Upload 14 files

.gitattributes

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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,120 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' }}
+        {%- if messages[0].content is string %}
+            {{- messages[0].content }}
+        {%- else %}
+            {%- for content in messages[0].content %}
+                {%- if 'text' in content %}
+                    {{- content.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- for message in messages %}
+    {%- if message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- 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 %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- else %}
+            {%- for content_item in message.content %}
+                {%- if 'text' in content_item %}
+                    {{- content_item.text }}
+                {%- endif %}
+            {%- endfor %}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and message.content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {%- if message.content is string %}
+            {{- message.content }}
+        {%- 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 %}
+        {%- endif %}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.0",
+  "use_cache": true,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.57.0"
+}

model.safetensors.index.json

@@ -0,0 +1,758 @@
+{
+  "metadata": {
+    "total_parameters": 770288,
+    "total_size": 17534247392
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

@@ -0,0 +1,39 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "disable_grouping": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_pad": null,
+  "do_rescale": true,
+  "do_resize": true,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_processor_type": "Qwen2VLImageProcessorFast",
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_pixels": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1436 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 199,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005037783375314861,
+      "grad_norm": 45.14028549194336,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.8127,
+      "step": 1
+    },
+    {
+      "epoch": 0.010075566750629723,
+      "grad_norm": 41.275089263916016,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.8862,
+      "step": 2
+    },
+    {
+      "epoch": 0.015113350125944584,
+      "grad_norm": 45.339202880859375,
+      "learning_rate": 2.5e-06,
+      "loss": 1.8741,
+      "step": 3
+    },
+    {
+      "epoch": 0.020151133501259445,
+      "grad_norm": 38.83050537109375,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.7667,
+      "step": 4
+    },
+    {
+      "epoch": 0.02518891687657431,
+      "grad_norm": 33.30706024169922,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 1.5813,
+      "step": 5
+    },
+    {
+      "epoch": 0.030226700251889168,
+      "grad_norm": 26.171358108520508,
+      "learning_rate": 5e-06,
+      "loss": 1.2841,
+      "step": 6
+    },
+    {
+      "epoch": 0.03526448362720403,
+      "grad_norm": 19.258102416992188,
+      "learning_rate": 4.99966880364306e-06,
+      "loss": 1.1433,
+      "step": 7
+    },
+    {
+      "epoch": 0.04030226700251889,
+      "grad_norm": 9.452253341674805,
+      "learning_rate": 4.998675302325061e-06,
+      "loss": 1.042,
+      "step": 8
+    },
+    {
+      "epoch": 0.04534005037783375,
+      "grad_norm": 11.662043571472168,
+      "learning_rate": 4.997019759281217e-06,
+      "loss": 1.0348,
+      "step": 9
+    },
+    {
+      "epoch": 0.05037783375314862,
+      "grad_norm": 15.509767532348633,
+      "learning_rate": 4.994702613159386e-06,
+      "loss": 1.0352,
+      "step": 10
+    },
+    {
+      "epoch": 0.055415617128463476,
+      "grad_norm": 9.309309959411621,
+      "learning_rate": 4.991724477903854e-06,
+      "loss": 1.0574,
+      "step": 11
+    },
+    {
+      "epoch": 0.060453400503778336,
+      "grad_norm": 6.886810779571533,
+      "learning_rate": 4.988086142592658e-06,
+      "loss": 0.9625,
+      "step": 12
+    },
+    {
+      "epoch": 0.0654911838790932,
+      "grad_norm": 6.271539211273193,
+      "learning_rate": 4.983788571228516e-06,
+      "loss": 0.944,
+      "step": 13
+    },
+    {
+      "epoch": 0.07052896725440806,
+      "grad_norm": 6.019953727722168,
+      "learning_rate": 4.978832902483415e-06,
+      "loss": 0.9427,
+      "step": 14
+    },
+    {
+      "epoch": 0.07556675062972293,
+      "grad_norm": 4.751285552978516,
+      "learning_rate": 4.9732204493969e-06,
+      "loss": 0.9923,
+      "step": 15
+    },
+    {
+      "epoch": 0.08060453400503778,
+      "grad_norm": 7.569280624389648,
+      "learning_rate": 4.9669526990281855e-06,
+      "loss": 1.0161,
+      "step": 16
+    },
+    {
+      "epoch": 0.08564231738035265,
