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 +1,2276 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 319,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003134796238244514,
+      "grad_norm": 43.949100494384766,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 1.8127,
+      "step": 1
+    },
+    {
+      "epoch": 0.006269592476489028,
+      "grad_norm": 46.380184173583984,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 1.782,
+      "step": 2
+    },
+    {
+      "epoch": 0.009404388714733543,
+      "grad_norm": 42.30755615234375,
+      "learning_rate": 1.5e-06,
+      "loss": 1.7996,
+      "step": 3
+    },
+    {
+      "epoch": 0.012539184952978056,
+      "grad_norm": 42.93296813964844,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 1.789,
+      "step": 4
+    },
+    {
+      "epoch": 0.01567398119122257,
+      "grad_norm": 38.31450653076172,
+      "learning_rate": 2.5e-06,
+      "loss": 1.6763,
+      "step": 5
+    },
+    {
+      "epoch": 0.018808777429467086,
+      "grad_norm": 30.79650115966797,
+      "learning_rate": 3e-06,
+      "loss": 1.4802,
+      "step": 6
+    },
+    {
+      "epoch": 0.0219435736677116,
+      "grad_norm": 37.57395935058594,
+      "learning_rate": 3.5e-06,
+      "loss": 1.4183,
+      "step": 7
+    },
+    {
+      "epoch": 0.025078369905956112,
+      "grad_norm": 19.238168716430664,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.1746,
+      "step": 8
+    },
+    {
+      "epoch": 0.02821316614420063,
+      "grad_norm": 20.116256713867188,
+      "learning_rate": 4.5e-06,
+      "loss": 1.0266,
+      "step": 9
+    },
+    {
+      "epoch": 0.03134796238244514,
+      "grad_norm": 8.39165210723877,
+      "learning_rate": 5e-06,
+      "loss": 0.9115,
+      "step": 10
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 9.131606101989746,
+      "learning_rate": 4.9998707921028104e-06,
+      "loss": 0.8921,
+      "step": 11
+    },
+    {
+      "epoch": 0.03761755485893417,
+      "grad_norm": 6.591880798339844,
+      "learning_rate": 4.999483181766986e-06,
+      "loss": 0.8571,
+      "step": 12
+    },
+    {
+      "epoch": 0.04075235109717868,
+      "grad_norm": 6.148767948150635,
+      "learning_rate": 4.998837209058379e-06,
+      "loss": 0.8377,
+      "step": 13
+    },
+    {
+      "epoch": 0.0438871473354232,
+      "grad_norm": 5.670365333557129,
+      "learning_rate": 4.997932940748811e-06,
+      "loss": 0.8791,
+      "step": 14
+    },
+    {
+      "epoch": 0.047021943573667714,
+      "grad_norm": 4.403618335723877,
+      "learning_rate": 4.996770470309167e-06,
+      "loss": 0.892,
+      "step": 15
+    },
+    {
+      "epoch": 0.050156739811912224,
+      "grad_norm": 3.835578441619873,
+      "learning_rate": 4.995349917899735e-06,
+      "loss": 0.7415,
+      "step": 16
+    },
+    {
+      "epoch": 0.05329153605015674,
+      "grad_norm": 4.489407062530518,
+      "learning_rate": 4.993671430357788e-06,
+      "loss": 0.7822,
+      "step": 17
+    },
+    {
+      "epoch": 0.05642633228840126,
+      "grad_norm": 5.612992763519287,
+      "learning_rate": 4.991735181182401e-06,
+      "loss": 0.7184,
+      "step": 18
+    },
+    {
+      "epoch": 0.05956112852664577,
+      "grad_norm": 13.66352367401123,
+      "learning_rate": 4.989541370516523e-06,
+      "loss": 0.7222,
+      "step": 19
+    },
+    {
+      "epoch": 0.06269592476489028,
+      "grad_norm": 3.666353940963745,
+      "learning_rate": 4.987090225126285e-06,
+      "loss": 0.7231,
+      "step": 20
+    },
+    {
+      "epoch": 0.06583072100313479,
+      "grad_norm": 4.0020294189453125,
+      "learning_rate": 4.9843819983775575e-06,
+      "loss": 0.7674,
+      "step": 21
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 3.6200690269470215,
+      "learning_rate": 4.98141697020977e-06,
+      "loss": 0.7478,
+      "step": 22
+    },
+    {
+      "epoch": 0.07210031347962383,
+      "grad_norm": 3.7657089233398438,
+      "learning_rate": 4.978195447106965e-06,
+      "loss": 0.7388,
+      "step": 23
+    },
+    {
+      "epoch": 0.07523510971786834,
+      "grad_norm": 3.262274742126465,
+      "learning_rate": 4.974717762066123e-06,
+      "loss": 0.7176,
+      "step": 24
+    },
+    {
+      "epoch": 0.07836990595611286,
+      "grad_norm": 3.8943138122558594,
+      "learning_rate": 4.970984274562741e-06,
+      "loss": 0.6745,
+      "step": 25
+    },
+    {
+      "epoch": 0.08150470219435736,
+      "grad_norm": 3.2295124530792236,
+      "learning_rate": 4.966995370513675e-06,
+      "loss": 0.7079,
+      "step": 26
+    },
+    {
+      "epoch": 0.08463949843260188,
+      "grad_norm": 4.9130730628967285,
+      "learning_rate": 4.962751462237248e-06,
+      "loss": 0.7824,
+      "step": 27
+    },
+    {
+      "epoch": 0.0877742946708464,
+      "grad_norm": 3.4682295322418213,
+      "learning_rate": 4.958252988410631e-06,
+      "loss": 0.7122,
+      "step": 28
+    },
+    {
+      "epoch": 0.09090909090909091,
+      "grad_norm": 3.1807892322540283,
+      "learning_rate": 4.9535004140245005e-06,
+      "loss": 0.752,
+      "step": 29
+    },
+    {
+      "epoch": 0.09404388714733543,
+      "grad_norm": 6.412112712860107,
+      "learning_rate": 4.94849423033497e-06,
+      "loss": 0.7503,
+      "step": 30
+    },
+    {
+      "epoch": 0.09717868338557993,
+      "grad_norm": 3.3517048358917236,
+      "learning_rate": 4.943234954812812e-06,
+      "loss": 0.6783,
+      "step": 31
+    },
+    {
+      "epoch": 0.10031347962382445,
+      "grad_norm": 3.2728397846221924,
+      "learning_rate": 4.937723131089974e-06,
+      "loss": 0.713,
+      "step": 32
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 3.6628053188323975,
+      "learning_rate": 4.931959328903376e-06,
+      "loss": 0.6842,
+      "step": 33
+    },
+    {
+      "epoch": 0.10658307210031348,
+      "grad_norm": 4.155019283294678,
+      "learning_rate": 4.925944144036027e-06,
+      "loss": 0.6627,
+      "step": 34
+    },
+    {
+      "epoch": 0.109717868338558,
+      "grad_norm": 2.7333738803863525,
+      "learning_rate": 4.919678198255438e-06,
+      "loss": 0.6807,
+      "step": 35
+    },
+    {
+      "epoch": 0.11285266457680251,
+      "grad_norm": 3.560575246810913,
+      "learning_rate": 4.91316213924935e-06,
+      "loss": 0.6802,
+      "step": 36
+    },
+    {
+      "epoch": 0.11598746081504702,
+      "grad_norm": 2.562624454498291,
+      "learning_rate": 4.90639664055879e-06,
+      "loss": 0.6264,
+      "step": 37
+    },
+    {
+      "epoch": 0.11912225705329153,
+      "grad_norm": 5.172059059143066,
+      "learning_rate": 4.899382401508446e-06,
+      "loss": 0.6783,
+      "step": 38
+    },
+    {
+      "epoch": 0.12225705329153605,
+      "grad_norm": 3.2025134563446045,
+      "learning_rate": 4.892120147134378e-06,
+      "loss": 0.7013,
+      "step": 39
+    },
+    {
+      "epoch": 0.12539184952978055,
+      "grad_norm": 2.37896466255188,
+      "learning_rate": 4.884610628109082e-06,
+      "loss": 0.6241,
+      "step": 40
+    },
+    {
+      "epoch": 0.12852664576802508,
