Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 checkpoint-2113/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

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

chat_template.jinja

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

config.json

@@ -0,0 +1,67 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 2560,
+    "initializer_range": 0.02,
+    "intermediate_size": 9728,
+    "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,
+    "tie_word_embeddings": true,
+    "use_cache": true,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      5,
+      11,
+      17
+    ],
+    "depth": 24,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1024,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4096,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 2560,
+    "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"
+}

latest

@@ -0,0 +1 @@
+global_step2113

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd00c1db433ecfc23f2b39abde45f0210109a55f45092a8c169f61fb37114f9
+size 4990497880

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e55746c433dfe11214a27d007edb46aaefad5782a13ca2fee8ca7fa559aebbc
+size 4663133960

model.safetensors.index.json

@@ -0,0 +1,722 @@
+{
+  "metadata": {
+    "total_parameters": 4437815808,
+    "total_size": 9653543936
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00002.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": 1024,
+  "merge_size": 2,
+  "min_pixels": 1024,
+  "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
+}

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d355e48f036ee809fe47cea3a966dfaac74e37c5bb93d7478856f64a9ef76ef2
+size 1465

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 +1,242 @@
+{
+  "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": {},
+  "max_pixels": 1024,
+  "min_pixels": 1024,
+  "model_max_length": 1024,
+  "pad_token": "<|endoftext|>",
+  "processor_class": "Qwen3VLProcessor",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2144 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2113,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.9664676249027253,
+      "epoch": 0.004733167672464797,
+      "grad_norm": 2.9172720909118652,
+      "learning_rate": 8.490566037735849e-07,
+      "loss": 2.4508,
+      "mean_token_accuracy": 0.5263931974768639,
+      "num_tokens": 3879417.0,
+      "step": 10
+    },
+    {
+      "entropy": 2.0464825958013533,
+      "epoch": 0.009466335344929595,
+      "grad_norm": 0.7783076763153076,
+      "learning_rate": 1.7924528301886793e-06,
+      "loss": 2.2632,
+      "mean_token_accuracy": 0.5380982637405396,
+      "num_tokens": 7799425.0,
+      "step": 20
+    },
+    {
+      "entropy": 2.0156721025705338,
+      "epoch": 0.014199503017394392,
+      "grad_norm": 0.38891270756721497,
+      "learning_rate": 2.7358490566037738e-06,
+      "loss": 2.0189,
+      "mean_token_accuracy": 0.568930983543396,
+      "num_tokens": 11646570.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.8222261607646941,
+      "epoch": 0.01893267068985919,
+      "grad_norm": 0.2623351812362671,
+      "learning_rate": 3.679245283018868e-06,
+      "loss": 1.8679,
+      "mean_token_accuracy": 0.5922655925154686,
+      "num_tokens": 15549095.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.7781452298164369,
+      "epoch": 0.023665838362323985,
+      "grad_norm": 0.19355912506580353,
+      "learning_rate": 4.622641509433963e-06,
+      "loss": 1.7967,
+      "mean_token_accuracy": 0.6030044049024582,
+      "num_tokens": 19395583.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.756221604347229,
+      "epoch": 0.028399006034788784,
+      "grad_norm": 0.17072290182113647,
+      "learning_rate": 5.566037735849057e-06,
+      "loss": 1.7705,
+      "mean_token_accuracy": 0.6082265704870224,
+      "num_tokens": 23287255.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.721426972746849,
+      "epoch": 0.033132173707253576,
+      "grad_norm": 0.18896205723285675,
+      "learning_rate": 6.5094339622641515e-06,
+      "loss": 1.7402,
+      "mean_token_accuracy": 0.6131706237792969,
+      "num_tokens": 27155383.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.720760390162468,
+      "epoch": 0.03786534137971838,
+      "grad_norm": 0.16523988544940948,
+      "learning_rate": 7.452830188679246e-06,
+      "loss": 1.7276,
+      "mean_token_accuracy": 0.615737484395504,
+      "num_tokens": 31071816.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.696010684967041,
+      "epoch": 0.042598509052183174,
+      "grad_norm": 0.17002570629119873,
+      "learning_rate": 8.39622641509434e-06,
+      "loss": 1.7075,
+      "mean_token_accuracy": 0.6187006324529648,
+      "num_tokens": 34979450.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.6817427426576614,
+      "epoch": 0.04733167672464797,
+      "grad_norm": 0.1671409159898758,
+      "learning_rate": 9.339622641509435e-06,
+      "loss": 1.689,
+      "mean_token_accuracy": 0.6216033041477204,
+      "num_tokens": 38828299.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.6723841279745102,
+      "epoch": 0.052064844397112765,
+      "grad_norm": 0.1683770716190338,
+      "learning_rate": 9.999944870161476e-06,
+      "loss": 1.683,
+      "mean_token_accuracy": 0.6222904548048973,
+      "num_tokens": 42710858.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.6607272058725357,
+      "epoch": 0.05679801206957757,
+      "grad_norm": 0.16289345920085907,
+      "learning_rate": 9.998964817962902e-06,
+      "loss": 1.6697,
+      "mean_token_accuracy": 0.6255089312791824,
+      "num_tokens": 46563041.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.6530560374259948,
+      "epoch": 0.06153117974204236,
+      "grad_norm": 0.1647324562072754,
+      "learning_rate": 9.996759934642046e-06,
+      "loss": 1.66,
+      "mean_token_accuracy": 0.6271017372608185,
+      "num_tokens": 50473774.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.646892574429512,
+      "epoch": 0.06626434741450715,
+      "grad_norm": 0.1683024764060974,
+      "learning_rate": 9.993330760432702e-06,
+      "loss": 1.6506,
+      "mean_token_accuracy": 0.6288532495498658,
+      "num_tokens": 54345703.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.6421253114938736,
+      "epoch": 0.07099751508697195,
+      "grad_norm": 0.16962556540966034,
+      "learning_rate": 9.98867813554068e-06,
+      "loss": 1.649,
+      "mean_token_accuracy": 0.6289903283119201,
+      "num_tokens": 58224397.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.6290255516767502,
+      "epoch": 0.07573068275943676,
+      "grad_norm": 0.16403813660144806,
+      "learning_rate": 9.98280319993795e-06,
+      "loss": 1.6341,
+      "mean_token_accuracy": 0.6317014634609223,
+      "num_tokens": 62114712.0,
+      "step": 160
+    },
+    {
+      "entropy": 1.6350149989128113,
+      "epoch": 0.08046385043190155,
+      "grad_norm": 0.16714808344841003,
+      "learning_rate": 9.975707393083328e-06,
+      "loss": 1.6379,
+      "mean_token_accuracy": 0.6297940164804459,
+      "num_tokens": 65991061.0,
+      "step": 170
+    },
+    {
+      "entropy": 1.6163844734430313,
+      "epoch": 0.08519701810436635,
+      "grad_norm": 0.17177364230155945,
+      "learning_rate": 9.967392453569775e-06,
+      "loss": 1.6222,
+      "mean_token_accuracy": 0.6339128240942955,
+      "num_tokens": 69856575.0,
+      "step": 180
+    },
+    {