+      "grad_norm": 8.2361421585083,
+      "learning_rate": 4.960031312062141e-06,
+      "loss": 0.8856,
+      "step": 17
+    },
+    {
+      "epoch": 0.0906801007556675,
+      "grad_norm": 8.086812973022461,
+      "learning_rate": 4.952458122369286e-06,
+      "loss": 1.0242,
+      "step": 18
+    },
+    {
+      "epoch": 0.09571788413098237,
+      "grad_norm": 4.911264896392822,
+      "learning_rate": 4.944235136519888e-06,
+      "loss": 0.88,
+      "step": 19
+    },
+    {
+      "epoch": 0.10075566750629723,
+      "grad_norm": 5.140178203582764,
+      "learning_rate": 4.935364533252314e-06,
+      "loss": 0.9321,
+      "step": 20
+    },
+    {
+      "epoch": 0.10579345088161209,
+      "grad_norm": 4.421811580657959,
+      "learning_rate": 4.925848662895753e-06,
+      "loss": 0.9492,
+      "step": 21
+    },
+    {
+      "epoch": 0.11083123425692695,
+      "grad_norm": 5.252143859863281,
+      "learning_rate": 4.9156900467474785e-06,
+      "loss": 0.8854,
+      "step": 22
+    },
+    {
+      "epoch": 0.11586901763224182,
+      "grad_norm": 5.303826808929443,
+      "learning_rate": 4.904891376404822e-06,
+      "loss": 0.9771,
+      "step": 23
+    },
+    {
+      "epoch": 0.12090680100755667,
+      "grad_norm": 4.818070888519287,
+      "learning_rate": 4.893455513052003e-06,
+      "loss": 0.9085,
+      "step": 24
+    },
+    {
+      "epoch": 0.12594458438287154,
+      "grad_norm": 4.050323486328125,
+      "learning_rate": 4.881385486702047e-06,
+      "loss": 0.8741,
+      "step": 25
+    },
+    {
+      "epoch": 0.1309823677581864,
+      "grad_norm": 4.825730800628662,
+      "learning_rate": 4.868684495393958e-06,
+      "loss": 0.8568,
+      "step": 26
+    },
+    {
+      "epoch": 0.13602015113350127,
+      "grad_norm": 4.85552978515625,
+      "learning_rate": 4.855355904345377e-06,
+      "loss": 0.9123,
+      "step": 27
+    },
+    {
+      "epoch": 0.14105793450881612,
+      "grad_norm": 3.755789041519165,
+      "learning_rate": 4.841403245060943e-06,
+      "loss": 0.9049,
+      "step": 28
+    },
+    {
+      "epoch": 0.14609571788413098,
+      "grad_norm": 4.334013938903809,
+      "learning_rate": 4.826830214396594e-06,
+      "loss": 0.8393,
+      "step": 29
+    },
+    {
+      "epoch": 0.15113350125944586,
+      "grad_norm": 4.264854907989502,
+      "learning_rate": 4.8116406735800645e-06,
+      "loss": 0.8636,
+      "step": 30
+    },
+    {
+      "epoch": 0.1561712846347607,
+      "grad_norm": 4.067491054534912,
+      "learning_rate": 4.7958386471878185e-06,
+      "loss": 0.9626,
+      "step": 31
+    },
+    {
+      "epoch": 0.16120906801007556,
+      "grad_norm": 3.913526773452759,
+      "learning_rate": 4.779428322078716e-06,
+      "loss": 0.8366,
+      "step": 32
+    },
+    {
+      "epoch": 0.16624685138539042,
+      "grad_norm": 4.512166500091553,
+      "learning_rate": 4.76241404628467e-06,
+      "loss": 0.8766,
+      "step": 33
+    },
+    {
+      "epoch": 0.1712846347607053,
+      "grad_norm": 3.469944477081299,
+      "learning_rate": 4.744800327858608e-06,
+      "loss": 0.8931,
+      "step": 34
+    },
+    {
+      "epoch": 0.17632241813602015,
+      "grad_norm": 3.761395215988159,
+      "learning_rate": 4.726591833680031e-06,
+      "loss": 0.9317,
+      "step": 35
+    },
+    {
+      "epoch": 0.181360201511335,
+      "grad_norm": 3.780844211578369,
+      "learning_rate": 4.7077933882184864e-06,
+      "loss": 0.8701,
+      "step": 36
+    },
+    {
+      "epoch": 0.18639798488664988,
+      "grad_norm": 3.842653751373291,
+      "learning_rate": 4.688409972255299e-06,
+      "loss": 0.8502,
+      "step": 37
+    },
+    {
+      "epoch": 0.19143576826196473,
+      "grad_norm": 3.1387386322021484,
+      "learning_rate": 4.6684467215638694e-06,
+      "loss": 0.8606,
+      "step": 38
+    },
+    {
+      "epoch": 0.1964735516372796,
+      "grad_norm": 5.945749282836914,
+      "learning_rate": 4.647908925548918e-06,
+      "loss": 0.8836,
+      "step": 39
+    },
+    {
+      "epoch": 0.20151133501259447,
+      "grad_norm": 3.8087077140808105,
+      "learning_rate": 4.626802025845023e-06,
+      "loss": 0.8729,
+      "step": 40
+    },
+    {
+      "epoch": 0.20654911838790932,
+      "grad_norm": 4.801278591156006,
+      "learning_rate": 4.605131614874813e-06,
+      "loss": 0.8895,
+      "step": 41
+    },
+    {
+      "epoch": 0.21158690176322417,
+      "grad_norm": 3.3816072940826416,
+      "learning_rate": 4.582903434367222e-06,
+      "loss": 0.875,
+      "step": 42
+    },
+    {
+      "epoch": 0.21662468513853905,
+      "grad_norm": 3.7405855655670166,
+      "learning_rate": 4.560123373836174e-06,
+      "loss": 0.8679,
+      "step": 43
+    },
+    {
+      "epoch": 0.2216624685138539,
+      "grad_norm": 3.2052128314971924,
