0.8677803874015808,
+      "learning_rate": 7.8e-07,
+      "loss": 0.4055,
+      "step": 27
+    },
+    {
+      "epoch": 0.20454545454545456,
+      "eval_loss": 0.3944890797138214,
+      "eval_runtime": 3.7697,
+      "eval_samples_per_second": 11.937,
+      "eval_steps_per_second": 0.796,
+      "step": 27
+    },
+    {
+      "epoch": 0.21212121212121213,
+      "grad_norm": 0.8824054002761841,
+      "learning_rate": 8.100000000000001e-07,
+      "loss": 0.3872,
+      "step": 28
+    },
+    {
+      "epoch": 0.2196969696969697,
+      "grad_norm": 0.7678095102310181,
+      "learning_rate": 8.400000000000001e-07,
+      "loss": 0.3732,
+      "step": 29
+    },
+    {
+      "epoch": 0.22727272727272727,
+      "grad_norm": 0.7380478382110596,
+      "learning_rate": 8.699999999999999e-07,
+      "loss": 0.3756,
+      "step": 30
+    },
+    {
+      "epoch": 0.23484848484848486,
+      "grad_norm": 0.8654037117958069,
+      "learning_rate": 9e-07,
+      "loss": 0.3878,
+      "step": 31
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.8067331910133362,
+      "learning_rate": 9.3e-07,
+      "loss": 0.3908,
+      "step": 32
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.8579528331756592,
+      "learning_rate": 9.600000000000001e-07,
+      "loss": 0.4066,
+      "step": 33
+    },
+    {
+      "epoch": 0.25757575757575757,
+      "grad_norm": 0.7353713512420654,
+      "learning_rate": 9.9e-07,
+      "loss": 0.3732,
+      "step": 34
+    },
+    {
+      "epoch": 0.26515151515151514,
+      "grad_norm": 0.6627735495567322,
+      "learning_rate": 1.0200000000000002e-06,
+      "loss": 0.3382,
+      "step": 35
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 0.6454169750213623,
+      "learning_rate": 1.05e-06,
+      "loss": 0.3135,
+      "step": 36
+    },
+    {
+      "epoch": 0.2803030303030303,
+      "grad_norm": 0.6702368855476379,
+      "learning_rate": 1.08e-06,
+      "loss": 0.3447,
+      "step": 37
+    },
+    {
+      "epoch": 0.2878787878787879,
+      "grad_norm": 0.645977795124054,
+      "learning_rate": 1.11e-06,
+      "loss": 0.3562,
+      "step": 38
+    },
+    {
+      "epoch": 0.29545454545454547,
+      "grad_norm": 0.5999881625175476,
+      "learning_rate": 1.14e-06,
+      "loss": 0.3366,
+      "step": 39
+    },
+    {
+      "epoch": 0.30303030303030304,
+      "grad_norm": 0.5902673006057739,
+      "learning_rate": 1.17e-06,
+      "loss": 0.3596,
+      "step": 40
+    },
+    {
+      "epoch": 0.3106060606060606,
+      "grad_norm": 0.5958601832389832,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.349,
+      "step": 41
+    },
+    {
+      "epoch": 0.3181818181818182,
+      "grad_norm": 0.5236920118331909,
+      "learning_rate": 1.2299999999999999e-06,
+      "loss": 0.3148,
+      "step": 42
+    },
+    {
+      "epoch": 0.32575757575757575,
+      "grad_norm": 0.5363168120384216,
+      "learning_rate": 1.26e-06,
+      "loss": 0.332,
+      "step": 43
+    },
+    {
+      "epoch": 0.3333333333333333,
+      "grad_norm": 0.5424143671989441,
+      "learning_rate": 1.29e-06,
+      "loss": 0.3316,
+      "step": 44
+    },
+    {
+      "epoch": 0.3409090909090909,
+      "grad_norm": 0.5639642477035522,
+      "learning_rate": 1.32e-06,
+      "loss": 0.3188,
+      "step": 45
+    },
+    {
+      "epoch": 0.3484848484848485,
+      "grad_norm": 0.5987851619720459,
+      "learning_rate": 1.35e-06,
+      "loss": 0.2883,
+      "step": 46
+    },
+    {
+      "epoch": 0.3560606060606061,
+      "grad_norm": 0.5352199673652649,
+      "learning_rate": 1.3800000000000001e-06,
+      "loss": 0.2668,
+      "step": 47
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 0.831302285194397,
+      "learning_rate": 1.41e-06,
+      "loss": 0.2921,
+      "step": 48
+    },
+    {
+      "epoch": 0.3712121212121212,
+      "grad_norm": 0.5643541216850281,
+      "learning_rate": 1.44e-06,
+      "loss": 0.2829,
+      "step": 49
+    },
+    {
+      "epoch": 0.3787878787878788,
+      "grad_norm": 0.7044408321380615,
+      "learning_rate": 1.4700000000000001e-06,
+      "loss": 0.2863,
+      "step": 50
+    },
+    {
+      "epoch": 0.38636363636363635,
+      "grad_norm": 0.4754178822040558,
+      "learning_rate": 1.5e-06,
+      "loss": 0.2763,
+      "step": 51
+    },
+    {
+      "epoch": 0.3939393939393939,
+      "grad_norm": 0.4912967085838318,
+      "learning_rate": 1.53e-06,
+      "loss": 0.3328,
+      "step": 52
+    },
+    {
+      "epoch": 0.4015151515151515,
+      "grad_norm": 0.4431014358997345,
+      "learning_rate": 1.56e-06,
+      "loss": 0.2962,
+      "step": 53
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "grad_norm": 0.4252887964248657,
+      "learning_rate": 1.59e-06,
+      "loss": 0.2827,
+      "step": 54
+    },
+    {
+      "epoch": 0.4090909090909091,
+      "eval_loss": 0.27877840399742126,
+      "eval_runtime": 3.9092,
+      "eval_samples_per_second": 11.511,
+      "eval_steps_per_second": 0.767,
+      "step": 54
+    },
+    {
+      "epoch": 0.4166666666666667,
+      "grad_norm": 0.42729446291923523,
+      "learning_rate": 1.6200000000000002e-06,
+      "loss": 0.2732,
+      "step": 55
+    },
+    {
+      "epoch": 0.42424242424242425,
+      "grad_norm": 0.4075598418712616,
+      "learning_rate": 1.65e-06,
+      "loss": 0.2618,
+      "step": 56
+    },
+    {
+      "epoch": 0.4318181818181818,
+      "grad_norm": 0.40114349126815796,