+      "entropy": 1.6292197763919831,
+      "epoch": 0.08993018577683115,
+      "grad_norm": 0.16445177793502808,
+      "learning_rate": 9.95786041869843e-06,
+      "loss": 1.6316,
+      "mean_token_accuracy": 0.6325667470693588,
+      "num_tokens": 73718253.0,
+      "step": 190
+    },
+    {
+      "entropy": 1.6217930316925049,
+      "epoch": 0.09466335344929594,
+      "grad_norm": 0.15951167047023773,
+      "learning_rate": 9.947113623979423e-06,
+      "loss": 1.6253,
+      "mean_token_accuracy": 0.6325555801391601,
+      "num_tokens": 77599124.0,
+      "step": 200
+    },
+    {
+      "entropy": 1.6170487314462663,
+      "epoch": 0.09939652112176074,
+      "grad_norm": 0.15958699584007263,
+      "learning_rate": 9.935154702559637e-06,
+      "loss": 1.6246,
+      "mean_token_accuracy": 0.6333600997924804,
+      "num_tokens": 81539199.0,
+      "step": 210
+    },
+    {
+      "entropy": 1.6078982055187225,
+      "epoch": 0.10412968879422553,
+      "grad_norm": 0.16408687829971313,
+      "learning_rate": 9.921986584577545e-06,
+      "loss": 1.6135,
+      "mean_token_accuracy": 0.6353577077388763,
+      "num_tokens": 85404474.0,
+      "step": 220
+    },
+    {
+      "entropy": 1.6178746074438095,
+      "epoch": 0.10886285646669033,
+      "grad_norm": 0.16022811830043793,
+      "learning_rate": 9.90761249644528e-06,
+      "loss": 1.6173,
+      "mean_token_accuracy": 0.6340486526489257,
+      "num_tokens": 89310569.0,
+      "step": 230
+    },
+    {
+      "entropy": 1.6118096917867661,
+      "epoch": 0.11359602413915514,
+      "grad_norm": 0.16375407576560974,
+      "learning_rate": 9.8920359600581e-06,
+      "loss": 1.6195,
+      "mean_token_accuracy": 0.6345633432269097,
+      "num_tokens": 93225240.0,
+      "step": 240
+    },
+    {
+      "entropy": 1.6142515003681184,
+      "epoch": 0.11832919181161992,
+      "grad_norm": 0.16436107456684113,
+      "learning_rate": 9.875260791931474e-06,
+      "loss": 1.6154,
+      "mean_token_accuracy": 0.6353823691606522,
+      "num_tokens": 97106446.0,
+      "step": 250
+    },
+    {
+      "entropy": 1.6073731541633607,
+      "epoch": 0.12306235948408473,
+      "grad_norm": 0.16237056255340576,
+      "learning_rate": 9.85729110226596e-06,
+      "loss": 1.6087,
+      "mean_token_accuracy": 0.6353139713406563,
+      "num_tokens": 100977975.0,
+      "step": 260
+    },
+    {
+      "entropy": 1.6020812511444091,
+      "epoch": 0.12779552715654952,
+      "grad_norm": 0.15944795310497284,
+      "learning_rate": 9.838131293940148e-06,
+      "loss": 1.6071,
+      "mean_token_accuracy": 0.6363679498434067,
+      "num_tokens": 104876425.0,
+      "step": 270
+    },
+    {
+      "entropy": 1.6033865660429,
+      "epoch": 0.1325286948290143,
+      "grad_norm": 0.17549684643745422,
+      "learning_rate": 9.817786061431874e-06,
+      "loss": 1.6091,
+      "mean_token_accuracy": 0.6354461714625359,
+      "num_tokens": 108709842.0,
+      "step": 280
+    },
+    {
+      "entropy": 1.5905151784420013,
+      "epoch": 0.13726186250147912,
+      "grad_norm": 0.1742265522480011,
+      "learning_rate": 9.79626038966799e-06,
+      "loss": 1.596,
+      "mean_token_accuracy": 0.6382940918207168,
+      "num_tokens": 112609412.0,
+      "step": 290
+    },
+    {
+      "entropy": 1.5923225700855255,
+      "epoch": 0.1419950301739439,
+      "grad_norm": 0.16349110007286072,
+      "learning_rate": 9.773559552802982e-06,
+      "loss": 1.5926,
+      "mean_token_accuracy": 0.6394994035363197,
+      "num_tokens": 116498424.0,
+      "step": 300
+    },
+    {
+      "entropy": 1.5896567821502685,
+      "epoch": 0.1467281978464087,
+      "grad_norm": 0.1612998992204666,
+      "learning_rate": 9.749689112926701e-06,
+      "loss": 1.5973,
+      "mean_token_accuracy": 0.6379290148615837,
+      "num_tokens": 120371695.0,
+      "step": 310
+    },
+    {
+      "entropy": 1.596482390165329,
+      "epoch": 0.15146136551887351,
+      "grad_norm": 0.16588379442691803,
+      "learning_rate": 9.724654918701568e-06,
+      "loss": 1.6006,
+      "mean_token_accuracy": 0.6373828530311585,
+      "num_tokens": 124255939.0,
+      "step": 320
+    },
+    {
+      "entropy": 1.584341713786125,
+      "epoch": 0.1561945331913383,
+      "grad_norm": 0.16518791019916534,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 1.5887,
+      "mean_token_accuracy": 0.6403212890028953,
+      "num_tokens": 128177070.0,
+      "step": 330
+    },
+    {
+      "entropy": 1.5725542455911636,
+      "epoch": 0.1609277008638031,
+      "grad_norm": 0.16715767979621887,
+      "learning_rate": 9.671120086049246e-06,
+      "loss": 1.5799,
+      "mean_token_accuracy": 0.6416747942566872,
+      "num_tokens": 132121810.0,
+      "step": 340
+    },
+    {
+      "entropy": 1.5927457183599472,
+      "epoch": 0.1656608685362679,
+      "grad_norm": 0.17323796451091766,
+      "learning_rate": 9.642632564563576e-06,
+      "loss": 1.5939,
+      "mean_token_accuracy": 0.6393081307411194,
+      "num_tokens": 136012804.0,
+      "step": 350
+    },
+    {
+      "entropy": 1.5822071313858033,
+      "epoch": 0.1703940362087327,
+      "grad_norm": 0.16068372130393982,
+      "learning_rate": 9.61300751939821e-06,
+      "loss": 1.583,
+      "mean_token_accuracy": 0.6409055680036545,
+      "num_tokens": 139940284.0,
+      "step": 360
+    },
+    {
+      "entropy": 1.568736445903778,
+      "epoch": 0.17512720388119749,
+      "grad_norm": 0.16828852891921997,
+      "learning_rate": 9.582252209191417e-06,
+      "loss": 1.5788,
+      "mean_token_accuracy": 0.6417408421635628,
+      "num_tokens": 143849853.0,
+      "step": 370
+    },
+    {
+      "entropy": 1.5762336939573287,
+      "epoch": 0.1798603715536623,
+      "grad_norm": 0.1591760367155075,
+      "learning_rate": 9.550374169515557e-06,
+      "loss": 1.5863,
+      "mean_token_accuracy": 0.6399773553013801,
+      "num_tokens": 147708328.0,
+      "step": 380
+    },
+    {
+      "entropy": 1.5851975083351135,
+      "epoch": 0.1845935392261271,
+      "grad_norm": 0.16111813485622406,
+      "learning_rate": 9.517381211030745e-06,
+      "loss": 1.5859,
+      "mean_token_accuracy": 0.6406419515609741,
+      "num_tokens": 151541012.0,
+      "step": 390
+    },
+    {
+      "entropy": 1.5762753903865814,
+      "epoch": 0.18932670689859188,
+      "grad_norm": 0.1650865077972412,
+      "learning_rate": 9.4832814175711e-06,
+      "loss": 1.583,
+      "mean_token_accuracy": 0.6416757836937904,
+      "num_tokens": 155434817.0,
+      "step": 400
+    },
+    {
+      "entropy": 1.5776998460292817,
+      "epoch": 0.19405987457105667,
+      "grad_norm": 0.1527196615934372,
+      "learning_rate": 9.448083144164078e-06,
+      "loss": 1.5798,
+      "mean_token_accuracy": 0.6412320747971535,
+      "num_tokens": 159311737.0,
+      "step": 410
+    },
+    {
+      "entropy": 1.5809161812067032,
+      "epoch": 0.19879304224352148,
+      "grad_norm": 0.16029658913612366,
+      "learning_rate": 9.411795014983338e-06,
+      "loss": 1.5847,
+      "mean_token_accuracy": 0.64069664478302,
+      "num_tokens": 163185815.0,
+      "step": 420
+    },
+    {
+      "entropy": 1.582759228348732,
+      "epoch": 0.20352620991598627,
+      "grad_norm": 0.15568074584007263,
+      "learning_rate": 9.374425921235684e-06,
+      "loss": 1.5865,
+      "mean_token_accuracy": 0.6403465285897255,
+      "num_tokens": 167027904.0,