+      "learning_rate": 4.536797469020116e-06,
+      "loss": 0.8453,
+      "step": 44
+    },
+    {
+      "epoch": 0.22670025188916876,
+      "grad_norm": 3.2078239917755127,
+      "learning_rate": 4.512931900282807e-06,
+      "loss": 0.8965,
+      "step": 45
+    },
+    {
+      "epoch": 0.23173803526448364,
+      "grad_norm": 3.318209409713745,
+      "learning_rate": 4.4885329909757836e-06,
+      "loss": 0.7962,
+      "step": 46
+    },
+    {
+      "epoch": 0.2367758186397985,
+      "grad_norm": 4.799398899078369,
+      "learning_rate": 4.463607205762948e-06,
+      "loss": 0.8804,
+      "step": 47
+    },
+    {
+      "epoch": 0.24181360201511334,
+      "grad_norm": 2.9974491596221924,
+      "learning_rate": 4.438161148907703e-06,
+      "loss": 0.8118,
+      "step": 48
+    },
+    {
+      "epoch": 0.24685138539042822,
+      "grad_norm": 2.7640256881713867,
+      "learning_rate": 4.4122015625231125e-06,
+      "loss": 0.8798,
+      "step": 49
+    },
+    {
+      "epoch": 0.2518891687657431,
+      "grad_norm": 3.4179089069366455,
+      "learning_rate": 4.385735324785528e-06,
+      "loss": 0.8466,
+      "step": 50
+    },
+    {
+      "epoch": 0.25692695214105793,
+      "grad_norm": 3.160508632659912,
+      "learning_rate": 4.3587694481121664e-06,
+      "loss": 0.8293,
+      "step": 51
+    },
+    {
+      "epoch": 0.2619647355163728,
+      "grad_norm": 3.2087128162384033,
+      "learning_rate": 4.331311077303119e-06,
+      "loss": 0.8523,
+      "step": 52
+    },
+    {
+      "epoch": 0.26700251889168763,
+      "grad_norm": 2.897143840789795,
+      "learning_rate": 4.303367487648289e-06,
+      "loss": 0.8541,
+      "step": 53
+    },
+    {
+      "epoch": 0.27204030226700254,
+      "grad_norm": 3.211749792098999,
+      "learning_rate": 4.274946082999753e-06,
+      "loss": 0.8348,
+      "step": 54
+    },
+    {
+      "epoch": 0.2770780856423174,
+      "grad_norm": 3.2269697189331055,
+      "learning_rate": 4.246054393810053e-06,
+      "loss": 0.8849,
+      "step": 55
+    },
+    {
+      "epoch": 0.28211586901763225,
+      "grad_norm": 3.219303607940674,
+      "learning_rate": 4.2167000751369535e-06,
+      "loss": 0.7562,
+      "step": 56
+    },
+    {
+      "epoch": 0.2871536523929471,
+      "grad_norm": 2.986050844192505,
+      "learning_rate": 4.186890904615178e-06,
+      "loss": 0.7716,
+      "step": 57
+    },
+    {
+      "epoch": 0.29219143576826195,
+      "grad_norm": 3.107534885406494,
+      "learning_rate": 4.156634780395672e-06,
+      "loss": 0.8897,
+      "step": 58
+    },
+    {
+      "epoch": 0.2972292191435768,
+      "grad_norm": 3.1411337852478027,
+      "learning_rate": 4.125939719052927e-06,
+      "loss": 0.8865,
+      "step": 59
+    },
+    {
+      "epoch": 0.3022670025188917,
+      "grad_norm": 3.5057530403137207,
+      "learning_rate": 4.094813853460938e-06,
+      "loss": 0.8619,
+      "step": 60
+    },
+    {
+      "epoch": 0.30730478589420657,
+      "grad_norm": 3.040756940841675,
+      "learning_rate": 4.063265430638338e-06,
+      "loss": 0.8592,
+      "step": 61
+    },
+    {
+      "epoch": 0.3123425692695214,
+      "grad_norm": 2.7552523612976074,
+      "learning_rate": 4.031302809563292e-06,
+      "loss": 0.7954,
+      "step": 62
+    },
+    {
+      "epoch": 0.31738035264483627,
+      "grad_norm": 2.9611120223999023,
+      "learning_rate": 3.998934458958726e-06,
+      "loss": 0.8734,
+      "step": 63
+    },
+    {
+      "epoch": 0.3224181360201511,
+      "grad_norm": 4.978094577789307,
+      "learning_rate": 3.96616895504848e-06,
+      "loss": 0.8818,
+      "step": 64
+    },
+    {
+      "epoch": 0.327455919395466,
+      "grad_norm": 4.14245080947876,
+      "learning_rate": 3.933014979284978e-06,
+      "loss": 0.8783,
+      "step": 65
+    },
+    {
+      "epoch": 0.33249370277078083,
+      "grad_norm": 2.922802209854126,
+      "learning_rate": 3.899481316049012e-06,
+      "loss": 0.8348,
+      "step": 66
+    },
+    {
+      "epoch": 0.33753148614609574,
+      "grad_norm": 2.9351940155029297,
+      "learning_rate": 3.86557685032226e-06,
+      "loss": 0.7839,
+      "step": 67
+    },
+    {
+      "epoch": 0.3425692695214106,
+      "grad_norm": 3.6585469245910645,
+      "learning_rate": 3.83131056533315e-06,
+      "loss": 0.9167,
+      "step": 68
+    },
+    {
+      "epoch": 0.34760705289672544,
+      "grad_norm": 2.93361496925354,
+      "learning_rate": 3.7966915401766845e-06,
+      "loss": 0.8308,
+      "step": 69
+    },
+    {
+      "epoch": 0.3526448362720403,
+      "grad_norm": 3.2033188343048096,
+      "learning_rate": 3.7617289474088725e-06,
+      "loss": 0.8435,
+      "step": 70
+    },
+    {
+      "epoch": 0.35768261964735515,
+      "grad_norm": 3.1813461780548096,