+      "learning_rate": 1.6800000000000002e-06,
+      "loss": 0.2767,
+      "step": 57
+    },
+    {
+      "epoch": 0.4393939393939394,
+      "grad_norm": 0.4322529137134552,
+      "learning_rate": 1.71e-06,
+      "loss": 0.2704,
+      "step": 58
+    },
+    {
+      "epoch": 0.44696969696969696,
+      "grad_norm": 0.37781625986099243,
+      "learning_rate": 1.7399999999999999e-06,
+      "loss": 0.2648,
+      "step": 59
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 0.3737211525440216,
+      "learning_rate": 1.77e-06,
+      "loss": 0.2679,
+      "step": 60
+    },
+    {
+      "epoch": 0.4621212121212121,
+      "grad_norm": 0.43071067333221436,
+      "learning_rate": 1.8e-06,
+      "loss": 0.3099,
+      "step": 61
+    },
+    {
+      "epoch": 0.4696969696969697,
+      "grad_norm": 0.403502494096756,
+      "learning_rate": 1.83e-06,
+      "loss": 0.2608,
+      "step": 62
+    },
+    {
+      "epoch": 0.4772727272727273,
+      "grad_norm": 0.3696764409542084,
+      "learning_rate": 1.86e-06,
+      "loss": 0.2706,
+      "step": 63
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.39039525389671326,
+      "learning_rate": 1.8900000000000001e-06,
+      "loss": 0.2643,
+      "step": 64
+    },
+    {
+      "epoch": 0.49242424242424243,
+      "grad_norm": 0.3760799467563629,
+      "learning_rate": 1.9200000000000003e-06,
+      "loss": 0.278,
+      "step": 65
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.3563688099384308,
+      "learning_rate": 1.95e-06,
+      "loss": 0.257,
+      "step": 66
+    },
+    {
+      "epoch": 0.5075757575757576,
+      "grad_norm": 0.4797223210334778,
+      "learning_rate": 1.98e-06,
+      "loss": 0.2872,
+      "step": 67
+    },
+    {
+      "epoch": 0.5151515151515151,
+      "grad_norm": 0.3515148460865021,
+      "learning_rate": 2.0100000000000002e-06,
+      "loss": 0.2547,
+      "step": 68
+    },
+    {
+      "epoch": 0.5227272727272727,
+      "grad_norm": 0.3484012484550476,
+      "learning_rate": 2.0400000000000004e-06,
+      "loss": 0.2586,
+      "step": 69
+    },
+    {
+      "epoch": 0.5303030303030303,
+      "grad_norm": 0.3298349380493164,
+      "learning_rate": 2.07e-06,
+      "loss": 0.2412,
+      "step": 70
+    },
+    {
+      "epoch": 0.5378787878787878,
+      "grad_norm": 0.36822959780693054,
+      "learning_rate": 2.1e-06,
+      "loss": 0.2537,
+      "step": 71
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 0.37264522910118103,
+      "learning_rate": 2.13e-06,
+      "loss": 0.2446,
+      "step": 72
+    },
+    {
+      "epoch": 0.553030303030303,
+      "grad_norm": 0.36304572224617004,
+      "learning_rate": 2.16e-06,
+      "loss": 0.265,
+      "step": 73
+    },
+    {
+      "epoch": 0.5606060606060606,
+      "grad_norm": 0.3426221013069153,
+      "learning_rate": 2.19e-06,
+      "loss": 0.2502,
+      "step": 74
+    },
+    {
+      "epoch": 0.5681818181818182,
+      "grad_norm": 0.36188438534736633,
+      "learning_rate": 2.22e-06,
+      "loss": 0.2577,
+      "step": 75
+    },
+    {
+      "epoch": 0.5757575757575758,
+      "grad_norm": 0.3483147621154785,
+      "learning_rate": 2.25e-06,
+      "loss": 0.2372,
+      "step": 76
+    },
+    {
+      "epoch": 0.5833333333333334,
+      "grad_norm": 0.32986128330230713,
+      "learning_rate": 2.28e-06,
+      "loss": 0.2341,
+      "step": 77
+    },
+    {
+      "epoch": 0.5909090909090909,
+      "grad_norm": 0.4219978153705597,
+      "learning_rate": 2.31e-06,
+      "loss": 0.2385,
+      "step": 78
+    },
+    {
+      "epoch": 0.5984848484848485,
+      "grad_norm": 0.36854755878448486,
+      "learning_rate": 2.34e-06,
+      "loss": 0.2512,
+      "step": 79
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 0.360362708568573,
+      "learning_rate": 2.37e-06,
+      "loss": 0.2493,
+      "step": 80
+    },
+    {
+      "epoch": 0.6136363636363636,
+      "grad_norm": 0.3742498755455017,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.2545,
+      "step": 81
+    },
+    {
+      "epoch": 0.6136363636363636,
+      "eval_loss": 0.2342466115951538,
+      "eval_runtime": 3.7547,
+      "eval_samples_per_second": 11.985,
+      "eval_steps_per_second": 0.799,
+      "step": 81
+    },
+    {
+      "epoch": 0.6212121212121212,
+      "grad_norm": 0.35598456859588623,
+      "learning_rate": 2.43e-06,
+      "loss": 0.221,
+      "step": 82
+    },
+    {
+      "epoch": 0.6287878787878788,
+      "grad_norm": 0.33837515115737915,
+      "learning_rate": 2.4599999999999997e-06,
+      "loss": 0.2227,
+      "step": 83
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 0.32989123463630676,
+      "learning_rate": 2.49e-06,
+      "loss": 0.2133,
+      "step": 84
+    },
+    {
+      "epoch": 0.6439393939393939,
+      "grad_norm": 0.35090968012809753,
+      "learning_rate": 2.52e-06,
+      "loss": 0.2475,
+      "step": 85
+    },
+    {
+      "epoch": 0.6515151515151515,
+      "grad_norm": 0.3564332127571106,
+      "learning_rate": 2.55e-06,
+      "loss": 0.2284,
+      "step": 86
+    },
+    {
+      "epoch": 0.6590909090909091,
+      "grad_norm": 0.3637895882129669,
+      "learning_rate": 2.58e-06,
+      "loss": 0.2296,
+      "step": 87
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.3655780851840973,
+      "learning_rate": 2.61e-06,
+      "loss": 0.2554,
+      "step": 88
+    },
+    {
+      "epoch": 0.6742424242424242,