+      "step": 430
+    },
+    {
+      "entropy": 1.5735624372959136,
+      "epoch": 0.20825937758845106,
+      "grad_norm": 0.15200895071029663,
+      "learning_rate": 9.33598501898256e-06,
+      "loss": 1.5796,
+      "mean_token_accuracy": 0.6411942645907402,
+      "num_tokens": 170922541.0,
+      "step": 440
+    },
+    {
+      "entropy": 1.573996353149414,
+      "epoch": 0.21299254526091588,
+      "grad_norm": 0.15826307237148285,
+      "learning_rate": 9.296481726896663e-06,
+      "loss": 1.5784,
+      "mean_token_accuracy": 0.6419912785291672,
+      "num_tokens": 174791554.0,
+      "step": 450
+    },
+    {
+      "entropy": 1.573242038488388,
+      "epoch": 0.21772571293338067,
+      "grad_norm": 0.16425147652626038,
+      "learning_rate": 9.25592572395421e-06,
+      "loss": 1.5741,
+      "mean_token_accuracy": 0.6426722049713135,
+      "num_tokens": 178691330.0,
+      "step": 460
+    },
+    {
+      "entropy": 1.5621694713830947,
+      "epoch": 0.22245888060584545,
+      "grad_norm": 0.15976452827453613,
+      "learning_rate": 9.214326947063424e-06,
+      "loss": 1.569,
+      "mean_token_accuracy": 0.6429914653301239,
+      "num_tokens": 182540865.0,
+      "step": 470
+    },
+    {
+      "entropy": 1.5637736171483994,
+      "epoch": 0.22719204827831027,
+      "grad_norm": 0.15400023758411407,
+      "learning_rate": 9.171695588629818e-06,
+      "loss": 1.5669,
+      "mean_token_accuracy": 0.6447574943304062,
+      "num_tokens": 186445682.0,
+      "step": 480
+    },
+    {
+      "entropy": 1.5614915072917939,
+      "epoch": 0.23192521595077506,
+      "grad_norm": 0.1612849235534668,
+      "learning_rate": 9.128042094058892e-06,
+      "loss": 1.5661,
+      "mean_token_accuracy": 0.6434317573904991,
+      "num_tokens": 190298343.0,
+      "step": 490
+    },
+    {
+      "entropy": 1.57402603328228,
+      "epoch": 0.23665838362323985,
+      "grad_norm": 0.1595270037651062,
+      "learning_rate": 9.083377159196824e-06,
+      "loss": 1.5783,
+      "mean_token_accuracy": 0.6416443169116974,
+      "num_tokens": 194193930.0,
+      "step": 500
+    },
+    {
+      "entropy": 1.5727292507886887,
+      "epoch": 0.24139155129570464,
+      "grad_norm": 0.1542680561542511,
+      "learning_rate": 9.037711727709812e-06,
+      "loss": 1.5708,
+      "mean_token_accuracy": 0.6426661461591721,
+      "num_tokens": 198099362.0,
+      "step": 510
+    },
+    {
+      "entropy": 1.5556272625923158,
+      "epoch": 0.24612471896816945,
+      "grad_norm": 0.16021884977817535,
+      "learning_rate": 8.991056988402682e-06,
+      "loss": 1.5594,
+      "mean_token_accuracy": 0.6437688574194909,
+      "num_tokens": 201971348.0,
+      "step": 520
+    },
+    {
+      "entropy": 1.561934667825699,
+      "epoch": 0.25085788664063424,
+      "grad_norm": 0.160409614443779,
+      "learning_rate": 8.943424372477455e-06,
+      "loss": 1.5663,
+      "mean_token_accuracy": 0.6441657856106758,
+      "num_tokens": 205887553.0,
+      "step": 530
+    },
+    {
+      "entropy": 1.5650932669639588,
+      "epoch": 0.25559105431309903,
+      "grad_norm": 0.16672302782535553,
+      "learning_rate": 8.894825550732491e-06,
+      "loss": 1.5651,
+      "mean_token_accuracy": 0.6445234566926956,
+      "num_tokens": 209773471.0,
+      "step": 540
+    },
+    {
+      "entropy": 1.5703383475542068,
+      "epoch": 0.2603242219855638,
+      "grad_norm": 0.1647508144378662,
+      "learning_rate": 8.845272430702962e-06,
+      "loss": 1.5719,
+      "mean_token_accuracy": 0.6425846204161644,
+      "num_tokens": 213667761.0,
+      "step": 550
+    },
+    {
+      "entropy": 1.5690355956554414,
+      "epoch": 0.2650573896580286,
+      "grad_norm": 0.16149023175239563,
+      "learning_rate": 8.79477715374329e-06,
+      "loss": 1.5733,
+      "mean_token_accuracy": 0.6426513850688934,
+      "num_tokens": 217473103.0,
+      "step": 560
+    },
+    {
+      "entropy": 1.565832221508026,
+      "epoch": 0.26979055733049345,
+      "grad_norm": 0.1554195135831833,
+      "learning_rate": 8.743352092052326e-06,
+      "loss": 1.568,
+      "mean_token_accuracy": 0.6430184543132782,
+      "num_tokens": 221365501.0,
+      "step": 570
+    },
+    {
+      "entropy": 1.562074252963066,
+      "epoch": 0.27452372500295824,
+      "grad_norm": 0.16073721647262573,
+      "learning_rate": 8.691009845641931e-06,
+      "loss": 1.5701,
+      "mean_token_accuracy": 0.6420939102768898,
+      "num_tokens": 225235652.0,
+      "step": 580
+    },
+    {
+      "entropy": 1.5577911257743835,
+      "epoch": 0.27925689267542303,
+      "grad_norm": 0.16031447052955627,
+      "learning_rate": 8.637763239249778e-06,
+      "loss": 1.5627,
+      "mean_token_accuracy": 0.6444457039237023,
+      "num_tokens": 229134110.0,
+      "step": 590
+    },
+    {
+      "entropy": 1.556574183702469,
+      "epoch": 0.2839900603478878,
+      "grad_norm": 0.1577136367559433,
+      "learning_rate": 8.583625319197063e-06,
+      "loss": 1.5565,
+      "mean_token_accuracy": 0.6455687090754509,
+      "num_tokens": 233039906.0,
+      "step": 600
+    },
+    {
+      "entropy": 1.5509059250354766,
+      "epoch": 0.2887232280203526,
+      "grad_norm": 0.15498368442058563,
+      "learning_rate": 8.528609350191938e-06,
+      "loss": 1.558,
+      "mean_token_accuracy": 0.6440837427973747,
+      "num_tokens": 236877041.0,
+      "step": 610
+    },
+    {
+      "entropy": 1.5675470024347304,
+      "epoch": 0.2934563956928174,
+      "grad_norm": 0.16251349449157715,
+      "learning_rate": 8.472728812079436e-06,
+      "loss": 1.5698,
+      "mean_token_accuracy": 0.6437425896525383,
+      "num_tokens": 240760840.0,
+      "step": 620
+    },
+    {
+      "entropy": 1.5483269661664962,
+      "epoch": 0.29818956336528224,
+      "grad_norm": 0.16416430473327637,
+      "learning_rate": 8.415997396538671e-06,
+      "loss": 1.5516,
+      "mean_token_accuracy": 0.6461272791028023,
+      "num_tokens": 244646788.0,
+      "step": 630
+    },
+    {
+      "entropy": 1.5591329038143158,
+      "epoch": 0.30292273103774703,
+      "grad_norm": 0.15344582498073578,
+      "learning_rate": 8.358429003728158e-06,
+      "loss": 1.5631,
+      "mean_token_accuracy": 0.6448241740465164,
+      "num_tokens": 248505578.0,
+      "step": 640
+    },
+    {
+      "entropy": 1.5571163922548295,
+      "epoch": 0.3076558987102118,
+      "grad_norm": 0.16142602264881134,
+      "learning_rate": 8.30003773888003e-06,
+      "loss": 1.561,
+      "mean_token_accuracy": 0.6446821197867394,
+      "num_tokens": 252442387.0,
+      "step": 650
+    },
+    {
+      "entropy": 1.543628853559494,
+      "epoch": 0.3123890663826766,
+      "grad_norm": 0.16222691535949707,
+      "learning_rate": 8.240837908844011e-06,
+      "loss": 1.5465,
+      "mean_token_accuracy": 0.6476170778274536,
+      "num_tokens": 256347145.0,
+      "step": 660
+    },
+    {
+      "entropy": 1.5412938565015792,
+      "epoch": 0.3171222340551414,
+      "grad_norm": 0.1638648957014084,
+      "learning_rate": 8.180844018582014e-06,
+      "loss": 1.5483,
+      "mean_token_accuracy": 0.6471631437540054,
+      "num_tokens": 260255832.0,
+      "step": 670
+    },
+    {
+      "entropy": 1.5546195566654206,
+      "epoch": 0.3218554017276062,
+      "grad_norm": 0.1579921394586563,
+      "learning_rate": 8.12007076761416e-06,
+      "loss": 1.5539,
+      "mean_token_accuracy": 0.6463906392455101,
