upload checkpoint

.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 +1,68 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_size": 4096,
+  "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": "float32",
+    "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": false,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "dtype": "float32",
+    "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": "4.57.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d856b7e5a82ee1e8155ceec112310564c8a59fcabbafbe07be4f50e8d9aa4f8e
+size 4998056552

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12213ffdaf19716d30c12888d589a2fbcbe234891e23ed85b46b68d098edde31
+size 4915962464

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:474cda281e631228d16b2e99d51a25d99319cfbe97842347fd6683923d918a13
+size 4915962496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83dae3134cc7be19af15d87a566953770dfbead3bbfefa4d92336dc614721986
+size 2704357976

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 +1,241 @@
+{
+  "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|>",
+  "padding_side": "right",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2624 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3702,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008103727714748784,
+      "grad_norm": 3.8143791754060645,
+      "learning_rate": 4.851752021563343e-07,
+      "loss": 0.6291,
+      "step": 10
+    },
+    {
+      "epoch": 0.01620745542949757,
+      "grad_norm": 1.8519716488145948,
+      "learning_rate": 1.0242587601078167e-06,
+      "loss": 0.61,
+      "step": 20
+    },
+    {
+      "epoch": 0.024311183144246355,
+      "grad_norm": 1.0912378733265808,
+      "learning_rate": 1.5633423180592994e-06,
+      "loss": 0.5528,
+      "step": 30
+    },
+    {
+      "epoch": 0.03241491085899514,
+      "grad_norm": 0.8848161405840956,
+      "learning_rate": 2.1024258760107817e-06,
+      "loss": 0.492,
+      "step": 40
+    },
+    {
+      "epoch": 0.04051863857374392,
+      "grad_norm": 0.664355371317233,
+      "learning_rate": 2.6415094339622644e-06,
+      "loss": 0.475,
+      "step": 50
+    },
+    {
+      "epoch": 0.04862236628849271,
+      "grad_norm": 0.47064606635063655,
+      "learning_rate": 3.1805929919137467e-06,
+      "loss": 0.4493,
+      "step": 60
+    },
+    {
+      "epoch": 0.05672609400324149,
+      "grad_norm": 0.537044398839108,
+      "learning_rate": 3.7196765498652294e-06,
+      "loss": 0.4454,
+      "step": 70
+    },
+    {
+      "epoch": 0.06482982171799027,
+      "grad_norm": 0.4732528060859788,
+      "learning_rate": 4.258760107816712e-06,
+      "loss": 0.4364,
+      "step": 80
+    },
+    {
+      "epoch": 0.07293354943273905,
+      "grad_norm": 0.49827029588438393,
+      "learning_rate": 4.797843665768194e-06,
+      "loss": 0.4197,
+      "step": 90
+    },
+    {
+      "epoch": 0.08103727714748785,
+      "grad_norm": 0.526552938047935,
+      "learning_rate": 5.336927223719677e-06,
+      "loss": 0.4304,
+      "step": 100
+    },
+    {
+      "epoch": 0.08914100486223663,
+      "grad_norm": 0.47074524257904116,
+      "learning_rate": 5.8760107816711595e-06,
+      "loss": 0.4125,
+      "step": 110
+    },
+    {
+      "epoch": 0.09724473257698542,
+      "grad_norm": 0.49822874629726954,
+      "learning_rate": 6.415094339622642e-06,
+      "loss": 0.4047,
+      "step": 120
+    },
+    {
+      "epoch": 0.1053484602917342,
+      "grad_norm": 0.5488012906399791,
+      "learning_rate": 6.954177897574125e-06,
+      "loss": 0.4105,
+      "step": 130
+    },
+    {
+      "epoch": 0.11345218800648298,
+      "grad_norm": 0.4643145806097566,
+      "learning_rate": 7.493261455525606e-06,
+      "loss": 0.4057,
+      "step": 140
+    },
+    {
+      "epoch": 0.12155591572123177,
+      "grad_norm": 0.5452510769440807,
+      "learning_rate": 8.03234501347709e-06,
+      "loss": 0.4025,
+      "step": 150
+    },
+    {
+      "epoch": 0.12965964343598055,
+      "grad_norm": 0.5140465400625914,
+      "learning_rate": 8.571428571428571e-06,
+      "loss": 0.4053,
+      "step": 160
+    },
+    {
+      "epoch": 0.13776337115072934,
+      "grad_norm": 0.48964582989375527,
+      "learning_rate": 9.110512129380054e-06,
+      "loss": 0.4074,
+      "step": 170
+    },
+    {
+      "epoch": 0.1458670988654781,
+      "grad_norm": 0.512071161530771,
+      "learning_rate": 9.649595687331537e-06,
+      "loss": 0.3968,
+      "step": 180
+    },
+    {
+      "epoch": 0.1539708265802269,
+      "grad_norm": 0.4516459632559221,
+      "learning_rate": 1.018867924528302e-05,
+      "loss": 0.4027,
+      "step": 190
+    },
+    {
+      "epoch": 0.1620745542949757,
+      "grad_norm": 0.5076505275755172,
+      "learning_rate": 1.0727762803234503e-05,
+      "loss": 0.399,
+      "step": 200
+    },
+    {
+      "epoch": 0.17017828200972449,
+      "grad_norm": 0.5908404481996066,
+      "learning_rate": 1.1266846361185985e-05,
+      "loss": 0.3884,
+      "step": 210
+    },
+    {
+      "epoch": 0.17828200972447325,
+      "grad_norm": 0.4955320619962085,
+      "learning_rate": 1.1805929919137466e-05,
+      "loss": 0.3974,
+      "step": 220
+    },
+    {
+      "epoch": 0.18638573743922204,
+      "grad_norm": 0.5607037938582617,
+      "learning_rate": 1.234501347708895e-05,
+      "loss": 0.387,
+      "step": 230
+    },
+    {
+      "epoch": 0.19448946515397084,
+      "grad_norm": 0.4295253742172914,
+      "learning_rate": 1.2884097035040433e-05,
+      "loss": 0.3857,
+      "step": 240
+    },
+    {
+      "epoch": 0.2025931928687196,
+      "grad_norm": 0.5054181419633219,
+      "learning_rate": 1.3423180592991916e-05,
+      "loss": 0.3998,
+      "step": 250
+    },
+    {
+      "epoch": 0.2106969205834684,
+      "grad_norm": 0.43182606180332783,
+      "learning_rate": 1.3962264150943397e-05,
+      "loss": 0.3831,
+      "step": 260
+    },
+    {
+      "epoch": 0.2188006482982172,
+      "grad_norm": 0.5291878778596819,
+      "learning_rate": 1.4501347708894879e-05,
+      "loss": 0.385,
+      "step": 270
+    },
+    {
+      "epoch": 0.22690437601296595,
+      "grad_norm": 0.501381844547934,
+      "learning_rate": 1.5040431266846362e-05,
+      "loss": 0.3913,
+      "step": 280
+    },
+    {
+      "epoch": 0.23500810372771475,
+      "grad_norm": 0.5296207369417244,
+      "learning_rate": 1.5579514824797845e-05,
+      "loss": 0.4023,
+      "step": 290
+    },
+    {
+      "epoch": 0.24311183144246354,
+      "grad_norm": 0.521876454499286,
+      "learning_rate": 1.6118598382749326e-05,
+      "loss": 0.3928,
+      "step": 300
+    },
+    {
+      "epoch": 0.25121555915721233,
+      "grad_norm": 0.5057167686972207,
+      "learning_rate": 1.6657681940700808e-05,
+      "loss": 0.3931,
+      "step": 310
+    },
+    {
+      "epoch": 0.2593192868719611,
+      "grad_norm": 0.4891464545952626,
+      "learning_rate": 1.7196765498652293e-05,
+      "loss": 0.3842,
+      "step": 320
+    },
+    {
+      "epoch": 0.26742301458670986,
+      "grad_norm": 0.44726682673309526,
+      "learning_rate": 1.7735849056603774e-05,
+      "loss": 0.395,
+      "step": 330
+    },
+    {
+      "epoch": 0.2755267423014587,
+      "grad_norm": 0.5114985087428332,
+      "learning_rate": 1.827493261455526e-05,
+      "loss": 0.3863,
+      "step": 340
+    },
+    {
+      "epoch": 0.28363047001620745,
+      "grad_norm": 0.4970832014319048,
+      "learning_rate": 1.881401617250674e-05,
+      "loss": 0.3863,
+      "step": 350
+    },
+    {
+      "epoch": 0.2917341977309562,
+      "grad_norm": 0.4532285090880423,
+      "learning_rate": 1.9353099730458222e-05,
+      "loss": 0.3861,
+      "step": 360
+    },
+    {
+      "epoch": 0.29983792544570503,
+      "grad_norm": 0.48258842329305224,
+      "learning_rate": 1.9892183288409707e-05,
+      "loss": 0.3939,
+      "step": 370
+    },
+    {
+      "epoch": 0.3079416531604538,
+      "grad_norm": 0.4781021807071079,
+      "learning_rate": 1.999971535838293e-05,
+      "loss": 0.3943,
+      "step": 380
+    },
+    {
+      "epoch": 0.3160453808752026,
+      "grad_norm": 0.48027043137048486,
+      "learning_rate": 1.999855902958531e-05,
+      "loss": 0.3892,
+      "step": 390
+    },
+    {
+      "epoch": 0.3241491085899514,
+      "grad_norm": 0.4804127881451221,
+      "learning_rate": 1.999651332628271e-05,
+      "loss": 0.3899,
+      "step": 400
+    },
+    {
+      "epoch": 0.33225283630470015,
+      "grad_norm": 0.4775478202015837,
