Upload fine-tuned model

.gitattributes

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

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.json

@@ -0,0 +1,3 @@
+{
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
+}

config.json

@@ -0,0 +1,65 @@
+{
+  "architectures": [
+    "Qwen2_5_VLForConditionalGeneration"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "image_token_id": 151655,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 128000,
+  "max_window_layers": 70,
+  "model_type": "qwen2_5_vl",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "mrope_section": [
+      16,
+      24,
+      24
+    ],
+    "rope_type": "default",
+    "type": "default"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "depth": 32,
+    "fullatt_block_indexes": [
+      7,
+      15,
+      23,
+      31
+    ],
+    "hidden_act": "silu",
+    "hidden_size": 1280,
+    "in_channels": 3,
+    "in_chans": 3,
+    "intermediate_size": 3420,
+    "model_type": "qwen2_5_vl",
+    "num_heads": 16,
+    "out_hidden_size": 2048,
+    "patch_size": 14,
+    "spatial_merge_size": 2,
+    "spatial_patch_size": 14,
+    "temporal_patch_size": 2,
+    "tokens_per_second": 2,
+    "torch_dtype": "bfloat16",
+    "window_size": 112
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652,
+  "vision_token_id": 151654,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 1e-06,
+  "transformers_version": "4.51.3"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ad9bf46a1a6285138b3c7a0cf1cfcebcae8f1b89a1cf2e815c2544a6712adbc
+size 4958351144

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:265e8af1de6dbb58861ef6fca73341de8c4dc53c233e23f93fe9bfcd8d754ec4
+size 4932949296

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:064af84cad543d1388e8b82799bfe6933e27b0086bcaa1586b752345ed812824
+size 3789914528

model.safetensors.index.json

@@ -0,0 +1,831 @@
+{
+  "metadata": {
+    "total_size": 13681123328
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors",
+    "visual.blocks.0.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.0.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.1.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.10.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.11.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.12.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.13.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.14.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.15.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.16.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.17.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.18.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.19.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.2.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.20.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.21.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.22.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.23.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.24.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.25.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.26.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.27.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.28.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.29.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.3.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.30.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.31.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.4.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.5.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.6.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.7.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.8.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.attn.proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.attn.proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.attn.qkv.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.attn.qkv.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.norm1.weight": "model-00001-of-00003.safetensors",
+    "visual.blocks.9.norm2.weight": "model-00001-of-00003.safetensors",
+    "visual.merger.ln_q.weight": "model-00001-of-00003.safetensors",
+    "visual.merger.mlp.0.bias": "model-00001-of-00003.safetensors",
+    "visual.merger.mlp.0.weight": "model-00001-of-00003.safetensors",
+    "visual.merger.mlp.2.bias": "model-00001-of-00003.safetensors",
+    "visual.merger.mlp.2.weight": "model-00001-of-00003.safetensors",
+    "visual.patch_embed.proj.weight": "model-00001-of-00003.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,29 @@
+{
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_processor_type": "Qwen2VLImageProcessor",
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "max_pixels": 12845056,
+  "merge_size": 2,
+  "min_pixels": 3136,
+  "patch_size": 14,
+  "processor_class": "Qwen2_5_VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "size": {
+    "longest_edge": 12845056,
+    "shortest_edge": 3136
+  },
+  "temporal_patch_size": 2
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9196a1e708bf24d6abba41cce3f8558820acc3e50f9394c5955e29eb41ffea3d
+size 14244

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,210 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "processor_class": "Qwen2_5_VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1756 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9969604863221884,
+  "eval_steps": 500,
+  "global_step": 2466,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0121580547112462,
+      "grad_norm": 5.922801494598389,
+      "learning_rate": 3.6437246963562754e-07,
+      "loss": 1.1863,
+      "step": 10
+    },
+    {
+      "epoch": 0.0243161094224924,
+      "grad_norm": 6.66644811630249,
+      "learning_rate": 7.692307692307694e-07,
+      "loss": 1.1376,
+      "step": 20
+    },
+    {
+      "epoch": 0.0364741641337386,
+      "grad_norm": 7.5532402992248535,
+      "learning_rate": 1.174089068825911e-06,
+      "loss": 1.1034,
+      "step": 30
+    },
+    {
+      "epoch": 0.0486322188449848,
+      "grad_norm": 4.451807498931885,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 1.0824,