+      "num_tokens": 264145360.0,
+      "step": 680
+    },
+    {
+      "entropy": 1.538521057367325,
+      "epoch": 0.32658856940007097,
+      "grad_norm": 0.15421803295612335,
+      "learning_rate": 8.05853304641716e-06,
+      "loss": 1.5499,
+      "mean_token_accuracy": 0.6467000633478165,
+      "num_tokens": 268031581.0,
+      "step": 690
+    },
+    {
+      "entropy": 1.5507268905639648,
+      "epoch": 0.3313217370725358,
+      "grad_norm": 0.16604824364185333,
+      "learning_rate": 7.996245932775883e-06,
+      "loss": 1.5511,
+      "mean_token_accuracy": 0.6466175228357315,
+      "num_tokens": 271952881.0,
+      "step": 700
+    },
+    {
+      "entropy": 1.5473167181015015,
+      "epoch": 0.3360549047450006,
+      "grad_norm": 0.16262564063072205,
+      "learning_rate": 7.933224688089059e-06,
+      "loss": 1.5454,
+      "mean_token_accuracy": 0.6477824598550797,
+      "num_tokens": 275858331.0,
+      "step": 710
+    },
+    {
+      "entropy": 1.5481310993433,
+      "epoch": 0.3407880724174654,
+      "grad_norm": 0.1532575786113739,
+      "learning_rate": 7.869484753629963e-06,
+      "loss": 1.5541,
+      "mean_token_accuracy": 0.6460428267717362,
+      "num_tokens": 279739647.0,
+      "step": 720
+    },
+    {
+      "entropy": 1.5434869408607483,
+      "epoch": 0.3455212400899302,
+      "grad_norm": 0.1606515794992447,
+      "learning_rate": 7.805041746763052e-06,
+      "loss": 1.5495,
+      "mean_token_accuracy": 0.6475459963083268,
+      "num_tokens": 283656822.0,
+      "step": 730
+    },
+    {
+      "entropy": 1.550658145546913,
+      "epoch": 0.35025440776239497,
+      "grad_norm": 0.16676083207130432,
+      "learning_rate": 7.739911457117437e-06,
+      "loss": 1.5461,
+      "mean_token_accuracy": 0.6471642255783081,
+      "num_tokens": 287491081.0,
+      "step": 740
+    },
+    {
+      "entropy": 1.5445130974054337,
+      "epoch": 0.35498757543485976,
+      "grad_norm": 0.15253710746765137,
+      "learning_rate": 7.674109842718163e-06,
+      "loss": 1.5545,
+      "mean_token_accuracy": 0.646132855117321,
+      "num_tokens": 291367807.0,
+      "step": 750
+    },
+    {
+      "entropy": 1.5350563913583755,
+      "epoch": 0.3597207431073246,
+      "grad_norm": 0.16385188698768616,
+      "learning_rate": 7.607653026076218e-06,
+      "loss": 1.5395,
+      "mean_token_accuracy": 0.6482170835137367,
+      "num_tokens": 295210867.0,
+      "step": 760
+    },
+    {
+      "entropy": 1.5343231499195098,
+      "epoch": 0.3644539107797894,
+      "grad_norm": 0.1605066955089569,
+      "learning_rate": 7.540557290238251e-06,
+      "loss": 1.5386,
+      "mean_token_accuracy": 0.648663455247879,
+      "num_tokens": 299093246.0,
+      "step": 770
+    },
+    {
+      "entropy": 1.5489379942417145,
+      "epoch": 0.3691870784522542,
+      "grad_norm": 0.16125887632369995,
+      "learning_rate": 7.4728390747969385e-06,
+      "loss": 1.554,
+      "mean_token_accuracy": 0.646386744081974,
+      "num_tokens": 302979174.0,
+      "step": 780
+    },
+    {
+      "entropy": 1.5436400204896927,
+      "epoch": 0.37392024612471897,
+      "grad_norm": 0.16131755709648132,
+      "learning_rate": 7.404514971863015e-06,
+      "loss": 1.5547,
+      "mean_token_accuracy": 0.6458986714482308,
+      "num_tokens": 306861334.0,
+      "step": 790
+    },
+    {
+      "entropy": 1.5432285010814666,
+      "epoch": 0.37865341379718376,
+      "grad_norm": 0.15674395859241486,
+      "learning_rate": 7.3356017219999236e-06,
+      "loss": 1.543,
+      "mean_token_accuracy": 0.6479764103889465,
+      "num_tokens": 310763957.0,
+      "step": 800
+    },
+    {
+      "entropy": 1.5451003342866898,
+      "epoch": 0.38338658146964855,
+      "grad_norm": 0.1598990261554718,
+      "learning_rate": 7.2661162101220895e-06,
+      "loss": 1.5494,
+      "mean_token_accuracy": 0.6463793829083443,
+      "num_tokens": 314645121.0,
+      "step": 810
+    },
+    {
+      "entropy": 1.5456315219402312,
+      "epoch": 0.38811974914211333,
+      "grad_norm": 0.15369856357574463,
+      "learning_rate": 7.196075461357831e-06,
+      "loss": 1.5488,
+      "mean_token_accuracy": 0.6465605661273003,
+      "num_tokens": 318500691.0,
+      "step": 820
+    },
+    {
+      "entropy": 1.5482069969177246,
+      "epoch": 0.3928529168145782,
+      "grad_norm": 0.1560712456703186,
+      "learning_rate": 7.125496636877922e-06,
+      "loss": 1.5473,
+      "mean_token_accuracy": 0.6471294403076172,
+      "num_tokens": 322430307.0,
+      "step": 830
+    },
+    {
+      "entropy": 1.527587327361107,
+      "epoch": 0.39758608448704297,
+      "grad_norm": 0.154985710978508,
+      "learning_rate": 7.054397029690802e-06,
+      "loss": 1.5341,
+      "mean_token_accuracy": 0.6498543590307235,
+      "num_tokens": 326334568.0,
+      "step": 840
+    },
+    {
+      "entropy": 1.5514892965555191,
+      "epoch": 0.40231925215950776,
+      "grad_norm": 0.15923038125038147,
+      "learning_rate": 6.982794060405502e-06,
+      "loss": 1.5525,
+      "mean_token_accuracy": 0.6457523703575134,
+      "num_tokens": 330201587.0,
+      "step": 850
+    },
+    {
+      "entropy": 1.533634251356125,
+      "epoch": 0.40705241983197255,
+      "grad_norm": 0.16257378458976746,
+      "learning_rate": 6.910705272963307e-06,
+      "loss": 1.5412,
+      "mean_token_accuracy": 0.6487752512097359,
+      "num_tokens": 334119000.0,
+      "step": 860
+    },
+    {
+      "entropy": 1.5422323346138,
+      "epoch": 0.41178558750443733,
+      "grad_norm": 0.15663348138332367,
+      "learning_rate": 6.8381483303391795e-06,
+      "loss": 1.5437,
+      "mean_token_accuracy": 0.6477985471487046,
+      "num_tokens": 337973430.0,
+      "step": 870
+    },
+    {
+      "entropy": 1.5455356657505035,
+      "epoch": 0.4165187551769021,
+      "grad_norm": 0.15920013189315796,
+      "learning_rate": 6.765141010214038e-06,
+      "loss": 1.5461,
+      "mean_token_accuracy": 0.6477194577455521,
+      "num_tokens": 341848262.0,
+      "step": 880
+    },
+    {
+      "entropy": 1.5300615668296813,
+      "epoch": 0.42125192284936697,
+      "grad_norm": 0.15260560810565948,
+      "learning_rate": 6.691701200618925e-06,
+      "loss": 1.5355,
+      "mean_token_accuracy": 0.6492922276258468,
+      "num_tokens": 345741246.0,
+      "step": 890
+    },
+    {
+      "entropy": 1.5360501438379288,
+      "epoch": 0.42598509052183176,
+      "grad_norm": 0.1613568812608719,
+      "learning_rate": 6.617846895552137e-06,
+      "loss": 1.5409,
+      "mean_token_accuracy": 0.6486483410000801,
+      "num_tokens": 349581218.0,
+      "step": 900
+    },
+    {
+      "entropy": 1.5319293648004533,
+      "epoch": 0.43071825819429654,
+      "grad_norm": 0.16074907779693604,
+      "learning_rate": 6.543596190570381e-06,
+      "loss": 1.5406,
+      "mean_token_accuracy": 0.6477162018418312,
+      "num_tokens": 353439070.0,
+      "step": 910
+    },
+    {
+      "entropy": 1.5505404442548751,
+      "epoch": 0.43545142586676133,
+      "grad_norm": 0.1633734107017517,
+      "learning_rate": 6.4689672783550715e-06,
+      "loss": 1.551,
+      "mean_token_accuracy": 0.6463420912623405,
+      "num_tokens": 357338828.0,
+      "step": 920
+    },
+    {
+      "entropy": 1.5329742044210435,
+      "epoch": 0.4401845935392261,
+      "grad_norm": 0.1549346148967743,
+      "learning_rate": 6.393978444254798e-06,