+      "learning_rate": 1.9993578430440986e-05,
+      "loss": 0.3966,
+      "step": 410
+    },
+    {
+      "epoch": 0.34035656401944897,
+      "grad_norm": 0.46302683771567343,
+      "learning_rate": 1.9989754603119914e-05,
+      "loss": 0.3891,
+      "step": 420
+    },
+    {
+      "epoch": 0.34846029173419774,
+      "grad_norm": 0.4891193115104772,
+      "learning_rate": 1.9985042184449953e-05,
+      "loss": 0.3888,
+      "step": 430
+    },
+    {
+      "epoch": 0.3565640194489465,
+      "grad_norm": 0.48232916616215277,
+      "learning_rate": 1.997944159360201e-05,
+      "loss": 0.3768,
+      "step": 440
+    },
+    {
+      "epoch": 0.3646677471636953,
+      "grad_norm": 0.45512799624489886,
+      "learning_rate": 1.997295332875014e-05,
+      "loss": 0.385,
+      "step": 450
+    },
+    {
+      "epoch": 0.3727714748784441,
+      "grad_norm": 0.4257077433962391,
+      "learning_rate": 1.9965577967027244e-05,
+      "loss": 0.3867,
+      "step": 460
+    },
+    {
+      "epoch": 0.38087520259319285,
+      "grad_norm": 0.45481283720569005,
+      "learning_rate": 1.9957316164473717e-05,
+      "loss": 0.3835,
+      "step": 470
+    },
+    {
+      "epoch": 0.3889789303079417,
+      "grad_norm": 0.4289665064867179,
+      "learning_rate": 1.9948168655979115e-05,
+      "loss": 0.3844,
+      "step": 480
+    },
+    {
+      "epoch": 0.39708265802269044,
+      "grad_norm": 0.4157844428844032,
+      "learning_rate": 1.993813625521677e-05,
+      "loss": 0.3741,
+      "step": 490
+    },
+    {
+      "epoch": 0.4051863857374392,
+      "grad_norm": 0.4622765447861317,
+      "learning_rate": 1.9927219854571415e-05,
+      "loss": 0.3808,
+      "step": 500
+    },
+    {
+      "epoch": 0.413290113452188,
+      "grad_norm": 0.44373230658635465,
+      "learning_rate": 1.9915420425059816e-05,
+      "loss": 0.3754,
+      "step": 510
+    },
+    {
+      "epoch": 0.4213938411669368,
+      "grad_norm": 0.49709986290531505,
+      "learning_rate": 1.9902739016244386e-05,
+      "loss": 0.3765,
+      "step": 520
+    },
+    {
+      "epoch": 0.42949756888168555,
+      "grad_norm": 0.43589133961016346,
+      "learning_rate": 1.9889176756139838e-05,
+      "loss": 0.3849,
+      "step": 530
+    },
+    {
+      "epoch": 0.4376012965964344,
+      "grad_norm": 0.4517761618007384,
+      "learning_rate": 1.987473485111285e-05,
+      "loss": 0.3834,
+      "step": 540
+    },
+    {
+      "epoch": 0.44570502431118314,
+      "grad_norm": 0.4283867022363049,
+      "learning_rate": 1.9859414585774735e-05,
+      "loss": 0.3859,
+      "step": 550
+    },
+    {
+      "epoch": 0.4538087520259319,
+      "grad_norm": 0.41149886169920735,
+      "learning_rate": 1.9843217322867204e-05,
+      "loss": 0.3792,
+      "step": 560
+    },
+    {
+      "epoch": 0.4619124797406807,
+      "grad_norm": 0.53851792345421,
+      "learning_rate": 1.9826144503141132e-05,
+      "loss": 0.384,
+      "step": 570
+    },
+    {
+      "epoch": 0.4700162074554295,
+      "grad_norm": 0.4583802566321094,
+      "learning_rate": 1.9808197645228408e-05,
+      "loss": 0.3731,
+      "step": 580
+    },
+    {
+      "epoch": 0.47811993517017826,
+      "grad_norm": 0.43885584344879375,
+      "learning_rate": 1.9789378345506854e-05,
+      "loss": 0.3717,
+      "step": 590
+    },
+    {
+      "epoch": 0.4862236628849271,
+      "grad_norm": 0.48953511927615007,
+      "learning_rate": 1.976968827795822e-05,
+      "loss": 0.3876,
+      "step": 600
+    },
+    {
+      "epoch": 0.49432739059967584,
+      "grad_norm": 0.42715534640284347,
+      "learning_rate": 1.97491291940193e-05,
+      "loss": 0.3791,
+      "step": 610
+    },
+    {
+      "epoch": 0.5024311183144247,
+      "grad_norm": 0.4377753607219907,
+      "learning_rate": 1.972770292242611e-05,
+      "loss": 0.3808,
+      "step": 620
+    },
+    {
+      "epoch": 0.5105348460291734,
+      "grad_norm": 0.4186354729876052,
+      "learning_rate": 1.9705411369051252e-05,
+      "loss": 0.3699,
+      "step": 630
+    },
+    {
+      "epoch": 0.5186385737439222,
+      "grad_norm": 0.4181895805262258,
+      "learning_rate": 1.9682256516734377e-05,
+      "loss": 0.3831,
+      "step": 640
+    },
+    {
+      "epoch": 0.526742301458671,
+      "grad_norm": 0.43538529466596526,
+      "learning_rate": 1.9658240425105792e-05,
+      "loss": 0.3723,
+      "step": 650
+    },
+    {
+      "epoch": 0.5348460291734197,
+      "grad_norm": 0.4121702955601702,
+      "learning_rate": 1.9633365230403294e-05,
+      "loss": 0.3728,
+      "step": 660
+    },
+    {
+      "epoch": 0.5429497568881686,
+      "grad_norm": 0.4771784907130955,
+      "learning_rate": 1.9607633145282117e-05,
+      "loss": 0.3743,
+      "step": 670
+    },
+    {
+      "epoch": 0.5510534846029174,
+      "grad_norm": 0.45997135130591743,
+      "learning_rate": 1.958104645861812e-05,
+      "loss": 0.373,
+      "step": 680
+    },
+    {
+      "epoch": 0.5591572123176661,
+      "grad_norm": 0.43196833610674273,
+      "learning_rate": 1.9553607535304214e-05,
+      "loss": 0.379,
+      "step": 690
+    },
+    {
+      "epoch": 0.5672609400324149,
+      "grad_norm": 0.4037760483080695,
+      "learning_rate": 1.9525318816039975e-05,
+      "loss": 0.3733,
+      "step": 700
+    },
+    {
+      "epoch": 0.5753646677471637,
+      "grad_norm": 0.4473646241278942,
+      "learning_rate": 1.9496182817114567e-05,
+      "loss": 0.3806,
+      "step": 710
+    },
+    {
+      "epoch": 0.5834683954619124,
+      "grad_norm": 0.47617176813082657,
+      "learning_rate": 1.9466202130182898e-05,
+      "loss": 0.3769,
+      "step": 720
+    },
+    {
+      "epoch": 0.5915721231766613,
+      "grad_norm": 0.38900672372621603,
+      "learning_rate": 1.9435379422035104e-05,
+      "loss": 0.3681,
+      "step": 730
+    },
+    {
+      "epoch": 0.5996758508914101,
+      "grad_norm": 0.4469426655893551,
+      "learning_rate": 1.940371743435934e-05,
+      "loss": 0.3713,
+      "step": 740
+    },
+    {
+      "epoch": 0.6077795786061588,
+      "grad_norm": 0.431711580832028,
+      "learning_rate": 1.9371218983497888e-05,
+      "loss": 0.3752,
+      "step": 750
+    },
+    {
+      "epoch": 0.6158833063209076,
+      "grad_norm": 0.40891577509363053,
+      "learning_rate": 1.9337886960196666e-05,
+      "loss": 0.3755,
+      "step": 760
+    },
+    {
+      "epoch": 0.6239870340356564,
+      "grad_norm": 0.3949637878335169,
+      "learning_rate": 1.9303724329348072e-05,
+      "loss": 0.3733,
+      "step": 770
+    },
+    {
+      "epoch": 0.6320907617504052,
+      "grad_norm": 0.4382586105308017,
+      "learning_rate": 1.926873412972728e-05,
+      "loss": 0.3618,
+      "step": 780
+    },
+    {
+      "epoch": 0.640194489465154,
+      "grad_norm": 0.4687694305028729,
+      "learning_rate": 1.9232919473721918e-05,
+      "loss": 0.3656,
+      "step": 790
+    },
+    {
+      "epoch": 0.6482982171799028,
+      "grad_norm": 0.45223518463083157,
+      "learning_rate": 1.919628354705524e-05,
+      "loss": 0.3743,
+      "step": 800
+    },
+    {
+      "epoch": 0.6564019448946515,
+      "grad_norm": 0.4248355634658964,
+      "learning_rate": 1.915882960850274e-05,
+      "loss": 0.3701,
+      "step": 810
+    },
+    {
+      "epoch": 0.6645056726094003,
+      "grad_norm": 0.3657813779610828,
+      "learning_rate": 1.9120560989602282e-05,
+      "loss": 0.3745,
+      "step": 820
+    },
+    {
+      "epoch": 0.6726094003241491,
+      "grad_norm": 0.4383831942363292,
+      "learning_rate": 1.9081481094357778e-05,
+      "loss": 0.3722,
+      "step": 830
+    },
+    {
+      "epoch": 0.6807131280388979,
+      "grad_norm": 0.3781698372532506,
+      "learning_rate": 1.904159339893638e-05,
+      "loss": 0.3655,
+      "step": 840
+    },
+    {
+      "epoch": 0.6888168557536467,
+      "grad_norm": 0.4554387399061095,
+      "learning_rate": 1.9000901451359286e-05,
+      "loss": 0.3677,
+      "step": 850
+    },
+    {
+      "epoch": 0.6969205834683955,
+      "grad_norm": 0.43538923618195835,
+      "learning_rate": 1.8959408871186134e-05,
+      "loss": 0.3709,
+      "step": 860
+    },
+    {
+      "epoch": 0.7050243111831442,
+      "grad_norm": 2.230890645204416,
+      "learning_rate": 1.8917119349193054e-05,
+      "loss": 0.37,
+      "step": 870
+    },
+    {
+      "epoch": 0.713128038897893,
+      "grad_norm": 0.43315363378637484,
+      "learning_rate": 1.8874036647044356e-05,
+      "loss": 0.3662,