+      "step": 40
+    },
+    {
+      "epoch": 0.060790273556231005,
+      "grad_norm": 4.282721996307373,
+      "learning_rate": 1.9838056680161946e-06,
+      "loss": 0.9437,
+      "step": 50
+    },
+    {
+      "epoch": 0.0729483282674772,
+      "grad_norm": 3.476186990737915,
+      "learning_rate": 2.3886639676113362e-06,
+      "loss": 0.8906,
+      "step": 60
+    },
+    {
+      "epoch": 0.0851063829787234,
+      "grad_norm": 2.9487781524658203,
+      "learning_rate": 2.7935222672064783e-06,
+      "loss": 0.8558,
+      "step": 70
+    },
+    {
+      "epoch": 0.0972644376899696,
+      "grad_norm": 3.981879949569702,
+      "learning_rate": 3.19838056680162e-06,
+      "loss": 0.7978,
+      "step": 80
+    },
+    {
+      "epoch": 0.1094224924012158,
+      "grad_norm": 3.0333662033081055,
+      "learning_rate": 3.6032388663967615e-06,
+      "loss": 0.7652,
+      "step": 90
+    },
+    {
+      "epoch": 0.12158054711246201,
+      "grad_norm": 2.985710859298706,
+      "learning_rate": 4.008097165991903e-06,
+      "loss": 0.7671,
+      "step": 100
+    },
+    {
+      "epoch": 0.1337386018237082,
+      "grad_norm": 2.512871026992798,
+      "learning_rate": 4.412955465587045e-06,
+      "loss": 0.7848,
+      "step": 110
+    },
+    {
+      "epoch": 0.1458966565349544,
+      "grad_norm": 3.5035741329193115,
+      "learning_rate": 4.817813765182186e-06,
+      "loss": 0.7419,
+      "step": 120
+    },
+    {
+      "epoch": 0.1580547112462006,
+      "grad_norm": 4.36132287979126,
+      "learning_rate": 5.222672064777329e-06,
+      "loss": 0.7379,
+      "step": 130
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 3.3608834743499756,
+      "learning_rate": 5.6275303643724695e-06,
+      "loss": 0.7135,
+      "step": 140
+    },
+    {
+      "epoch": 0.182370820668693,
+      "grad_norm": 3.3592512607574463,
+      "learning_rate": 6.0323886639676124e-06,
+      "loss": 0.7427,
+      "step": 150
+    },
+    {
+      "epoch": 0.1945288753799392,
+      "grad_norm": 2.913890838623047,
+      "learning_rate": 6.437246963562754e-06,
+      "loss": 0.6847,
+      "step": 160
+    },
+    {
+      "epoch": 0.2066869300911854,
+      "grad_norm": 2.6773297786712646,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.7409,
+      "step": 170
+    },
+    {
+      "epoch": 0.2188449848024316,
+      "grad_norm": 2.984339714050293,
+      "learning_rate": 7.246963562753037e-06,
+      "loss": 0.6755,
+      "step": 180
+    },
+    {
+      "epoch": 0.23100303951367782,
+      "grad_norm": 3.006441593170166,
+      "learning_rate": 7.651821862348178e-06,
+      "loss": 0.7105,
+      "step": 190
+    },
+    {
+      "epoch": 0.24316109422492402,
+      "grad_norm": 3.7500977516174316,
+      "learning_rate": 8.056680161943322e-06,
+      "loss": 0.6796,
+      "step": 200
+    },
+    {
+      "epoch": 0.2553191489361702,
+      "grad_norm": 3.6839091777801514,
+      "learning_rate": 8.461538461538462e-06,
+      "loss": 0.6716,
+      "step": 210
+    },
+    {
+      "epoch": 0.2674772036474164,
+      "grad_norm": 3.265120267868042,
+      "learning_rate": 8.866396761133604e-06,
+      "loss": 0.6728,
+      "step": 220
+    },
+    {
+      "epoch": 0.2796352583586626,
+      "grad_norm": 3.2442452907562256,
+      "learning_rate": 9.271255060728746e-06,
+      "loss": 0.6807,
+      "step": 230
+    },
+    {
+      "epoch": 0.2917933130699088,
+      "grad_norm": 3.7613420486450195,
+      "learning_rate": 9.676113360323888e-06,
+      "loss": 0.674,
+      "step": 240
+    },
+    {
+      "epoch": 0.303951367781155,
+      "grad_norm": 4.201897621154785,
+      "learning_rate": 9.999979955978923e-06,
+      "loss": 0.6987,
+      "step": 250
+    },
+    {
+      "epoch": 0.3161094224924012,
+      "grad_norm": 3.1414012908935547,
+      "learning_rate": 9.999278432115106e-06,
+      "loss": 0.6584,
+      "step": 260
+    },
+    {
+      "epoch": 0.3282674772036474,
+      "grad_norm": 3.2702925205230713,
+      "learning_rate": 9.99757486789673e-06,
+      "loss": 0.683,
+      "step": 270
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 2.9207000732421875,
+      "learning_rate": 9.9948696047811e-06,
+      "loss": 0.6895,
+      "step": 280
+    },
+    {
+      "epoch": 0.3525835866261398,
+      "grad_norm": 3.319397211074829,
+      "learning_rate": 9.991163185003028e-06,
+      "loss": 0.66,
+      "step": 290
+    },
+    {
+      "epoch": 0.364741641337386,
+      "grad_norm": 2.8080954551696777,
+      "learning_rate": 9.98645635146616e-06,
+      "loss": 0.6914,
+      "step": 300
+    },
+    {
+      "epoch": 0.3768996960486322,
+      "grad_norm": 4.024887561798096,
+      "learning_rate": 9.980750047594076e-06,
+      "loss": 0.6511,
+      "step": 310
+    },
+    {
+      "epoch": 0.3890577507598784,
+      "grad_norm": 2.6032838821411133,
+      "learning_rate": 9.974045417141186e-06,
+      "loss": 0.6522,
+      "step": 320
+    },
+    {
+      "epoch": 0.4012158054711246,
+      "grad_norm": 2.4978721141815186,
+      "learning_rate": 9.966343803963481e-06,
+      "loss": 0.6517,
+      "step": 330
+    },
+    {
+      "epoch": 0.4133738601823708,
+      "grad_norm": 3.0864603519439697,
+      "learning_rate": 9.957646751749178e-06,
+      "loss": 0.662,
+      "step": 340
+    },
+    {
+      "epoch": 0.425531914893617,
+      "grad_norm": 3.713203191757202,
+      "learning_rate": 9.947956003709301e-06,
+      "loss": 0.6728,
+      "step": 350
+    },
+    {
+      "epoch": 0.4376899696048632,
+      "grad_norm": 2.8905911445617676,
+      "learning_rate": 9.937273502228283e-06,
+      "loss": 0.6905,
+      "step": 360
+    },
+    {
+      "epoch": 0.44984802431610943,
+      "grad_norm": 3.0076723098754883,
+      "learning_rate": 9.925601388474637e-06,
+      "loss": 0.6955,
+      "step": 370
+    },
+    {
+      "epoch": 0.46200607902735563,
+      "grad_norm": 3.2814724445343018,
+      "learning_rate": 9.912942001971792e-06,
+      "loss": 0.6176,
+      "step": 380
+    },
+    {
+      "epoch": 0.47416413373860183,
+      "grad_norm": 2.9065964221954346,
+      "learning_rate": 9.899297880129156e-06,
+      "loss": 0.6768,