+      "loss": 1.5368,
+      "mean_token_accuracy": 0.6490220680832863,
+      "num_tokens": 361226544.0,
+      "step": 930
+    },
+    {
+      "entropy": 1.5339823961257935,
+      "epoch": 0.4449177612116909,
+      "grad_norm": 0.15460601449012756,
+      "learning_rate": 6.3186480618051215e-06,
+      "loss": 1.5398,
+      "mean_token_accuracy": 0.6480798035860061,
+      "num_tokens": 365067789.0,
+      "step": 940
+    },
+    {
+      "entropy": 1.5356625199317933,
+      "epoch": 0.4496509288841557,
+      "grad_norm": 0.1592043936252594,
+      "learning_rate": 6.242994588226731e-06,
+      "loss": 1.5378,
+      "mean_token_accuracy": 0.6489008024334908,
+      "num_tokens": 368967569.0,
+      "step": 950
+    },
+    {
+      "entropy": 1.532603034377098,
+      "epoch": 0.45438409655662054,
+      "grad_norm": 0.15242810547351837,
+      "learning_rate": 6.1670365599031215e-06,
+      "loss": 1.5352,
+      "mean_token_accuracy": 0.649759191274643,
+      "num_tokens": 372857431.0,
+      "step": 960
+    },
+    {
+      "entropy": 1.5232465624809266,
+      "epoch": 0.45911726422908533,
+      "grad_norm": 0.1570185422897339,
+      "learning_rate": 6.090792587838867e-06,
+      "loss": 1.5277,
+      "mean_token_accuracy": 0.6510468333959579,
+      "num_tokens": 376736423.0,
+      "step": 970
+    },
+    {
+      "entropy": 1.5315758377313613,
+      "epoch": 0.4638504319015501,
+      "grad_norm": 0.15817788243293762,
+      "learning_rate": 6.014281353099601e-06,
+      "loss": 1.5306,
+      "mean_token_accuracy": 0.6500695019960403,
+      "num_tokens": 380611456.0,
+      "step": 980
+    },
+    {
+      "entropy": 1.5315613538026809,
+      "epoch": 0.4685835995740149,
+      "grad_norm": 0.16947001218795776,
+      "learning_rate": 5.937521602234842e-06,
+      "loss": 1.5368,
+      "mean_token_accuracy": 0.6481669098138809,
+      "num_tokens": 384494701.0,
+      "step": 990
+    },
+    {
+      "entropy": 1.541380015015602,
+      "epoch": 0.4733167672464797,
+      "grad_norm": 0.1462167650461197,
+      "learning_rate": 5.8605321426847795e-06,
+      "loss": 1.5436,
+      "mean_token_accuracy": 0.6473192036151886,
+      "num_tokens": 388320020.0,
+      "step": 1000
+    },
+    {
+      "entropy": 1.5256280928850174,
+      "epoch": 0.4780499349189445,
+      "grad_norm": 0.16574805974960327,
+      "learning_rate": 5.783331838172116e-06,
+      "loss": 1.5349,
+      "mean_token_accuracy": 0.6488758757710457,
+      "num_tokens": 392189228.0,
+      "step": 1010
+    },
+    {
+      "entropy": 1.527175721526146,
+      "epoch": 0.4827831025914093,
+      "grad_norm": 0.15633495151996613,
+      "learning_rate": 5.705939604080147e-06,
+      "loss": 1.5316,
+      "mean_token_accuracy": 0.6492022335529327,
+      "num_tokens": 396051728.0,
+      "step": 1020
+    },
+    {
+      "entropy": 1.5351572215557099,
+      "epoch": 0.4875162702638741,
+      "grad_norm": 0.17186181247234344,
+      "learning_rate": 5.628374402818173e-06,
+      "loss": 1.54,
+      "mean_token_accuracy": 0.6493882149457931,
+      "num_tokens": 399969073.0,
+      "step": 1030
+    },
+    {
+      "entropy": 1.5383628755807877,
+      "epoch": 0.4922494379363389,
+      "grad_norm": 0.1601661890745163,
+      "learning_rate": 5.550655239175377e-06,
+      "loss": 1.5395,
+      "mean_token_accuracy": 0.6477264970541,
+      "num_tokens": 403812928.0,
+      "step": 1040
+    },
+    {
+      "entropy": 1.5366960883140564,
+      "epoch": 0.4969826056088037,
+      "grad_norm": 0.16334351897239685,
+      "learning_rate": 5.472801155664339e-06,
+      "loss": 1.539,
+      "mean_token_accuracy": 0.6490108296275139,
+      "num_tokens": 407675957.0,
+      "step": 1050
+    },
+    {
+      "entropy": 1.5218679517507554,
+      "epoch": 0.5017157732812685,
+      "grad_norm": 0.15565453469753265,
+      "learning_rate": 5.394831227855291e-06,
+      "loss": 1.5295,
+      "mean_token_accuracy": 0.64990915954113,
+      "num_tokens": 411549219.0,
+      "step": 1060
+    },
+    {
+      "entropy": 1.5312676399946212,
+      "epoch": 0.5064489409537333,
+      "grad_norm": 0.16980209946632385,
+      "learning_rate": 5.3167645597022855e-06,
+      "loss": 1.5335,
+      "mean_token_accuracy": 0.6499560788273812,
+      "num_tokens": 415463466.0,
+      "step": 1070
+    },
+    {
+      "entropy": 1.5292291462421417,
+      "epoch": 0.5111821086261981,
+      "grad_norm": 0.1765119880437851,
+      "learning_rate": 5.238620278862397e-06,
+      "loss": 1.5346,
+      "mean_token_accuracy": 0.649413350224495,
+      "num_tokens": 419305289.0,
+      "step": 1080
+    },
+    {
+      "entropy": 1.5442948073148728,
+      "epoch": 0.5159152762986629,
+      "grad_norm": 0.1539527326822281,
+      "learning_rate": 5.160417532009122e-06,
+      "loss": 1.5398,
+      "mean_token_accuracy": 0.6489475637674331,
+      "num_tokens": 423200780.0,
+      "step": 1090
+    },
+    {
+      "entropy": 1.5311467558145524,
+      "epoch": 0.5206484439711276,
+      "grad_norm": 0.15670068562030792,
+      "learning_rate": 5.082175480141126e-06,
+      "loss": 1.5399,
+      "mean_token_accuracy": 0.6483099237084389,
+      "num_tokens": 427105709.0,
+      "step": 1100
+    },
+    {
+      "entropy": 1.5239627480506897,
+      "epoch": 0.5253816116435924,
+      "grad_norm": 0.15966466069221497,
+      "learning_rate": 5.003913293887467e-06,
+      "loss": 1.5261,
+      "mean_token_accuracy": 0.6510903730988502,
+      "num_tokens": 430984481.0,
+      "step": 1110
+    },
+    {
+      "entropy": 1.521809309720993,
+      "epoch": 0.5301147793160572,
+      "grad_norm": 0.15411856770515442,
+      "learning_rate": 4.925650148810465e-06,
+      "loss": 1.5239,
+      "mean_token_accuracy": 0.6515027031302452,
+      "num_tokens": 434868955.0,
+      "step": 1120
+    },
+    {
+      "entropy": 1.5308598577976227,
+      "epoch": 0.5348479469885221,
+      "grad_norm": 0.16343414783477783,
+      "learning_rate": 4.847405220707378e-06,
+      "loss": 1.537,
+      "mean_token_accuracy": 0.6491450101137162,
+      "num_tokens": 438789538.0,
+      "step": 1130
+    },
+    {
+      "entropy": 1.522998222708702,
+      "epoch": 0.5395811146609869,
+      "grad_norm": 0.1585935652256012,
+      "learning_rate": 4.7691976809119835e-06,
+      "loss": 1.5227,
+      "mean_token_accuracy": 0.6509381130337715,
+      "num_tokens": 442659205.0,
+      "step": 1140
+    },
+    {
+      "entropy": 1.5199230432510376,
+      "epoch": 0.5443142823334517,
+      "grad_norm": 0.15242497622966766,
+      "learning_rate": 4.691046691597303e-06,
+      "loss": 1.5277,
+      "mean_token_accuracy": 0.6500678122043609,
+      "num_tokens": 446546475.0,
+      "step": 1150
+    },
+    {
+      "entropy": 1.5328166007995605,
+      "epoch": 0.5490474500059165,
+      "grad_norm": 0.1544242948293686,
+      "learning_rate": 4.612971401080521e-06,
+      "loss": 1.5344,
+      "mean_token_accuracy": 0.6496497511863708,
+      "num_tokens": 450440495.0,
+      "step": 1160
+    },
+    {
+      "entropy": 1.5248778969049455,
+      "epoch": 0.5537806176783813,
+      "grad_norm": 0.15791839361190796,
+      "learning_rate": 4.5349909391313384e-06,
+      "loss": 1.529,
+      "mean_token_accuracy": 0.6500067859888077,
+      "num_tokens": 454368931.0,
+      "step": 1170
+    },
+    {
+      "entropy": 1.5288578271865845,
+      "epoch": 0.5585137853508461,
+      "grad_norm": 0.1565057933330536,