+      "learning_rate": 3.726432050616399e-06,
+      "loss": 0.9147,
+      "step": 71
+    },
+    {
+      "epoch": 0.36272040302267,
+      "grad_norm": 13.234034538269043,
+      "learning_rate": 3.6908102019621667e-06,
+      "loss": 0.8469,
+      "step": 72
+    },
+    {
+      "epoch": 0.3677581863979849,
+      "grad_norm": 4.6746392250061035,
+      "learning_rate": 3.6548728397073756e-06,
+      "loss": 0.8532,
+      "step": 73
+    },
+    {
+      "epoch": 0.37279596977329976,
+      "grad_norm": 2.943939447402954,
+      "learning_rate": 3.6186294857107933e-06,
+      "loss": 0.8466,
+      "step": 74
+    },
+    {
+      "epoch": 0.3778337531486146,
+      "grad_norm": 3.160301923751831,
+      "learning_rate": 3.582089742905864e-06,
+      "loss": 0.9207,
+      "step": 75
+    },
+    {
+      "epoch": 0.38287153652392947,
+      "grad_norm": 3.0454745292663574,
+      "learning_rate": 3.545263292756348e-06,
+      "loss": 0.8529,
+      "step": 76
+    },
+    {
+      "epoch": 0.3879093198992443,
+      "grad_norm": 2.6905884742736816,
+      "learning_rate": 3.5081598926911487e-06,
+      "loss": 0.823,
+      "step": 77
+    },
+    {
+      "epoch": 0.3929471032745592,
+      "grad_norm": 3.0475916862487793,
+      "learning_rate": 3.470789373519012e-06,
+      "loss": 0.8753,
+      "step": 78
+    },
+    {
+      "epoch": 0.3979848866498741,
+      "grad_norm": 3.0917882919311523,
+      "learning_rate": 3.433161636823782e-06,
+      "loss": 0.8456,
+      "step": 79
+    },
+    {
+      "epoch": 0.40302267002518893,
+      "grad_norm": 3.0129034519195557,
+      "learning_rate": 3.39528665234091e-06,
+      "loss": 0.8902,
+      "step": 80
+    },
+    {
+      "epoch": 0.4080604534005038,
+      "grad_norm": 2.6000654697418213,
+      "learning_rate": 3.3571744553159e-06,
+      "loss": 0.8188,
+      "step": 81
+    },
+    {
+      "epoch": 0.41309823677581864,
+      "grad_norm": 3.156890392303467,
+      "learning_rate": 3.3188351438454e-06,
+      "loss": 0.7446,
+      "step": 82
+    },
+    {
+      "epoch": 0.4181360201511335,
+      "grad_norm": 3.192892074584961,
+      "learning_rate": 3.2802788762016385e-06,
+      "loss": 0.9118,
+      "step": 83
+    },
+    {
+      "epoch": 0.42317380352644834,
+      "grad_norm": 5.0082621574401855,
+      "learning_rate": 3.2415158681409215e-06,
+      "loss": 0.832,
+      "step": 84
+    },
+    {
+      "epoch": 0.4282115869017632,
+      "grad_norm": 3.4209702014923096,
+      "learning_rate": 3.2025563901968903e-06,
+      "loss": 0.8107,
+      "step": 85
+    },
+    {
+      "epoch": 0.4332493702770781,
+      "grad_norm": 2.90742564201355,
+      "learning_rate": 3.1634107649592772e-06,
+      "loss": 0.8065,
+      "step": 86
+    },
+    {
+      "epoch": 0.43828715365239296,
+      "grad_norm": 3.0818216800689697,
+      "learning_rate": 3.1240893643388558e-06,
+      "loss": 0.8992,
+      "step": 87
+    },
+    {
+      "epoch": 0.4433249370277078,
+      "grad_norm": 2.713526725769043,
+      "learning_rate": 3.0846026068193354e-06,
+      "loss": 0.8297,
+      "step": 88
+    },
+    {
+      "epoch": 0.44836272040302266,
+      "grad_norm": 2.930645704269409,
+      "learning_rate": 3.044960954696906e-06,
+      "loss": 0.8479,
+      "step": 89
+    },
+    {
+      "epoch": 0.4534005037783375,
+      "grad_norm": 2.680250644683838,
+      "learning_rate": 3.00517491130818e-06,
+      "loss": 0.8159,
+      "step": 90
+    },
+    {
+      "epoch": 0.45843828715365237,
+      "grad_norm": 2.9555230140686035,
+      "learning_rate": 2.96525501824726e-06,
+      "loss": 0.9478,
+      "step": 91
+    },
+    {
+      "epoch": 0.4634760705289673,
+      "grad_norm": 4.101602554321289,
+      "learning_rate": 2.925211852572667e-06,
+      "loss": 0.8625,
+      "step": 92
+    },
+    {
+      "epoch": 0.46851385390428213,
+      "grad_norm": 5.067833423614502,
+      "learning_rate": 2.8850560240048737e-06,
+      "loss": 0.8574,
+      "step": 93
+    },
+    {
+      "epoch": 0.473551637279597,
+      "grad_norm": 2.771819591522217,
+      "learning_rate": 2.844798172115185e-06,
+      "loss": 0.871,
+      "step": 94
+    },
+    {
+      "epoch": 0.47858942065491183,
+      "grad_norm": 2.993462085723877,
+      "learning_rate": 2.80444896350671e-06,
+      "loss": 0.9423,
+      "step": 95
+    },
+    {
+      "epoch": 0.4836272040302267,
+      "grad_norm": 2.8279411792755127,
+      "learning_rate": 2.764019088988165e-06,
+      "loss": 0.8155,
+      "step": 96
+    },
+    {
+      "epoch": 0.48866498740554154,
+      "grad_norm": 2.840853452682495,
+      "learning_rate": 2.723519260741271e-06,
+      "loss": 0.8262,
+      "step": 97
+    },
+    {
+      "epoch": 0.49370277078085645,
+      "grad_norm": 3.424471378326416,
+      "learning_rate": 2.6829602094824864e-06,