+      "step": 390
+    },
+    {
+      "epoch": 0.48632218844984804,
+      "grad_norm": 2.724536657333374,
+      "learning_rate": 9.884671757733534e-06,
+      "loss": 0.6382,
+      "step": 400
+    },
+    {
+      "epoch": 0.49848024316109424,
+      "grad_norm": 2.8882269859313965,
+      "learning_rate": 9.869066566400975e-06,
+      "loss": 0.6603,
+      "step": 410
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 2.5395541191101074,
+      "learning_rate": 9.852485433989158e-06,
+      "loss": 0.642,
+      "step": 420
+    },
+    {
+      "epoch": 0.5227963525835866,
+      "grad_norm": 2.759591579437256,
+      "learning_rate": 9.834931683970468e-06,
+      "loss": 0.6424,
+      "step": 430
+    },
+    {
+      "epoch": 0.5349544072948328,
+      "grad_norm": 2.4878828525543213,
+      "learning_rate": 9.816408834765838e-06,
+      "loss": 0.6435,
+      "step": 440
+    },
+    {
+      "epoch": 0.547112462006079,
+      "grad_norm": 2.7571871280670166,
+      "learning_rate": 9.796920599039536e-06,
+      "loss": 0.6766,
+      "step": 450
+    },
+    {
+      "epoch": 0.5592705167173252,
+      "grad_norm": 2.585879325866699,
+      "learning_rate": 9.776470882954998e-06,
+      "loss": 0.6082,
+      "step": 460
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 2.5847771167755127,
+      "learning_rate": 9.7550637853919e-06,
+      "loss": 0.6551,
+      "step": 470
+    },
+    {
+      "epoch": 0.5835866261398176,
+      "grad_norm": 2.795027732849121,
+      "learning_rate": 9.732703597124586e-06,
+      "loss": 0.6429,
+      "step": 480
+    },
+    {
+      "epoch": 0.5957446808510638,
+      "grad_norm": 2.377835273742676,
+      "learning_rate": 9.709394799962038e-06,
+      "loss": 0.6386,
+      "step": 490
+    },
+    {
+      "epoch": 0.60790273556231,
+      "grad_norm": 3.254490852355957,
+      "learning_rate": 9.685142065849556e-06,
+      "loss": 0.5844,
+      "step": 500
+    },
+    {
+      "epoch": 0.6200607902735562,
+      "grad_norm": 2.866058588027954,
+      "learning_rate": 9.659950255932324e-06,
+      "loss": 0.6079,
+      "step": 510
+    },
+    {
+      "epoch": 0.6322188449848024,
+      "grad_norm": 2.680647373199463,
+      "learning_rate": 9.633824419581069e-06,
+      "loss": 0.6294,
+      "step": 520
+    },
+    {
+      "epoch": 0.6443768996960486,
+      "grad_norm": 3.1423895359039307,
+      "learning_rate": 9.60676979337996e-06,
+      "loss": 0.6311,
+      "step": 530
+    },
+    {
+      "epoch": 0.6565349544072948,
+      "grad_norm": 2.480421304702759,
+      "learning_rate": 9.578791800077021e-06,
+      "loss": 0.6395,
+      "step": 540
+    },
+    {
+      "epoch": 0.668693009118541,
+      "grad_norm": 3.06001877784729,
+      "learning_rate": 9.549896047497202e-06,
+      "loss": 0.6613,
+      "step": 550
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 2.8360841274261475,
+      "learning_rate": 9.520088327418371e-06,
+      "loss": 0.6161,
+      "step": 560
+    },
+    {
+      "epoch": 0.6930091185410334,
+      "grad_norm": 3.1503562927246094,
+      "learning_rate": 9.489374614410413e-06,
+      "loss": 0.6137,
+      "step": 570
+    },
+    {
+      "epoch": 0.7051671732522796,
+      "grad_norm": 2.579737663269043,
+      "learning_rate": 9.457761064637727e-06,
+      "loss": 0.6068,
+      "step": 580
+    },
+    {
+      "epoch": 0.7173252279635258,
+      "grad_norm": 3.200549602508545,
+      "learning_rate": 9.425254014625278e-06,
+      "loss": 0.6436,
+      "step": 590
+    },
+    {
+      "epoch": 0.729483282674772,
+      "grad_norm": 2.9303839206695557,
+      "learning_rate": 9.391859979988546e-06,
+      "loss": 0.6062,
+      "step": 600
+    },
+    {
+      "epoch": 0.7416413373860182,
+      "grad_norm": 3.0887465476989746,
+      "learning_rate": 9.35758565412754e-06,
+      "loss": 0.6244,
+      "step": 610
+    },
+    {
+      "epoch": 0.7537993920972644,
+      "grad_norm": 3.22578763961792,
+      "learning_rate": 9.322437906885199e-06,
+      "loss": 0.6544,
+      "step": 620
+    },
+    {
+      "epoch": 0.7659574468085106,
+      "grad_norm": 3.8590402603149414,
+      "learning_rate": 9.28642378317042e-06,
+      "loss": 0.6369,
+      "step": 630
+    },
+    {
+      "epoch": 0.7781155015197568,
+      "grad_norm": 3.001377820968628,
+      "learning_rate": 9.249550501545998e-06,
+      "loss": 0.6556,
+      "step": 640
+    },
+    {
+      "epoch": 0.790273556231003,
+      "grad_norm": 2.9286224842071533,
+      "learning_rate": 9.211825452781762e-06,
+      "loss": 0.599,
+      "step": 650
+    },
+    {
+      "epoch": 0.8024316109422492,
+      "grad_norm": 3.0069026947021484,
+      "learning_rate": 9.173256198373185e-06,
+      "loss": 0.6284,
+      "step": 660
+    },
+    {
+      "epoch": 0.8145896656534954,
+      "grad_norm": 3.2098565101623535,
+      "learning_rate": 9.133850469025786e-06,
+      "loss": 0.6047,
+      "step": 670
+    },
+    {
+      "epoch": 0.8267477203647416,
+      "grad_norm": 2.4998652935028076,
+      "learning_rate": 9.093616163105609e-06,
+      "loss": 0.6233,
+      "step": 680
+    },
+    {
+      "epoch": 0.8389057750759878,
+      "grad_norm": 2.6951255798339844,
+      "learning_rate": 9.052561345056095e-06,
+      "loss": 0.6288,
+      "step": 690
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 2.79081654548645,
+      "learning_rate": 9.010694243781671e-06,
+      "loss": 0.6248,
+      "step": 700
+    },
+    {
+      "epoch": 0.8632218844984803,
+      "grad_norm": 3.0113465785980225,
+      "learning_rate": 8.96802325099838e-06,
+      "loss": 0.6262,
+      "step": 710
+    },
+    {
+      "epoch": 0.8753799392097265,
+      "grad_norm": 2.396683692932129,
+      "learning_rate": 8.924556919551863e-06,
+      "loss": 0.6154,
+      "step": 720
+    },
+    {
+      "epoch": 0.8875379939209727,
+      "grad_norm": 2.604168176651001,
+      "learning_rate": 8.880303961703048e-06,
+      "loss": 0.6044,
+      "step": 730
+    },
+    {
+      "epoch": 0.8996960486322189,
+      "grad_norm": 2.6339340209960938,
+      "learning_rate": 8.835273247381903e-06,
+      "loss": 0.6367,
+      "step": 740
+    },
+    {