+      "grad_norm": 2.381072759628296,
+      "learning_rate": 4.876854620663887e-06,
+      "loss": 0.6328,
+      "step": 41
+    },
+    {
+      "epoch": 0.13166144200626959,
+      "grad_norm": 2.695284605026245,
+      "learning_rate": 4.868852926508721e-06,
+      "loss": 0.6626,
+      "step": 42
+    },
+    {
+      "epoch": 0.13479623824451412,
+      "grad_norm": 6.515556335449219,
+      "learning_rate": 4.860606372749247e-06,
+      "loss": 0.7056,
+      "step": 43
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 3.1236801147460938,
+      "learning_rate": 4.8521158118013605e-06,
+      "loss": 0.678,
+      "step": 44
+    },
+    {
+      "epoch": 0.14106583072100312,
+      "grad_norm": 3.5594000816345215,
+      "learning_rate": 4.843382121303082e-06,
+      "loss": 0.6649,
+      "step": 45
+    },
+    {
+      "epoch": 0.14420062695924765,
+      "grad_norm": 2.737841844558716,
+      "learning_rate": 4.83440620402384e-06,
+      "loss": 0.5953,
+      "step": 46
+    },
+    {
+      "epoch": 0.14733542319749215,
+      "grad_norm": 2.5807104110717773,
+      "learning_rate": 4.825188987771149e-06,
+      "loss": 0.6678,
+      "step": 47
+    },
+    {
+      "epoch": 0.15047021943573669,
+      "grad_norm": 2.5918169021606445,
+      "learning_rate": 4.815731425294716e-06,
+      "loss": 0.7223,
+      "step": 48
+    },
+    {
+      "epoch": 0.1536050156739812,
+      "grad_norm": 2.677417278289795,
+      "learning_rate": 4.806034494187949e-06,
+      "loss": 0.6688,
+      "step": 49
+    },
+    {
+      "epoch": 0.15673981191222572,
+      "grad_norm": 2.6603641510009766,
+      "learning_rate": 4.796099196786908e-06,
+      "loss": 0.6652,
+      "step": 50
+    },
+    {
+      "epoch": 0.15987460815047022,
+      "grad_norm": 2.502426862716675,
+      "learning_rate": 4.785926560066703e-06,
+      "loss": 0.6092,
+      "step": 51
+    },
+    {
+      "epoch": 0.16300940438871472,
+      "grad_norm": 6.598116397857666,
+      "learning_rate": 4.775517635535332e-06,
+      "loss": 0.6496,
+      "step": 52
+    },
+    {
+      "epoch": 0.16614420062695925,
+      "grad_norm": 3.122972249984741,
+      "learning_rate": 4.764873499124997e-06,
+      "loss": 0.6687,
+      "step": 53
+    },
+    {
+      "epoch": 0.16927899686520376,
+      "grad_norm": 3.360384225845337,
+      "learning_rate": 4.753995251080884e-06,
+      "loss": 0.6911,
+      "step": 54
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 2.609579563140869,
+      "learning_rate": 4.742884015847436e-06,
+      "loss": 0.6397,
+      "step": 55
+    },
+    {
+      "epoch": 0.1755485893416928,
+      "grad_norm": 2.5354106426239014,
+      "learning_rate": 4.731540941952126e-06,
+      "loss": 0.6009,
+      "step": 56
+    },
+    {
+      "epoch": 0.1786833855799373,
+      "grad_norm": 2.5063207149505615,
+      "learning_rate": 4.719967201886734e-06,
+      "loss": 0.5991,
+      "step": 57
+    },
+    {
+      "epoch": 0.18181818181818182,
+      "grad_norm": 2.7579185962677,
+      "learning_rate": 4.708163991986152e-06,
+      "loss": 0.6064,
+      "step": 58
+    },
+    {
+      "epoch": 0.18495297805642633,
+      "grad_norm": 2.891486883163452,
+      "learning_rate": 4.696132532304727e-06,
+      "loss": 0.6391,
+      "step": 59
+    },
+    {
+      "epoch": 0.18808777429467086,
+      "grad_norm": 2.916727304458618,
+      "learning_rate": 4.683874066490143e-06,
+      "loss": 0.6727,
+      "step": 60
+    },
+    {
+      "epoch": 0.19122257053291536,
+      "grad_norm": 2.708406686782837,
+      "learning_rate": 4.671389861654873e-06,
+      "loss": 0.6499,
+      "step": 61
+    },
+    {
+      "epoch": 0.19435736677115986,
+      "grad_norm": 4.942819118499756,
+      "learning_rate": 4.658681208245198e-06,
+      "loss": 0.6356,
+      "step": 62
+    },
+    {
+      "epoch": 0.1974921630094044,
+      "grad_norm": 3.262690544128418,
+      "learning_rate": 4.645749419907829e-06,
+      "loss": 0.6732,
+      "step": 63
+    },
+    {
+      "epoch": 0.2006269592476489,
+      "grad_norm": 2.6621508598327637,
+      "learning_rate": 4.632595833354105e-06,
+      "loss": 0.6615,
+      "step": 64
+    },
+    {
+      "epoch": 0.20376175548589343,
+      "grad_norm": 2.9821105003356934,
+      "learning_rate": 4.619221808221833e-06,
+      "loss": 0.6667,
+      "step": 65
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 5.076481342315674,
+      "learning_rate": 4.605628726934747e-06,
+      "loss": 0.6505,
+      "step": 66
+    },
+    {
+      "epoch": 0.21003134796238246,
+      "grad_norm": 4.245087623596191,
+      "learning_rate": 4.5918179945596055e-06,
+      "loss": 0.6129,
+      "step": 67
+    },
+    {
+      "epoch": 0.21316614420062696,
+      "grad_norm": 3.060851812362671,
+      "learning_rate": 4.577791038660959e-06,
+      "loss": 0.6436,
+      "step": 68
+    },
+    {
+      "epoch": 0.21630094043887146,
+      "grad_norm": 3.0752642154693604,
+      "learning_rate": 4.563549309153589e-06,
+      "loss": 0.6957,
+      "step": 69
+    },
+    {
+      "epoch": 0.219435736677116,
+      "grad_norm": 2.996229887008667,
+      "learning_rate": 4.549094278152631e-06,
+      "loss": 0.6877,
+      "step": 70
+    },
+    {
+      "epoch": 0.2225705329153605,
+      "grad_norm": 4.217442035675049,
+      "learning_rate": 4.534427439821416e-06,
+      "loss": 0.6231,
+      "step": 71
+    },
+    {
+      "epoch": 0.22570532915360503,
+      "grad_norm": 3.009230136871338,
+      "learning_rate": 4.519550310217013e-06,
+      "loss": 0.6574,
+      "step": 72
+    },
+    {
+      "epoch": 0.22884012539184953,
+      "grad_norm": 3.037616491317749,
+      "learning_rate": 4.504464427133527e-06,
+      "loss": 0.6238,
+      "step": 73
+    },
+    {
+      "epoch": 0.23197492163009403,
+      "grad_norm": 3.02176833152771,
+      "learning_rate": 4.489171349943144e-06,
+      "loss": 0.6985,
+      "step": 74
+    },
+    {
+      "epoch": 0.23510971786833856,
+      "grad_norm": 3.0625197887420654,
+      "learning_rate": 4.473672659434941e-06,
+      "loss": 0.7531,
+      "step": 75
+    },
+    {
+      "epoch": 0.23824451410658307,
+      "grad_norm": 3.099853277206421,
+      "learning_rate": 4.457969957651485e-06,
+      "loss": 0.6188,
+      "step": 76
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 3.041682004928589,
+      "learning_rate": 4.442064867723236e-06,
+      "loss": 0.6754,
+      "step": 77
+    },
+    {
+      "epoch": 0.2445141065830721,
+      "grad_norm": 2.7343809604644775,
+      "learning_rate": 4.425959033700776e-06,
+      "loss": 0.615,
+      "step": 78
+    },
+    {
+      "epoch": 0.2476489028213166,
+      "grad_norm": 2.6281471252441406,
+      "learning_rate": 4.409654120384863e-06,
+      "loss": 0.6247,
+      "step": 79
+    },
+    {
+      "epoch": 0.2507836990595611,
+      "grad_norm": 2.4146194458007812,
+      "learning_rate": 4.393151813154345e-06,
+      "loss": 0.6237,
+      "step": 80
+    },
+    {
+      "epoch": 0.25391849529780564,
+      "grad_norm": 2.641150712966919,
+      "learning_rate": 4.3764538177919555e-06,