+      "learning_rate": 4.457124412284849e-06,
+      "loss": 1.5328,
+      "mean_token_accuracy": 0.6499333620071411,
+      "num_tokens": 458289128.0,
+      "step": 1180
+    },
+    {
+      "entropy": 1.5237576812505722,
+      "epoch": 0.5632469530233108,
+      "grad_norm": 0.16522431373596191,
+      "learning_rate": 4.379390899160116e-06,
+      "loss": 1.5242,
+      "mean_token_accuracy": 0.6513824790716172,
+      "num_tokens": 462166520.0,
+      "step": 1190
+    },
+    {
+      "entropy": 1.5189936101436614,
+      "epoch": 0.5679801206957756,
+      "grad_norm": 0.1568940430879593,
+      "learning_rate": 4.301809445785582e-06,
+      "loss": 1.5221,
+      "mean_token_accuracy": 0.6510216951370239,
+      "num_tokens": 466060024.0,
+      "step": 1200
+    },
+    {
+      "entropy": 1.52001011967659,
+      "epoch": 0.5727132883682404,
+      "grad_norm": 0.16081492602825165,
+      "learning_rate": 4.224399060932477e-06,
+      "loss": 1.5253,
+      "mean_token_accuracy": 0.6509154736995697,
+      "num_tokens": 469988704.0,
+      "step": 1210
+    },
+    {
+      "entropy": 1.518327683210373,
+      "epoch": 0.5774464560407052,
+      "grad_norm": 0.1593891978263855,
+      "learning_rate": 4.147178711457343e-06,
+      "loss": 1.5268,
+      "mean_token_accuracy": 0.6499305665493011,
+      "num_tokens": 473843546.0,
+      "step": 1220
+    },
+    {
+      "entropy": 1.5157315611839295,
+      "epoch": 0.58217962371317,
+      "grad_norm": 0.1540728062391281,
+      "learning_rate": 4.070167317654829e-06,
+      "loss": 1.5215,
+      "mean_token_accuracy": 0.6516207203269004,
+      "num_tokens": 477705517.0,
+      "step": 1230
+    },
+    {
+      "entropy": 1.5173570811748505,
+      "epoch": 0.5869127913856348,
+      "grad_norm": 0.1539110541343689,
+      "learning_rate": 3.9933837486219065e-06,
+      "loss": 1.5212,
+      "mean_token_accuracy": 0.6517001137137413,
+      "num_tokens": 481587746.0,
+      "step": 1240
+    },
+    {
+      "entropy": 1.519597727060318,
+      "epoch": 0.5916459590580996,
+      "grad_norm": 0.1510864943265915,
+      "learning_rate": 3.916846817634618e-06,
+      "loss": 1.5254,
+      "mean_token_accuracy": 0.6502514213323594,
+      "num_tokens": 485420622.0,
+      "step": 1250
+    },
+    {
+      "entropy": 1.5250845789909362,
+      "epoch": 0.5963791267305645,
+      "grad_norm": 0.15542279183864594,
+      "learning_rate": 3.840575277538495e-06,
+      "loss": 1.5268,
+      "mean_token_accuracy": 0.6506903722882271,
+      "num_tokens": 489322234.0,
+      "step": 1260
+    },
+    {
+      "entropy": 1.530037170648575,
+      "epoch": 0.6011122944030293,
+      "grad_norm": 0.16025404632091522,
+      "learning_rate": 3.764587816153813e-06,
+      "loss": 1.5328,
+      "mean_token_accuracy": 0.6497552871704102,
+      "num_tokens": 493213867.0,
+      "step": 1270
+    },
+    {
+      "entropy": 1.5264522224664687,
+      "epoch": 0.6058454620754941,
+      "grad_norm": 0.1563606560230255,
+      "learning_rate": 3.688903051696737e-06,
+      "loss": 1.5271,
+      "mean_token_accuracy": 0.6511508211493492,
+      "num_tokens": 497079317.0,
+      "step": 1280
+    },
+    {
+      "entropy": 1.517073431611061,
+      "epoch": 0.6105786297479588,
+      "grad_norm": 0.15244126319885254,
+      "learning_rate": 3.61353952821756e-06,
+      "loss": 1.519,
+      "mean_token_accuracy": 0.6525383740663528,
+      "num_tokens": 501003584.0,
+      "step": 1290
+    },
+    {
+      "entropy": 1.520869755744934,
+      "epoch": 0.6153117974204236,
+      "grad_norm": 0.15403762459754944,
+      "learning_rate": 3.5385157110570917e-06,
+      "loss": 1.5296,
+      "mean_token_accuracy": 0.6494565770030022,
+      "num_tokens": 504882648.0,
+      "step": 1300
+    },
+    {
+      "entropy": 1.5278783291578293,
+      "epoch": 0.6200449650928884,
+      "grad_norm": 0.1558082103729248,
+      "learning_rate": 3.463849982322326e-06,
+      "loss": 1.532,
+      "mean_token_accuracy": 0.6506448686122894,
+      "num_tokens": 508796374.0,
+      "step": 1310
+    },
+    {
+      "entropy": 1.5135444432497025,
+      "epoch": 0.6247781327653532,
+      "grad_norm": 0.16050703823566437,
+      "learning_rate": 3.389560636382531e-06,
+      "loss": 1.5184,
+      "mean_token_accuracy": 0.6528948619961739,
+      "num_tokens": 512676763.0,
+      "step": 1320
+    },
+    {
+      "entropy": 1.5228564977645873,
+      "epoch": 0.629511300437818,
+      "grad_norm": 0.1465277224779129,
+      "learning_rate": 3.315665875386807e-06,
+      "loss": 1.5259,
+      "mean_token_accuracy": 0.6503187119960785,
+      "num_tokens": 516588257.0,
+      "step": 1330
+    },
+    {
+      "entropy": 1.5219411462545396,
+      "epoch": 0.6342444681102828,
+      "grad_norm": 0.15017631649971008,
+      "learning_rate": 3.2421838048042516e-06,
+      "loss": 1.5266,
+      "mean_token_accuracy": 0.6507244795560837,
+      "num_tokens": 520496855.0,
+      "step": 1340
+    },
+    {
+      "entropy": 1.5131709426641464,
+      "epoch": 0.6389776357827476,
+      "grad_norm": 0.1609673649072647,
+      "learning_rate": 3.169132428987819e-06,
+      "loss": 1.5171,
+      "mean_token_accuracy": 0.652211906015873,
+      "num_tokens": 524368593.0,
+      "step": 1350
+    },
+    {
+      "entropy": 1.5158830434083939,
+      "epoch": 0.6437108034552124,
+      "grad_norm": 0.1541507989168167,
+      "learning_rate": 3.0965296467629413e-06,
+      "loss": 1.5207,
+      "mean_token_accuracy": 0.6517833650112153,
+      "num_tokens": 528292613.0,
+      "step": 1360
+    },
+    {
+      "entropy": 1.5173752516508103,
+      "epoch": 0.6484439711276772,
+      "grad_norm": 0.14874839782714844,
+      "learning_rate": 3.024393247042018e-06,
+      "loss": 1.5186,
+      "mean_token_accuracy": 0.6526758641004562,
+      "num_tokens": 532197090.0,
+      "step": 1370
+    },
+    {
+      "entropy": 1.5261268466711044,
+      "epoch": 0.6531771388001419,
+      "grad_norm": 0.1556578129529953,
+      "learning_rate": 2.9527409044658286e-06,
+      "loss": 1.529,
+      "mean_token_accuracy": 0.6497259110212326,
+      "num_tokens": 536037282.0,
+      "step": 1380
+    },
+    {
+      "entropy": 1.5166011482477189,
+      "epoch": 0.6579103064726068,
+      "grad_norm": 0.15171046555042267,
+      "learning_rate": 2.881590175072948e-06,
+      "loss": 1.5189,
+      "mean_token_accuracy": 0.6521017536520958,
+      "num_tokens": 539892183.0,
+      "step": 1390
+    },
+    {
+      "entropy": 1.5153537422418595,
+      "epoch": 0.6626434741450716,
+      "grad_norm": 0.1611650586128235,
+      "learning_rate": 2.8109584919982145e-06,
+      "loss": 1.5221,
+      "mean_token_accuracy": 0.6510555073618889,
+      "num_tokens": 543786829.0,
+      "step": 1400
+    },
+    {
+      "entropy": 1.5176646322011949,
+      "epoch": 0.6673766418175364,
+      "grad_norm": 0.16072982549667358,
+      "learning_rate": 2.7408631612013228e-06,
+      "loss": 1.5198,
+      "mean_token_accuracy": 0.6510667949914932,
+      "num_tokens": 547697306.0,
+      "step": 1410
+    },
+    {
+      "entropy": 1.516287124156952,
+      "epoch": 0.6721098094900012,
+      "grad_norm": 0.15958984196186066,
+      "learning_rate": 2.671321357226566e-06,
+      "loss": 1.5191,
+      "mean_token_accuracy": 0.6518496558070183,
+      "num_tokens": 551553208.0,
+      "step": 1420
+    },
+    {
+      "entropy": 1.5146547496318816,