+      "grad_norm": 0.35350096225738525,
+      "learning_rate": 2.64e-06,
+      "loss": 0.2548,
+      "step": 89
+    },
+    {
+      "epoch": 0.6818181818181818,
+      "grad_norm": 0.36496269702911377,
+      "learning_rate": 2.6700000000000003e-06,
+      "loss": 0.2437,
+      "step": 90
+    },
+    {
+      "epoch": 0.6893939393939394,
+      "grad_norm": 0.3612903654575348,
+      "learning_rate": 2.7e-06,
+      "loss": 0.247,
+      "step": 91
+    },
+    {
+      "epoch": 0.696969696969697,
+      "grad_norm": 0.32694000005722046,
+      "learning_rate": 2.73e-06,
+      "loss": 0.232,
+      "step": 92
+    },
+    {
+      "epoch": 0.7045454545454546,
+      "grad_norm": 0.3464793860912323,
+      "learning_rate": 2.7600000000000003e-06,
+      "loss": 0.2345,
+      "step": 93
+    },
+    {
+      "epoch": 0.7121212121212122,
+      "grad_norm": 0.3449086546897888,
+      "learning_rate": 2.7900000000000004e-06,
+      "loss": 0.2236,
+      "step": 94
+    },
+    {
+      "epoch": 0.7196969696969697,
+      "grad_norm": 0.3284997344017029,
+      "learning_rate": 2.82e-06,
+      "loss": 0.2192,
+      "step": 95
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.367760568857193,
+      "learning_rate": 2.85e-06,
+      "loss": 0.228,
+      "step": 96
+    },
+    {
+      "epoch": 0.7348484848484849,
+      "grad_norm": 0.3416701555252075,
+      "learning_rate": 2.88e-06,
+      "loss": 0.2104,
+      "step": 97
+    },
+    {
+      "epoch": 0.7424242424242424,
+      "grad_norm": 0.33400392532348633,
+      "learning_rate": 2.91e-06,
+      "loss": 0.2405,
+      "step": 98
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.3645849823951721,
+      "learning_rate": 2.9400000000000002e-06,
+      "loss": 0.2138,
+      "step": 99
+    },
+    {
+      "epoch": 0.7575757575757576,
+      "grad_norm": 0.4128020703792572,
+      "learning_rate": 2.97e-06,
+      "loss": 0.2252,
+      "step": 100
+    },
+    {
+      "epoch": 0.7651515151515151,
+      "grad_norm": 0.3398718535900116,
+      "learning_rate": 3e-06,
+      "loss": 0.2236,
+      "step": 101
+    },
+    {
+      "epoch": 0.7727272727272727,
+      "grad_norm": 0.34870442748069763,
+      "learning_rate": 2.999915516186367e-06,
+      "loss": 0.2177,
+      "step": 102
+    },
+    {
+      "epoch": 0.7803030303030303,
+      "grad_norm": 0.3742092549800873,
+      "learning_rate": 2.9996620742621543e-06,
+      "loss": 0.2231,
+      "step": 103
+    },
+    {
+      "epoch": 0.7878787878787878,
+      "grad_norm": 0.3324211537837982,
+      "learning_rate": 2.9992397027763487e-06,
+      "loss": 0.2301,
+      "step": 104
+    },
+    {
+      "epoch": 0.7954545454545454,
+      "grad_norm": 0.3623178005218506,
+      "learning_rate": 2.9986484493070226e-06,
+      "loss": 0.2443,
+      "step": 105
+    },
+    {
+      "epoch": 0.803030303030303,
+      "grad_norm": 0.32361772656440735,
+      "learning_rate": 2.997888380455972e-06,
+      "loss": 0.2084,
+      "step": 106
+    },
+    {
+      "epoch": 0.8106060606060606,
+      "grad_norm": 0.2985866069793701,
+      "learning_rate": 2.996959581841219e-06,
+      "loss": 0.1787,
+      "step": 107
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 0.3364095389842987,
+      "learning_rate": 2.9958621580873606e-06,
+      "loss": 0.2279,
+      "step": 108
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "eval_loss": 0.21483248472213745,
+      "eval_runtime": 3.8156,
+      "eval_samples_per_second": 11.794,
+      "eval_steps_per_second": 0.786,
+      "step": 108
+    },
+    {
+      "epoch": 0.8257575757575758,
+      "grad_norm": 0.3655584156513214,
+      "learning_rate": 2.99459623281379e-06,
+      "loss": 0.2167,
+      "step": 109
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.3509344160556793,
+      "learning_rate": 2.993161948620766e-06,
+      "loss": 0.2331,
+      "step": 110
+    },
+    {
+      "epoch": 0.8409090909090909,
+      "grad_norm": 0.3420751988887787,
+      "learning_rate": 2.991559467073354e-06,
+      "loss": 0.2249,
+      "step": 111
+    },
+    {
+      "epoch": 0.8484848484848485,
+      "grad_norm": 0.36244380474090576,
+      "learning_rate": 2.989788968683223e-06,
+      "loss": 0.2342,
+      "step": 112
+    },
+    {
+      "epoch": 0.8560606060606061,
+      "grad_norm": 0.3350719213485718,
+      "learning_rate": 2.987850652888315e-06,
+      "loss": 0.2149,
+      "step": 113
+    },
+    {
+      "epoch": 0.8636363636363636,
+      "grad_norm": 0.33088400959968567,
+      "learning_rate": 2.985744738030378e-06,
+      "loss": 0.2308,
+      "step": 114
+    },
+    {
+      "epoch": 0.8712121212121212,
+      "grad_norm": 0.35577788949012756,
+      "learning_rate": 2.9834714613303683e-06,
+      "loss": 0.2309,
+      "step": 115
+    },
+    {
+      "epoch": 0.8787878787878788,
+      "grad_norm": 0.33692941069602966,
+      "learning_rate": 2.981031078861733e-06,
+      "loss": 0.2206,
+      "step": 116
+    },
+    {
+      "epoch": 0.8863636363636364,
+      "grad_norm": 0.30027806758880615,
+      "learning_rate": 2.978423865521563e-06,
+      "loss": 0.1778,
+      "step": 117
+    },
+    {
+      "epoch": 0.8939393939393939,
+      "grad_norm": 0.33589160442352295,
+      "learning_rate": 2.9756501149996258e-06,
+      "loss": 0.2064,
+      "step": 118
+    },
+    {
+      "epoch": 0.9015151515151515,
+      "grad_norm": 0.3447880446910858,