+      "loss": 0.5891,
+      "step": 81
+    },
+    {
+      "epoch": 0.25705329153605017,
+      "grad_norm": 2.4911434650421143,
+      "learning_rate": 4.35956186030799e-06,
+      "loss": 0.6456,
+      "step": 82
+    },
+    {
+      "epoch": 0.2601880877742947,
+      "grad_norm": 3.6674325466156006,
+      "learning_rate": 4.3424776867618935e-06,
+      "loss": 0.5946,
+      "step": 83
+    },
+    {
+      "epoch": 0.26332288401253917,
+      "grad_norm": 8.596332550048828,
+      "learning_rate": 4.325203063081776e-06,
+      "loss": 0.6133,
+      "step": 84
+    },
+    {
+      "epoch": 0.2664576802507837,
+      "grad_norm": 2.6561825275421143,
+      "learning_rate": 4.307739774881878e-06,
+      "loss": 0.6654,
+      "step": 85
+    },
+    {
+      "epoch": 0.26959247648902823,
+      "grad_norm": 3.8426294326782227,
+      "learning_rate": 4.290089627277998e-06,
+      "loss": 0.6124,
+      "step": 86
+    },
+    {
+      "epoch": 0.2727272727272727,
+      "grad_norm": 3.1375346183776855,
+      "learning_rate": 4.2722544447008995e-06,
+      "loss": 0.6183,
+      "step": 87
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 2.7622690200805664,
+      "learning_rate": 4.254236070707734e-06,
+      "loss": 0.6555,
+      "step": 88
+    },
+    {
+      "epoch": 0.27899686520376177,
+      "grad_norm": 2.8743462562561035,
+      "learning_rate": 4.236036367791471e-06,
+      "loss": 0.5867,
+      "step": 89
+    },
+    {
+      "epoch": 0.28213166144200624,
+      "grad_norm": 2.7058961391448975,
+      "learning_rate": 4.2176572171883865e-06,
+      "loss": 0.6346,
+      "step": 90
+    },
+    {
+      "epoch": 0.2852664576802508,
+      "grad_norm": 2.520024538040161,
+      "learning_rate": 4.199100518683601e-06,
+      "loss": 0.646,
+      "step": 91
+    },
+    {
+      "epoch": 0.2884012539184953,
+      "grad_norm": 2.6446547508239746,
+      "learning_rate": 4.18036819041471e-06,
+      "loss": 0.6502,
+      "step": 92
+    },
+    {
+      "epoch": 0.29153605015673983,
+      "grad_norm": 2.559896945953369,
+      "learning_rate": 4.161462168673508e-06,
+      "loss": 0.6166,
+      "step": 93
+    },
+    {
+      "epoch": 0.2946708463949843,
+      "grad_norm": 2.6093804836273193,
+      "learning_rate": 4.142384407705846e-06,
+      "loss": 0.607,
+      "step": 94
+    },
+    {
+      "epoch": 0.29780564263322884,
+      "grad_norm": 2.8598270416259766,
+      "learning_rate": 4.123136879509626e-06,
+      "loss": 0.6094,
+      "step": 95
+    },
+    {
+      "epoch": 0.30094043887147337,
+      "grad_norm": 2.6045126914978027,
+      "learning_rate": 4.103721573630965e-06,
+      "loss": 0.6639,
+      "step": 96
+    },
+    {
+      "epoch": 0.30407523510971785,
+      "grad_norm": 2.7823448181152344,
+      "learning_rate": 4.084140496958539e-06,
+      "loss": 0.6341,
+      "step": 97
+    },
+    {
+      "epoch": 0.3072100313479624,
+      "grad_norm": 2.320493459701538,
+      "learning_rate": 4.06439567351614e-06,
+      "loss": 0.5939,
+      "step": 98
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 2.2848961353302,
+      "learning_rate": 4.0444891442534615e-06,
+      "loss": 0.5916,
+      "step": 99
+    },
+    {
+      "epoch": 0.31347962382445144,
+      "grad_norm": 2.4216668605804443,
+      "learning_rate": 4.024422966835137e-06,
+      "loss": 0.6116,
+      "step": 100
+    },
+    {
+      "epoch": 0.3166144200626959,
+      "grad_norm": 2.654069185256958,
+      "learning_rate": 4.004199215428032e-06,
+      "loss": 0.654,
+      "step": 101
+    },
+    {
+      "epoch": 0.31974921630094044,
+      "grad_norm": 2.4687626361846924,
+      "learning_rate": 3.9838199804868635e-06,
+      "loss": 0.6136,
+      "step": 102
+    },
+    {
+      "epoch": 0.322884012539185,
+      "grad_norm": 3.22712779045105,
+      "learning_rate": 3.963287368538105e-06,
+      "loss": 0.6208,
+      "step": 103
+    },
+    {
+      "epoch": 0.32601880877742945,
+      "grad_norm": 2.4066531658172607,
+      "learning_rate": 3.942603501962249e-06,
+      "loss": 0.6191,
+      "step": 104
+    },
+    {
+      "epoch": 0.329153605015674,
+      "grad_norm": 2.9688427448272705,
+      "learning_rate": 3.92177051877442e-06,
+      "loss": 0.6132,
+      "step": 105
+    },
+    {
+      "epoch": 0.3322884012539185,
+      "grad_norm": 2.6026861667633057,
+      "learning_rate": 3.900790572403376e-06,
+      "loss": 0.5957,
+      "step": 106
+    },
+    {
+      "epoch": 0.335423197492163,
+      "grad_norm": 3.1237998008728027,
+      "learning_rate": 3.8796658314689205e-06,
+      "loss": 0.6267,
+      "step": 107
+    },
+    {
+      "epoch": 0.3385579937304075,
+      "grad_norm": 2.7337708473205566,
+      "learning_rate": 3.858398479557739e-06,
+      "loss": 0.6635,
+      "step": 108
+    },
+    {
+      "epoch": 0.34169278996865204,
+      "grad_norm": 2.707108497619629,
+      "learning_rate": 3.836990714997686e-06,
+      "loss": 0.6217,
+      "step": 109
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 2.4689037799835205,
+      "learning_rate": 3.815444750630555e-06,
+      "loss": 0.6364,
+      "step": 110
+    },
+    {
+      "epoch": 0.34796238244514105,
+      "grad_norm": 2.9303574562072754,
+      "learning_rate": 3.7937628135833453e-06,
+      "loss": 0.6117,
+      "step": 111
+    },
+    {
+      "epoch": 0.3510971786833856,
+      "grad_norm": 2.5677459239959717,
+      "learning_rate": 3.7719471450380518e-06,
+      "loss": 0.6007,
+      "step": 112
+    },
+    {
+      "epoch": 0.3542319749216301,
+      "grad_norm": 2.688203811645508,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.5778,
+      "step": 113
+    },
+    {
+      "epoch": 0.3573667711598746,
+      "grad_norm": 2.5018489360809326,
+      "learning_rate": 3.7279236470647593e-06,
+      "loss": 0.5826,
+      "step": 114
+    },
+    {
+      "epoch": 0.3605015673981191,
+      "grad_norm": 2.8333818912506104,
+      "learning_rate": 3.7057203681836407e-06,
+      "loss": 0.59,
+      "step": 115
+    },
+    {
+      "epoch": 0.36363636363636365,
+      "grad_norm": 2.9619221687316895,
+      "learning_rate": 3.683392458427825e-06,
+      "loss": 0.6616,
+      "step": 116
+    },
+    {
+      "epoch": 0.3667711598746082,
+      "grad_norm": 2.860719919204712,
+      "learning_rate": 3.660942225751126e-06,
+      "loss": 0.5618,
+      "step": 117
+    },
+    {
+      "epoch": 0.36990595611285265,
+      "grad_norm": 2.507951021194458,
+      "learning_rate": 3.638371990751428e-06,
+      "loss": 0.6305,
+      "step": 118
+    },
+    {
+      "epoch": 0.3730407523510972,
+      "grad_norm": 2.5088613033294678,
+      "learning_rate": 3.615684086430815e-06,
+      "loss": 0.5831,
+      "step": 119
+    },
+    {
+      "epoch": 0.3761755485893417,
+      "grad_norm": 2.534837245941162,
+      "learning_rate": 3.592880857954413e-06,
+      "loss": 0.5818,
+      "step": 120
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 2.4578607082366943,
+      "learning_rate": 3.5699646624079824e-06,
+      "loss": 0.6267,
+      "step": 121