+      "step": 880
+    },
+    {
+      "epoch": 0.7212317666126418,
+      "grad_norm": 0.40547140745981486,
+      "learning_rate": 1.883016459695794e-05,
+      "loss": 0.3678,
+      "step": 890
+    },
+    {
+      "epoch": 0.7293354943273906,
+      "grad_norm": 0.610283505577365,
+      "learning_rate": 1.8785507101364423e-05,
+      "loss": 0.3697,
+      "step": 900
+    },
+    {
+      "epoch": 0.7374392220421394,
+      "grad_norm": 0.4128570889957437,
+      "learning_rate": 1.8740068132559995e-05,
+      "loss": 0.3823,
+      "step": 910
+    },
+    {
+      "epoch": 0.7455429497568882,
+      "grad_norm": 0.4201216041085128,
+      "learning_rate": 1.869385173235312e-05,
+      "loss": 0.3649,
+      "step": 920
+    },
+    {
+      "epoch": 0.7536466774716369,
+      "grad_norm": 0.3976995949997488,
+      "learning_rate": 1.864686201170497e-05,
+      "loss": 0.3639,
+      "step": 930
+    },
+    {
+      "epoch": 0.7617504051863857,
+      "grad_norm": 0.3919731189992052,
+      "learning_rate": 1.8599103150363796e-05,
+      "loss": 0.3687,
+      "step": 940
+    },
+    {
+      "epoch": 0.7698541329011345,
+      "grad_norm": 0.4183852565583889,
+      "learning_rate": 1.8550579396493108e-05,
+      "loss": 0.3589,
+      "step": 950
+    },
+    {
+      "epoch": 0.7779578606158833,
+      "grad_norm": 0.4336989305383055,
+      "learning_rate": 1.8501295066293818e-05,
+      "loss": 0.3736,
+      "step": 960
+    },
+    {
+      "epoch": 0.7860615883306321,
+      "grad_norm": 0.4333472376126472,
+      "learning_rate": 1.84512545436203e-05,
+      "loss": 0.3584,
+      "step": 970
+    },
+    {
+      "epoch": 0.7941653160453809,
+      "grad_norm": 0.41188998286918327,
+      "learning_rate": 1.8400462279590455e-05,
+      "loss": 0.3676,
+      "step": 980
+    },
+    {
+      "epoch": 0.8022690437601296,
+      "grad_norm": 0.4172108271051564,
+      "learning_rate": 1.8348922792189786e-05,
+      "loss": 0.3625,
+      "step": 990
+    },
+    {
+      "epoch": 0.8103727714748784,
+      "grad_norm": 0.40173625360414567,
+      "learning_rate": 1.82966406658695e-05,
+      "loss": 0.3602,
+      "step": 1000
+    },
+    {
+      "epoch": 0.8184764991896273,
+      "grad_norm": 0.3962216396307209,
+      "learning_rate": 1.8243620551138752e-05,
+      "loss": 0.3642,
+      "step": 1010
+    },
+    {
+      "epoch": 0.826580226904376,
+      "grad_norm": 0.3810648376483969,
+      "learning_rate": 1.8189867164150946e-05,
+      "loss": 0.3634,
+      "step": 1020
+    },
+    {
+      "epoch": 0.8346839546191248,
+      "grad_norm": 0.45176986655226553,
+      "learning_rate": 1.8135385286284263e-05,
+      "loss": 0.3585,
+      "step": 1030
+    },
+    {
+      "epoch": 0.8427876823338736,
+      "grad_norm": 0.4358279765510063,
+      "learning_rate": 1.8080179763716343e-05,
+      "loss": 0.3634,
+      "step": 1040
+    },
+    {
+      "epoch": 0.8508914100486223,
+      "grad_norm": 0.38447670081388613,
+      "learning_rate": 1.8024255506993203e-05,
+      "loss": 0.3659,
+      "step": 1050
+    },
+    {
+      "epoch": 0.8589951377633711,
+      "grad_norm": 0.3803774125404372,
+      "learning_rate": 1.796761749059247e-05,
+      "loss": 0.3636,
+      "step": 1060
+    },
+    {
+      "epoch": 0.86709886547812,
+      "grad_norm": 0.4047776986609743,
+      "learning_rate": 1.791027075248088e-05,
+      "loss": 0.3586,
+      "step": 1070
+    },
+    {
+      "epoch": 0.8752025931928687,
+      "grad_norm": 0.4329036606972538,
+      "learning_rate": 1.7852220393666155e-05,
+      "loss": 0.3712,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8833063209076175,
+      "grad_norm": 0.41515795472367945,
+      "learning_rate": 1.7793471577743263e-05,
+      "loss": 0.3634,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8914100486223663,
+      "grad_norm": 0.45533281869879083,
+      "learning_rate": 1.7734029530435128e-05,
+      "loss": 0.3705,
+      "step": 1100
+    },
+    {
+      "epoch": 0.899513776337115,
+      "grad_norm": 0.4836970184646456,
+      "learning_rate": 1.7673899539127785e-05,
+      "loss": 0.3646,
+      "step": 1110
+    },
+    {
+      "epoch": 0.9076175040518638,
+      "grad_norm": 0.3858999331504026,
+      "learning_rate": 1.7613086952400072e-05,
+      "loss": 0.3769,
+      "step": 1120
+    },
+    {
+      "epoch": 0.9157212317666127,
+      "grad_norm": 0.41525121951715827,
+      "learning_rate": 1.7551597179547876e-05,
+      "loss": 0.3683,
+      "step": 1130
+    },
+    {
+      "epoch": 0.9238249594813615,
+      "grad_norm": 0.5067822097011675,
+      "learning_rate": 1.7489435690102975e-05,
+      "loss": 0.3741,
+      "step": 1140
+    },
+    {
+      "epoch": 0.9319286871961102,
+      "grad_norm": 0.37723731328875554,
+      "learning_rate": 1.7426608013346504e-05,
+      "loss": 0.3664,
+      "step": 1150
+    },
+    {
+      "epoch": 0.940032414910859,
+      "grad_norm": 0.4020624317459784,
+      "learning_rate": 1.7363119737817148e-05,
+      "loss": 0.3643,
+      "step": 1160
+    },
+    {
+      "epoch": 0.9481361426256077,
+      "grad_norm": 0.394416220918231,
+      "learning_rate": 1.7298976510814026e-05,
+      "loss": 0.3738,
+      "step": 1170
+    },
+    {
+      "epoch": 0.9562398703403565,
+      "grad_norm": 0.4051768296867602,
+      "learning_rate": 1.723418403789438e-05,
+      "loss": 0.3692,
+      "step": 1180
+    },
+    {
+      "epoch": 0.9643435980551054,
+      "grad_norm": 0.4100164339896498,
+      "learning_rate": 1.716874808236602e-05,
+      "loss": 0.3513,
+      "step": 1190
+    },
+    {
+      "epoch": 0.9724473257698542,
+      "grad_norm": 0.5567986050192375,
+      "learning_rate": 1.710267446477474e-05,
+      "loss": 0.3701,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9805510534846029,
+      "grad_norm": 0.3784739194547327,
+      "learning_rate": 1.7035969062386527e-05,
+      "loss": 0.3608,
+      "step": 1210
+    },
+    {
+      "epoch": 0.9886547811993517,
+      "grad_norm": 0.41057084065002897,
+      "learning_rate": 1.69686378086648e-05,
+      "loss": 0.3703,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9967585089141004,
+      "grad_norm": 0.39660969497464443,
+      "learning_rate": 1.6900686692742617e-05,
+      "loss": 0.3581,
+      "step": 1230
+    },
+    {
+      "epoch": 1.0048622366288493,
+      "grad_norm": 0.42322649069140084,
+      "learning_rate": 1.683212175888994e-05,
+      "loss": 0.3337,
+      "step": 1240
+    },
+    {
+      "epoch": 1.012965964343598,
+      "grad_norm": 0.40814645825690765,
+      "learning_rate": 1.6762949105976028e-05,
+      "loss": 0.3092,
+      "step": 1250
+    },
+    {
+      "epoch": 1.0210696920583469,
+      "grad_norm": 0.3886034442221133,
+      "learning_rate": 1.6693174886926878e-05,
+      "loss": 0.3112,
+      "step": 1260
+    },
+    {
+      "epoch": 1.0291734197730957,
+      "grad_norm": 0.4904101243804896,
+      "learning_rate": 1.6622805308177972e-05,
+      "loss": 0.3043,
+      "step": 1270
+    },
+    {
+      "epoch": 1.0372771474878444,
+      "grad_norm": 0.41832890463198136,
+      "learning_rate": 1.6551846629122204e-05,
+      "loss": 0.3092,
+      "step": 1280
+    },
+    {
+      "epoch": 1.0453808752025933,
+      "grad_norm": 0.4341215598768056,
+      "learning_rate": 1.648030516155309e-05,
+      "loss": 0.3099,
+      "step": 1290
+    },
+    {
+      "epoch": 1.053484602917342,
+      "grad_norm": 0.47291051372343795,
+      "learning_rate": 1.6408187269103334e-05,
+      "loss": 0.3057,
+      "step": 1300
+    },
+    {
+      "epoch": 1.0615883306320908,
+      "grad_norm": 0.39368995484662067,
+      "learning_rate": 1.63354993666788e-05,
+      "loss": 0.3063,
+      "step": 1310
+    },
+    {
+      "epoch": 1.0696920583468394,
+      "grad_norm": 0.3911051093768693,
+      "learning_rate": 1.626224791988789e-05,
+      "loss": 0.3111,
+      "step": 1320
+    },
+    {
+      "epoch": 1.0777957860615883,
+      "grad_norm": 0.4429022242394122,
+      "learning_rate": 1.618843944446642e-05,
+      "loss": 0.3055,
+      "step": 1330
+    },
+    {
+      "epoch": 1.0858995137763372,
+      "grad_norm": 0.3709324359443042,
+      "learning_rate": 1.6114080505698057e-05,
+      "loss": 0.3117,
+      "step": 1340
+    },
+    {
+      "epoch": 1.0940032414910859,
+      "grad_norm": 0.4244895808117866,
+      "learning_rate": 1.6039177717830334e-05,
+      "loss": 0.3122,
+      "step": 1350
+    },
+    {
+      "epoch": 1.1021069692058347,