+      "learning_rate": 2.972710139745284e-06,
+      "loss": 0.2269,
+      "step": 119
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 0.3275374174118042,
+      "learning_rate": 2.9696042709323e-06,
+      "loss": 0.2146,
+      "step": 120
+    },
+    {
+      "epoch": 0.9166666666666666,
+      "grad_norm": 0.3791568875312805,
+      "learning_rate": 2.9663328584215296e-06,
+      "loss": 0.2452,
+      "step": 121
+    },
+    {
+      "epoch": 0.9242424242424242,
+      "grad_norm": 0.3592163920402527,
+      "learning_rate": 2.9628962707215127e-06,
+      "loss": 0.2514,
+      "step": 122
+    },
+    {
+      "epoch": 0.9318181818181818,
+      "grad_norm": 0.3707539737224579,
+      "learning_rate": 2.9592948949469618e-06,
+      "loss": 0.2324,
+      "step": 123
+    },
+    {
+      "epoch": 0.9393939393939394,
+      "grad_norm": 0.3237663209438324,
+      "learning_rate": 2.9555291367751577e-06,
+      "loss": 0.2035,
+      "step": 124
+    },
+    {
+      "epoch": 0.946969696969697,
+      "grad_norm": 0.373311847448349,
+      "learning_rate": 2.9515994204002487e-06,
+      "loss": 0.2095,
+      "step": 125
+    },
+    {
+      "epoch": 0.9545454545454546,
+      "grad_norm": 0.3151170015335083,
+      "learning_rate": 2.9475061884854686e-06,
+      "loss": 0.2034,
+      "step": 126
+    },
+    {
+      "epoch": 0.9621212121212122,
+      "grad_norm": 0.31887397170066833,
+      "learning_rate": 2.943249902113274e-06,
+      "loss": 0.2139,
+      "step": 127
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.3232063353061676,
+      "learning_rate": 2.9388310407334053e-06,
+      "loss": 0.1973,
+      "step": 128
+    },
+    {
+      "epoch": 0.9772727272727273,
+      "grad_norm": 0.31135034561157227,
+      "learning_rate": 2.9342501021088764e-06,
+      "loss": 0.1966,
+      "step": 129
+    },
+    {
+      "epoch": 0.9848484848484849,
+      "grad_norm": 0.3399612307548523,
+      "learning_rate": 2.929507602259908e-06,
+      "loss": 0.2182,
+      "step": 130
+    },
+    {
+      "epoch": 0.9924242424242424,
+      "grad_norm": 0.3196345567703247,
+      "learning_rate": 2.924604075405798e-06,
+      "loss": 0.1989,
+      "step": 131
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.32773980498313904,
+      "learning_rate": 2.919540073904744e-06,
+      "loss": 0.2204,
+      "step": 132
+    },
+    {
+      "epoch": 1.0075757575757576,
+      "grad_norm": 0.2987237572669983,
+      "learning_rate": 2.9143161681916264e-06,
+      "loss": 0.2057,
+      "step": 133
+    },
+    {
+      "epoch": 1.0151515151515151,
+      "grad_norm": 0.3353113532066345,
+      "learning_rate": 2.908932946713746e-06,
+      "loss": 0.2168,
+      "step": 134
+    },
+    {
+      "epoch": 1.0227272727272727,
+      "grad_norm": 0.3060712516307831,
+      "learning_rate": 2.903391015864543e-06,
+      "loss": 0.201,
+      "step": 135
+    },
+    {
+      "epoch": 1.0227272727272727,
+      "eval_loss": 0.20574720203876495,
+      "eval_runtime": 4.0962,
+      "eval_samples_per_second": 10.986,
+      "eval_steps_per_second": 0.732,
+      "step": 135
+    },
+    {
+      "epoch": 1.0303030303030303,
+      "grad_norm": 0.30177003145217896,
+      "learning_rate": 2.8976909999152893e-06,
+      "loss": 0.2079,
+      "step": 136
+    },
+    {
+      "epoch": 1.0378787878787878,
+      "grad_norm": 0.3422546684741974,
+      "learning_rate": 2.891833540944764e-06,
+      "loss": 0.2327,
+      "step": 137
+    },
+    {
+      "epoch": 1.0454545454545454,
+      "grad_norm": 0.3491850793361664,
+      "learning_rate": 2.88581929876693e-06,
+      "loss": 0.1927,
+      "step": 138
+    },
+    {
+      "epoch": 1.053030303030303,
+      "grad_norm": 0.3588053584098816,
+      "learning_rate": 2.879648950856608e-06,
+      "loss": 0.2106,
+      "step": 139
+    },
+    {
+      "epoch": 1.0606060606060606,
+      "grad_norm": 0.3346102833747864,
+      "learning_rate": 2.873323192273162e-06,
+      "loss": 0.2087,
+      "step": 140
+    },
+    {
+      "epoch": 1.0681818181818181,
+      "grad_norm": 0.33741819858551025,
+      "learning_rate": 2.866842735582204e-06,
+      "loss": 0.208,
+      "step": 141
+    },
+    {
+      "epoch": 1.0757575757575757,
+      "grad_norm": 0.3306257128715515,
+      "learning_rate": 2.8602083107753274e-06,
+      "loss": 0.2217,
+      "step": 142
+    },
+    {
+      "epoch": 1.0833333333333333,
+      "grad_norm": 0.31300610303878784,
+      "learning_rate": 2.853420665187878e-06,
+      "loss": 0.2174,
+      "step": 143
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.31147757172584534,
+      "learning_rate": 2.846480563414769e-06,
+      "loss": 0.2103,
+      "step": 144
+    },
+    {
+      "epoch": 1.0984848484848484,
+      "grad_norm": 0.32579827308654785,
+      "learning_rate": 2.8393887872243527e-06,
+      "loss": 0.2377,
+      "step": 145
+    },
+    {
+      "epoch": 1.106060606060606,
+      "grad_norm": 0.35583895444869995,
+      "learning_rate": 2.8321461354703605e-06,
+      "loss": 0.2139,
+      "step": 146
+    },
+    {
+      "epoch": 1.1136363636363635,
+      "grad_norm": 0.31982478499412537,
+      "learning_rate": 2.824753424001914e-06,
+      "loss": 0.2117,
+      "step": 147
+    },
+    {
+      "epoch": 1.121212121212121,
+      "grad_norm": 0.3036634624004364,
+      "learning_rate": 2.8172114855716235e-06,
+      "loss": 0.1867,
+      "step": 148
+    },
+    {