+    },
+    {
+      "epoch": 0.3824451410658307,
+      "grad_norm": 2.6599507331848145,
+      "learning_rate": 3.5469378685542742e-06,
+      "loss": 0.5954,
+      "step": 122
+    },
+    {
+      "epoch": 0.38557993730407525,
+      "grad_norm": 3.10658597946167,
+      "learning_rate": 3.52380285658818e-06,
+      "loss": 0.5963,
+      "step": 123
+    },
+    {
+      "epoch": 0.3887147335423197,
+      "grad_norm": 2.4190332889556885,
+      "learning_rate": 3.500562017890695e-06,
+      "loss": 0.6224,
+      "step": 124
+    },
+    {
+      "epoch": 0.39184952978056425,
+      "grad_norm": 3.2278661727905273,
+      "learning_rate": 3.4772177547817387e-06,
+      "loss": 0.6182,
+      "step": 125
+    },
+    {
+      "epoch": 0.3949843260188088,
+      "grad_norm": 2.7765655517578125,
+      "learning_rate": 3.4537724802718294e-06,
+      "loss": 0.6399,
+      "step": 126
+    },
+    {
+      "epoch": 0.3981191222570533,
+      "grad_norm": 2.6910951137542725,
+      "learning_rate": 3.430228617812661e-06,
+      "loss": 0.5898,
+      "step": 127
+    },
+    {
+      "epoch": 0.4012539184952978,
+      "grad_norm": 4.030726909637451,
+      "learning_rate": 3.4065886010466014e-06,
+      "loss": 0.6093,
+      "step": 128
+    },
+    {
+      "epoch": 0.4043887147335423,
+      "grad_norm": 2.7327334880828857,
+      "learning_rate": 3.382854873555137e-06,
+      "loss": 0.5574,
+      "step": 129
+    },
+    {
+      "epoch": 0.40752351097178685,
+      "grad_norm": 3.4407501220703125,
+      "learning_rate": 3.3590298886062833e-06,
+      "loss": 0.6339,
+      "step": 130
+    },
+    {
+      "epoch": 0.4106583072100313,
+      "grad_norm": 2.798560380935669,
+      "learning_rate": 3.3351161089010055e-06,
+      "loss": 0.6152,
+      "step": 131
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 2.4109294414520264,
+      "learning_rate": 3.3111160063186553e-06,
+      "loss": 0.5964,
+      "step": 132
+    },
+    {
+      "epoch": 0.4169278996865204,
+      "grad_norm": 6.183897018432617,
+      "learning_rate": 3.2870320616614626e-06,
+      "loss": 0.5906,
+      "step": 133
+    },
+    {
+      "epoch": 0.4200626959247649,
+      "grad_norm": 2.960341691970825,
+      "learning_rate": 3.2628667643981036e-06,
+      "loss": 0.663,
+      "step": 134
+    },
+    {
+      "epoch": 0.4231974921630094,
+      "grad_norm": 2.809236764907837,
+      "learning_rate": 3.238622612406373e-06,
+      "loss": 0.6198,
+      "step": 135
+    },
+    {
+      "epoch": 0.4263322884012539,
+      "grad_norm": 3.4371628761291504,
+      "learning_rate": 3.21430211171499e-06,
+      "loss": 0.6275,
+      "step": 136
+    },
+    {
+      "epoch": 0.42946708463949845,
+      "grad_norm": 3.0913808345794678,
+      "learning_rate": 3.189907776244556e-06,
+      "loss": 0.6232,
+      "step": 137
+    },
+    {
+      "epoch": 0.43260188087774293,
+      "grad_norm": 2.930027961730957,
+      "learning_rate": 3.1654421275477045e-06,
+      "loss": 0.5638,
+      "step": 138
+    },
+    {
+      "epoch": 0.43573667711598746,
+      "grad_norm": 2.9050416946411133,
+      "learning_rate": 3.1409076945484513e-06,
+      "loss": 0.621,
+      "step": 139
+    },
+    {
+      "epoch": 0.438871473354232,
+      "grad_norm": 2.39300274848938,
+      "learning_rate": 3.116307013280793e-06,
+      "loss": 0.5852,
+      "step": 140
+    },
+    {
+      "epoch": 0.44200626959247646,
+      "grad_norm": 2.8745641708374023,
+      "learning_rate": 3.0916426266265676e-06,
+      "loss": 0.6119,
+      "step": 141
+    },
+    {
+      "epoch": 0.445141065830721,
+      "grad_norm": 3.0072708129882812,
+      "learning_rate": 3.066917084052603e-06,
+      "loss": 0.5851,
+      "step": 142
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 2.8062074184417725,
+      "learning_rate": 3.042132941347189e-06,
+      "loss": 0.586,
+      "step": 143
+    },
+    {
+      "epoch": 0.45141065830721006,
+      "grad_norm": 3.202028274536133,
+      "learning_rate": 3.017292760355896e-06,
+      "loss": 0.6312,
+      "step": 144
+    },
+    {
+      "epoch": 0.45454545454545453,
+      "grad_norm": 2.7520525455474854,
+      "learning_rate": 2.9923991087167657e-06,
+      "loss": 0.5769,
+      "step": 145
+    },
+    {
+      "epoch": 0.45768025078369906,
+      "grad_norm": 2.7981884479522705,
+      "learning_rate": 2.967454559594903e-06,
+      "loss": 0.6349,
+      "step": 146
+    },
+    {
+      "epoch": 0.4608150470219436,
+      "grad_norm": 2.9364802837371826,
+      "learning_rate": 2.9424616914164982e-06,
+      "loss": 0.5936,
+      "step": 147
+    },
+    {
+      "epoch": 0.46394984326018807,
+      "grad_norm": 2.985931873321533,
+      "learning_rate": 2.917423087602306e-06,
+      "loss": 0.5731,
+      "step": 148
+    },
+    {
+      "epoch": 0.4670846394984326,
+      "grad_norm": 2.4261667728424072,
+      "learning_rate": 2.8923413363006038e-06,
+      "loss": 0.602,
+      "step": 149
+    },
+    {
+      "epoch": 0.4702194357366771,
+      "grad_norm": 2.6361424922943115,
+      "learning_rate": 2.8672190301196655e-06,
+      "loss": 0.5851,
+      "step": 150
+    },
+    {
+      "epoch": 0.47335423197492166,
+      "grad_norm": 2.6938276290893555,
+      "learning_rate": 2.842058765859776e-06,
+      "loss": 0.6026,
+      "step": 151
+    },
+    {
+      "epoch": 0.47648902821316613,
+      "grad_norm": 2.6547839641571045,
+      "learning_rate": 2.8168631442448046e-06,
+      "loss": 0.5863,
+      "step": 152
+    },
+    {
+      "epoch": 0.47962382445141066,
+      "grad_norm": 2.8255505561828613,
+      "learning_rate": 2.791634769653381e-06,
+      "loss": 0.6096,
+      "step": 153
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 2.461580514907837,
+      "learning_rate": 2.7663762498496905e-06,
+      "loss": 0.5744,
+      "step": 154
+    },
+    {
+      "epoch": 0.48589341692789967,
+      "grad_norm": 2.9616644382476807,
+      "learning_rate": 2.741090195713917e-06,
+      "loss": 0.5849,
+      "step": 155
+    },
+    {
+      "epoch": 0.4890282131661442,
+      "grad_norm": 2.7509751319885254,
+      "learning_rate": 2.7157792209723654e-06,
+      "loss": 0.5711,
+      "step": 156
+    },
+    {
+      "epoch": 0.49216300940438873,
+      "grad_norm": 3.163322687149048,
+      "learning_rate": 2.6904459419272955e-06,
+      "loss": 0.6491,
+      "step": 157
+    },
+    {
+      "epoch": 0.4952978056426332,
+      "grad_norm": 2.5019166469573975,
+      "learning_rate": 2.6650929771864776e-06,
+      "loss": 0.5608,
+      "step": 158
+    },
+    {
+      "epoch": 0.49843260188087773,
+      "grad_norm": 2.8161232471466064,
+      "learning_rate": 2.639722947392521e-06,
+      "loss": 0.6116,
+      "step": 159
+    },
+    {
+      "epoch": 0.5015673981191222,
+      "grad_norm": 2.9896793365478516,
+      "learning_rate": 2.614338474951987e-06,
+      "loss": 0.5859,
+      "step": 160
+    },
+    {
+      "epoch": 0.5047021943573667,
+      "grad_norm": 2.9633073806762695,
+      "learning_rate": 2.5889421837643186e-06,
+      "loss": 0.5757,
+      "step": 161