+      "epoch": 0.676842977162466,
+      "grad_norm": 0.156447172164917,
+      "learning_rate": 2.602350118994782e-06,
+      "loss": 1.5178,
+      "mean_token_accuracy": 0.6530700176954269,
+      "num_tokens": 555450956.0,
+      "step": 1430
+    },
+    {
+      "entropy": 1.5136778473854064,
+      "epoch": 0.6815761448349308,
+      "grad_norm": 0.15450631082057953,
+      "learning_rate": 2.5339663456285302e-06,
+      "loss": 1.5173,
+      "mean_token_accuracy": 0.6531704932451248,
+      "num_tokens": 559347478.0,
+      "step": 1440
+    },
+    {
+      "entropy": 1.5194635063409805,
+      "epoch": 0.6863093125073956,
+      "grad_norm": 0.1552649736404419,
+      "learning_rate": 2.466186792311522e-06,
+      "loss": 1.5282,
+      "mean_token_accuracy": 0.6514062762260437,
+      "num_tokens": 563180332.0,
+      "step": 1450
+    },
+    {
+      "entropy": 1.5103699028491975,
+      "epoch": 0.6910424801798604,
+      "grad_norm": 0.15950508415699005,
+      "learning_rate": 2.399028066183306e-06,
+      "loss": 1.515,
+      "mean_token_accuracy": 0.6529736325144768,
+      "num_tokens": 567111777.0,
+      "step": 1460
+    },
+    {
+      "entropy": 1.515543583035469,
+      "epoch": 0.6957756478523252,
+      "grad_norm": 0.1573014110326767,
+      "learning_rate": 2.332506622270256e-06,
+      "loss": 1.5143,
+      "mean_token_accuracy": 0.6537506148219109,
+      "num_tokens": 570991505.0,
+      "step": 1470
+    },
+    {
+      "entropy": 1.5154441595077515,
+      "epoch": 0.7005088155247899,
+      "grad_norm": 0.1603464037179947,
+      "learning_rate": 2.2666387594537896e-06,
+      "loss": 1.5204,
+      "mean_token_accuracy": 0.652016893029213,
+      "num_tokens": 574883883.0,
+      "step": 1480
+    },
+    {
+      "entropy": 1.5132777452468873,
+      "epoch": 0.7052419831972547,
+      "grad_norm": 0.15662123262882233,
+      "learning_rate": 2.201440616476885e-06,
+      "loss": 1.5177,
+      "mean_token_accuracy": 0.6527584567666054,
+      "num_tokens": 578724891.0,
+      "step": 1490
+    },
+    {
+      "entropy": 1.5139577269554139,
+      "epoch": 0.7099751508697195,
+      "grad_norm": 0.15398600697517395,
+      "learning_rate": 2.136928167989803e-06,
+      "loss": 1.5188,
+      "mean_token_accuracy": 0.6523755803704262,
+      "num_tokens": 582630649.0,
+      "step": 1500
+    },
+    {
+      "entropy": 1.5097831279039382,
+      "epoch": 0.7147083185421843,
+      "grad_norm": 0.1604987233877182,
+      "learning_rate": 2.073117220636027e-06,
+      "loss": 1.517,
+      "mean_token_accuracy": 0.653074149787426,
+      "num_tokens": 586509280.0,
+      "step": 1510
+    },
+    {
+      "entropy": 1.5180349677801133,
+      "epoch": 0.7194414862146492,
+      "grad_norm": 0.15329141914844513,
+      "learning_rate": 2.0100234091793778e-06,
+      "loss": 1.5201,
+      "mean_token_accuracy": 0.6520388692617416,
+      "num_tokens": 590387510.0,
+      "step": 1520
+    },
+    {
+      "entropy": 1.5136069297790526,
+      "epoch": 0.724174653887114,
+      "grad_norm": 0.15793868899345398,
+      "learning_rate": 1.9476621926732227e-06,
+      "loss": 1.5221,
+      "mean_token_accuracy": 0.6520983532071114,
+      "num_tokens": 594314494.0,
+      "step": 1530
+    },
+    {
+      "entropy": 1.5157446891069413,
+      "epoch": 0.7289078215595788,
+      "grad_norm": 0.15694737434387207,
+      "learning_rate": 1.8860488506727409e-06,
+      "loss": 1.5175,
+      "mean_token_accuracy": 0.6533299177885056,
+      "num_tokens": 598258201.0,
+      "step": 1540
+    },
+    {
+      "entropy": 1.522775200009346,
+      "epoch": 0.7336409892320436,
+      "grad_norm": 0.15210026502609253,
+      "learning_rate": 1.8251984794911887e-06,
+      "loss": 1.526,
+      "mean_token_accuracy": 0.6508068576455116,
+      "num_tokens": 602110882.0,
+      "step": 1550
+    },
+    {
+      "entropy": 1.5086775600910187,
+      "epoch": 0.7383741569045084,
+      "grad_norm": 0.15608255565166473,
+      "learning_rate": 1.765125988501034e-06,
+      "loss": 1.513,
+      "mean_token_accuracy": 0.6531857639551163,
+      "num_tokens": 606013390.0,
+      "step": 1560
+    },
+    {
+      "entropy": 1.5057473361492157,
+      "epoch": 0.7431073245769731,
+      "grad_norm": 0.1536129117012024,
+      "learning_rate": 1.7058460964809086e-06,
+      "loss": 1.5105,
+      "mean_token_accuracy": 0.6533811703324318,
+      "num_tokens": 609866962.0,
+      "step": 1570
+    },
+    {
+      "entropy": 1.5125353664159775,
+      "epoch": 0.7478404922494379,
+      "grad_norm": 0.15434998273849487,
+      "learning_rate": 1.6473733280092658e-06,
+      "loss": 1.5163,
+      "mean_token_accuracy": 0.6529958829283714,
+      "num_tokens": 613748468.0,
+      "step": 1580
+    },
+    {
+      "entropy": 1.5094835668802262,
+      "epoch": 0.7525736599219027,
+      "grad_norm": 0.16267992556095123,
+      "learning_rate": 1.589722009905606e-06,
+      "loss": 1.512,
+      "mean_token_accuracy": 0.6539744392037392,
+      "num_tokens": 617586252.0,
+      "step": 1590
+    },
+    {
+      "entropy": 1.5102200895547866,
+      "epoch": 0.7573068275943675,
+      "grad_norm": 0.15085026621818542,
+      "learning_rate": 1.5329062677201594e-06,
+      "loss": 1.5152,
+      "mean_token_accuracy": 0.652720046043396,
+      "num_tokens": 621473159.0,
+      "step": 1600
+    },
+    {
+      "entropy": 1.5119531810283662,
+      "epoch": 0.7620399952668323,
+      "grad_norm": 0.15508662164211273,
+      "learning_rate": 1.4769400222728974e-06,
+      "loss": 1.5176,
+      "mean_token_accuracy": 0.6533014222979545,
+      "num_tokens": 625366303.0,
+      "step": 1610
+    },
+    {
+      "entropy": 1.5167303442955018,
+      "epoch": 0.7667731629392971,
+      "grad_norm": 0.14820463955402374,
+      "learning_rate": 1.4218369862426896e-06,
+      "loss": 1.5186,
+      "mean_token_accuracy": 0.6529193088412285,
+      "num_tokens": 629214314.0,
+      "step": 1620
+    },
+    {
+      "entropy": 1.510753783583641,
+      "epoch": 0.7715063306117619,
+      "grad_norm": 0.1586351990699768,
+      "learning_rate": 1.3676106608074602e-06,
+      "loss": 1.5144,
+      "mean_token_accuracy": 0.653745847940445,
+      "num_tokens": 633129219.0,
+      "step": 1630
+    },
+    {
+      "entropy": 1.5246556103229523,
+      "epoch": 0.7762394982842267,
+      "grad_norm": 0.15720601379871368,
+      "learning_rate": 1.3142743323361818e-06,
+      "loss": 1.5293,
+      "mean_token_accuracy": 0.6503741011023522,
+      "num_tokens": 636956832.0,
+      "step": 1640
+    },
+    {
+      "entropy": 1.518925702571869,
+      "epoch": 0.7809726659566916,
+      "grad_norm": 0.15746639668941498,
+      "learning_rate": 1.2618410691334805e-06,
+      "loss": 1.5244,
+      "mean_token_accuracy": 0.6520501941442489,
+      "num_tokens": 640891051.0,
+      "step": 1650
+    },
+    {
+      "entropy": 1.51315179169178,
+      "epoch": 0.7857058336291564,
+      "grad_norm": 0.15106885135173798,
+      "learning_rate": 1.2103237182376848e-06,
+      "loss": 1.5184,
+      "mean_token_accuracy": 0.6530534133315087,
+      "num_tokens": 644765813.0,
+      "step": 1660
+    },
+    {
+      "entropy": 1.5101027220487595,
+      "epoch": 0.7904390013016211,
+      "grad_norm": 0.15605495870113373,
+      "learning_rate": 1.159734902273078e-06,
+      "loss": 1.5137,
+      "mean_token_accuracy": 0.6541712284088135,
+      "num_tokens": 648685831.0,