+      "epoch": 0.9118541033434651,
+      "grad_norm": 2.699192762374878,
+      "learning_rate": 8.789473802409565e-06,
+      "loss": 0.6598,
+      "step": 750
+    },
+    {
+      "epoch": 0.9240121580547113,
+      "grad_norm": 3.0326826572418213,
+      "learning_rate": 8.742914806689234e-06,
+      "loss": 0.596,
+      "step": 760
+    },
+    {
+      "epoch": 0.9361702127659575,
+      "grad_norm": 3.168898582458496,
+      "learning_rate": 8.695605592366184e-06,
+      "loss": 0.5843,
+      "step": 770
+    },
+    {
+      "epoch": 0.9483282674772037,
+      "grad_norm": 2.6533005237579346,
+      "learning_rate": 8.647555641957243e-06,
+      "loss": 0.598,
+      "step": 780
+    },
+    {
+      "epoch": 0.9604863221884499,
+      "grad_norm": 3.4256536960601807,
+      "learning_rate": 8.59877458645017e-06,
+      "loss": 0.588,
+      "step": 790
+    },
+    {
+      "epoch": 0.9726443768996961,
+      "grad_norm": 2.429436445236206,
+      "learning_rate": 8.54927220337322e-06,
+      "loss": 0.5955,
+      "step": 800
+    },
+    {
+      "epoch": 0.9848024316109423,
+      "grad_norm": 2.6898012161254883,
+      "learning_rate": 8.499058414835389e-06,
+      "loss": 0.6068,
+      "step": 810
+    },
+    {
+      "epoch": 0.9969604863221885,
+      "grad_norm": 2.064389944076538,
+      "learning_rate": 8.448143285537645e-06,
+      "loss": 0.5694,
+      "step": 820
+    },
+    {
+      "epoch": 1.0085106382978724,
+      "grad_norm": 2.412479877471924,
+      "learning_rate": 8.396537020755588e-06,
+      "loss": 0.4937,
+      "step": 830
+    },
+    {
+      "epoch": 1.0206686930091184,
+      "grad_norm": 2.439929246902466,
+      "learning_rate": 8.344249964293942e-06,
+      "loss": 0.4945,
+      "step": 840
+    },
+    {
+      "epoch": 1.0328267477203648,
+      "grad_norm": 2.665113687515259,
+      "learning_rate": 8.291292596413272e-06,
+      "loss": 0.499,
+      "step": 850
+    },
+    {
+      "epoch": 1.0449848024316108,
+      "grad_norm": 2.39530086517334,
+      "learning_rate": 8.237675531729345e-06,
+      "loss": 0.4825,
+      "step": 860
+    },
+    {
+      "epoch": 1.0571428571428572,
+      "grad_norm": 2.943648099899292,
+      "learning_rate": 8.18340951708558e-06,
+      "loss": 0.4683,
+      "step": 870
+    },
+    {
+      "epoch": 1.0693009118541033,
+      "grad_norm": 2.766900062561035,
+      "learning_rate": 8.128505429398976e-06,
+      "loss": 0.477,
+      "step": 880
+    },
+    {
+      "epoch": 1.0814589665653496,
+      "grad_norm": 2.389639139175415,
+      "learning_rate": 8.072974273479972e-06,
+      "loss": 0.5606,
+      "step": 890
+    },
+    {
+      "epoch": 1.0936170212765957,
+      "grad_norm": 2.3432369232177734,
+      "learning_rate": 8.016827179826685e-06,
+      "loss": 0.4753,
+      "step": 900
+    },
+    {
+      "epoch": 1.105775075987842,
+      "grad_norm": 2.27811598777771,
+      "learning_rate": 7.960075402393937e-06,
+      "loss": 0.4733,
+      "step": 910
+    },
+    {
+      "epoch": 1.117933130699088,
+      "grad_norm": 2.5332465171813965,
+      "learning_rate": 7.902730316337556e-06,
+      "loss": 0.4444,
+      "step": 920
+    },
+    {
+      "epoch": 1.1300911854103344,
+      "grad_norm": 2.445450782775879,
+      "learning_rate": 7.844803415734368e-06,
+      "loss": 0.4694,
+      "step": 930
+    },
+    {
+      "epoch": 1.1422492401215805,
+      "grad_norm": 2.309290647506714,
+      "learning_rate": 7.786306311278354e-06,
+      "loss": 0.4617,
+      "step": 940
+    },
+    {
+      "epoch": 1.1544072948328268,
+      "grad_norm": 2.7566754817962646,
+      "learning_rate": 7.727250727953445e-06,
+      "loss": 0.5046,
+      "step": 950
+    },
+    {
+      "epoch": 1.1665653495440729,
+      "grad_norm": 2.475858211517334,
+      "learning_rate": 7.667648502683406e-06,
+      "loss": 0.5175,
+      "step": 960
+    },
+    {
+      "epoch": 1.1787234042553192,
+      "grad_norm": 2.5813775062561035,
+      "learning_rate": 7.607511581959261e-06,
+      "loss": 0.4656,
+      "step": 970
+    },
+    {
+      "epoch": 1.1908814589665653,
+      "grad_norm": 2.9376819133758545,
+      "learning_rate": 7.5468520194447925e-06,
+      "loss": 0.4945,
+      "step": 980
+    },
+    {
+      "epoch": 1.2030395136778116,
+      "grad_norm": 2.2708747386932373,
+      "learning_rate": 7.485681973560532e-06,
+      "loss": 0.4931,
+      "step": 990
+    },
+    {
+      "epoch": 1.2151975683890577,
+      "grad_norm": 2.87481427192688,
+      "learning_rate": 7.4240137050467635e-06,
+      "loss": 0.4713,
+      "step": 1000
+    },
+    {
+      "epoch": 1.227355623100304,
+      "grad_norm": 3.1325576305389404,
+      "learning_rate": 7.361859574506017e-06,
+      "loss": 0.4775,
+      "step": 1010
+    },
+    {
+      "epoch": 1.23951367781155,
+      "grad_norm": 2.519160509109497,
+      "learning_rate": 7.299232039925552e-06,
+      "loss": 0.4747,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2516717325227964,
+      "grad_norm": 3.1819024085998535,
+      "learning_rate": 7.236143654180311e-06,
+      "loss": 0.4836,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2638297872340425,
+      "grad_norm": 2.5699877738952637,
+      "learning_rate": 7.172607062516856e-06,
+      "loss": 0.4471,
+      "step": 1040
+    },
+    {
+      "epoch": 1.2759878419452888,
+      "grad_norm": 3.718123435974121,
+      "learning_rate": 7.108635000018802e-06,
+      "loss": 0.5022,
+      "step": 1050
+    },
+    {
+      "epoch": 1.288145896656535,
+      "grad_norm": 3.3233118057250977,
+      "learning_rate": 7.044240289054227e-06,
+      "loss": 0.4829,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3003039513677812,
+      "grad_norm": 2.362790584564209,
+      "learning_rate": 6.979435836705602e-06,
+      "loss": 0.4801,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3124620060790273,
+      "grad_norm": 2.5460381507873535,
+      "learning_rate": 6.9142346321827246e-06,
+      "loss": 0.4922,
+      "step": 1080
+    },
+    {
+      "epoch": 1.3246200607902736,
+      "grad_norm": 3.0161983966827393,
+      "learning_rate": 6.84864974421921e-06,
+      "loss": 0.4734,