+      "loss": 0.8527,
+      "step": 98
+    },
+    {
+      "epoch": 0.4987405541561713,
+      "grad_norm": 3.408869981765747,
+      "learning_rate": 2.6423526816198253e-06,
+      "loss": 0.8253,
+      "step": 99
+    },
+    {
+      "epoch": 0.5037783375314862,
+      "grad_norm": 5.029043674468994,
+      "learning_rate": 2.601707436405521e-06,
+      "loss": 0.8504,
+      "step": 100
+    },
+    {
+      "epoch": 0.5088161209068011,
+      "grad_norm": 3.400862216949463,
+      "learning_rate": 2.5610352430852888e-06,
+      "loss": 0.8509,
+      "step": 101
+    },
+    {
+      "epoch": 0.5138539042821159,
+      "grad_norm": 3.2282321453094482,
+      "learning_rate": 2.5203468780449324e-06,
+      "loss": 0.8145,
+      "step": 102
+    },
+    {
+      "epoch": 0.5188916876574308,
+      "grad_norm": 3.0265862941741943,
+      "learning_rate": 2.4796531219550684e-06,
+      "loss": 0.8479,
+      "step": 103
+    },
+    {
+      "epoch": 0.5239294710327456,
+      "grad_norm": 3.553727388381958,
+      "learning_rate": 2.438964756914712e-06,
+      "loss": 0.8581,
+      "step": 104
+    },
+    {
+      "epoch": 0.5289672544080605,
+      "grad_norm": 3.089478015899658,
+      "learning_rate": 2.398292563594479e-06,
+      "loss": 0.8849,
+      "step": 105
+    },
+    {
+      "epoch": 0.5340050377833753,
+      "grad_norm": 2.7626805305480957,
+      "learning_rate": 2.357647318380176e-06,
+      "loss": 0.8332,
+      "step": 106
+    },
+    {
+      "epoch": 0.5390428211586902,
+      "grad_norm": 3.013871192932129,
+      "learning_rate": 2.3170397905175144e-06,
+      "loss": 0.8032,
+      "step": 107
+    },
+    {
+      "epoch": 0.5440806045340051,
+      "grad_norm": 3.2517004013061523,
+      "learning_rate": 2.2764807392587303e-06,
+      "loss": 0.798,
+      "step": 108
+    },
+    {
+      "epoch": 0.5491183879093199,
+      "grad_norm": 14.13714599609375,
+      "learning_rate": 2.2359809110118358e-06,
+      "loss": 0.8714,
+      "step": 109
+    },
+    {
+      "epoch": 0.5541561712846348,
+      "grad_norm": 3.096505641937256,
+      "learning_rate": 2.1955510364932904e-06,
+      "loss": 0.7631,
+      "step": 110
+    },
+    {
+      "epoch": 0.5591939546599496,
+      "grad_norm": 2.820859432220459,
+      "learning_rate": 2.1552018278848145e-06,
+      "loss": 0.8005,
+      "step": 111
+    },
+    {
+      "epoch": 0.5642317380352645,
+      "grad_norm": 6.947901248931885,
+      "learning_rate": 2.1149439759951276e-06,
+      "loss": 0.799,
+      "step": 112
+    },
+    {
+      "epoch": 0.5692695214105793,
+      "grad_norm": 2.9445698261260986,
+      "learning_rate": 2.074788147427334e-06,
+      "loss": 0.806,
+      "step": 113
+    },
+    {
+      "epoch": 0.5743073047858942,
+      "grad_norm": 2.744227409362793,
+      "learning_rate": 2.034744981752741e-06,
+      "loss": 0.8305,
+      "step": 114
+    },
+    {
+      "epoch": 0.5793450881612091,
+      "grad_norm": 2.6451659202575684,
+      "learning_rate": 1.9948250886918204e-06,
+      "loss": 0.7354,
+      "step": 115
+    },
+    {
+      "epoch": 0.5843828715365239,
+      "grad_norm": 2.812647819519043,
+      "learning_rate": 1.955039045303095e-06,
+      "loss": 0.7877,
+      "step": 116
+    },
+    {
+      "epoch": 0.5894206549118388,
+      "grad_norm": 3.6654205322265625,
+      "learning_rate": 1.915397393180665e-06,
+      "loss": 0.8502,
+      "step": 117
+    },
+    {
+      "epoch": 0.5944584382871536,
+      "grad_norm": 3.1642322540283203,
+      "learning_rate": 1.8759106356611453e-06,
+      "loss": 0.8214,
+      "step": 118
+    },
+    {
+      "epoch": 0.5994962216624685,
+      "grad_norm": 2.7508504390716553,
+      "learning_rate": 1.8365892350407238e-06,
+      "loss": 0.8778,
+      "step": 119
+    },
+    {
+      "epoch": 0.6045340050377834,
+      "grad_norm": 2.832481622695923,
+      "learning_rate": 1.7974436098031105e-06,
+      "loss": 0.7971,
+      "step": 120
+    },
+    {
+      "epoch": 0.6095717884130982,
+      "grad_norm": 3.0751426219940186,
+      "learning_rate": 1.7584841318590796e-06,
+      "loss": 0.8394,
+      "step": 121
+    },
+    {
+      "epoch": 0.6146095717884131,
+      "grad_norm": 2.66140079498291,
+      "learning_rate": 1.719721123798362e-06,
+      "loss": 0.7793,
+      "step": 122
+    },
+    {
+      "epoch": 0.6196473551637279,
+      "grad_norm": 3.033729314804077,
+      "learning_rate": 1.6811648561546003e-06,
+      "loss": 0.7719,
+      "step": 123
+    },
+    {
+      "epoch": 0.6246851385390428,
+      "grad_norm": 24.4138240814209,
+      "learning_rate": 1.642825544684101e-06,
+      "loss": 0.8482,
+      "step": 124
+    },
+    {
+      "epoch": 0.6297229219143576,
+      "grad_norm": 3.2902424335479736,
+      "learning_rate": 1.6047133476590908e-06,
+      "loss": 0.8713,