+      "epoch": 1.128787878787879,
+      "grad_norm": 0.34311625361442566,
+      "learning_rate": 2.8095211697417823e-06,
+      "loss": 0.2221,
+      "step": 149
+    },
+    {
+      "epoch": 1.1363636363636362,
+      "grad_norm": 0.3297724723815918,
+      "learning_rate": 2.801683342788671e-06,
+      "loss": 0.216,
+      "step": 150
+    },
+    {
+      "epoch": 1.143939393939394,
+      "grad_norm": 0.30701613426208496,
+      "learning_rate": 2.7936988876049708e-06,
+      "loss": 0.204,
+      "step": 151
+    },
+    {
+      "epoch": 1.1515151515151516,
+      "grad_norm": 0.3359236419200897,
+      "learning_rate": 2.785568703600314e-06,
+      "loss": 0.195,
+      "step": 152
+    },
+    {
+      "epoch": 1.1590909090909092,
+      "grad_norm": 0.3641625642776489,
+      "learning_rate": 2.777293706599967e-06,
+      "loss": 0.2144,
+      "step": 153
+    },
+    {
+      "epoch": 1.1666666666666667,
+      "grad_norm": 0.3085581660270691,
+      "learning_rate": 2.7688748287416693e-06,
+      "loss": 0.1971,
+      "step": 154
+    },
+    {
+      "epoch": 1.1742424242424243,
+      "grad_norm": 0.36984890699386597,
+      "learning_rate": 2.7603130183706316e-06,
+      "loss": 0.2262,
+      "step": 155
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 0.3120734393596649,
+      "learning_rate": 2.7516092399327093e-06,
+      "loss": 0.1977,
+      "step": 156
+    },
+    {
+      "epoch": 1.1893939393939394,
+      "grad_norm": 0.7143038511276245,
+      "learning_rate": 2.7427644738657634e-06,
+      "loss": 0.2276,
+      "step": 157
+    },
+    {
+      "epoch": 1.196969696969697,
+      "grad_norm": 0.3517268896102905,
+      "learning_rate": 2.733779716489217e-06,
+      "loss": 0.1914,
+      "step": 158
+    },
+    {
+      "epoch": 1.2045454545454546,
+      "grad_norm": 0.34322699904441833,
+      "learning_rate": 2.7246559798918283e-06,
+      "loss": 0.218,
+      "step": 159
+    },
+    {
+      "epoch": 1.2121212121212122,
+      "grad_norm": 0.32622596621513367,
+      "learning_rate": 2.71539429181768e-06,
+      "loss": 0.1981,
+      "step": 160
+    },
+    {
+      "epoch": 1.2196969696969697,
+      "grad_norm": 0.3444068729877472,
+      "learning_rate": 2.705995695550411e-06,
+      "loss": 0.2008,
+      "step": 161
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "grad_norm": 0.31855490803718567,
+      "learning_rate": 2.696461249795695e-06,
+      "loss": 0.2016,
+      "step": 162
+    },
+    {
+      "epoch": 1.2272727272727273,
+      "eval_loss": 0.19937294721603394,
+      "eval_runtime": 3.8719,
+      "eval_samples_per_second": 11.622,
+      "eval_steps_per_second": 0.775,
+      "step": 162
+    },
+    {
+      "epoch": 1.2348484848484849,
+      "grad_norm": 0.32609114050865173,
+      "learning_rate": 2.6867920285619828e-06,
+      "loss": 0.2096,
+      "step": 163
+    },
+    {
+      "epoch": 1.2424242424242424,
+      "grad_norm": 0.3202066421508789,
+      "learning_rate": 2.676989121039521e-06,
+      "loss": 0.2063,
+      "step": 164
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.3223087191581726,
+      "learning_rate": 2.6670536314776595e-06,
+      "loss": 0.2219,
+      "step": 165
+    },
+    {
+      "epoch": 1.2575757575757576,
+      "grad_norm": 0.3077775537967682,
+      "learning_rate": 2.6569866790604623e-06,
+      "loss": 0.2091,
+      "step": 166
+    },
+    {
+      "epoch": 1.2651515151515151,
+      "grad_norm": 0.3209894597530365,
+      "learning_rate": 2.646789397780639e-06,
+      "loss": 0.1945,
+      "step": 167
+    },
+    {
+      "epoch": 1.2727272727272727,
+      "grad_norm": 0.3583175837993622,
+      "learning_rate": 2.636462936311804e-06,
+      "loss": 0.1803,
+      "step": 168
+    },
+    {
+      "epoch": 1.2803030303030303,
+      "grad_norm": 0.3185870945453644,
+      "learning_rate": 2.6260084578790864e-06,
+      "loss": 0.2002,
+      "step": 169
+    },
+    {
+      "epoch": 1.2878787878787878,
+      "grad_norm": 0.31969261169433594,
+      "learning_rate": 2.615427140128096e-06,
+      "loss": 0.2113,
+      "step": 170
+    },
+    {
+      "epoch": 1.2954545454545454,
+      "grad_norm": 0.3077215850353241,
+      "learning_rate": 2.6047201749922685e-06,
+      "loss": 0.2002,
+      "step": 171
+    },
+    {
+      "epoch": 1.303030303030303,
+      "grad_norm": 0.330035924911499,
+      "learning_rate": 2.5938887685585998e-06,
+      "loss": 0.2245,
+      "step": 172
+    },
+    {
+      "epoch": 1.3106060606060606,
+      "grad_norm": 0.32292619347572327,
+      "learning_rate": 2.5829341409317867e-06,
+      "loss": 0.2144,
+      "step": 173
+    },
+    {
+      "epoch": 1.3181818181818181,
+      "grad_norm": 0.302539199590683,
+      "learning_rate": 2.571857526096788e-06,
+      "loss": 0.1969,
+      "step": 174
+    },
+    {
+      "epoch": 1.3257575757575757,
+      "grad_norm": 0.3287748694419861,
+      "learning_rate": 2.5606601717798212e-06,
+      "loss": 0.2091,
+      "step": 175
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.3326898217201233,
+      "learning_rate": 2.5493433393078135e-06,
+      "loss": 0.2055,
+      "step": 176
+    },
+    {
+      "epoch": 1.3409090909090908,
+      "grad_norm": 0.36989283561706543,
+      "learning_rate": 2.5379083034663196e-06,
+      "loss": 0.2023,
+      "step": 177
+    },
+    {
+      "epoch": 1.3484848484848486,
+      "grad_norm": 0.3084871172904968,