+      "step": 1090
+    },
+    {
+      "epoch": 1.3367781155015197,
+      "grad_norm": 2.387080669403076,
+      "learning_rate": 6.782694318453033e-06,
+      "loss": 0.4924,
+      "step": 1100
+    },
+    {
+      "epoch": 1.348936170212766,
+      "grad_norm": 3.0172154903411865,
+      "learning_rate": 6.716381574791648e-06,
+      "loss": 0.4669,
+      "step": 1110
+    },
+    {
+      "epoch": 1.361094224924012,
+      "grad_norm": 3.0593836307525635,
+      "learning_rate": 6.649724804762236e-06,
+      "loss": 0.4689,
+      "step": 1120
+    },
+    {
+      "epoch": 1.3732522796352584,
+      "grad_norm": 2.0975329875946045,
+      "learning_rate": 6.5827373688475925e-06,
+      "loss": 0.501,
+      "step": 1130
+    },
+    {
+      "epoch": 1.3854103343465045,
+      "grad_norm": 2.6222572326660156,
+      "learning_rate": 6.5154326938081866e-06,
+      "loss": 0.487,
+      "step": 1140
+    },
+    {
+      "epoch": 1.3975683890577508,
+      "grad_norm": 2.6791985034942627,
+      "learning_rate": 6.447824269990947e-06,
+      "loss": 0.4589,
+      "step": 1150
+    },
+    {
+      "epoch": 1.409726443768997,
+      "grad_norm": 3.0119071006774902,
+      "learning_rate": 6.3799256486252945e-06,
+      "loss": 0.4839,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4218844984802432,
+      "grad_norm": 3.6317973136901855,
+      "learning_rate": 6.311750439106976e-06,
+      "loss": 0.4391,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4340425531914893,
+      "grad_norm": 1.9667277336120605,
+      "learning_rate": 6.243312306270235e-06,
+      "loss": 0.4379,
+      "step": 1180
+    },
+    {
+      "epoch": 1.4462006079027356,
+      "grad_norm": 2.5585360527038574,
+      "learning_rate": 6.174624967648877e-06,
+      "loss": 0.4954,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4583586626139817,
+      "grad_norm": 2.421276330947876,
+      "learning_rate": 6.105702190726765e-06,
+      "loss": 0.4558,
+      "step": 1200
+    },
+    {
+      "epoch": 1.470516717325228,
+      "grad_norm": 2.7117786407470703,
+      "learning_rate": 6.03655779017831e-06,
+      "loss": 0.488,
+      "step": 1210
+    },
+    {
+      "epoch": 1.4826747720364741,
+      "grad_norm": 2.3945164680480957,
+      "learning_rate": 5.967205625099496e-06,
+      "loss": 0.4849,
+      "step": 1220
+    },
+    {
+      "epoch": 1.4948328267477204,
+      "grad_norm": 2.291707754135132,
+      "learning_rate": 5.897659596230003e-06,
+      "loss": 0.4614,
+      "step": 1230
+    },
+    {
+      "epoch": 1.5069908814589665,
+      "grad_norm": 2.583559036254883,
+      "learning_rate": 5.827933643166993e-06,
+      "loss": 0.4626,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5191489361702128,
+      "grad_norm": 2.1779534816741943,
+      "learning_rate": 5.758041741571088e-06,
+      "loss": 0.4774,
+      "step": 1250
+    },
+    {
+      "epoch": 1.531306990881459,
+      "grad_norm": 3.738179922103882,
+      "learning_rate": 5.687997900365134e-06,
+      "loss": 0.4487,
+      "step": 1260
+    },
+    {
+      "epoch": 1.543465045592705,
+      "grad_norm": 2.461461305618286,
+      "learning_rate": 5.617816158926303e-06,
+      "loss": 0.4851,
+      "step": 1270
+    },
+    {
+      "epoch": 1.5556231003039513,
+      "grad_norm": 2.784620523452759,
+      "learning_rate": 5.547510584272069e-06,
+      "loss": 0.5079,
+      "step": 1280
+    },
+    {
+      "epoch": 1.5677811550151977,
+      "grad_norm": 2.8999369144439697,
+      "learning_rate": 5.477095268240669e-06,
+      "loss": 0.4596,
+      "step": 1290
+    },
+    {
+      "epoch": 1.5799392097264437,
+      "grad_norm": 2.786457061767578,
+      "learning_rate": 5.406584324666565e-06,
+      "loss": 0.4226,
+      "step": 1300
+    },
+    {
+      "epoch": 1.5920972644376898,
+      "grad_norm": 3.0281615257263184,
+      "learning_rate": 5.335991886551526e-06,
+      "loss": 0.4826,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6042553191489362,
+      "grad_norm": 2.60740327835083,
+      "learning_rate": 5.2653321032318315e-06,
+      "loss": 0.5185,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6164133738601825,
+      "grad_norm": 2.150132179260254,
+      "learning_rate": 5.194619137542241e-06,
+      "loss": 0.511,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6285714285714286,
+      "grad_norm": 2.7613778114318848,
+      "learning_rate": 5.123867162977224e-06,
+      "loss": 0.4653,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6407294832826747,
+      "grad_norm": 2.5103297233581543,
+      "learning_rate": 5.053090360850072e-06,
+      "loss": 0.4206,
+      "step": 1350
+    },
+    {
+      "epoch": 1.652887537993921,
+      "grad_norm": 2.6275055408477783,
+      "learning_rate": 4.9823029174504335e-06,
+      "loss": 0.4727,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6650455927051673,
+      "grad_norm": 2.6730258464813232,
+      "learning_rate": 4.9115190212008745e-06,
+      "loss": 0.4616,
+      "step": 1370
+    },
+    {
+      "epoch": 1.6772036474164134,
+      "grad_norm": 2.8876965045928955,
+      "learning_rate": 4.840752859812972e-06,
+      "loss": 0.4868,
+      "step": 1380
+    },
+    {
+      "epoch": 1.6893617021276595,
+      "grad_norm": 2.7904891967773438,
+      "learning_rate": 4.770018617443578e-06,
+      "loss": 0.4453,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7015197568389058,
+      "grad_norm": 2.7088356018066406,
+      "learning_rate": 4.699330471851798e-06,
+      "loss": 0.4708,
+      "step": 1400
+    },
+    {
+      "epoch": 1.713677811550152,
+      "grad_norm": 2.1268298625946045,
+      "learning_rate": 4.628702591557237e-06,
+      "loss": 0.4901,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7258358662613982,
+      "grad_norm": 2.3978848457336426,
+      "learning_rate": 4.558149133000104e-06,
+      "loss": 0.5164,
+      "step": 1420
+    },
+    {
+      "epoch": 1.7379939209726443,
+      "grad_norm": 1.8490489721298218,
+      "learning_rate": 4.487684237703734e-06,
+      "loss": 0.4342,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7501519756838906,
+      "grad_norm": 2.7367939949035645,