+    },
+    {
+      "epoch": 0.5078369905956113,
+      "grad_norm": 7.553648471832275,
+      "learning_rate": 2.563536698950624e-06,
+      "loss": 0.5985,
+      "step": 162
+    },
+    {
+      "epoch": 0.5109717868338558,
+      "grad_norm": 2.4814646244049072,
+      "learning_rate": 2.538124646582315e-06,
+      "loss": 0.5918,
+      "step": 163
+    },
+    {
+      "epoch": 0.5141065830721003,
+      "grad_norm": 2.601158380508423,
+      "learning_rate": 2.512708653409674e-06,
+      "loss": 0.5768,
+      "step": 164
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 2.3953468799591064,
+      "learning_rate": 2.487291346590326e-06,
+      "loss": 0.5801,
+      "step": 165
+    },
+    {
+      "epoch": 0.5203761755485894,
+      "grad_norm": 2.782278060913086,
+      "learning_rate": 2.4618753534176854e-06,
+      "loss": 0.5953,
+      "step": 166
+    },
+    {
+      "epoch": 0.5235109717868338,
+      "grad_norm": 2.6170544624328613,
+      "learning_rate": 2.436463301049378e-06,
+      "loss": 0.584,
+      "step": 167
+    },
+    {
+      "epoch": 0.5266457680250783,
+      "grad_norm": 2.2067277431488037,
+      "learning_rate": 2.4110578162356814e-06,
+      "loss": 0.5709,
+      "step": 168
+    },
+    {
+      "epoch": 0.5297805642633229,
+      "grad_norm": 2.650946617126465,
+      "learning_rate": 2.385661525048014e-06,
+      "loss": 0.6157,
+      "step": 169
+    },
+    {
+      "epoch": 0.5329153605015674,
+      "grad_norm": 2.4111557006835938,
+      "learning_rate": 2.3602770526074804e-06,
+      "loss": 0.587,
+      "step": 170
+    },
+    {
+      "epoch": 0.5360501567398119,
+      "grad_norm": 2.574047088623047,
+      "learning_rate": 2.334907022813523e-06,
+      "loss": 0.5945,
+      "step": 171
+    },
+    {
+      "epoch": 0.5391849529780565,
+      "grad_norm": 5.312939167022705,
+      "learning_rate": 2.3095540580727054e-06,
+      "loss": 0.5584,
+      "step": 172
+    },
+    {
+      "epoch": 0.542319749216301,
+      "grad_norm": 2.999335289001465,
+      "learning_rate": 2.2842207790276355e-06,
+      "loss": 0.5588,
+      "step": 173
+    },
+    {
+      "epoch": 0.5454545454545454,
+      "grad_norm": 2.8886678218841553,
+      "learning_rate": 2.2589098042860838e-06,
+      "loss": 0.5834,
+      "step": 174
+    },
+    {
+      "epoch": 0.54858934169279,
+      "grad_norm": 2.7539076805114746,
+      "learning_rate": 2.2336237501503103e-06,
+      "loss": 0.529,
+      "step": 175
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 2.600677967071533,
+      "learning_rate": 2.2083652303466196e-06,
+      "loss": 0.5694,
+      "step": 176
+    },
+    {
+      "epoch": 0.554858934169279,
+      "grad_norm": 2.550015449523926,
+      "learning_rate": 2.1831368557551962e-06,
+      "loss": 0.5734,
+      "step": 177
+    },
+    {
+      "epoch": 0.5579937304075235,
+      "grad_norm": 2.4202213287353516,
+      "learning_rate": 2.157941234140225e-06,
+      "loss": 0.5664,
+      "step": 178
+    },
+    {
+      "epoch": 0.5611285266457681,
+      "grad_norm": 2.6022562980651855,
+      "learning_rate": 2.1327809698803354e-06,
+      "loss": 0.5516,
+      "step": 179
+    },
+    {
+      "epoch": 0.5642633228840125,
+      "grad_norm": 2.3936119079589844,
+      "learning_rate": 2.1076586636993975e-06,
+      "loss": 0.5697,
+      "step": 180
+    },
+    {
+      "epoch": 0.567398119122257,
+      "grad_norm": 2.6119375228881836,
+      "learning_rate": 2.0825769123976954e-06,
+      "loss": 0.5524,
+      "step": 181
+    },
+    {
+      "epoch": 0.5705329153605015,
+      "grad_norm": 2.9607300758361816,
+      "learning_rate": 2.057538308583502e-06,
+      "loss": 0.5539,
+      "step": 182
+    },
+    {
+      "epoch": 0.5736677115987461,
+      "grad_norm": 2.5394551753997803,
+      "learning_rate": 2.0325454404050983e-06,
+      "loss": 0.5902,
+      "step": 183
+    },
+    {
+      "epoch": 0.5768025078369906,
+      "grad_norm": 2.248412609100342,
+      "learning_rate": 2.0076008912832355e-06,
+      "loss": 0.5684,
+      "step": 184
+    },
+    {
+      "epoch": 0.5799373040752351,
+      "grad_norm": 2.369102954864502,
+      "learning_rate": 1.9827072396441044e-06,
+      "loss": 0.5473,
+      "step": 185
+    },
+    {
+      "epoch": 0.5830721003134797,
+      "grad_norm": 2.8046441078186035,
+      "learning_rate": 1.957867058652812e-06,
+      "loss": 0.5125,
+      "step": 186
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 2.5482161045074463,
+      "learning_rate": 1.933082915947398e-06,
+      "loss": 0.5586,
+      "step": 187
+    },
+    {
+      "epoch": 0.5893416927899686,
+      "grad_norm": 2.53220534324646,
+      "learning_rate": 1.9083573733734328e-06,
+      "loss": 0.598,
+      "step": 188
+    },
+    {
+      "epoch": 0.5924764890282131,
+      "grad_norm": 2.742966413497925,
+      "learning_rate": 1.8836929867192077e-06,
+      "loss": 0.5432,
+      "step": 189
+    },
+    {
+      "epoch": 0.5956112852664577,
+      "grad_norm": 4.084339141845703,
+      "learning_rate": 1.8590923054515504e-06,
+      "loss": 0.5232,
+      "step": 190
+    },
+    {
+      "epoch": 0.5987460815047022,
+      "grad_norm": 2.8514344692230225,
+      "learning_rate": 1.8345578724522957e-06,
+      "loss": 0.5748,
+      "step": 191
+    },
+    {
+      "epoch": 0.6018808777429467,
+      "grad_norm": 2.736140012741089,
+      "learning_rate": 1.8100922237554442e-06,
+      "loss": 0.5315,
+      "step": 192
+    },
+    {
+      "epoch": 0.6050156739811913,
+      "grad_norm": 2.4470133781433105,
+      "learning_rate": 1.7856978882850112e-06,
+      "loss": 0.5722,
+      "step": 193
+    },
+    {
+      "epoch": 0.6081504702194357,
+      "grad_norm": 2.587562084197998,
+      "learning_rate": 1.7613773875936274e-06,
+      "loss": 0.5697,
+      "step": 194
+    },
+    {
+      "epoch": 0.6112852664576802,
+      "grad_norm": 2.340610980987549,
+      "learning_rate": 1.7371332356018972e-06,
+      "loss": 0.5292,
+      "step": 195
+    },
+    {
+      "epoch": 0.6144200626959248,
+      "grad_norm": 4.569915771484375,
+      "learning_rate": 1.7129679383385384e-06,
+      "loss": 0.582,
+      "step": 196
+    },
+    {
+      "epoch": 0.6175548589341693,
+      "grad_norm": 2.7119388580322266,
+      "learning_rate": 1.688883993681345e-06,
+      "loss": 0.6219,
+      "step": 197
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 2.8180112838745117,
+      "learning_rate": 1.6648838910989955e-06,
+      "loss": 0.5649,
+      "step": 198
+    },
+    {
+      "epoch": 0.6238244514106583,
+      "grad_norm": 3.1212546825408936,
+      "learning_rate": 1.6409701113937182e-06,
+      "loss": 0.5269,
+      "step": 199
+    },
+    {
+      "epoch": 0.6269592476489029,
+      "grad_norm": 3.6080574989318848,
+      "learning_rate": 1.617145126444864e-06,
+      "loss": 0.5903,
+      "step": 200
+    },
+    {
+      "epoch": 0.6300940438871473,
+      "grad_norm": 2.5957369804382324,
+      "learning_rate": 1.5934113989533992e-06,
+      "loss": 0.6123,
+      "step": 201
+    },
+    {