+      "learning_rate": 2.5263563523559204e-06,
+      "loss": 0.1855,
+      "step": 178
+    },
+    {
+      "epoch": 1.356060606060606,
+      "grad_norm": 0.2833186388015747,
+      "learning_rate": 2.5146887872471307e-06,
+      "loss": 0.1656,
+      "step": 179
+    },
+    {
+      "epoch": 1.3636363636363638,
+      "grad_norm": 0.3151361644268036,
+      "learning_rate": 2.50290692243381e-06,
+      "loss": 0.1878,
+      "step": 180
+    },
+    {
+      "epoch": 1.371212121212121,
+      "grad_norm": 0.30283328890800476,
+      "learning_rate": 2.4910120850851222e-06,
+      "loss": 0.1861,
+      "step": 181
+    },
+    {
+      "epoch": 1.378787878787879,
+      "grad_norm": 0.30020758509635925,
+      "learning_rate": 2.479005615096028e-06,
+      "loss": 0.1959,
+      "step": 182
+    },
+    {
+      "epoch": 1.3863636363636362,
+      "grad_norm": 0.3308952748775482,
+      "learning_rate": 2.466888864936359e-06,
+      "loss": 0.1815,
+      "step": 183
+    },
+    {
+      "epoch": 1.393939393939394,
+      "grad_norm": 0.35493314266204834,
+      "learning_rate": 2.4546631994984632e-06,
+      "loss": 0.2303,
+      "step": 184
+    },
+    {
+      "epoch": 1.4015151515151514,
+      "grad_norm": 0.3346848785877228,
+      "learning_rate": 2.442329995943464e-06,
+      "loss": 0.2079,
+      "step": 185
+    },
+    {
+      "epoch": 1.4090909090909092,
+      "grad_norm": 0.3430391848087311,
+      "learning_rate": 2.4298906435461193e-06,
+      "loss": 0.1977,
+      "step": 186
+    },
+    {
+      "epoch": 1.4166666666666667,
+      "grad_norm": 0.3464934229850769,
+      "learning_rate": 2.417346543538337e-06,
+      "loss": 0.1895,
+      "step": 187
+    },
+    {
+      "epoch": 1.4242424242424243,
+      "grad_norm": 0.295786589384079,
+      "learning_rate": 2.404699108951327e-06,
+      "loss": 0.1823,
+      "step": 188
+    },
+    {
+      "epoch": 1.4318181818181819,
+      "grad_norm": 0.3324595093727112,
+      "learning_rate": 2.39194976445643e-06,
+      "loss": 0.1953,
+      "step": 189
+    },
+    {
+      "epoch": 1.4318181818181819,
+      "eval_loss": 0.19519075751304626,
+      "eval_runtime": 3.7562,
+      "eval_samples_per_second": 11.98,
+      "eval_steps_per_second": 0.799,
+      "step": 189
+    },
+    {
+      "epoch": 1.4393939393939394,
+      "grad_norm": 0.31282567977905273,
+      "learning_rate": 2.3790999462046396e-06,
+      "loss": 0.1895,
+      "step": 190
+    },
+    {
+      "epoch": 1.446969696969697,
+      "grad_norm": 0.3378220498561859,
+      "learning_rate": 2.3661511016648225e-06,
+      "loss": 0.1835,
+      "step": 191
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 0.3161669075489044,
+      "learning_rate": 2.3531046894606707e-06,
+      "loss": 0.1918,
+      "step": 192
+    },
+    {
+      "epoch": 1.4621212121212122,
+      "grad_norm": 0.35834869742393494,
+      "learning_rate": 2.3399621792063933e-06,
+      "loss": 0.2308,
+      "step": 193
+    },
+    {
+      "epoch": 1.4696969696969697,
+      "grad_norm": 0.33311378955841064,
+      "learning_rate": 2.3267250513411735e-06,
+      "loss": 0.1892,
+      "step": 194
+    },
+    {
+      "epoch": 1.4772727272727273,
+      "grad_norm": 0.34119582176208496,
+      "learning_rate": 2.313394796962403e-06,
+      "loss": 0.1962,
+      "step": 195
+    },
+    {
+      "epoch": 1.4848484848484849,
+      "grad_norm": 0.3146674931049347,
+      "learning_rate": 2.2999729176577163e-06,
+      "loss": 0.1941,
+      "step": 196
+    },
+    {
+      "epoch": 1.4924242424242424,
+      "grad_norm": 0.3688969314098358,
+      "learning_rate": 2.286460925335848e-06,
+      "loss": 0.2075,
+      "step": 197
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.3341940939426422,
+      "learning_rate": 2.2728603420563177e-06,
+      "loss": 0.1914,
+      "step": 198
+    },
+    {
+      "epoch": 1.5075757575757576,
+      "grad_norm": 0.3501006066799164,
+      "learning_rate": 2.2591726998579847e-06,
+      "loss": 0.2187,
+      "step": 199
+    },
+    {
+      "epoch": 1.5151515151515151,
+      "grad_norm": 0.3143168091773987,
+      "learning_rate": 2.245399540586464e-06,
+      "loss": 0.19,
+      "step": 200
+    },
+    {
+      "epoch": 1.5227272727272727,
+      "grad_norm": 0.34771814942359924,
+      "learning_rate": 2.231542415720452e-06,
+      "loss": 0.1963,
+      "step": 201
+    },
+    {
+      "epoch": 1.5303030303030303,
+      "grad_norm": 0.2961455285549164,
+      "learning_rate": 2.2176028861969536e-06,
+      "loss": 0.182,
+      "step": 202
+    },
+    {
+      "epoch": 1.5378787878787878,
+      "grad_norm": 0.33416032791137695,
+      "learning_rate": 2.2035825222354556e-06,
+      "loss": 0.1957,
+      "step": 203
+    },
+    {
+      "epoch": 1.5454545454545454,
+      "grad_norm": 0.3191990256309509,
+      "learning_rate": 2.1894829031610454e-06,
+      "loss": 0.1838,
+      "step": 204
+    },
+    {
+      "epoch": 1.553030303030303,
+      "grad_norm": 0.3659611642360687,
+      "learning_rate": 2.17530561722651e-06,
+      "loss": 0.2049,
+      "step": 205
+    },
+    {
+      "epoch": 1.5606060606060606,
+      "grad_norm": 0.32181087136268616,
+      "learning_rate": 2.1610522614334266e-06,
+      "loss": 0.1939,
+      "step": 206
+    },
+    {
+      "epoch": 1.5681818181818183,
+      "grad_norm": 0.33514729142189026,
+      "learning_rate": 2.1467244413522676e-06,
+      "loss": 0.198,
+      "step": 207