+      "grad_norm": 0.40515002905473985,
+      "learning_rate": 1.5963737743486296e-05,
+      "loss": 0.3081,
+      "step": 1360
+    },
+    {
+      "epoch": 1.1102106969205834,
+      "grad_norm": 0.4148956262941055,
+      "learning_rate": 1.5887767293071886e-05,
+      "loss": 0.3171,
+      "step": 1370
+    },
+    {
+      "epoch": 1.1183144246353323,
+      "grad_norm": 0.47812058716341943,
+      "learning_rate": 1.581127312417902e-05,
+      "loss": 0.308,
+      "step": 1380
+    },
+    {
+      "epoch": 1.1264181523500811,
+      "grad_norm": 0.41259806001969435,
+      "learning_rate": 1.5734262040984518e-05,
+      "loss": 0.3094,
+      "step": 1390
+    },
+    {
+      "epoch": 1.1345218800648298,
+      "grad_norm": 0.3970894499446707,
+      "learning_rate": 1.565674089364487e-05,
+      "loss": 0.3043,
+      "step": 1400
+    },
+    {
+      "epoch": 1.1426256077795787,
+      "grad_norm": 0.40546915070908546,
+      "learning_rate": 1.5578716577686906e-05,
+      "loss": 0.3131,
+      "step": 1410
+    },
+    {
+      "epoch": 1.1507293354943273,
+      "grad_norm": 0.5014026413856193,
+      "learning_rate": 1.550019603339444e-05,
+      "loss": 0.3072,
+      "step": 1420
+    },
+    {
+      "epoch": 1.1588330632090762,
+      "grad_norm": 0.407173287163731,
+      "learning_rate": 1.542118624519092e-05,
+      "loss": 0.3166,
+      "step": 1430
+    },
+    {
+      "epoch": 1.1669367909238249,
+      "grad_norm": 0.4315503970245671,
+      "learning_rate": 1.5341694241018186e-05,
+      "loss": 0.3066,
+      "step": 1440
+    },
+    {
+      "epoch": 1.1750405186385737,
+      "grad_norm": 0.4007652352366936,
+      "learning_rate": 1.5261727091711304e-05,
+      "loss": 0.3069,
+      "step": 1450
+    },
+    {
+      "epoch": 1.1831442463533226,
+      "grad_norm": 0.4353750890221181,
+      "learning_rate": 1.5181291910369643e-05,
+      "loss": 0.304,
+      "step": 1460
+    },
+    {
+      "epoch": 1.1912479740680713,
+      "grad_norm": 0.4127119435889391,
+      "learning_rate": 1.5100395851724127e-05,
+      "loss": 0.3074,
+      "step": 1470
+    },
+    {
+      "epoch": 1.1993517017828201,
+      "grad_norm": 0.4235225792240717,
+      "learning_rate": 1.501904611150086e-05,
+      "loss": 0.3039,
+      "step": 1480
+    },
+    {
+      "epoch": 1.2074554294975688,
+      "grad_norm": 0.43382299145881303,
+      "learning_rate": 1.4937249925781025e-05,
+      "loss": 0.3104,
+      "step": 1490
+    },
+    {
+      "epoch": 1.2155591572123177,
+      "grad_norm": 0.41686747945784425,
+      "learning_rate": 1.4855014570357266e-05,
+      "loss": 0.3079,
+      "step": 1500
+    },
+    {
+      "epoch": 1.2236628849270665,
+      "grad_norm": 0.43748173637208837,
+      "learning_rate": 1.477234736008648e-05,
+      "loss": 0.3023,
+      "step": 1510
+    },
+    {
+      "epoch": 1.2317666126418152,
+      "grad_norm": 0.37046566703974587,
+      "learning_rate": 1.4689255648239182e-05,
+      "loss": 0.3025,
+      "step": 1520
+    },
+    {
+      "epoch": 1.239870340356564,
+      "grad_norm": 0.43845366795783164,
+      "learning_rate": 1.4605746825845394e-05,
+      "loss": 0.3088,
+      "step": 1530
+    },
+    {
+      "epoch": 1.2479740680713127,
+      "grad_norm": 0.3984371305663356,
+      "learning_rate": 1.452182832103726e-05,
+      "loss": 0.3056,
+      "step": 1540
+    },
+    {
+      "epoch": 1.2560777957860616,
+      "grad_norm": 0.4101042748210193,
+      "learning_rate": 1.4437507598388256e-05,
+      "loss": 0.3046,
+      "step": 1550
+    },
+    {
+      "epoch": 1.2641815235008105,
+      "grad_norm": 0.3996048084545691,
+      "learning_rate": 1.4352792158249267e-05,
+      "loss": 0.3096,
+      "step": 1560
+    },
+    {
+      "epoch": 1.2722852512155591,
+      "grad_norm": 0.36488556744003037,
+      "learning_rate": 1.4267689536081391e-05,
+      "loss": 0.2982,
+      "step": 1570
+    },
+    {
+      "epoch": 1.280388978930308,
+      "grad_norm": 0.4012968995203178,
+      "learning_rate": 1.4182207301785673e-05,
+      "loss": 0.2973,
+      "step": 1580
+    },
+    {
+      "epoch": 1.2884927066450567,
+      "grad_norm": 0.44643414456413244,
+      "learning_rate": 1.4096353059029759e-05,
+      "loss": 0.3082,
+      "step": 1590
+    },
+    {
+      "epoch": 1.2965964343598055,
+      "grad_norm": 0.4065188189801923,
+      "learning_rate": 1.4010134444571554e-05,
+      "loss": 0.3065,
+      "step": 1600
+    },
+    {
+      "epoch": 1.3047001620745542,
+      "grad_norm": 0.4075346625253715,
+      "learning_rate": 1.3923559127579917e-05,
+      "loss": 0.3071,
+      "step": 1610
+    },
+    {
+      "epoch": 1.312803889789303,
+      "grad_norm": 0.40275824757361317,
+      "learning_rate": 1.3836634808952488e-05,
+      "loss": 0.3117,
+      "step": 1620
+    },
+    {
+      "epoch": 1.320907617504052,
+      "grad_norm": 0.41721756053539133,
+      "learning_rate": 1.3749369220630706e-05,
+      "loss": 0.3044,
+      "step": 1630
+    },
+    {
+      "epoch": 1.3290113452188006,
+      "grad_norm": 0.42628477078338034,
+      "learning_rate": 1.3661770124912037e-05,
+      "loss": 0.3145,
+      "step": 1640
+    },
+    {
+      "epoch": 1.3371150729335495,
+      "grad_norm": 0.41482016093973356,
+      "learning_rate": 1.357384531375952e-05,
+      "loss": 0.3085,
+      "step": 1650
+    },
+    {
+      "epoch": 1.3452188006482984,
+      "grad_norm": 0.4194321503620031,
+      "learning_rate": 1.3485602608108665e-05,
+      "loss": 0.3122,
+      "step": 1660
+    },
+    {
+      "epoch": 1.353322528363047,
+      "grad_norm": 0.4078840439187206,
+      "learning_rate": 1.3397049857171789e-05,
+      "loss": 0.3153,
+      "step": 1670
+    },
+    {
+      "epoch": 1.3614262560777957,
+      "grad_norm": 0.4017661566201599,
+      "learning_rate": 1.3308194937739811e-05,
+      "loss": 0.3061,
+      "step": 1680
+    },
+    {
+      "epoch": 1.3695299837925445,
+      "grad_norm": 0.3489593029294948,
+      "learning_rate": 1.3219045753481633e-05,
+      "loss": 0.3102,
+      "step": 1690
+    },
+    {
+      "epoch": 1.3776337115072934,
+      "grad_norm": 0.39406194262191907,
+      "learning_rate": 1.3129610234241078e-05,
+      "loss": 0.3067,
+      "step": 1700
+    },
+    {
+      "epoch": 1.385737439222042,
+      "grad_norm": 0.34800667620341075,
+      "learning_rate": 1.3039896335331553e-05,
+      "loss": 0.3031,
+      "step": 1710
+    },
+    {
+      "epoch": 1.393841166936791,
+      "grad_norm": 0.3684624897450172,
+      "learning_rate": 1.2949912036828402e-05,
+      "loss": 0.3039,
+      "step": 1720
+    },
+    {
+      "epoch": 1.4019448946515398,
+      "grad_norm": 0.4382711077957787,
+      "learning_rate": 1.2859665342859094e-05,
+      "loss": 0.3098,
+      "step": 1730
+    },
+    {
+      "epoch": 1.4100486223662885,
+      "grad_norm": 0.4171963139846023,
+      "learning_rate": 1.2769164280891232e-05,
+      "loss": 0.3077,
+      "step": 1740
+    },
+    {
+      "epoch": 1.4181523500810373,
+      "grad_norm": 0.3825478745960653,
+      "learning_rate": 1.2678416901018547e-05,
+      "loss": 0.3145,
+      "step": 1750
+    },
+    {
+      "epoch": 1.426256077795786,
+      "grad_norm": 0.42738446874462166,
+      "learning_rate": 1.2587431275244776e-05,
+      "loss": 0.3068,
+      "step": 1760
+    },
+    {
+      "epoch": 1.4343598055105349,
+      "grad_norm": 0.36853959920698665,
+      "learning_rate": 1.2496215496765725e-05,
+      "loss": 0.3081,
+      "step": 1770
+    },
+    {
+      "epoch": 1.4424635332252835,
+      "grad_norm": 0.4363599637459905,
+      "learning_rate": 1.2404777679249331e-05,
+      "loss": 0.3086,
+      "step": 1780
+    },
+    {
+      "epoch": 1.4505672609400324,
+      "grad_norm": 0.434681625316516,
+      "learning_rate": 1.2313125956113963e-05,
+      "loss": 0.3072,
+      "step": 1790
+    },
+    {
+      "epoch": 1.4586709886547813,
+      "grad_norm": 0.3659344257802947,
+      "learning_rate": 1.2221268479804952e-05,
+      "loss": 0.3019,
+      "step": 1800
+    },
+    {
+      "epoch": 1.46677471636953,
+      "grad_norm": 0.3696274377552102,
+      "learning_rate": 1.2129213421069434e-05,
+      "loss": 0.3014,
+      "step": 1810
+    },
+    {
+      "epoch": 1.4748784440842788,
+      "grad_norm": 0.3399488801666935,
+      "learning_rate": 1.2036968968229553e-05,
+      "loss": 0.2989,
+      "step": 1820
+    },
+    {
+      "epoch": 1.4829821717990275,
+      "grad_norm": 0.41480568694514613,