+      "step": 125
+    },
+    {
+      "epoch": 0.6347607052896725,
+      "grad_norm": 2.7968010902404785,
+      "learning_rate": 1.566838363176219e-06,
+      "loss": 0.7406,
+      "step": 126
+    },
+    {
+      "epoch": 0.6397984886649875,
+      "grad_norm": 3.296938419342041,
+      "learning_rate": 1.5292106264809888e-06,
+      "loss": 0.7567,
+      "step": 127
+    },
+    {
+      "epoch": 0.6448362720403022,
+      "grad_norm": 2.7469353675842285,
+      "learning_rate": 1.4918401073088517e-06,
+      "loss": 0.8542,
+      "step": 128
+    },
+    {
+      "epoch": 0.6498740554156172,
+      "grad_norm": 2.775825262069702,
+      "learning_rate": 1.4547367072436519e-06,
+      "loss": 0.7611,
+      "step": 129
+    },
+    {
+      "epoch": 0.654911838790932,
+      "grad_norm": 3.243407726287842,
+      "learning_rate": 1.4179102570941368e-06,
+      "loss": 0.8393,
+      "step": 130
+    },
+    {
+      "epoch": 0.6599496221662469,
+      "grad_norm": 2.9354608058929443,
+      "learning_rate": 1.3813705142892082e-06,
+      "loss": 0.8897,
+      "step": 131
+    },
+    {
+      "epoch": 0.6649874055415617,
+      "grad_norm": 2.8261704444885254,
+      "learning_rate": 1.3451271602926248e-06,
+      "loss": 0.8167,
+      "step": 132
+    },
+    {
+      "epoch": 0.6700251889168766,
+      "grad_norm": 2.76542067527771,
+      "learning_rate": 1.309189798037834e-06,
+      "loss": 0.8355,
+      "step": 133
+    },
+    {
+      "epoch": 0.6750629722921915,
+      "grad_norm": 2.8934812545776367,
+      "learning_rate": 1.273567949383601e-06,
+      "loss": 0.8766,
+      "step": 134
+    },
+    {
+      "epoch": 0.6801007556675063,
+      "grad_norm": 3.0498292446136475,
+      "learning_rate": 1.238271052591127e-06,
+      "loss": 0.861,
+      "step": 135
+    },
+    {
+      "epoch": 0.6851385390428212,
+      "grad_norm": 2.881106376647949,
+      "learning_rate": 1.2033084598233163e-06,
+      "loss": 0.7946,
+      "step": 136
+    },
+    {
+      "epoch": 0.690176322418136,
+      "grad_norm": 2.83734130859375,
+      "learning_rate": 1.1686894346668512e-06,
+      "loss": 0.7484,
+      "step": 137
+    },
+    {
+      "epoch": 0.6952141057934509,
+      "grad_norm": 2.4155306816101074,
+      "learning_rate": 1.1344231496777406e-06,
+      "loss": 0.8025,
+      "step": 138
+    },
+    {
+      "epoch": 0.7002518891687658,
+      "grad_norm": 2.696739435195923,
+      "learning_rate": 1.1005186839509887e-06,
+      "loss": 0.7984,
+      "step": 139
+    },
+    {
+      "epoch": 0.7052896725440806,
+      "grad_norm": 2.9532501697540283,
+      "learning_rate": 1.066985020715022e-06,
+      "loss": 0.8436,
+      "step": 140
+    },
+    {
+      "epoch": 0.7103274559193955,
+      "grad_norm": 2.7825965881347656,
+      "learning_rate": 1.0338310449515197e-06,
+      "loss": 0.8718,
+      "step": 141
+    },
+    {
+      "epoch": 0.7153652392947103,
+      "grad_norm": 2.916924238204956,
+      "learning_rate": 1.0010655410412745e-06,
+      "loss": 0.7749,
+      "step": 142
+    },
+    {
+      "epoch": 0.7204030226700252,
+      "grad_norm": 2.610424757003784,
+      "learning_rate": 9.68697190436709e-07,
+      "loss": 0.7614,
+      "step": 143
+    },
+    {
+      "epoch": 0.72544080604534,
+      "grad_norm": 2.67132830619812,
+      "learning_rate": 9.367345693616625e-07,
+      "loss": 0.821,
+      "step": 144
+    },
+    {
+      "epoch": 0.7304785894206549,
+      "grad_norm": 2.876641035079956,
+      "learning_rate": 9.051861465390624e-07,
+      "loss": 0.7234,
+      "step": 145
+    },
+    {
+      "epoch": 0.7355163727959698,
+      "grad_norm": 2.9514031410217285,
+      "learning_rate": 8.740602809470736e-07,
+      "loss": 0.7861,
+      "step": 146
+    },
+    {
+      "epoch": 0.7405541561712846,
+      "grad_norm": 2.6026699542999268,
+      "learning_rate": 8.433652196043288e-07,
+      "loss": 0.8253,
+      "step": 147
+    },
+    {
+      "epoch": 0.7455919395465995,
+      "grad_norm": 2.879054069519043,
+      "learning_rate": 8.131090953848228e-07,
+      "loss": 0.7749,
+      "step": 148
+    },
+    {
+      "epoch": 0.7506297229219143,
+      "grad_norm": 2.8631882667541504,
+      "learning_rate": 7.832999248630479e-07,
+      "loss": 0.9273,
+      "step": 149
+    },
+    {
+      "epoch": 0.7556675062972292,
+      "grad_norm": 2.6118288040161133,
+      "learning_rate": 7.53945606189948e-07,
+      "loss": 0.8117,
+      "step": 150
+    },
+    {
+      "epoch": 0.760705289672544,
+      "grad_norm": 2.8277623653411865,
+      "learning_rate": 7.250539170002477e-07,
+      "loss": 0.7862,
+      "step": 151
+    },
+    {
+      "epoch": 0.7657430730478589,
+      "grad_norm": 5.133010387420654,
+      "learning_rate": 6.96632512351711e-07,
+      "loss": 0.8225,
+      "step": 152