+    },
+    {
+      "epoch": 1.5757575757575757,
+      "grad_norm": 0.3041897416114807,
+      "learning_rate": 2.1323237709415414e-06,
+      "loss": 0.1835,
+      "step": 208
+    },
+    {
+      "epoch": 1.5833333333333335,
+      "grad_norm": 0.3258063495159149,
+      "learning_rate": 2.1178518723659894e-06,
+      "loss": 0.1817,
+      "step": 209
+    },
+    {
+      "epoch": 1.5909090909090908,
+      "grad_norm": 0.32818150520324707,
+      "learning_rate": 2.103310375813853e-06,
+      "loss": 0.1882,
+      "step": 210
+    },
+    {
+      "epoch": 1.5984848484848486,
+      "grad_norm": 0.3213556706905365,
+      "learning_rate": 2.0887009193132455e-06,
+      "loss": 0.1979,
+      "step": 211
+    },
+    {
+      "epoch": 1.606060606060606,
+      "grad_norm": 0.3745511770248413,
+      "learning_rate": 2.074025148547635e-06,
+      "loss": 0.1986,
+      "step": 212
+    },
+    {
+      "epoch": 1.6136363636363638,
+      "grad_norm": 0.3967829644680023,
+      "learning_rate": 2.059284716670463e-06,
+      "loss": 0.2025,
+      "step": 213
+    },
+    {
+      "epoch": 1.621212121212121,
+      "grad_norm": 0.307931512594223,
+      "learning_rate": 2.0444812841189297e-06,
+      "loss": 0.176,
+      "step": 214
+    },
+    {
+      "epoch": 1.628787878787879,
+      "grad_norm": 0.2962440550327301,
+      "learning_rate": 2.029616518426951e-06,
+      "loss": 0.1788,
+      "step": 215
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "grad_norm": 0.2896229326725006,
+      "learning_rate": 2.0146920940373197e-06,
+      "loss": 0.1694,
+      "step": 216
+    },
+    {
+      "epoch": 1.6363636363636362,
+      "eval_loss": 0.19209322333335876,
+      "eval_runtime": 3.8052,
+      "eval_samples_per_second": 11.826,
+      "eval_steps_per_second": 0.788,
+      "step": 216
+    },
+    {
+      "epoch": 1.643939393939394,
+      "grad_norm": 1.972029209136963,
+      "learning_rate": 1.999709692113086e-06,
+      "loss": 0.1989,
+      "step": 217
+    },
+    {
+      "epoch": 1.6515151515151514,
+      "grad_norm": 0.3244214951992035,
+      "learning_rate": 1.984671000348188e-06,
+      "loss": 0.1828,
+      "step": 218
+    },
+    {
+      "epoch": 1.6590909090909092,
+      "grad_norm": 0.2895407974720001,
+      "learning_rate": 1.9695777127773334e-06,
+      "loss": 0.1864,
+      "step": 219
+    },
+    {
+      "epoch": 1.6666666666666665,
+      "grad_norm": 0.3591076731681824,
+      "learning_rate": 1.9544315295851827e-06,
+      "loss": 0.2076,
+      "step": 220
+    },
+    {
+      "epoch": 1.6742424242424243,
+      "grad_norm": 0.3215983211994171,
+      "learning_rate": 1.9392341569148255e-06,
+      "loss": 0.2097,
+      "step": 221
+    },
+    {
+      "epoch": 1.6818181818181817,
+      "grad_norm": 0.307209849357605,
+      "learning_rate": 1.923987306675597e-06,
+      "loss": 0.1987,
+      "step": 222
+    },
+    {
+      "epoch": 1.6893939393939394,
+      "grad_norm": 0.31707704067230225,
+      "learning_rate": 1.9086926963502344e-06,
+      "loss": 0.2022,
+      "step": 223
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 0.2985476553440094,
+      "learning_rate": 1.893352048801417e-06,
+      "loss": 0.1908,
+      "step": 224
+    },
+    {
+      "epoch": 1.7045454545454546,
+      "grad_norm": 0.31373029947280884,
+      "learning_rate": 1.8779670920776879e-06,
+      "loss": 0.1928,
+      "step": 225
+    },
+    {
+      "epoch": 1.7121212121212122,
+      "grad_norm": 0.2975498139858246,
+      "learning_rate": 1.8625395592188038e-06,
+      "loss": 0.1841,
+      "step": 226
+    },
+    {
+      "epoch": 1.7196969696969697,
+      "grad_norm": 0.28644615411758423,
+      "learning_rate": 1.8470711880605126e-06,
+      "loss": 0.1801,
+      "step": 227
+    },
+    {
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.3171145021915436,
+      "learning_rate": 1.831563721038795e-06,
+      "loss": 0.1893,
+      "step": 228
+    },
+    {
+      "epoch": 1.7348484848484849,
+      "grad_norm": 0.27974143624305725,
+      "learning_rate": 1.8160189049935894e-06,
+      "loss": 0.1727,
+      "step": 229
+    },
+    {
+      "epoch": 1.7424242424242424,
+      "grad_norm": 0.31066396832466125,
+      "learning_rate": 1.800438490972019e-06,
+      "loss": 0.1994,
+      "step": 230
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.28362569212913513,
+      "learning_rate": 1.7848242340311425e-06,
+      "loss": 0.1773,
+      "step": 231
+    },
+    {
+      "epoch": 1.7575757575757576,
+      "grad_norm": 0.35266178846359253,
+      "learning_rate": 1.7691778930402583e-06,
+      "loss": 0.1886,
+      "step": 232
+    },
+    {
+      "epoch": 1.7651515151515151,
+      "grad_norm": 0.2889408767223358,
+      "learning_rate": 1.7535012304827739e-06,
+      "loss": 0.185,
+      "step": 233
+    },
+    {
+      "epoch": 1.7727272727272727,
+      "grad_norm": 0.29847362637519836,
+      "learning_rate": 1.7377960122576734e-06,
+      "loss": 0.1834,
+      "step": 234
+    },
+    {
+      "epoch": 1.7803030303030303,
+      "grad_norm": 0.3321170508861542,
+      "learning_rate": 1.7220640074805974e-06,
+      "loss": 0.1862,
+      "step": 235
+    },
+    {
+      "epoch": 1.7878787878787878,
+      "grad_norm": 0.4294266998767853,
+      "learning_rate": 1.7063069882845578e-06,
+      "loss": 0.1946,
+      "step": 236
+    },
+    {
+      "epoch": 1.7954545454545454,