+      "epoch": 0.6332288401253918,
+      "grad_norm": 2.664415121078491,
+      "learning_rate": 1.5697713821873401e-06,
+      "loss": 0.6159,
+      "step": 202
+    },
+    {
+      "epoch": 0.6363636363636364,
+      "grad_norm": 2.5966672897338867,
+      "learning_rate": 1.5462275197281717e-06,
+      "loss": 0.5255,
+      "step": 203
+    },
+    {
+      "epoch": 0.6394984326018809,
+      "grad_norm": 2.552795886993408,
+      "learning_rate": 1.5227822452182617e-06,
+      "loss": 0.5485,
+      "step": 204
+    },
+    {
+      "epoch": 0.6426332288401254,
+      "grad_norm": 2.581660032272339,
+      "learning_rate": 1.499437982109305e-06,
+      "loss": 0.5727,
+      "step": 205
+    },
+    {
+      "epoch": 0.64576802507837,
+      "grad_norm": 2.6740126609802246,
+      "learning_rate": 1.4761971434118207e-06,
+      "loss": 0.568,
+      "step": 206
+    },
+    {
+      "epoch": 0.6489028213166145,
+      "grad_norm": 2.314016342163086,
+      "learning_rate": 1.4530621314457255e-06,
+      "loss": 0.5335,
+      "step": 207
+    },
+    {
+      "epoch": 0.6520376175548589,
+      "grad_norm": 2.5612449645996094,
+      "learning_rate": 1.430035337592018e-06,
+      "loss": 0.5422,
+      "step": 208
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 6.558284759521484,
+      "learning_rate": 1.4071191420455873e-06,
+      "loss": 0.5938,
+      "step": 209
+    },
+    {
+      "epoch": 0.658307210031348,
+      "grad_norm": 2.5115890502929688,
+      "learning_rate": 1.3843159135691859e-06,
+      "loss": 0.5194,
+      "step": 210
+    },
+    {
+      "epoch": 0.6614420062695925,
+      "grad_norm": 3.0726919174194336,
+      "learning_rate": 1.3616280092485719e-06,
+      "loss": 0.554,
+      "step": 211
+    },
+    {
+      "epoch": 0.664576802507837,
+      "grad_norm": 2.4502389430999756,
+      "learning_rate": 1.3390577742488747e-06,
+      "loss": 0.6057,
+      "step": 212
+    },
+    {
+      "epoch": 0.6677115987460815,
+      "grad_norm": 2.853550434112549,
+      "learning_rate": 1.3166075415721762e-06,
+      "loss": 0.5049,
+      "step": 213
+    },
+    {
+      "epoch": 0.670846394984326,
+      "grad_norm": 2.496123790740967,
+      "learning_rate": 1.2942796318163595e-06,
+      "loss": 0.5625,
+      "step": 214
+    },
+    {
+      "epoch": 0.6739811912225705,
+      "grad_norm": 2.3185224533081055,
+      "learning_rate": 1.2720763529352415e-06,
+      "loss": 0.5336,
+      "step": 215
+    },
+    {
+      "epoch": 0.677115987460815,
+      "grad_norm": 2.621919631958008,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.539,
+      "step": 216
+    },
+    {
+      "epoch": 0.6802507836990596,
+      "grad_norm": 2.744100570678711,
+      "learning_rate": 1.2280528549619487e-06,
+      "loss": 0.5213,
+      "step": 217
+    },
+    {
+      "epoch": 0.6833855799373041,
+      "grad_norm": 2.494028329849243,
+      "learning_rate": 1.2062371864166553e-06,
+      "loss": 0.5419,
+      "step": 218
+    },
+    {
+      "epoch": 0.6865203761755486,
+      "grad_norm": 2.599900245666504,
+      "learning_rate": 1.1845552493694462e-06,
+      "loss": 0.5456,
+      "step": 219
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 2.5224337577819824,
+      "learning_rate": 1.1630092850023148e-06,
+      "loss": 0.566,
+      "step": 220
+    },
+    {
+      "epoch": 0.6927899686520376,
+      "grad_norm": 2.492403030395508,
+      "learning_rate": 1.141601520442262e-06,
+      "loss": 0.5415,
+      "step": 221
+    },
+    {
+      "epoch": 0.6959247648902821,
+      "grad_norm": 2.5345394611358643,
+      "learning_rate": 1.120334168531081e-06,
+      "loss": 0.5301,
+      "step": 222
+    },
+    {
+      "epoch": 0.6990595611285266,
+      "grad_norm": 2.418922185897827,
+      "learning_rate": 1.0992094275966256e-06,
+      "loss": 0.5764,
+      "step": 223
+    },
+    {
+      "epoch": 0.7021943573667712,
+      "grad_norm": 3.3536760807037354,
+      "learning_rate": 1.078229481225582e-06,
+      "loss": 0.5596,
+      "step": 224
+    },
+    {
+      "epoch": 0.7053291536050157,
+      "grad_norm": 2.531526803970337,
+      "learning_rate": 1.0573964980377517e-06,
+      "loss": 0.549,
+      "step": 225
+    },
+    {
+      "epoch": 0.7084639498432602,
+      "grad_norm": 2.7442548274993896,
+      "learning_rate": 1.0367126314618946e-06,
+      "loss": 0.5025,
+      "step": 226
+    },
+    {
+      "epoch": 0.7115987460815048,
+      "grad_norm": 2.368351459503174,
+      "learning_rate": 1.0161800195131372e-06,
+      "loss": 0.5311,
+      "step": 227
+    },
+    {
+      "epoch": 0.7147335423197492,
+      "grad_norm": 2.8416459560394287,
+      "learning_rate": 9.95800784571969e-07,
+      "loss": 0.5243,
+      "step": 228
+    },
+    {
+      "epoch": 0.7178683385579937,
+      "grad_norm": 2.772183656692505,
+      "learning_rate": 9.755770331648642e-07,
+      "loss": 0.5677,
+      "step": 229
+    },
+    {
+      "epoch": 0.7210031347962382,
+      "grad_norm": 2.4133315086364746,
+      "learning_rate": 9.555108557465383e-07,
+      "loss": 0.5507,
+      "step": 230
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 2.677746295928955,
+      "learning_rate": 9.356043264838607e-07,
+      "loss": 0.5553,
+      "step": 231
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 2.8451437950134277,
+      "learning_rate": 9.158595030414621e-07,
+      "loss": 0.5135,
+      "step": 232
+    },
+    {
+      "epoch": 0.7304075235109718,
+      "grad_norm": 2.838019609451294,
+      "learning_rate": 8.962784263690358e-07,
+      "loss": 0.59,
+      "step": 233
+    },
+    {
+      "epoch": 0.7335423197492164,
+      "grad_norm": 2.865750312805176,
+      "learning_rate": 8.768631204903738e-07,
+      "loss": 0.5164,
+      "step": 234
+    },
+    {
+      "epoch": 0.7366771159874608,
+      "grad_norm": 2.9796836376190186,
+      "learning_rate": 8.576155922941548e-07,
+      "loss": 0.5242,
+      "step": 235
+    },
+    {
+      "epoch": 0.7398119122257053,
+      "grad_norm": 3.789559841156006,
+      "learning_rate": 8.385378313264933e-07,
+      "loss": 0.5419,
+      "step": 236
+    },
+    {
+      "epoch": 0.7429467084639498,
+      "grad_norm": 2.552150249481201,
+      "learning_rate": 8.196318095852909e-07,
+      "loss": 0.5426,
+      "step": 237
+    },
+    {
+      "epoch": 0.7460815047021944,
+      "grad_norm": 3.243431568145752,
+      "learning_rate": 8.008994813163995e-07,
+      "loss": 0.5121,
+      "step": 238
+    },
+    {
+      "epoch": 0.7492163009404389,
+      "grad_norm": 3.1874783039093018,
+      "learning_rate": 7.823427828116148e-07,
+      "loss": 0.5512,
+      "step": 239
+    },
+    {
+      "epoch": 0.7523510971786834,
+      "grad_norm": 2.545905828475952,
+      "learning_rate": 7.6396363220853e-07,
+      "loss": 0.5483,
+      "step": 240
+    },
+    {
+      "epoch": 0.7554858934169278,
+      "grad_norm": 2.719782829284668,
+      "learning_rate": 7.457639292922675e-07,
+      "loss": 0.5683,
+      "step": 241
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 2.9073195457458496,