+      "learning_rate": 1.1944543326454099e-05,
+      "loss": 0.3076,
+      "step": 1830
+    },
+    {
+      "epoch": 1.4910858995137763,
+      "grad_norm": 0.42174306368026826,
+      "learning_rate": 1.1851944717028685e-05,
+      "loss": 0.2995,
+      "step": 1840
+    },
+    {
+      "epoch": 1.499189627228525,
+      "grad_norm": 0.3779914900812468,
+      "learning_rate": 1.1759181376624425e-05,
+      "loss": 0.304,
+      "step": 1850
+    },
+    {
+      "epoch": 1.5072933549432739,
+      "grad_norm": 1.6148993914237835,
+      "learning_rate": 1.1666261556565311e-05,
+      "loss": 0.3134,
+      "step": 1860
+    },
+    {
+      "epoch": 1.5153970826580228,
+      "grad_norm": 0.35295295082412437,
+      "learning_rate": 1.1573193522094235e-05,
+      "loss": 0.3059,
+      "step": 1870
+    },
+    {
+      "epoch": 1.5235008103727714,
+      "grad_norm": 0.3977213576066596,
+      "learning_rate": 1.1479985551637802e-05,
+      "loss": 0.3086,
+      "step": 1880
+    },
+    {
+      "epoch": 1.5316045380875203,
+      "grad_norm": 0.4117601008514046,
+      "learning_rate": 1.1386645936069959e-05,
+      "loss": 0.3014,
+      "step": 1890
+    },
+    {
+      "epoch": 1.5397082658022692,
+      "grad_norm": 0.4157906473216355,
+      "learning_rate": 1.129318297797453e-05,
+      "loss": 0.3131,
+      "step": 1900
+    },
+    {
+      "epoch": 1.5478119935170178,
+      "grad_norm": 0.37850588522376016,
+      "learning_rate": 1.1199604990906673e-05,
+      "loss": 0.2979,
+      "step": 1910
+    },
+    {
+      "epoch": 1.5559157212317665,
+      "grad_norm": 0.41416372867681706,
+      "learning_rate": 1.1105920298653424e-05,
+      "loss": 0.301,
+      "step": 1920
+    },
+    {
+      "epoch": 1.5640194489465153,
+      "grad_norm": 0.379323016055736,
+      "learning_rate": 1.1012137234493257e-05,
+      "loss": 0.3066,
+      "step": 1930
+    },
+    {
+      "epoch": 1.5721231766612642,
+      "grad_norm": 0.7955126524066898,
+      "learning_rate": 1.0918264140454858e-05,
+      "loss": 0.3083,
+      "step": 1940
+    },
+    {
+      "epoch": 1.5802269043760129,
+      "grad_norm": 0.3999865277844089,
+      "learning_rate": 1.0824309366575102e-05,
+      "loss": 0.3004,
+      "step": 1950
+    },
+    {
+      "epoch": 1.5883306320907618,
+      "grad_norm": 0.38799693022468235,
+      "learning_rate": 1.07302812701563e-05,
+      "loss": 0.3122,
+      "step": 1960
+    },
+    {
+      "epoch": 1.5964343598055106,
+      "grad_norm": 0.36528454102409375,
+      "learning_rate": 1.0636188215022822e-05,
+      "loss": 0.3055,
+      "step": 1970
+    },
+    {
+      "epoch": 1.6045380875202593,
+      "grad_norm": 0.40466065799611856,
+      "learning_rate": 1.0542038570777145e-05,
+      "loss": 0.301,
+      "step": 1980
+    },
+    {
+      "epoch": 1.6126418152350082,
+      "grad_norm": 0.4361168394444497,
+      "learning_rate": 1.0447840712055346e-05,
+      "loss": 0.2993,
+      "step": 1990
+    },
+    {
+      "epoch": 1.620745542949757,
+      "grad_norm": 0.4209274177422905,
+      "learning_rate": 1.0353603017782198e-05,
+      "loss": 0.306,
+      "step": 2000
+    },
+    {
+      "epoch": 1.6288492706645057,
+      "grad_norm": 0.3919282812418125,
+      "learning_rate": 1.025933387042587e-05,
+      "loss": 0.3012,
+      "step": 2010
+    },
+    {
+      "epoch": 1.6369529983792543,
+      "grad_norm": 0.37194050534762674,
+      "learning_rate": 1.0165041655252273e-05,
+      "loss": 0.3072,
+      "step": 2020
+    },
+    {
+      "epoch": 1.6450567260940032,
+      "grad_norm": 0.3935264030095676,
+      "learning_rate": 1.0070734759579213e-05,
+      "loss": 0.3033,
+      "step": 2030
+    },
+    {
+      "epoch": 1.653160453808752,
+      "grad_norm": 0.4252269412177971,
+      "learning_rate": 9.976421572030335e-06,
+      "loss": 0.3064,
+      "step": 2040
+    },
+    {
+      "epoch": 1.6612641815235007,
+      "grad_norm": 0.39352227497086834,
+      "learning_rate": 9.882110481788943e-06,
+      "loss": 0.2992,
+      "step": 2050
+    },
+    {
+      "epoch": 1.6693679092382496,
+      "grad_norm": 0.4185906324173881,
+      "learning_rate": 9.787809877851788e-06,
+      "loss": 0.3032,
+      "step": 2060
+    },
+    {
+      "epoch": 1.6774716369529985,
+      "grad_norm": 0.36781002222342246,
+      "learning_rate": 9.693528148282858e-06,
+      "loss": 0.3075,
+      "step": 2070
+    },
+    {
+      "epoch": 1.6855753646677472,
+      "grad_norm": 0.3619674954721495,
+      "learning_rate": 9.599273679467261e-06,
+      "loss": 0.3002,
+      "step": 2080
+    },
+    {
+      "epoch": 1.6936790923824958,
+      "grad_norm": 0.3683997067385245,
+      "learning_rate": 9.505054855365255e-06,
+      "loss": 0.3023,
+      "step": 2090
+    },
+    {
+      "epoch": 1.7017828200972447,
+      "grad_norm": 0.3834559843064888,
+      "learning_rate": 9.4108800567665e-06,
+      "loss": 0.3007,
+      "step": 2100
+    },
+    {
+      "epoch": 1.7098865478119936,
+      "grad_norm": 0.3737575615610543,
+      "learning_rate": 9.31675766054456e-06,
+      "loss": 0.2972,
+      "step": 2110
+    },
+    {
+      "epoch": 1.7179902755267422,
+      "grad_norm": 0.3978738368183821,
+      "learning_rate": 9.222696038911799e-06,
+      "loss": 0.3045,
+      "step": 2120
+    },
+    {
+      "epoch": 1.726094003241491,
+      "grad_norm": 0.39965197721390877,
+      "learning_rate": 9.128703558674671e-06,
+      "loss": 0.2978,
+      "step": 2130
+    },
+    {
+      "epoch": 1.73419773095624,
+      "grad_norm": 0.3599455657513092,
+      "learning_rate": 9.034788580489483e-06,
+      "loss": 0.3013,
+      "step": 2140
+    },
+    {
+      "epoch": 1.7423014586709886,
+      "grad_norm": 0.4080290089436696,
+      "learning_rate": 8.9409594581187e-06,
+      "loss": 0.2965,
+      "step": 2150
+    },
+    {
+      "epoch": 1.7504051863857373,
+      "grad_norm": 0.4497237137187179,
+      "learning_rate": 8.84722453768791e-06,
+      "loss": 0.2977,
+      "step": 2160
+    },
+    {
+      "epoch": 1.7585089141004864,
+      "grad_norm": 0.3741529876845959,
+      "learning_rate": 8.753592156943398e-06,
+      "loss": 0.2975,
+      "step": 2170
+    },
+    {
+      "epoch": 1.766612641815235,
+      "grad_norm": 0.4089056844276575,
+      "learning_rate": 8.660070644510527e-06,
+      "loss": 0.3,
+      "step": 2180
+    },
+    {
+      "epoch": 1.7747163695299837,
+      "grad_norm": 0.35625670427034406,
+      "learning_rate": 8.566668319152885e-06,
+      "loss": 0.2968,
+      "step": 2190
+    },
+    {
+      "epoch": 1.7828200972447326,
+      "grad_norm": 0.3893898095765407,
+      "learning_rate": 8.47339348903234e-06,
+      "loss": 0.2955,
+      "step": 2200
+    },
+    {
+      "epoch": 1.7909238249594814,
+      "grad_norm": 0.3990611499260032,
+      "learning_rate": 8.38025445097003e-06,
+      "loss": 0.3013,
+      "step": 2210
+    },
+    {
+      "epoch": 1.79902755267423,
+      "grad_norm": 0.3614737349469057,
+      "learning_rate": 8.287259489708345e-06,
+      "loss": 0.3021,
+      "step": 2220
+    },
+    {
+      "epoch": 1.807131280388979,
+      "grad_norm": 0.38973646427824704,
+      "learning_rate": 8.194416877174011e-06,
+      "loss": 0.299,
+      "step": 2230
+    },
+    {
+      "epoch": 1.8152350081037278,
+      "grad_norm": 0.41447716289276126,
+      "learning_rate": 8.101734871742293e-06,
+      "loss": 0.3002,
+      "step": 2240
+    },
+    {
+      "epoch": 1.8233387358184765,
+      "grad_norm": 0.3576818485334696,
+      "learning_rate": 8.00922171750241e-06,
+      "loss": 0.2995,
+      "step": 2250
+    },
+    {
+      "epoch": 1.8314424635332252,
+      "grad_norm": 0.38188137453697657,
+      "learning_rate": 7.916885643524218e-06,
+      "loss": 0.306,
+      "step": 2260
+    },
+    {
+      "epoch": 1.839546191247974,
+      "grad_norm": 0.37637494414677514,
+      "learning_rate": 7.824734863126242e-06,
+      "loss": 0.3019,
+      "step": 2270
+    },
+    {
+      "epoch": 1.847649918962723,
+      "grad_norm": 0.418740032736488,
+      "learning_rate": 7.732777573145095e-06,
+      "loss": 0.3,
+      "step": 2280
+    },
+    {
+      "epoch": 1.8557536466774716,
+      "grad_norm": 0.38756882229694817,
+      "learning_rate": 7.641021953206365e-06,
+      "loss": 0.3035,
+      "step": 2290
+    },
+    {
+      "epoch": 1.8638573743922204,
+      "grad_norm": 0.3522277249116831,
+      "learning_rate": 7.549476164997023e-06,
+      "loss": 0.3049,