+      "grad_norm": 0.3279866576194763,
+      "learning_rate": 1.6905267296203183e-06,
+      "loss": 0.2078,
+      "step": 237
+    },
+    {
+      "epoch": 1.803030303030303,
+      "grad_norm": 0.2862294018268585,
+      "learning_rate": 1.6747250090564558e-06,
+      "loss": 0.1755,
+      "step": 238
+    },
+    {
+      "epoch": 1.8106060606060606,
+      "grad_norm": 0.2822190523147583,
+      "learning_rate": 1.6589036065791241e-06,
+      "loss": 0.1484,
+      "step": 239
+    },
+    {
+      "epoch": 1.8181818181818183,
+      "grad_norm": 1.6264853477478027,
+      "learning_rate": 1.6430643043915472e-06,
+      "loss": 0.1939,
+      "step": 240
+    },
+    {
+      "epoch": 1.8257575757575757,
+      "grad_norm": 0.34288814663887024,
+      "learning_rate": 1.627208886713264e-06,
+      "loss": 0.1846,
+      "step": 241
+    },
+    {
+      "epoch": 1.8333333333333335,
+      "grad_norm": 0.32693156599998474,
+      "learning_rate": 1.6113391395791439e-06,
+      "loss": 0.1974,
+      "step": 242
+    },
+    {
+      "epoch": 1.8409090909090908,
+      "grad_norm": 0.30628105998039246,
+      "learning_rate": 1.5954568506381995e-06,
+      "loss": 0.1886,
+      "step": 243
+    },
+    {
+      "epoch": 1.8409090909090908,
+      "eval_loss": 0.1904776692390442,
+      "eval_runtime": 3.7653,
+      "eval_samples_per_second": 11.951,
+      "eval_steps_per_second": 0.797,
+      "step": 243
+    },
+    {
+      "epoch": 1.8484848484848486,
+      "grad_norm": 0.3182128965854645,
+      "learning_rate": 1.579563808952216e-06,
+      "loss": 0.1992,
+      "step": 244
+    },
+    {
+      "epoch": 1.856060606060606,
+      "grad_norm": 0.29879945516586304,
+      "learning_rate": 1.5636618047942224e-06,
+      "loss": 0.1839,
+      "step": 245
+    },
+    {
+      "epoch": 1.8636363636363638,
+      "grad_norm": 0.32079777121543884,
+      "learning_rate": 1.547752629446827e-06,
+      "loss": 0.1968,
+      "step": 246
+    },
+    {
+      "epoch": 1.871212121212121,
+      "grad_norm": 0.30363959074020386,
+      "learning_rate": 1.5318380750004354e-06,
+      "loss": 0.1975,
+      "step": 247
+    },
+    {
+      "epoch": 1.878787878787879,
+      "grad_norm": 0.30506575107574463,
+      "learning_rate": 1.5159199341513845e-06,
+      "loss": 0.1877,
+      "step": 248
+    },
+    {
+      "epoch": 1.8863636363636362,
+      "grad_norm": 0.2952151894569397,
+      "learning_rate": 1.5e-06,
+      "loss": 0.1502,
+      "step": 249
+    },
+    {
+      "epoch": 1.893939393939394,
+      "grad_norm": 0.30990463495254517,
+      "learning_rate": 1.484080065848616e-06,
+      "loss": 0.1774,
+      "step": 250
+    },
+    {
+      "epoch": 1.9015151515151514,
+      "grad_norm": 0.2962000072002411,
+      "learning_rate": 1.4681619249995647e-06,
+      "loss": 0.1951,
+      "step": 251
+    },
+    {
+      "epoch": 1.9090909090909092,
+      "grad_norm": 0.2885662615299225,
+      "learning_rate": 1.4522473705531736e-06,
+      "loss": 0.1857,
+      "step": 252
+    },
+    {
+      "epoch": 1.9166666666666665,
+      "grad_norm": 0.332658052444458,
+      "learning_rate": 1.4363381952057778e-06,
+      "loss": 0.2136,
+      "step": 253
+    },
+    {
+      "epoch": 1.9242424242424243,
+      "grad_norm": 0.322650671005249,
+      "learning_rate": 1.4204361910477844e-06,
+      "loss": 0.2193,
+      "step": 254
+    },
+    {
+      "epoch": 1.9318181818181817,
+      "grad_norm": 0.32375892996788025,
+      "learning_rate": 1.4045431493618006e-06,
+      "loss": 0.2025,
+      "step": 255
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 0.300975501537323,
+      "learning_rate": 1.3886608604208562e-06,
+      "loss": 0.1736,
+      "step": 256
+    },
+    {
+      "epoch": 1.946969696969697,
+      "grad_norm": 0.30063366889953613,
+      "learning_rate": 1.3727911132867368e-06,
+      "loss": 0.1824,
+      "step": 257
+    },
+    {
+      "epoch": 1.9545454545454546,
+      "grad_norm": 0.3479990065097809,
+      "learning_rate": 1.356935695608453e-06,
+      "loss": 0.176,
+      "step": 258
+    },
+    {
+      "epoch": 1.9621212121212122,
+      "grad_norm": 0.2887415587902069,
+      "learning_rate": 1.341096393420876e-06,
+      "loss": 0.1855,
+      "step": 259
+    },
+    {
+      "epoch": 1.9696969696969697,
+      "grad_norm": 0.29654136300086975,
+      "learning_rate": 1.3252749909435443e-06,
+      "loss": 0.1714,
+      "step": 260
+    },
+    {
+      "epoch": 1.9772727272727273,
+      "grad_norm": 0.2914469242095947,
+      "learning_rate": 1.3094732703796818e-06,
+      "loss": 0.169,
+      "step": 261
+    },
+    {
+      "epoch": 1.9848484848484849,
+      "grad_norm": 0.3069678544998169,
+      "learning_rate": 1.2936930117154427e-06,
+      "loss": 0.1912,
+      "step": 262
+    },
+    {
+      "epoch": 1.9924242424242424,
+      "grad_norm": 0.3112300634384155,
+      "learning_rate": 1.2779359925194031e-06,
+      "loss": 0.174,
+      "step": 263
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.3005240857601166,
+      "learning_rate": 1.2622039877423267e-06,
+      "loss": 0.1916,
+      "step": 264
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 396,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 132,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.809316809735668e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5be4b9c7ad237d856b18f7d40d4c3c6c85aa7dd7e7454d285a8547613325732
+size 12856