+      "learning_rate": 7.277455552991011e-07,
+      "loss": 0.5711,
+      "step": 242
+    },
+    {
+      "epoch": 0.7617554858934169,
+      "grad_norm": 2.301893949508667,
+      "learning_rate": 7.099103727220024e-07,
+      "loss": 0.533,
+      "step": 243
+    },
+    {
+      "epoch": 0.7648902821316614,
+      "grad_norm": 2.9436652660369873,
+      "learning_rate": 6.922602251181221e-07,
+      "loss": 0.5447,
+      "step": 244
+    },
+    {
+      "epoch": 0.768025078369906,
+      "grad_norm": 3.2471468448638916,
+      "learning_rate": 6.747969369182248e-07,
+      "loss": 0.5551,
+      "step": 245
+    },
+    {
+      "epoch": 0.7711598746081505,
+      "grad_norm": 2.480755567550659,
+      "learning_rate": 6.575223132381067e-07,
+      "loss": 0.5143,
+      "step": 246
+    },
+    {
+      "epoch": 0.774294670846395,
+      "grad_norm": 2.8075945377349854,
+      "learning_rate": 6.4043813969201e-07,
+      "loss": 0.5099,
+      "step": 247
+    },
+    {
+      "epoch": 0.7774294670846394,
+      "grad_norm": 3.024644136428833,
+      "learning_rate": 6.235461822080449e-07,
+      "loss": 0.5393,
+      "step": 248
+    },
+    {
+      "epoch": 0.780564263322884,
+      "grad_norm": 2.6839873790740967,
+      "learning_rate": 6.068481868456558e-07,
+      "loss": 0.5509,
+      "step": 249
+    },
+    {
+      "epoch": 0.7836990595611285,
+      "grad_norm": 3.0200679302215576,
+      "learning_rate": 5.903458796151382e-07,
+      "loss": 0.5647,
+      "step": 250
+    },
+    {
+      "epoch": 0.786833855799373,
+      "grad_norm": 2.65813946723938,
+      "learning_rate": 5.740409662992244e-07,
+      "loss": 0.5202,
+      "step": 251
+    },
+    {
+      "epoch": 0.7899686520376176,
+      "grad_norm": 2.6419460773468018,
+      "learning_rate": 5.579351322767643e-07,
+      "loss": 0.5412,
+      "step": 252
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 2.5918684005737305,
+      "learning_rate": 5.420300423485167e-07,
+      "loss": 0.5671,
+      "step": 253
+    },
+    {
+      "epoch": 0.7962382445141066,
+      "grad_norm": 2.6645092964172363,
+      "learning_rate": 5.263273405650601e-07,
+      "loss": 0.5971,
+      "step": 254
+    },
+    {
+      "epoch": 0.799373040752351,
+      "grad_norm": 2.6975386142730713,
+      "learning_rate": 5.108286500568562e-07,
+      "loss": 0.5569,
+      "step": 255
+    },
+    {
+      "epoch": 0.8025078369905956,
+      "grad_norm": 2.585435628890991,
+      "learning_rate": 4.95535572866474e-07,
+      "loss": 0.5394,
+      "step": 256
+    },
+    {
+      "epoch": 0.8056426332288401,
+      "grad_norm": 2.4776594638824463,
+      "learning_rate": 4.804496897829883e-07,
+      "loss": 0.5231,
+      "step": 257
+    },
+    {
+      "epoch": 0.8087774294670846,
+      "grad_norm": 2.783409833908081,
+      "learning_rate": 4.6557256017858485e-07,
+      "loss": 0.5114,
+      "step": 258
+    },
+    {
+      "epoch": 0.8119122257053292,
+      "grad_norm": 2.355269193649292,
+      "learning_rate": 4.5090572184736863e-07,
+      "loss": 0.5202,
+      "step": 259
+    },
+    {
+      "epoch": 0.8150470219435737,
+      "grad_norm": 2.541964292526245,
+      "learning_rate": 4.3645069084641195e-07,
+      "loss": 0.5414,
+      "step": 260
+    },
+    {
+      "epoch": 0.8181818181818182,
+      "grad_norm": 2.6445441246032715,
+      "learning_rate": 4.222089613390412e-07,
+      "loss": 0.5289,
+      "step": 261
+    },
+    {
+      "epoch": 0.8213166144200627,
+      "grad_norm": 2.8741798400878906,
+      "learning_rate": 4.0818200544039484e-07,
+      "loss": 0.5541,
+      "step": 262
+    },
+    {
+      "epoch": 0.8244514106583072,
+      "grad_norm": 3.0294582843780518,
+      "learning_rate": 3.9437127306525295e-07,
+      "loss": 0.5234,
+      "step": 263
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 2.6354918479919434,
+      "learning_rate": 3.8077819177816695e-07,
+      "loss": 0.5061,
+      "step": 264
+    },
+    {
+      "epoch": 0.8307210031347962,
+      "grad_norm": 2.5358927249908447,
+      "learning_rate": 3.6740416664589634e-07,
+      "loss": 0.5108,
+      "step": 265
+    },
+    {
+      "epoch": 0.8338557993730408,
+      "grad_norm": 3.637833595275879,
+      "learning_rate": 3.5425058009217193e-07,
+      "loss": 0.5398,
+      "step": 266
+    },
+    {
+      "epoch": 0.8369905956112853,
+      "grad_norm": 2.77534556388855,
+      "learning_rate": 3.413187917548019e-07,
+      "loss": 0.5727,
+      "step": 267
+    },
+    {
+      "epoch": 0.8401253918495298,
+      "grad_norm": 2.57776141166687,
+      "learning_rate": 3.2861013834512844e-07,
+      "loss": 0.5309,
+      "step": 268
+    },
+    {
+      "epoch": 0.8432601880877743,
+      "grad_norm": 2.4252471923828125,
+      "learning_rate": 3.161259335098571e-07,
+      "loss": 0.4912,
+      "step": 269
+    },
+    {
+      "epoch": 0.8463949843260188,
+      "grad_norm": 4.025521278381348,
+      "learning_rate": 3.0386746769527323e-07,
+      "loss": 0.5448,
+      "step": 270
+    },
+    {
+      "epoch": 0.8495297805642633,
+      "grad_norm": 2.6746034622192383,
+      "learning_rate": 2.9183600801384853e-07,
+      "loss": 0.5454,
+      "step": 271
+    },
+    {
+      "epoch": 0.8526645768025078,
+      "grad_norm": 2.7830092906951904,
+      "learning_rate": 2.8003279811326724e-07,
+      "loss": 0.539,
+      "step": 272
+    },
+    {
+      "epoch": 0.8557993730407524,
+      "grad_norm": 2.5394887924194336,
+      "learning_rate": 2.684590580478749e-07,
+      "loss": 0.5234,
+      "step": 273
+    },
+    {
+      "epoch": 0.8589341692789969,
+      "grad_norm": 2.765644073486328,
+      "learning_rate": 2.57115984152565e-07,
+      "loss": 0.5105,
+      "step": 274
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 2.5733540058135986,
+      "learning_rate": 2.4600474891911696e-07,
+      "loss": 0.5381,
+      "step": 275
+    },
+    {
+      "epoch": 0.8652037617554859,
+      "grad_norm": 2.2739200592041016,
+      "learning_rate": 2.3512650087500338e-07,
+      "loss": 0.5344,
+      "step": 276
+    },
+    {
+      "epoch": 0.8683385579937304,
+      "grad_norm": 2.446244478225708,
+      "learning_rate": 2.2448236446466847e-07,
+      "loss": 0.5271,
+      "step": 277
+    },
+    {
+      "epoch": 0.8714733542319749,
+      "grad_norm": 2.833040237426758,
+      "learning_rate": 2.140734399332975e-07,
+      "loss": 0.5841,
+      "step": 278
+    },
+    {
+      "epoch": 0.8746081504702194,
+      "grad_norm": 2.487649440765381,
+      "learning_rate": 2.0390080321309236e-07,
+      "loss": 0.5353,
+      "step": 279
+    },
+    {
+      "epoch": 0.877742946708464,
+      "grad_norm": 3.27183198928833,
+      "learning_rate": 1.9396550581205208e-07,
+      "loss": 0.5181,
+      "step": 280
+    },
+    {
+      "epoch": 0.8808777429467085,
+      "grad_norm": 2.5979673862457275,
+      "learning_rate": 1.8426857470528414e-07,
+      "loss": 0.521,
+      "step": 281
+    },
+    {
+      "epoch": 0.8840125391849529,
+      "grad_norm": 2.452927589416504,
+      "learning_rate": 1.7481101222885126e-07,