+      "step": 2300
+    },
+    {
+      "epoch": 1.8719611021069693,
+      "grad_norm": 0.3970737751096915,
+      "learning_rate": 7.458148351539469e-06,
+      "loss": 0.3002,
+      "step": 2310
+    },
+    {
+      "epoch": 1.880064829821718,
+      "grad_norm": 0.390292992400036,
+      "learning_rate": 7.367046636467181e-06,
+      "loss": 0.3015,
+      "step": 2320
+    },
+    {
+      "epoch": 1.8881685575364666,
+      "grad_norm": 0.3641897838066829,
+      "learning_rate": 7.276179123302132e-06,
+      "loss": 0.2977,
+      "step": 2330
+    },
+    {
+      "epoch": 1.8962722852512157,
+      "grad_norm": 0.3469879258131187,
+      "learning_rate": 7.185553894733961e-06,
+      "loss": 0.3049,
+      "step": 2340
+    },
+    {
+      "epoch": 1.9043760129659644,
+      "grad_norm": 0.3785678311275398,
+      "learning_rate": 7.0951790119010335e-06,
+      "loss": 0.3046,
+      "step": 2350
+    },
+    {
+      "epoch": 1.912479740680713,
+      "grad_norm": 0.37159218665298005,
+      "learning_rate": 7.0050625136734e-06,
+      "loss": 0.2971,
+      "step": 2360
+    },
+    {
+      "epoch": 1.920583468395462,
+      "grad_norm": 0.6152560151371722,
+      "learning_rate": 6.915212415937727e-06,
+      "loss": 0.2986,
+      "step": 2370
+    },
+    {
+      "epoch": 1.9286871961102108,
+      "grad_norm": 0.3913939757601664,
+      "learning_rate": 6.825636710884276e-06,
+      "loss": 0.2969,
+      "step": 2380
+    },
+    {
+      "epoch": 1.9367909238249594,
+      "grad_norm": 0.4176128533009644,
+      "learning_rate": 6.736343366296023e-06,
+      "loss": 0.3054,
+      "step": 2390
+    },
+    {
+      "epoch": 1.9448946515397083,
+      "grad_norm": 0.3565467616352092,
+      "learning_rate": 6.647340324839899e-06,
+      "loss": 0.2997,
+      "step": 2400
+    },
+    {
+      "epoch": 1.9529983792544572,
+      "grad_norm": 0.3941255058835232,
+      "learning_rate": 6.558635503360282e-06,
+      "loss": 0.2942,
+      "step": 2410
+    },
+    {
+      "epoch": 1.9611021069692058,
+      "grad_norm": 0.3708607373972731,
+      "learning_rate": 6.470236792174821e-06,
+      "loss": 0.2968,
+      "step": 2420
+    },
+    {
+      "epoch": 1.9692058346839545,
+      "grad_norm": 0.3880832797351479,
+      "learning_rate": 6.382152054372559e-06,
+      "loss": 0.2948,
+      "step": 2430
+    },
+    {
+      "epoch": 1.9773095623987034,
+      "grad_norm": 0.383558048697859,
+      "learning_rate": 6.294389125114533e-06,
+      "loss": 0.3021,
+      "step": 2440
+    },
+    {
+      "epoch": 1.9854132901134522,
+      "grad_norm": 0.36063970766363035,
+      "learning_rate": 6.206955810936812e-06,
+      "loss": 0.2992,
+      "step": 2450
+    },
+    {
+      "epoch": 1.993517017828201,
+      "grad_norm": 0.3166191287671094,
+      "learning_rate": 6.1198598890561245e-06,
+      "loss": 0.2964,
+      "step": 2460
+    },
+    {
+      "epoch": 2.0016207455429496,
+      "grad_norm": 0.4660217296625883,
+      "learning_rate": 6.033109106678061e-06,
+      "loss": 0.2832,
+      "step": 2470
+    },
+    {
+      "epoch": 2.0097244732576987,
+      "grad_norm": 0.407995409083507,
+      "learning_rate": 5.946711180307962e-06,
+      "loss": 0.2552,
+      "step": 2480
+    },
+    {
+      "epoch": 2.0178282009724473,
+      "grad_norm": 0.5289122734846362,
+      "learning_rate": 5.860673795064526e-06,
+      "loss": 0.2443,
+      "step": 2490
+    },
+    {
+      "epoch": 2.025931928687196,
+      "grad_norm": 0.4537365495718812,
+      "learning_rate": 5.7750046039962256e-06,
+      "loss": 0.2482,
+      "step": 2500
+    },
+    {
+      "epoch": 2.034035656401945,
+      "grad_norm": 0.3477277499739405,
+      "learning_rate": 5.689711227400565e-06,
+      "loss": 0.24,
+      "step": 2510
+    },
+    {
+      "epoch": 2.0421393841166937,
+      "grad_norm": 0.4074543041725379,
+      "learning_rate": 5.604801252146254e-06,
+      "loss": 0.2491,
+      "step": 2520
+    },
+    {
+      "epoch": 2.0502431118314424,
+      "grad_norm": 0.44063574223425644,
+      "learning_rate": 5.520282230998338e-06,
+      "loss": 0.2416,
+      "step": 2530
+    },
+    {
+      "epoch": 2.0583468395461915,
+      "grad_norm": 0.8357409178128945,
+      "learning_rate": 5.436161681946395e-06,
+      "loss": 0.242,
+      "step": 2540
+    },
+    {
+      "epoch": 2.06645056726094,
+      "grad_norm": 0.5508244446217927,
+      "learning_rate": 5.352447087535806e-06,
+      "loss": 0.2418,
+      "step": 2550
+    },
+    {
+      "epoch": 2.0745542949756888,
+      "grad_norm": 0.37415637717323663,
+      "learning_rate": 5.2691458942021824e-06,
+      "loss": 0.2477,
+      "step": 2560
+    },
+    {
+      "epoch": 2.0826580226904374,
+      "grad_norm": 0.41346781789193127,
+      "learning_rate": 5.186265511608986e-06,
+      "loss": 0.243,
+      "step": 2570
+    },
+    {
+      "epoch": 2.0907617504051865,
+      "grad_norm": 0.36169586382771485,
+      "learning_rate": 5.103813311988464e-06,
+      "loss": 0.252,
+      "step": 2580
+    },
+    {
+      "epoch": 2.098865478119935,
+      "grad_norm": 0.40760567909077583,
+      "learning_rate": 5.021796629485864e-06,
+      "loss": 0.2505,
+      "step": 2590
+    },
+    {
+      "epoch": 2.106969205834684,
+      "grad_norm": 0.3924479300565109,
+      "learning_rate": 4.9402227595070685e-06,
+      "loss": 0.2446,
+      "step": 2600
+    },
+    {
+      "epoch": 2.115072933549433,
+      "grad_norm": 0.43202040375016904,
+      "learning_rate": 4.859098958069676e-06,
+      "loss": 0.2452,
+      "step": 2610
+    },
+    {
+      "epoch": 2.1231766612641816,
+      "grad_norm": 0.3945116665878516,
+      "learning_rate": 4.778432441157563e-06,
+      "loss": 0.2456,
+      "step": 2620
+    },
+    {
+      "epoch": 2.1312803889789302,
+      "grad_norm": 0.3971635289819625,
+      "learning_rate": 4.698230384079027e-06,
+      "loss": 0.2418,
+      "step": 2630
+    },
+    {
+      "epoch": 2.139384116693679,
+      "grad_norm": 0.4083259569524127,
+      "learning_rate": 4.618499920828534e-06,
+      "loss": 0.24,
+      "step": 2640
+    },
+    {
+      "epoch": 2.147487844408428,
+      "grad_norm": 0.46706467015295594,
+      "learning_rate": 4.539248143452152e-06,
+      "loss": 0.2491,
+      "step": 2650
+    },
+    {
+      "epoch": 2.1555915721231766,
+      "grad_norm": 0.4142008764583011,
+      "learning_rate": 4.46048210141672e-06,
+      "loss": 0.2448,
+      "step": 2660
+    },
+    {
+      "epoch": 2.1636952998379253,
+      "grad_norm": 0.8114850471840835,
+      "learning_rate": 4.382208800982786e-06,
+      "loss": 0.2479,
+      "step": 2670
+    },
+    {
+      "epoch": 2.1717990275526744,
+      "grad_norm": 0.35734338843895713,
+      "learning_rate": 4.304435204581391e-06,
+      "loss": 0.2486,
+      "step": 2680
+    },
+    {
+      "epoch": 2.179902755267423,
+      "grad_norm": 0.4071788138919023,
+      "learning_rate": 4.227168230194784e-06,
+      "loss": 0.25,
+      "step": 2690
+    },
+    {
+      "epoch": 2.1880064829821717,
+      "grad_norm": 0.36994434936239384,
+      "learning_rate": 4.150414750741034e-06,
+      "loss": 0.2412,
+      "step": 2700
+    },
+    {
+      "epoch": 2.1961102106969204,
+      "grad_norm": 0.4461278403182746,
+      "learning_rate": 4.074181593462714e-06,
+      "loss": 0.2426,
+      "step": 2710
+    },
+    {
+      "epoch": 2.2042139384116695,
+      "grad_norm": 0.4011800469721519,
+      "learning_rate": 3.998475539319584e-06,
+      "loss": 0.2408,
+      "step": 2720
+    },
+    {
+      "epoch": 2.212317666126418,
+      "grad_norm": 0.4367556713506246,
+      "learning_rate": 3.92330332238545e-06,
+      "loss": 0.2396,
+      "step": 2730
+    },
+    {
+      "epoch": 2.2204213938411668,
+      "grad_norm": 0.3640083976837478,
+      "learning_rate": 3.8486716292491535e-06,
+      "loss": 0.2407,
+      "step": 2740
+    },
+    {
+      "epoch": 2.228525121555916,
+      "grad_norm": 0.39943748276335717,
+      "learning_rate": 3.7745870984198008e-06,
+      "loss": 0.2458,
+      "step": 2750
+    },
+    {
+      "epoch": 2.2366288492706645,
+      "grad_norm": 0.39445317928843804,
+      "learning_rate": 3.701056319736257e-06,
+      "loss": 0.246,
+      "step": 2760
+    },
+    {
+      "epoch": 2.244732576985413,
+      "grad_norm": 0.36163919583931875,
+      "learning_rate": 3.6280858337809875e-06,
+      "loss": 0.2434,
+      "step": 2770
+    },
+    {
+      "epoch": 2.2528363047001623,