+      "learning_rate": 4.417322029440119e-06,
+      "loss": 0.4887,
+      "step": 1440
+    },
+    {
+      "epoch": 1.762310030395137,
+      "grad_norm": 2.217988967895508,
+      "learning_rate": 4.347076611398961e-06,
+      "loss": 0.46,
+      "step": 1450
+    },
+    {
+      "epoch": 1.774468085106383,
+      "grad_norm": 2.8989672660827637,
+      "learning_rate": 4.2769620633608835e-06,
+      "loss": 0.4524,
+      "step": 1460
+    },
+    {
+      "epoch": 1.786626139817629,
+      "grad_norm": 2.5125184059143066,
+      "learning_rate": 4.206992438875318e-06,
+      "loss": 0.4346,
+      "step": 1470
+    },
+    {
+      "epoch": 1.7987841945288754,
+      "grad_norm": 2.9049086570739746,
+      "learning_rate": 4.137181762443658e-06,
+      "loss": 0.3629,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8109422492401217,
+      "grad_norm": 2.5007903575897217,
+      "learning_rate": 4.0675440267082236e-06,
+      "loss": 0.4943,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8231003039513678,
+      "grad_norm": 2.90285325050354,
+      "learning_rate": 3.998093189647622e-06,
+      "loss": 0.4331,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8352583586626139,
+      "grad_norm": 2.7467432022094727,
+      "learning_rate": 3.928843171779051e-06,
+      "loss": 0.4826,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8474164133738602,
+      "grad_norm": 2.5184881687164307,
+      "learning_rate": 3.859807853368112e-06,
+      "loss": 0.4204,
+      "step": 1520
+    },
+    {
+      "epoch": 1.8595744680851065,
+      "grad_norm": 2.262559652328491,
+      "learning_rate": 3.791001071646695e-06,
+      "loss": 0.455,
+      "step": 1530
+    },
+    {
+      "epoch": 1.8717325227963526,
+      "grad_norm": 2.8905036449432373,
+      "learning_rate": 3.72243661803948e-06,
+      "loss": 0.4584,
+      "step": 1540
+    },
+    {
+      "epoch": 1.8838905775075987,
+      "grad_norm": 3.1106526851654053,
+      "learning_rate": 3.6541282353996275e-06,
+      "loss": 0.4559,
+      "step": 1550
+    },
+    {
+      "epoch": 1.896048632218845,
+      "grad_norm": 2.7985055446624756,
+      "learning_rate": 3.5860896152542013e-06,
+      "loss": 0.4452,
+      "step": 1560
+    },
+    {
+      "epoch": 1.9082066869300913,
+      "grad_norm": 2.4769771099090576,
+      "learning_rate": 3.5183343950598825e-06,
+      "loss": 0.463,
+      "step": 1570
+    },
+    {
+      "epoch": 1.9203647416413374,
+      "grad_norm": 2.9029109477996826,
+      "learning_rate": 3.450876155469518e-06,
+      "loss": 0.4377,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9325227963525835,
+      "grad_norm": 2.444227457046509,
+      "learning_rate": 3.3837284176100543e-06,
+      "loss": 0.4559,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9446808510638298,
+      "grad_norm": 1.8885170221328735,
+      "learning_rate": 3.3169046403724004e-06,
+      "loss": 0.4315,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9568389057750761,
+      "grad_norm": 2.370542526245117,
+      "learning_rate": 3.250418217713771e-06,
+      "loss": 0.4496,
+      "step": 1610
+    },
+    {
+      "epoch": 1.9689969604863222,
+      "grad_norm": 2.281675338745117,
+      "learning_rate": 3.1842824759730518e-06,
+      "loss": 0.4651,
+      "step": 1620
+    },
+    {
+      "epoch": 1.9811550151975683,
+      "grad_norm": 2.4642460346221924,
+      "learning_rate": 3.1185106711996848e-06,
+      "loss": 0.4492,
+      "step": 1630
+    },
+    {
+      "epoch": 1.9933130699088146,
+      "grad_norm": 2.898085355758667,
+      "learning_rate": 3.0531159864966885e-06,
+      "loss": 0.4217,
+      "step": 1640
+    },
+    {
+      "epoch": 2.0048632218844986,
+      "grad_norm": 2.5043299198150635,
+      "learning_rate": 2.9881115293782638e-06,
+      "loss": 0.4087,
+      "step": 1650
+    },
+    {
+      "epoch": 2.0170212765957447,
+      "grad_norm": 2.5139353275299072,
+      "learning_rate": 2.923510329142568e-06,
+      "loss": 0.3166,
+      "step": 1660
+    },
+    {
+      "epoch": 2.029179331306991,
+      "grad_norm": 2.334691047668457,
+      "learning_rate": 2.8593253342601557e-06,
+      "loss": 0.2967,
+      "step": 1670
+    },
+    {
+      "epoch": 2.041337386018237,
+      "grad_norm": 2.763742685317993,
+      "learning_rate": 2.795569409778639e-06,
+      "loss": 0.3263,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0534954407294834,
+      "grad_norm": 2.539466142654419,
+      "learning_rate": 2.7322553347440368e-06,
+      "loss": 0.2964,
+      "step": 1690
+    },
+    {
+      "epoch": 2.0656534954407295,
+      "grad_norm": 3.0033152103424072,
+      "learning_rate": 2.6693957996393984e-06,
+      "loss": 0.3157,
+      "step": 1700
+    },
+    {
+      "epoch": 2.0778115501519756,
+      "grad_norm": 2.8573410511016846,
+      "learning_rate": 2.6070034038411553e-06,
+      "loss": 0.3542,
+      "step": 1710
+    },
+    {
+      "epoch": 2.0899696048632217,
+      "grad_norm": 2.31459641456604,
+      "learning_rate": 2.545090653093738e-06,
+      "loss": 0.2965,
+      "step": 1720
+    },
+    {
+      "epoch": 2.1021276595744682,
+      "grad_norm": 2.5029146671295166,
+      "learning_rate": 2.4836699570029623e-06,
+      "loss": 0.295,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1142857142857143,
+      "grad_norm": 2.295614004135132,
+      "learning_rate": 2.4227536265486885e-06,
+      "loss": 0.3075,
+      "step": 1740
+    },
+    {
+      "epoch": 2.1264437689969604,
+      "grad_norm": 2.5719516277313232,
+      "learning_rate": 2.3623538716172394e-06,
+      "loss": 0.3397,
+      "step": 1750
+    },
+    {
+      "epoch": 2.1386018237082065,
+      "grad_norm": 2.6095409393310547,
+      "learning_rate": 2.302482798554096e-06,
+      "loss": 0.324,
+      "step": 1760
+    },
+    {
+      "epoch": 2.150759878419453,
+      "grad_norm": 2.429758310317993,
+      "learning_rate": 2.2431524077373314e-06,
+      "loss": 0.2939,
+      "step": 1770
+    },
+    {
+      "epoch": 2.162917933130699,
+      "grad_norm": 2.9179751873016357,
+      "learning_rate": 2.1843745911722937e-06,
+      "loss": 0.308,
+      "step": 1780
+    },
+    {