+    },
+    {
+      "epoch": 0.7707808564231738,
+      "grad_norm": 2.7790756225585938,
+      "learning_rate": 6.686889226968815e-07,
+      "loss": 0.7539,
+      "step": 153
+    },
+    {
+      "epoch": 0.7758186397984886,
+      "grad_norm": 2.755314350128174,
+      "learning_rate": 6.412305518878343e-07,
+      "loss": 0.8238,
+      "step": 154
+    },
+    {
+      "epoch": 0.7808564231738035,
+      "grad_norm": 2.6783859729766846,
+      "learning_rate": 6.142646752144724e-07,
+      "loss": 0.7837,
+      "step": 155
+    },
+    {
+      "epoch": 0.7858942065491183,
+      "grad_norm": 2.760148763656616,
+      "learning_rate": 5.877984374768878e-07,
+      "loss": 0.8798,
+      "step": 156
+    },
+    {
+      "epoch": 0.7909319899244333,
+      "grad_norm": 2.8512697219848633,
+      "learning_rate": 5.618388510922979e-07,
+      "loss": 0.8237,
+      "step": 157
+    },
+    {
+      "epoch": 0.7959697732997482,
+      "grad_norm": 2.719089984893799,
+      "learning_rate": 5.363927942370528e-07,
+      "loss": 0.8031,
+      "step": 158
+    },
+    {
+      "epoch": 0.801007556675063,
+      "grad_norm": 7.449169158935547,
+      "learning_rate": 5.11467009024216e-07,
+      "loss": 0.7838,
+      "step": 159
+    },
+    {
+      "epoch": 0.8060453400503779,
+      "grad_norm": 3.0624005794525146,
+      "learning_rate": 4.870680997171934e-07,
+      "loss": 0.7585,
+      "step": 160
+    },
+    {
+      "epoch": 0.8110831234256927,
+      "grad_norm": 2.621262788772583,
+      "learning_rate": 4.6320253097988486e-07,
+      "loss": 0.8421,
+      "step": 161
+    },
+    {
+      "epoch": 0.8161209068010076,
+      "grad_norm": 3.4929068088531494,
+      "learning_rate": 4.398766261638271e-07,
+      "loss": 0.7814,
+      "step": 162
+    },
+    {
+      "epoch": 0.8211586901763224,
+      "grad_norm": 3.319396734237671,
+      "learning_rate": 4.170965656327791e-07,
+      "loss": 0.8786,
+      "step": 163
+    },
+    {
+      "epoch": 0.8261964735516373,
+      "grad_norm": 3.4810092449188232,
+      "learning_rate": 3.9486838512518777e-07,
+      "loss": 0.7662,
+      "step": 164
+    },
+    {
+      "epoch": 0.8312342569269522,
+      "grad_norm": 2.9049723148345947,
+      "learning_rate": 3.7319797415497737e-07,
+      "loss": 0.801,
+      "step": 165
+    },
+    {
+      "epoch": 0.836272040302267,
+      "grad_norm": 3.931922674179077,
+      "learning_rate": 3.5209107445108195e-07,
+      "loss": 0.8094,
+      "step": 166
+    },
+    {
+      "epoch": 0.8413098236775819,
+      "grad_norm": 2.9314591884613037,
+      "learning_rate": 3.3155327843613166e-07,
+      "loss": 0.7802,
+      "step": 167
+    },
+    {
+      "epoch": 0.8463476070528967,
+      "grad_norm": 2.7644076347351074,
+      "learning_rate": 3.1159002774470146e-07,
+      "loss": 0.8319,
+      "step": 168
+    },
+    {
+      "epoch": 0.8513853904282116,
+      "grad_norm": 2.9492383003234863,
+      "learning_rate": 2.9220661178151366e-07,
+      "loss": 0.7787,
+      "step": 169
+    },
+    {
+      "epoch": 0.8564231738035264,
+      "grad_norm": 2.547168254852295,
+      "learning_rate": 2.734081663199695e-07,
+      "loss": 0.7846,
+      "step": 170
+    },
+    {
+      "epoch": 0.8614609571788413,
+      "grad_norm": 3.1694071292877197,
+      "learning_rate": 2.551996721413916e-07,
+      "loss": 0.8104,
+      "step": 171
+    },
+    {
+      "epoch": 0.8664987405541562,
+      "grad_norm": 3.047084331512451,
+      "learning_rate": 2.375859537153302e-07,
+      "loss": 0.7466,
+      "step": 172
+    },
+    {
+      "epoch": 0.871536523929471,
+      "grad_norm": 2.832005262374878,
+      "learning_rate": 2.2057167792128493e-07,
+      "loss": 0.8075,
+      "step": 173
+    },
+    {
+      "epoch": 0.8765743073047859,
+      "grad_norm": 2.647271156311035,
+      "learning_rate": 2.0416135281218218e-07,
+      "loss": 0.8217,
+      "step": 174
+    },
+    {
+      "epoch": 0.8816120906801007,
+      "grad_norm": 2.717848539352417,
+      "learning_rate": 1.8835932641993627e-07,
+      "loss": 0.7855,
+      "step": 175
+    },
+    {
+      "epoch": 0.8866498740554156,
+      "grad_norm": 2.9493443965911865,
+      "learning_rate": 1.7316978560340647e-07,
+      "loss": 0.8201,
+      "step": 176
+    },
+    {
+      "epoch": 0.8916876574307305,
+      "grad_norm": 5.114314079284668,
+      "learning_rate": 1.5859675493905769e-07,
+      "loss": 0.7904,
+      "step": 177
+    },
+    {
+      "epoch": 0.8967254408060453,
+      "grad_norm": 2.8451216220855713,
+      "learning_rate": 1.4464409565462328e-07,
+      "loss": 0.805,
+      "step": 178
+    },
+    {
+      "epoch": 0.9017632241813602,
+      "grad_norm": 2.497908592224121,
+      "learning_rate": 1.3131550460604242e-07,
+      "loss": 0.7827,
+      "step": 179
+    },
+    {