+      "grad_norm": 0.3725113643783422,
+      "learning_rate": 3.555682131298279e-06,
+      "loss": 0.2443,
+      "step": 2780
+    },
+    {
+      "epoch": 2.260940032414911,
+      "grad_norm": 0.40578105363775085,
+      "learning_rate": 3.483851652616862e-06,
+      "loss": 0.2444,
+      "step": 2790
+    },
+    {
+      "epoch": 2.2690437601296596,
+      "grad_norm": 0.41832475832340055,
+      "learning_rate": 3.412600787077066e-06,
+      "loss": 0.2429,
+      "step": 2800
+    },
+    {
+      "epoch": 2.2771474878444082,
+      "grad_norm": 0.3930950216930059,
+      "learning_rate": 3.3419358724624785e-06,
+      "loss": 0.2439,
+      "step": 2810
+    },
+    {
+      "epoch": 2.2852512155591573,
+      "grad_norm": 0.3817799004498428,
+      "learning_rate": 3.2718631944361856e-06,
+      "loss": 0.2462,
+      "step": 2820
+    },
+    {
+      "epoch": 2.293354943273906,
+      "grad_norm": 0.4511023499074228,
+      "learning_rate": 3.2023889859816737e-06,
+      "loss": 0.2514,
+      "step": 2830
+    },
+    {
+      "epoch": 2.3014586709886546,
+      "grad_norm": 0.379383182419434,
+      "learning_rate": 3.1335194268484027e-06,
+      "loss": 0.2448,
+      "step": 2840
+    },
+    {
+      "epoch": 2.3095623987034037,
+      "grad_norm": 0.41701366040759896,
+      "learning_rate": 3.065260643002115e-06,
+      "loss": 0.2461,
+      "step": 2850
+    },
+    {
+      "epoch": 2.3176661264181524,
+      "grad_norm": 0.40218729209736664,
+      "learning_rate": 2.9976187060799254e-06,
+      "loss": 0.2468,
+      "step": 2860
+    },
+    {
+      "epoch": 2.325769854132901,
+      "grad_norm": 0.5149798804924962,
+      "learning_rate": 2.9305996328502473e-06,
+      "loss": 0.2474,
+      "step": 2870
+    },
+    {
+      "epoch": 2.3338735818476497,
+      "grad_norm": 0.3537966410672981,
+      "learning_rate": 2.8642093846776007e-06,
+      "loss": 0.2427,
+      "step": 2880
+    },
+    {
+      "epoch": 2.341977309562399,
+      "grad_norm": 0.38632460668582685,
+      "learning_rate": 2.7984538669923534e-06,
+      "loss": 0.244,
+      "step": 2890
+    },
+    {
+      "epoch": 2.3500810372771475,
+      "grad_norm": 0.3710773063176993,
+      "learning_rate": 2.7333389287654276e-06,
+      "loss": 0.2435,
+      "step": 2900
+    },
+    {
+      "epoch": 2.358184764991896,
+      "grad_norm": 0.41098636515925197,
+      "learning_rate": 2.6688703619880207e-06,
+      "loss": 0.2458,
+      "step": 2910
+    },
+    {
+      "epoch": 2.366288492706645,
+      "grad_norm": 0.42212915287085107,
+      "learning_rate": 2.6050539011564256e-06,
+      "loss": 0.2405,
+      "step": 2920
+    },
+    {
+      "epoch": 2.374392220421394,
+      "grad_norm": 0.3471299884615819,
+      "learning_rate": 2.5418952227619387e-06,
+      "loss": 0.2437,
+      "step": 2930
+    },
+    {
+      "epoch": 2.3824959481361425,
+      "grad_norm": 0.38907627938003014,
+      "learning_rate": 2.479399944785923e-06,
+      "loss": 0.2476,
+      "step": 2940
+    },
+    {
+      "epoch": 2.3905996758508916,
+      "grad_norm": 0.3825018552797764,
+      "learning_rate": 2.4175736262001003e-06,
+      "loss": 0.2437,
+      "step": 2950
+    },
+    {
+      "epoch": 2.3987034035656403,
+      "grad_norm": 0.4003402195922579,
+      "learning_rate": 2.356421766472077e-06,
+      "loss": 0.2427,
+      "step": 2960
+    },
+    {
+      "epoch": 2.406807131280389,
+      "grad_norm": 0.35508475535540746,
+      "learning_rate": 2.2959498050761665e-06,
+      "loss": 0.2466,
+      "step": 2970
+    },
+    {
+      "epoch": 2.4149108589951376,
+      "grad_norm": 0.4187690493214179,
+      "learning_rate": 2.236163121009535e-06,
+      "loss": 0.237,
+      "step": 2980
+    },
+    {
+      "epoch": 2.4230145867098867,
+      "grad_norm": 0.35589430838069036,
+      "learning_rate": 2.1770670323137543e-06,
+      "loss": 0.2461,
+      "step": 2990
+    },
+    {
+      "epoch": 2.4311183144246353,
+      "grad_norm": 0.3926639223548047,
+      "learning_rate": 2.118666795601746e-06,
+      "loss": 0.2474,
+      "step": 3000
+    },
+    {
+      "epoch": 2.439222042139384,
+      "grad_norm": 0.4329712621602187,
+      "learning_rate": 2.0609676055902206e-06,
+      "loss": 0.2423,
+      "step": 3010
+    },
+    {
+      "epoch": 2.447325769854133,
+      "grad_norm": 0.38666802803090544,
+      "learning_rate": 2.0039745946375843e-06,
+      "loss": 0.2469,
+      "step": 3020
+    },
+    {
+      "epoch": 2.4554294975688817,
+      "grad_norm": 0.37148012112460693,
+      "learning_rate": 1.9476928322874388e-06,
+      "loss": 0.2444,
+      "step": 3030
+    },
+    {
+      "epoch": 2.4635332252836304,
+      "grad_norm": 0.3634208666903963,
+      "learning_rate": 1.8921273248176274e-06,
+      "loss": 0.2391,
+      "step": 3040
+    },
+    {
+      "epoch": 2.471636952998379,
+      "grad_norm": 0.355519886297564,
+      "learning_rate": 1.8372830147949273e-06,
+      "loss": 0.2483,
+      "step": 3050
+    },
+    {
+      "epoch": 2.479740680713128,
+      "grad_norm": 0.3713871962443745,
+      "learning_rate": 1.783164780635409e-06,
+      "loss": 0.2313,
+      "step": 3060
+    },
+    {
+      "epoch": 2.487844408427877,
+      "grad_norm": 0.3759078137724125,
+      "learning_rate": 1.7297774361705067e-06,
+      "loss": 0.2448,
+      "step": 3070
+    },
+    {
+      "epoch": 2.4959481361426255,
+      "grad_norm": 0.3485711841045443,
+      "learning_rate": 1.6771257302188138e-06,
+      "loss": 0.2399,
+      "step": 3080
+    },
+    {
+      "epoch": 2.5040518638573745,
+      "grad_norm": 0.3363937506829417,
+      "learning_rate": 1.6252143461636894e-06,
+      "loss": 0.2398,
+      "step": 3090
+    },
+    {
+      "epoch": 2.512155591572123,
+      "grad_norm": 0.3588787472573543,
+      "learning_rate": 1.5740479015366516e-06,
+      "loss": 0.2462,
+      "step": 3100
+    },
+    {
+      "epoch": 2.520259319286872,
+      "grad_norm": 0.36857928716008176,
+      "learning_rate": 1.523630947606659e-06,
+      "loss": 0.2419,
+      "step": 3110
+    },
+    {
+      "epoch": 2.528363047001621,
+      "grad_norm": 0.4560312263878305,
+      "learning_rate": 1.4739679689752761e-06,
+      "loss": 0.2439,
+      "step": 3120
+    },
+    {
+      "epoch": 2.5364667747163696,
+      "grad_norm": 0.4487239477052906,
+      "learning_rate": 1.4250633831777617e-06,
+      "loss": 0.2447,
+      "step": 3130
+    },
+    {
+      "epoch": 2.5445705024311183,
+      "grad_norm": 0.33641842711140135,
+      "learning_rate": 1.3769215402901248e-06,
+      "loss": 0.2436,
+      "step": 3140
+    },
+    {
+      "epoch": 2.5526742301458674,
+      "grad_norm": 0.3625894331178874,
+      "learning_rate": 1.3295467225421922e-06,
+      "loss": 0.2371,
+      "step": 3150
+    },
+    {
+      "epoch": 2.560777957860616,
+      "grad_norm": 0.4462848969444906,
+      "learning_rate": 1.2829431439366979e-06,
+      "loss": 0.242,
+      "step": 3160
+    },
+    {
+      "epoch": 2.5688816855753647,
+      "grad_norm": 0.3587946417962074,
+      "learning_rate": 1.2371149498744483e-06,
+      "loss": 0.2412,
+      "step": 3170
+    },
+    {
+      "epoch": 2.5769854132901133,
+      "grad_norm": 0.36830382203343376,
+      "learning_rate": 1.1920662167855801e-06,
+      "loss": 0.2424,
+      "step": 3180
+    },
+    {
+      "epoch": 2.585089141004862,
+      "grad_norm": 0.37715567765830954,
+      "learning_rate": 1.1478009517669786e-06,
+      "loss": 0.2413,
+      "step": 3190
+    },
+    {
+      "epoch": 2.593192868719611,
+      "grad_norm": 0.4012409586115721,
+      "learning_rate": 1.1043230922258286e-06,
+      "loss": 0.2457,
+      "step": 3200
+    },
+    {
+      "epoch": 2.6012965964343597,
+      "grad_norm": 0.3170760273795616,
+      "learning_rate": 1.0616365055293832e-06,
+      "loss": 0.2434,
+      "step": 3210
+    },
+    {
+      "epoch": 2.6094003241491084,
+      "grad_norm": 0.4140931437435226,
+      "learning_rate": 1.0197449886609734e-06,
+      "loss": 0.243,
+      "step": 3220
+    },
+    {
+      "epoch": 2.6175040518638575,
+      "grad_norm": 0.3896642089079419,
+      "learning_rate": 9.786522678822441e-07,
+      "loss": 0.2347,
+      "step": 3230
+    },
+    {
+      "epoch": 2.625607779578606,
+      "grad_norm": 0.3645636276596164,
+      "learning_rate": 9.383619984017256e-07,
+      "loss": 0.2446,
+      "step": 3240
+    },
+    {
+      "epoch": 2.633711507293355,
+      "grad_norm": 0.40046394757499343,
+      "learning_rate": 8.988777640496804e-07,