+      "epoch": 2.1750759878419452,
+      "grad_norm": 3.281049966812134,
+      "learning_rate": 2.1261611301080063e-06,
+      "loss": 0.3229,
+      "step": 1790
+    },
+    {
+      "epoch": 2.1872340425531913,
+      "grad_norm": 2.931143283843994,
+      "learning_rate": 2.068523692675772e-06,
+      "loss": 0.3107,
+      "step": 1800
+    },
+    {
+      "epoch": 2.199392097264438,
+      "grad_norm": 2.432403802871704,
+      "learning_rate": 2.0114738315504505e-06,
+      "loss": 0.2925,
+      "step": 1810
+    },
+    {
+      "epoch": 2.211550151975684,
+      "grad_norm": 3.296288251876831,
+      "learning_rate": 1.955022981634863e-06,
+      "loss": 0.3115,
+      "step": 1820
+    },
+    {
+      "epoch": 2.22370820668693,
+      "grad_norm": 2.6482620239257812,
+      "learning_rate": 1.8991824577678269e-06,
+      "loss": 0.3423,
+      "step": 1830
+    },
+    {
+      "epoch": 2.235866261398176,
+      "grad_norm": 2.5689730644226074,
+      "learning_rate": 1.8439634524562423e-06,
+      "loss": 0.344,
+      "step": 1840
+    },
+    {
+      "epoch": 2.2480243161094227,
+      "grad_norm": 2.4932291507720947,
+      "learning_rate": 1.7893770336316928e-06,
+      "loss": 0.3052,
+      "step": 1850
+    },
+    {
+      "epoch": 2.2601823708206688,
+      "grad_norm": 2.985034704208374,
+      "learning_rate": 1.7354341424320286e-06,
+      "loss": 0.3056,
+      "step": 1860
+    },
+    {
+      "epoch": 2.272340425531915,
+      "grad_norm": 2.558969020843506,
+      "learning_rate": 1.6821455910083535e-06,
+      "loss": 0.2883,
+      "step": 1870
+    },
+    {
+      "epoch": 2.284498480243161,
+      "grad_norm": 2.731433868408203,
+      "learning_rate": 1.6295220603578727e-06,
+      "loss": 0.3017,
+      "step": 1880
+    },
+    {
+      "epoch": 2.2966565349544075,
+      "grad_norm": 2.7767181396484375,
+      "learning_rate": 1.5775740981830262e-06,
+      "loss": 0.3348,
+      "step": 1890
+    },
+    {
+      "epoch": 2.3088145896656536,
+      "grad_norm": 2.289393424987793,
+      "learning_rate": 1.526312116777336e-06,
+      "loss": 0.3377,
+      "step": 1900
+    },
+    {
+      "epoch": 2.3209726443768997,
+      "grad_norm": 2.3055357933044434,
+      "learning_rate": 1.475746390938399e-06,
+      "loss": 0.3111,
+      "step": 1910
+    },
+    {
+      "epoch": 2.3331306990881457,
+      "grad_norm": 3.120150089263916,
+      "learning_rate": 1.4258870559084387e-06,
+      "loss": 0.3172,
+      "step": 1920
+    },
+    {
+      "epoch": 2.3452887537993923,
+      "grad_norm": 2.520087718963623,
+      "learning_rate": 1.3767441053428244e-06,
+      "loss": 0.3071,
+      "step": 1930
+    },
+    {
+      "epoch": 2.3574468085106384,
+      "grad_norm": 2.533917188644409,
+      "learning_rate": 1.328327389306977e-06,
+      "loss": 0.328,
+      "step": 1940
+    },
+    {
+      "epoch": 2.3696048632218845,
+      "grad_norm": 2.611781120300293,
+      "learning_rate": 1.2806466123020479e-06,
+      "loss": 0.2373,
+      "step": 1950
+    },
+    {
+      "epoch": 2.3817629179331306,
+      "grad_norm": 2.3127501010894775,
+      "learning_rate": 1.2337113313197813e-06,
+      "loss": 0.3226,
+      "step": 1960
+    },
+    {
+      "epoch": 2.393920972644377,
+      "grad_norm": 3.0540225505828857,
+      "learning_rate": 1.1875309539269332e-06,
+      "loss": 0.3181,
+      "step": 1970
+    },
+    {
+      "epoch": 2.406079027355623,
+      "grad_norm": 2.2503840923309326,
+      "learning_rate": 1.1421147363796547e-06,
+      "loss": 0.2918,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4182370820668693,
+      "grad_norm": 2.5295841693878174,
+      "learning_rate": 1.097471781768194e-06,
+      "loss": 0.2941,
+      "step": 1990
+    },
+    {
+      "epoch": 2.4303951367781154,
+      "grad_norm": 2.7835609912872314,
+      "learning_rate": 1.053611038192296e-06,
+      "loss": 0.2901,
+      "step": 2000
+    },
+    {
+      "epoch": 2.4425531914893615,
+      "grad_norm": 2.6751868724823,
+      "learning_rate": 1.0105412969676758e-06,
+      "loss": 0.335,
+      "step": 2010
+    },
+    {
+      "epoch": 2.454711246200608,
+      "grad_norm": 2.333569049835205,
+      "learning_rate": 9.682711908639137e-07,
+      "loss": 0.2967,
+      "step": 2020
+    },
+    {
+      "epoch": 2.466869300911854,
+      "grad_norm": 2.4557461738586426,
+      "learning_rate": 9.268091923741246e-07,
+      "loss": 0.2856,
+      "step": 2030
+    },
+    {
+      "epoch": 2.4790273556231,
+      "grad_norm": 2.8368921279907227,
+      "learning_rate": 8.861636120167632e-07,
+      "loss": 0.3396,
+      "step": 2040
+    },
+    {
+      "epoch": 2.4911854103343467,
+      "grad_norm": 2.238975763320923,
+      "learning_rate": 8.463425966698857e-07,
+      "loss": 0.3138,
+      "step": 2050
+    },
+    {
+      "epoch": 2.503343465045593,
+      "grad_norm": 2.7118637561798096,
+      "learning_rate": 8.073541279382135e-07,
+      "loss": 0.3397,
+      "step": 2060
+    },
+    {
+      "epoch": 2.515501519756839,
+      "grad_norm": 2.528172731399536,
+      "learning_rate": 7.69206020553323e-07,
+      "loss": 0.3273,
+      "step": 2070
+    },
+    {
+      "epoch": 2.527659574468085,
+      "grad_norm": 2.3029799461364746,
+      "learning_rate": 7.319059208072909e-07,
+      "loss": 0.3238,
+      "step": 2080
+    },
+    {
+      "epoch": 2.539817629179331,
+      "grad_norm": 2.535954475402832,
+      "learning_rate": 6.954613050200859e-07,
+      "loss": 0.328,
+      "step": 2090
+    },
+    {
+      "epoch": 2.5519756838905776,
+      "grad_norm": 2.4356179237365723,
+      "learning_rate": 6.5987947804104e-07,
+      "loss": 0.3081,
+      "step": 2100
+    },
+    {
+      "epoch": 2.5641337386018237,
+      "grad_norm": 2.039999008178711,
+      "learning_rate": 6.251675717846905e-07,
+      "loss": 0.311,
+      "step": 2110
+    },
+    {
+      "epoch": 2.57629179331307,
+      "grad_norm": 2.296266794204712,
+      "learning_rate": 5.913325438012773e-07,
+      "loss": 0.2815,
+      "step": 2120
+    },
+    {
+      "epoch": 2.5884498480243163,
+      "grad_norm": 2.9788355827331543,
+      "learning_rate": 5.583811758821916e-07,