+      "epoch": 0.906801007556675,
+      "grad_norm": 3.690392017364502,
+      "learning_rate": 1.1861451329795326e-07,
+      "loss": 0.7521,
+      "step": 180
+    },
+    {
+      "epoch": 0.9118387909319899,
+      "grad_norm": 3.2087209224700928,
+      "learning_rate": 1.065444869479973e-07,
+      "loss": 0.7203,
+      "step": 181
+    },
+    {
+      "epoch": 0.9168765743073047,
+      "grad_norm": 2.854456901550293,
+      "learning_rate": 9.510862359517815e-08,
+      "loss": 0.819,
+      "step": 182
+    },
+    {
+      "epoch": 0.9219143576826196,
+      "grad_norm": 2.9602978229522705,
+      "learning_rate": 8.430995325252128e-08,
+      "loss": 0.798,
+      "step": 183
+    },
+    {
+      "epoch": 0.9269521410579346,
+      "grad_norm": 2.870439052581787,
+      "learning_rate": 7.415133710424794e-08,
+      "loss": 0.79,
+      "step": 184
+    },
+    {
+      "epoch": 0.9319899244332494,
+      "grad_norm": 2.710660219192505,
+      "learning_rate": 6.463546674768644e-08,
+      "loss": 0.7406,
+      "step": 185
+    },
+    {
+      "epoch": 0.9370277078085643,
+      "grad_norm": 3.1572258472442627,
+      "learning_rate": 5.5764863480112233e-08,
+      "loss": 0.8467,
+      "step": 186
+    },
+    {
+      "epoch": 0.9420654911838791,
+      "grad_norm": 2.8733699321746826,
+      "learning_rate": 4.754187763071488e-08,
+      "loss": 0.7988,
+      "step": 187
+    },
+    {
+      "epoch": 0.947103274559194,
+      "grad_norm": 3.7968437671661377,
+      "learning_rate": 3.996868793785913e-08,
+      "loss": 0.7472,
+      "step": 188
+    },
+    {
+      "epoch": 0.9521410579345088,
+      "grad_norm": 2.6690640449523926,
+      "learning_rate": 3.304730097181463e-08,
+      "loss": 0.7358,
+      "step": 189
+    },
+    {
+      "epoch": 0.9571788413098237,
+      "grad_norm": 2.642486333847046,
+      "learning_rate": 2.6779550603100168e-08,
+      "loss": 0.865,
+      "step": 190
+    },
+    {
+      "epoch": 0.9622166246851386,
+      "grad_norm": 3.4199740886688232,
+      "learning_rate": 2.116709751658591e-08,
+      "loss": 0.7681,
+      "step": 191
+    },
+    {
+      "epoch": 0.9672544080604534,
+      "grad_norm": 2.9348366260528564,
+      "learning_rate": 1.6211428771484295e-08,
+      "loss": 0.9291,
+      "step": 192
+    },
+    {
+      "epoch": 0.9722921914357683,
+      "grad_norm": 2.5914723873138428,
+      "learning_rate": 1.1913857407343244e-08,
+      "loss": 0.7852,
+      "step": 193
+    },
+    {
+      "epoch": 0.9773299748110831,
+      "grad_norm": 2.9415173530578613,
+      "learning_rate": 8.275522096146404e-09,
+      "loss": 0.7209,
+      "step": 194
+    },
+    {
+      "epoch": 0.982367758186398,
+      "grad_norm": 2.919996976852417,
+      "learning_rate": 5.297386840614205e-09,
+      "loss": 0.8159,
+      "step": 195
+    },
+    {
+      "epoch": 0.9874055415617129,
+      "grad_norm": 3.5275845527648926,
+      "learning_rate": 2.9802407187842773e-09,
+      "loss": 0.7429,
+      "step": 196
+    },
+    {
+      "epoch": 0.9924433249370277,
+      "grad_norm": 2.8735129833221436,
+      "learning_rate": 1.3246976749395346e-09,
+      "loss": 0.8319,
+      "step": 197
+    },
+    {
+      "epoch": 0.9974811083123426,
+      "grad_norm": 2.514472246170044,
+      "learning_rate": 3.3119635694023324e-10,
+      "loss": 0.7523,
+      "step": 198
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 3.6349916458129883,
+      "learning_rate": 0.0,
+      "loss": 0.8407,
+      "step": 199
+    },
+    {
+      "epoch": 1.0,
+      "step": 199,
+      "total_flos": 258447595339776.0,
+      "train_loss": 0.8690116378530186,
+      "train_runtime": 2505.9387,
+      "train_samples_per_second": 2.532,
+      "train_steps_per_second": 0.079
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 199,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 258447595339776.0,
+  "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:d6c5b1267be55c109c9dacb1344e07906b5a379cb11210552f709e35898a8983
+size 8977

video_preprocessor_config.json

@@ -0,0 +1,41 @@
+{
+  "crop_size": null,
+  "data_format": "channels_first",
+  "default_to_square": true,
+  "device": null,
+  "do_center_crop": null,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_rescale": true,
+  "do_resize": true,
+  "do_sample_frames": true,
+  "fps": 2,
+  "image_mean": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "image_std": [
+    0.5,
+    0.5,
+    0.5
+  ],
+  "input_data_format": null,
+  "max_frames": 768,
+  "merge_size": 2,
+  "min_frames": 4,
+  "num_frames": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_metadata": false,
+  "size": {
+    "longest_edge": 25165824,
+    "shortest_edge": 4096
+  },
+  "temporal_patch_size": 2,
+  "video_metadata": null,
+  "video_processor_type": "Qwen3VLVideoProcessor"
+}