+      "loss": 0.2447,
+      "step": 3250
+    },
+    {
+      "epoch": 2.641815235008104,
+      "grad_norm": 0.36791745231671324,
+      "learning_rate": 8.602030769593361e-07,
+      "loss": 0.2424,
+      "step": 3260
+    },
+    {
+      "epoch": 2.6499189627228525,
+      "grad_norm": 0.3513386208889417,
+      "learning_rate": 8.223413772544753e-07,
+      "loss": 0.2453,
+      "step": 3270
+    },
+    {
+      "epoch": 2.658022690437601,
+      "grad_norm": 0.35149227411663847,
+      "learning_rate": 7.8529603274343e-07,
+      "loss": 0.2462,
+      "step": 3280
+    },
+    {
+      "epoch": 2.6661264181523503,
+      "grad_norm": 0.37698716823527095,
+      "learning_rate": 7.490703386195209e-07,
+      "loss": 0.2423,
+      "step": 3290
+    },
+    {
+      "epoch": 2.674230145867099,
+      "grad_norm": 0.385028609831952,
+      "learning_rate": 7.136675171679486e-07,
+      "loss": 0.2422,
+      "step": 3300
+    },
+    {
+      "epoch": 2.6823338735818476,
+      "grad_norm": 0.5378889252817534,
+      "learning_rate": 6.790907174791673e-07,
+      "loss": 0.2438,
+      "step": 3310
+    },
+    {
+      "epoch": 2.6904376012965967,
+      "grad_norm": 0.3838809816352739,
+      "learning_rate": 6.453430151687778e-07,
+      "loss": 0.2377,
+      "step": 3320
+    },
+    {
+      "epoch": 2.6985413290113454,
+      "grad_norm": 0.36399909811291453,
+      "learning_rate": 6.124274121039409e-07,
+      "loss": 0.2403,
+      "step": 3330
+    },
+    {
+      "epoch": 2.706645056726094,
+      "grad_norm": 0.4223771585395702,
+      "learning_rate": 5.803468361363718e-07,
+      "loss": 0.237,
+      "step": 3340
+    },
+    {
+      "epoch": 2.7147487844408427,
+      "grad_norm": 0.8089123101603323,
+      "learning_rate": 5.491041408418973e-07,
+      "loss": 0.2372,
+      "step": 3350
+    },
+    {
+      "epoch": 2.7228525121555913,
+      "grad_norm": 0.36918012481907325,
+      "learning_rate": 5.187021052666364e-07,
+      "loss": 0.2447,
+      "step": 3360
+    },
+    {
+      "epoch": 2.7309562398703404,
+      "grad_norm": 0.34518982645416496,
+      "learning_rate": 4.891434336797995e-07,
+      "loss": 0.2382,
+      "step": 3370
+    },
+    {
+      "epoch": 2.739059967585089,
+      "grad_norm": 0.3908359372691203,
+      "learning_rate": 4.604307553331466e-07,
+      "loss": 0.2401,
+      "step": 3380
+    },
+    {
+      "epoch": 2.7471636952998377,
+      "grad_norm": 0.3763482460779644,
+      "learning_rate": 4.3256662422711203e-07,
+      "loss": 0.244,
+      "step": 3390
+    },
+    {
+      "epoch": 2.755267423014587,
+      "grad_norm": 0.4935616769207569,
+      "learning_rate": 4.0555351888362126e-07,
+      "loss": 0.2362,
+      "step": 3400
+    },
+    {
+      "epoch": 2.7633711507293355,
+      "grad_norm": 0.38728068087308454,
+      "learning_rate": 3.793938421256349e-07,
+      "loss": 0.2423,
+      "step": 3410
+    },
+    {
+      "epoch": 2.771474878444084,
+      "grad_norm": 0.4584551943804237,
+      "learning_rate": 3.5408992086340963e-07,
+      "loss": 0.2469,
+      "step": 3420
+    },
+    {
+      "epoch": 2.7795786061588332,
+      "grad_norm": 0.37580838068494204,
+      "learning_rate": 3.296440058875239e-07,
+      "loss": 0.2449,
+      "step": 3430
+    },
+    {
+      "epoch": 2.787682333873582,
+      "grad_norm": 0.40471874224510274,
+      "learning_rate": 3.060582716686633e-07,
+      "loss": 0.2434,
+      "step": 3440
+    },
+    {
+      "epoch": 2.7957860615883305,
+      "grad_norm": 0.37522911331627434,
+      "learning_rate": 2.833348161642091e-07,
+      "loss": 0.2444,
+      "step": 3450
+    },
+    {
+      "epoch": 2.8038897893030796,
+      "grad_norm": 0.39940364995265065,
+      "learning_rate": 2.61475660631616e-07,
+      "loss": 0.2449,
+      "step": 3460
+    },
+    {
+      "epoch": 2.8119935170178283,
+      "grad_norm": 0.35364502873855896,
+      "learning_rate": 2.4048274944862837e-07,
+      "loss": 0.2456,
+      "step": 3470
+    },
+    {
+      "epoch": 2.820097244732577,
+      "grad_norm": 0.36553829705078283,
+      "learning_rate": 2.2035794994031856e-07,
+      "loss": 0.2436,
+      "step": 3480
+    },
+    {
+      "epoch": 2.828200972447326,
+      "grad_norm": 0.3891241968932869,
+      "learning_rate": 2.0110305221299641e-07,
+      "loss": 0.2445,
+      "step": 3490
+    },
+    {
+      "epoch": 2.8363047001620747,
+      "grad_norm": 0.3190510082780262,
+      "learning_rate": 1.8271976899497555e-07,
+      "loss": 0.2465,
+      "step": 3500
+    },
+    {
+      "epoch": 2.8444084278768234,
+      "grad_norm": 0.36546653489886294,
+      "learning_rate": 1.6520973548422526e-07,
+      "loss": 0.2412,
+      "step": 3510
+    },
+    {
+      "epoch": 2.852512155591572,
+      "grad_norm": 0.4084608660183148,
+      "learning_rate": 1.485745092029145e-07,
+      "loss": 0.2442,
+      "step": 3520
+    },
+    {
+      "epoch": 2.8606158833063207,
+      "grad_norm": 0.44903837515118517,
+      "learning_rate": 1.328155698588829e-07,
+      "loss": 0.2399,
+      "step": 3530
+    },
+    {
+      "epoch": 2.8687196110210698,
+      "grad_norm": 0.3469836138716809,
+      "learning_rate": 1.1793431921400589e-07,
+      "loss": 0.2387,
+      "step": 3540
+    },
+    {
+      "epoch": 2.8768233387358184,
+      "grad_norm": 0.4120473242712089,
+      "learning_rate": 1.0393208095951569e-07,
+      "loss": 0.2428,
+      "step": 3550
+    },
+    {
+      "epoch": 2.884927066450567,
+      "grad_norm": 0.35963611960687336,
+      "learning_rate": 9.081010059825868e-08,
+      "loss": 0.2429,
+      "step": 3560
+    },
+    {
+      "epoch": 2.893030794165316,
+      "grad_norm": 0.3663944281205482,
+      "learning_rate": 7.856954533390305e-08,
+      "loss": 0.24,
+      "step": 3570
+    },
+    {
+      "epoch": 2.901134521880065,
+      "grad_norm": 0.36501099278443794,
+      "learning_rate": 6.721150396712062e-08,
+      "loss": 0.24,
+      "step": 3580
+    },
+    {
+      "epoch": 2.9092382495948135,
+      "grad_norm": 0.3805774262192798,
+      "learning_rate": 5.67369867987344e-08,
+      "loss": 0.2412,
+      "step": 3590
+    },
+    {
+      "epoch": 2.9173419773095626,
+      "grad_norm": 0.3941758041149872,
+      "learning_rate": 4.7146925539852675e-08,
+      "loss": 0.2414,
+      "step": 3600
+    },
+    {
+      "epoch": 2.9254457050243112,
+      "grad_norm": 0.3753240187042441,
+      "learning_rate": 3.8442173228994126e-08,
+      "loss": 0.2497,
+      "step": 3610
+    },
+    {
+      "epoch": 2.93354943273906,
+      "grad_norm": 0.3645915039853733,
+      "learning_rate": 3.0623504156210846e-08,
+      "loss": 0.2398,
+      "step": 3620
+    },
+    {
+      "epoch": 2.941653160453809,
+      "grad_norm": 0.3698264027559446,
+      "learning_rate": 2.3691613794210034e-08,
+      "loss": 0.2431,
+      "step": 3630
+    },
+    {
+      "epoch": 2.9497568881685576,
+      "grad_norm": 0.3502237148296759,
+      "learning_rate": 1.7647118736499046e-08,
+      "loss": 0.2425,
+      "step": 3640
+    },
+    {
+      "epoch": 2.9578606158833063,
+      "grad_norm": 0.3701006188693372,
+      "learning_rate": 1.2490556642530404e-08,
+      "loss": 0.2371,
+      "step": 3650
+    },
+    {
+      "epoch": 2.965964343598055,
+      "grad_norm": 0.36154653479213933,
+      "learning_rate": 8.222386189886688e-09,
+      "loss": 0.235,
+      "step": 3660
+    },
+    {
+      "epoch": 2.974068071312804,
+      "grad_norm": 0.36710053647230256,
+      "learning_rate": 4.84298703347319e-09,
+      "loss": 0.2422,
+      "step": 3670
+    },
+    {
+      "epoch": 2.9821717990275527,
+      "grad_norm": 0.38511187717009826,
+      "learning_rate": 2.3526597717482558e-09,
+      "loss": 0.247,
+      "step": 3680
+    },
+    {
+      "epoch": 2.9902755267423013,
+      "grad_norm": 0.3858326224545778,
+      "learning_rate": 7.516259199913389e-10,
+      "loss": 0.2414,
+      "step": 3690
+    },
+    {
+      "epoch": 2.99837925445705,
+      "grad_norm": 0.38258245366640214,
+      "learning_rate": 4.002789059098788e-11,
+      "loss": 0.2456,
+      "step": 3700
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3702,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 10000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7096684954255360.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dae2c3a4bfb46489609610626fadee5bb01f43f43aef6f449948841e4f539a87
+size 7800

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"
+}