+      "loss": 0.3346,
+      "step": 2130
+    },
+    {
+      "epoch": 2.6006079027355624,
+      "grad_norm": 3.0497772693634033,
+      "learning_rate": 5.263200727006568e-07,
+      "loss": 0.2976,
+      "step": 2140
+    },
+    {
+      "epoch": 2.6127659574468085,
+      "grad_norm": 2.972386121749878,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 0.272,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6249240121580546,
+      "grad_norm": 3.3032212257385254,
+      "learning_rate": 4.648941857451228e-07,
+      "loss": 0.2989,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6370820668693007,
+      "grad_norm": 2.078023672103882,
+      "learning_rate": 4.355417139914242e-07,
+      "loss": 0.3353,
+      "step": 2170
+    },
+    {
+      "epoch": 2.6492401215805472,
+      "grad_norm": 2.5029313564300537,
+      "learning_rate": 4.0710412854809255e-07,
+      "loss": 0.3413,
+      "step": 2180
+    },
+    {
+      "epoch": 2.6613981762917933,
+      "grad_norm": 2.516641616821289,
+      "learning_rate": 3.7958712935934726e-07,
+      "loss": 0.347,
+      "step": 2190
+    },
+    {
+      "epoch": 2.6735562310030394,
+      "grad_norm": 2.115417718887329,
+      "learning_rate": 3.5299623184986366e-07,
+      "loss": 0.2955,
+      "step": 2200
+    },
+    {
+      "epoch": 2.685714285714286,
+      "grad_norm": 2.419532299041748,
+      "learning_rate": 3.273367658192778e-07,
+      "loss": 0.285,
+      "step": 2210
+    },
+    {
+      "epoch": 2.697872340425532,
+      "grad_norm": 2.186316967010498,
+      "learning_rate": 3.0261387437389766e-07,
+      "loss": 0.3091,
+      "step": 2220
+    },
+    {
+      "epoch": 2.710030395136778,
+      "grad_norm": 2.725886583328247,
+      "learning_rate": 2.7883251289583467e-07,
+      "loss": 0.317,
+      "step": 2230
+    },
+    {
+      "epoch": 2.722188449848024,
+      "grad_norm": 2.355541944503784,
+      "learning_rate": 2.5599744804975956e-07,
+      "loss": 0.3093,
+      "step": 2240
+    },
+    {
+      "epoch": 2.7343465045592703,
+      "grad_norm": 2.3325600624084473,
+      "learning_rate": 2.3411325682748843e-07,
+      "loss": 0.2784,
+      "step": 2250
+    },
+    {
+      "epoch": 2.746504559270517,
+      "grad_norm": 2.1935389041900635,
+      "learning_rate": 2.1318432563058765e-07,
+      "loss": 0.2835,
+      "step": 2260
+    },
+    {
+      "epoch": 2.758662613981763,
+      "grad_norm": 2.6569478511810303,
+      "learning_rate": 1.9321484939116843e-07,
+      "loss": 0.2821,
+      "step": 2270
+    },
+    {
+      "epoch": 2.770820668693009,
+      "grad_norm": 2.2891359329223633,
+      "learning_rate": 1.742088307310741e-07,
+      "loss": 0.3362,
+      "step": 2280
+    },
+    {
+      "epoch": 2.7829787234042556,
+      "grad_norm": 2.387622833251953,
+      "learning_rate": 1.561700791596038e-07,
+      "loss": 0.2973,
+      "step": 2290
+    },
+    {
+      "epoch": 2.7951367781155017,
+      "grad_norm": 2.550020217895508,
+      "learning_rate": 1.3910221030994764e-07,
+      "loss": 0.279,
+      "step": 2300
+    },
+    {
+      "epoch": 2.8072948328267477,
+      "grad_norm": 2.9916679859161377,
+      "learning_rate": 1.2300864521447575e-07,
+      "loss": 0.3318,
+      "step": 2310
+    },
+    {
+      "epoch": 2.819452887537994,
+      "grad_norm": 2.5227696895599365,
+      "learning_rate": 1.0789260961904357e-07,
+      "loss": 0.2887,
+      "step": 2320
+    },
+    {
+      "epoch": 2.83161094224924,
+      "grad_norm": 2.750169038772583,
+      "learning_rate": 9.375713333642677e-08,
+      "loss": 0.3087,
+      "step": 2330
+    },
+    {
+      "epoch": 2.8437689969604865,
+      "grad_norm": 2.2595717906951904,
+      "learning_rate": 8.060504963903815e-08,
+      "loss": 0.28,
+      "step": 2340
+    },
+    {
+      "epoch": 2.8559270516717326,
+      "grad_norm": 2.5719687938690186,
+      "learning_rate": 6.843899469103521e-08,
+      "loss": 0.3007,
+      "step": 2350
+    },
+    {
+      "epoch": 2.8680851063829786,
+      "grad_norm": 2.3983314037323,
+      "learning_rate": 5.726140701993288e-08,
+      "loss": 0.3049,
+      "step": 2360
+    },
+    {
+      "epoch": 2.880243161094225,
+      "grad_norm": 2.910645008087158,
+      "learning_rate": 4.707452702783388e-08,
+      "loss": 0.3006,
+      "step": 2370
+    },
+    {
+      "epoch": 2.8924012158054713,
+      "grad_norm": 2.546748161315918,
+      "learning_rate": 3.7880396542369635e-08,
+      "loss": 0.3431,
+      "step": 2380
+    },
+    {
+      "epoch": 2.9045592705167174,
+      "grad_norm": 2.052919387817383,
+      "learning_rate": 2.9680858407441503e-08,
+      "loss": 0.2987,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9167173252279635,
+      "grad_norm": 2.4598567485809326,
+      "learning_rate": 2.24775561138485e-08,
+      "loss": 0.3207,
+      "step": 2400
+    },
+    {
+      "epoch": 2.9288753799392095,
+      "grad_norm": 2.4281694889068604,
+      "learning_rate": 1.627193346986744e-08,
+      "loss": 0.2847,
+      "step": 2410
+    },
+    {
+      "epoch": 2.941033434650456,
+      "grad_norm": 2.2293615341186523,
+      "learning_rate": 1.1065234311864459e-08,
+      "loss": 0.2952,
+      "step": 2420
+    },
+    {
+      "epoch": 2.953191489361702,
+      "grad_norm": 2.4415087699890137,
+      "learning_rate": 6.858502254981081e-09,
+      "loss": 0.2756,
+      "step": 2430
+    },
+    {
+      "epoch": 2.9653495440729483,
+      "grad_norm": 2.482046604156494,
+      "learning_rate": 3.652580483956558e-09,
+      "loss": 0.3162,
+      "step": 2440
+    },
+    {
+      "epoch": 2.977507598784195,
+      "grad_norm": 2.2831978797912598,
+      "learning_rate": 1.4481115841230574e-09,
+      "loss": 0.2904,
+      "step": 2450
+    },
+    {
+      "epoch": 2.989665653495441,
+      "grad_norm": 2.147287368774414,
+      "learning_rate": 2.4553741260535667e-10,
+      "loss": 0.3062,
+      "step": 2460
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2466,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.0307400421054874e+17,
+  "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 sha256:4863c68890fcaf8bb4f1b9520cdc750321428c756bb73e1387414d6d40275403
+size 5752