+      "loss": 0.5394,
+      "step": 282
+    },
+    {
+      "epoch": 0.8871473354231975,
+      "grad_norm": 3.278170585632324,
+      "learning_rate": 1.6559379597616136e-07,
+      "loss": 0.5098,
+      "step": 283
+    },
+    {
+      "epoch": 0.890282131661442,
+      "grad_norm": 2.9773340225219727,
+      "learning_rate": 1.5661787869691858e-07,
+      "loss": 0.5046,
+      "step": 284
+    },
+    {
+      "epoch": 0.8934169278996865,
+      "grad_norm": 2.6932992935180664,
+      "learning_rate": 1.4788418819864037e-07,
+      "loss": 0.5517,
+      "step": 285
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 2.7016708850860596,
+      "learning_rate": 1.3939362725075344e-07,
+      "loss": 0.5386,
+      "step": 286
+    },
+    {
+      "epoch": 0.8996865203761756,
+      "grad_norm": 3.2767891883850098,
+      "learning_rate": 1.3114707349127954e-07,
+      "loss": 0.53,
+      "step": 287
+    },
+    {
+      "epoch": 0.9028213166144201,
+      "grad_norm": 2.865053653717041,
+      "learning_rate": 1.2314537933611425e-07,
+      "loss": 0.5306,
+      "step": 288
+    },
+    {
+      "epoch": 0.9059561128526645,
+      "grad_norm": 2.703111410140991,
+      "learning_rate": 1.1538937189091825e-07,
+      "loss": 0.5677,
+      "step": 289
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 2.6944828033447266,
+      "learning_rate": 1.0787985286562219e-07,
+      "loss": 0.5488,
+      "step": 290
+    },
+    {
+      "epoch": 0.9122257053291536,
+      "grad_norm": 2.602788209915161,
+      "learning_rate": 1.00617598491555e-07,
+      "loss": 0.5406,
+      "step": 291
+    },
+    {
+      "epoch": 0.9153605015673981,
+      "grad_norm": 2.350580930709839,
+      "learning_rate": 9.360335944121029e-08,
+      "loss": 0.5027,
+      "step": 292
+    },
+    {
+      "epoch": 0.9184952978056427,
+      "grad_norm": 2.7530674934387207,
+      "learning_rate": 8.683786075065065e-08,
+      "loss": 0.5458,
+      "step": 293
+    },
+    {
+      "epoch": 0.9216300940438872,
+      "grad_norm": 2.564846992492676,
+      "learning_rate": 8.032180174456283e-08,
+      "loss": 0.5267,
+      "step": 294
+    },
+    {
+      "epoch": 0.9247648902821317,
+      "grad_norm": 3.4500110149383545,
+      "learning_rate": 7.405585596397314e-08,
+      "loss": 0.5129,
+      "step": 295
+    },
+    {
+      "epoch": 0.9278996865203761,
+      "grad_norm": 2.9540138244628906,
+      "learning_rate": 6.804067109662443e-08,
+      "loss": 0.5221,
+      "step": 296
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 2.5607857704162598,
+      "learning_rate": 6.227686891002671e-08,
+      "loss": 0.4751,
+      "step": 297
+    },
+    {
+      "epoch": 0.9341692789968652,
+      "grad_norm": 2.6755456924438477,
+      "learning_rate": 5.6765045187187614e-08,
+      "loss": 0.5014,
+      "step": 298
+    },
+    {
+      "epoch": 0.9373040752351097,
+      "grad_norm": 3.1413800716400146,
+      "learning_rate": 5.150576966503063e-08,
+      "loss": 0.5191,
+      "step": 299
+    },
+    {
+      "epoch": 0.9404388714733543,
+      "grad_norm": 2.7286934852600098,
+      "learning_rate": 4.649958597549964e-08,
+      "loss": 0.5229,
+      "step": 300
+    },
+    {
+      "epoch": 0.9435736677115988,
+      "grad_norm": 4.638148784637451,
+      "learning_rate": 4.174701158936895e-08,
+      "loss": 0.5181,
+      "step": 301
+    },
+    {
+      "epoch": 0.9467084639498433,
+      "grad_norm": 2.8824093341827393,
+      "learning_rate": 3.7248537762752666e-08,
+      "loss": 0.5899,
+      "step": 302
+    },
+    {
+      "epoch": 0.9498432601880877,
+      "grad_norm": 3.2580602169036865,
+      "learning_rate": 3.300462948632593e-08,
+      "loss": 0.5234,
+      "step": 303
+    },
+    {
+      "epoch": 0.9529780564263323,
+      "grad_norm": 2.773378610610962,
+      "learning_rate": 2.9015725437259724e-08,
+      "loss": 0.5406,
+      "step": 304
+    },
+    {
+      "epoch": 0.9561128526645768,
+      "grad_norm": 2.5910532474517822,
+      "learning_rate": 2.5282237933877962e-08,
+      "loss": 0.5322,
+      "step": 305
+    },
+    {
+      "epoch": 0.9592476489028213,
+      "grad_norm": 4.50349760055542,
+      "learning_rate": 2.180455289303579e-08,
+      "loss": 0.6053,
+      "step": 306
+    },
+    {
+      "epoch": 0.9623824451410659,
+      "grad_norm": 2.9559998512268066,
+      "learning_rate": 1.8583029790230356e-08,
+      "loss": 0.4884,
+      "step": 307
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 3.511509418487549,
+      "learning_rate": 1.561800162244248e-08,
+      "loss": 0.5252,
+      "step": 308
+    },
+    {
+      "epoch": 0.9686520376175548,
+      "grad_norm": 2.7472832202911377,
+      "learning_rate": 1.2909774873715585e-08,
+      "loss": 0.5427,
+      "step": 309
+    },
+    {
+      "epoch": 0.9717868338557993,
+      "grad_norm": 3.0372958183288574,
+      "learning_rate": 1.0458629483476868e-08,
+      "loss": 0.5447,
+      "step": 310
+    },
+    {
+      "epoch": 0.9749216300940439,
+      "grad_norm": 2.645599126815796,
+      "learning_rate": 8.264818817599052e-09,
+      "loss": 0.5911,
+      "step": 311
+    },
+    {
+      "epoch": 0.9780564263322884,
+      "grad_norm": 3.0988388061523438,
+      "learning_rate": 6.328569642212734e-09,
+      "loss": 0.522,
+      "step": 312
+    },
+    {
+      "epoch": 0.9811912225705329,
+      "grad_norm": 4.376644134521484,
+      "learning_rate": 4.6500821002654075e-09,
+      "loss": 0.551,
+      "step": 313
+    },
+    {
+      "epoch": 0.9843260188087775,
+      "grad_norm": 2.846813917160034,
+      "learning_rate": 3.2295296908338437e-09,
+      "loss": 0.5204,
+      "step": 314
+    },
+    {
+      "epoch": 0.987460815047022,
+      "grad_norm": 4.044336318969727,
+      "learning_rate": 2.067059251189274e-09,
+      "loss": 0.5254,
+      "step": 315
+    },
+    {
+      "epoch": 0.9905956112852664,
+      "grad_norm": 2.489978790283203,
+      "learning_rate": 1.1627909416211947e-09,
+      "loss": 0.5397,
+      "step": 316
+    },
+    {
+      "epoch": 0.9937304075235109,
+      "grad_norm": 2.610431671142578,
+      "learning_rate": 5.168182330145266e-10,
+      "loss": 0.555,
+      "step": 317
+    },
+    {
+      "epoch": 0.9968652037617555,
+      "grad_norm": 3.202317953109741,
+      "learning_rate": 1.292078971898425e-10,
+      "loss": 0.5094,
+      "step": 318
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.7502589225769043,
+      "learning_rate": 0.0,
+      "loss": 0.5585,
+      "step": 319
+    },
+    {
+      "epoch": 1.0,
+      "step": 319,
+      "total_flos": 834160017014784.0,
+      "train_loss": 0.6235808798325099,
+      "train_runtime": 6415.1151,
+      "train_samples_per_second": 3.182,
+      "train_steps_per_second": 0.05
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 319,
+  "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": 834160017014784.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee56d58c8af8a5c679451a5f0b8bd7b77cf1cfa2b51e0b7300ce8c72e077fbb5
+size 9041

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"
+}