+      "step": 1670
+    },
+    {
+      "entropy": 1.5037204265594482,
+      "epoch": 0.7951721689740859,
+      "grad_norm": 0.15608017146587372,
+      "learning_rate": 1.1100870163571486e-06,
+      "loss": 1.5085,
+      "mean_token_accuracy": 0.6543751254677772,
+      "num_tokens": 652549548.0,
+      "step": 1680
+    },
+    {
+      "entropy": 1.5166430234909059,
+      "epoch": 0.7999053366465507,
+      "grad_norm": 0.15508434176445007,
+      "learning_rate": 1.061392225063571e-06,
+      "loss": 1.524,
+      "mean_token_accuracy": 0.6517237603664399,
+      "num_tokens": 656455494.0,
+      "step": 1690
+    },
+    {
+      "entropy": 1.5094672977924346,
+      "epoch": 0.8046385043190155,
+      "grad_norm": 0.1599401831626892,
+      "learning_rate": 1.0136624594416828e-06,
+      "loss": 1.5145,
+      "mean_token_accuracy": 0.6521976351737976,
+      "num_tokens": 660321875.0,
+      "step": 1700
+    },
+    {
+      "entropy": 1.524332845211029,
+      "epoch": 0.8093716719914803,
+      "grad_norm": 0.15658311545848846,
+      "learning_rate": 9.669094140931678e-07,
+      "loss": 1.5249,
+      "mean_token_accuracy": 0.651316037774086,
+      "num_tokens": 664173208.0,
+      "step": 1710
+    },
+    {
+      "entropy": 1.5061070144176483,
+      "epoch": 0.8141048396639451,
+      "grad_norm": 0.15877439081668854,
+      "learning_rate": 9.211445443066896e-07,
+      "loss": 1.5095,
+      "mean_token_accuracy": 0.6547744259238243,
+      "num_tokens": 668090711.0,
+      "step": 1720
+    },
+    {
+      "entropy": 1.5110326170921327,
+      "epoch": 0.8188380073364099,
+      "grad_norm": 0.15988118946552277,
+      "learning_rate": 8.763790632511482e-07,
+      "loss": 1.52,
+      "mean_token_accuracy": 0.6521027386188507,
+      "num_tokens": 671930932.0,
+      "step": 1730
+    },
+    {
+      "entropy": 1.5050281405448913,
+      "epoch": 0.8235711750088747,
+      "grad_norm": 0.15555670857429504,
+      "learning_rate": 8.326239392282586e-07,
+      "loss": 1.5105,
+      "mean_token_accuracy": 0.6531902849674225,
+      "num_tokens": 675792125.0,
+      "step": 1740
+    },
+    {
+      "entropy": 1.5129504561424256,
+      "epoch": 0.8283043426813395,
+      "grad_norm": 0.16341622173786163,
+      "learning_rate": 7.898898929851406e-07,
+      "loss": 1.5162,
+      "mean_token_accuracy": 0.6542815431952477,
+      "num_tokens": 679648075.0,
+      "step": 1750
+    },
+    {
+      "entropy": 1.5132198542356492,
+      "epoch": 0.8330375103538042,
+      "grad_norm": 0.1575479656457901,
+      "learning_rate": 7.481873950875468e-07,
+      "loss": 1.5167,
+      "mean_token_accuracy": 0.6529857292771339,
+      "num_tokens": 683496935.0,
+      "step": 1760
+    },
+    {
+      "entropy": 1.514217236638069,
+      "epoch": 0.837770678026269,
+      "grad_norm": 0.16133052110671997,
+      "learning_rate": 7.075266633543959e-07,
+      "loss": 1.5176,
+      "mean_token_accuracy": 0.6526405304670334,
+      "num_tokens": 687412196.0,
+      "step": 1770
+    },
+    {
+      "entropy": 1.5245876908302307,
+      "epoch": 0.8425038456987339,
+      "grad_norm": 0.1658501774072647,
+      "learning_rate": 6.679176603542398e-07,
+      "loss": 1.5267,
+      "mean_token_accuracy": 0.6507634833455086,
+      "num_tokens": 691261759.0,
+      "step": 1780
+    },
+    {
+      "entropy": 1.520870679616928,
+      "epoch": 0.8472370133711987,
+      "grad_norm": 0.15542222559452057,
+      "learning_rate": 6.29370090964262e-07,
+      "loss": 1.5237,
+      "mean_token_accuracy": 0.6512942254543305,
+      "num_tokens": 695146169.0,
+      "step": 1790
+    },
+    {
+      "entropy": 1.5049445867538451,
+      "epoch": 0.8519701810436635,
+      "grad_norm": 0.15088842809200287,
+      "learning_rate": 5.918933999924143e-07,
+      "loss": 1.507,
+      "mean_token_accuracy": 0.6546556517481804,
+      "num_tokens": 699030254.0,
+      "step": 1800
+    },
+    {
+      "entropy": 1.5152593225240707,
+      "epoch": 0.8567033487161283,
+      "grad_norm": 0.15672406554222107,
+      "learning_rate": 5.55496769863288e-07,
+      "loss": 1.5197,
+      "mean_token_accuracy": 0.652678707242012,
+      "num_tokens": 702916640.0,
+      "step": 1810
+    },
+    {
+      "entropy": 1.5112317591905593,
+      "epoch": 0.8614365163885931,
+      "grad_norm": 0.15444321930408478,
+      "learning_rate": 5.201891183682545e-07,
+      "loss": 1.5167,
+      "mean_token_accuracy": 0.6519044652581215,
+      "num_tokens": 706729238.0,
+      "step": 1820
+    },
+    {
+      "entropy": 1.5071990102529527,
+      "epoch": 0.8661696840610579,
+      "grad_norm": 0.1569969356060028,
+      "learning_rate": 4.859790964804617e-07,
+      "loss": 1.5104,
+      "mean_token_accuracy": 0.6534604758024216,
+      "num_tokens": 710608784.0,
+      "step": 1830
+    },
+    {
+      "entropy": 1.5036645025014876,
+      "epoch": 0.8709028517335227,
+      "grad_norm": 0.16283676028251648,
+      "learning_rate": 4.5287508623519773e-07,
+      "loss": 1.5068,
+      "mean_token_accuracy": 0.6550710022449493,
+      "num_tokens": 714514707.0,
+      "step": 1840
+    },
+    {
+      "entropy": 1.5189965814352036,
+      "epoch": 0.8756360194059875,
+      "grad_norm": 0.15639755129814148,
+      "learning_rate": 4.2088519867614585e-07,
+      "loss": 1.5222,
+      "mean_token_accuracy": 0.6517624288797379,
+      "num_tokens": 718366975.0,
+      "step": 1850
+    },
+    {
+      "entropy": 1.5078352093696594,
+      "epoch": 0.8803691870784522,
+      "grad_norm": 0.1577681601047516,
+      "learning_rate": 3.900172718680484e-07,
+      "loss": 1.5131,
+      "mean_token_accuracy": 0.6530882626771927,
+      "num_tokens": 722251285.0,
+      "step": 1860
+    },
+    {
+      "entropy": 1.5013979017734527,
+      "epoch": 0.885102354750917,
+      "grad_norm": 0.16839657723903656,
+      "learning_rate": 3.6027886897624376e-07,
+      "loss": 1.5079,
+      "mean_token_accuracy": 0.6545991912484169,
+      "num_tokens": 726162080.0,
+      "step": 1870
+    },
+    {
+      "entropy": 1.5258357018232345,
+      "epoch": 0.8898355224233818,
+      "grad_norm": 0.1610095053911209,
+      "learning_rate": 3.3167727641356064e-07,
+      "loss": 1.529,
+      "mean_token_accuracy": 0.6494020417332649,
+      "num_tokens": 730048788.0,
+      "step": 1880
+    },
+    {
+      "entropy": 1.5098802983760833,
+      "epoch": 0.8945686900958466,
+      "grad_norm": 0.15612637996673584,
+      "learning_rate": 3.0421950205502813e-07,
+      "loss": 1.5136,
+      "mean_token_accuracy": 0.6532332092523575,
+      "num_tokens": 733943282.0,
+      "step": 1890
+    },
+    {
+      "entropy": 1.5100417882204056,
+      "epoch": 0.8993018577683114,
+      "grad_norm": 0.154027059674263,
+      "learning_rate": 2.779122735208267e-07,
+      "loss": 1.5139,
+      "mean_token_accuracy": 0.6538966566324234,
+      "num_tokens": 737803762.0,
+      "step": 1900
+    },
+    {
+      "entropy": 1.511214417219162,
+      "epoch": 0.9040350254407762,
+      "grad_norm": 0.1588786244392395,
+      "learning_rate": 2.527620365279021e-07,
+      "loss": 1.5141,
+      "mean_token_accuracy": 0.6533711299300193,
+      "num_tokens": 741703649.0,
+      "step": 1910
+    },
+    {
+      "entropy": 1.5116032123565675,
+      "epoch": 0.9087681931132411,
+      "grad_norm": 0.15595540404319763,
+      "learning_rate": 2.2877495331066312e-07,
+      "loss": 1.5156,
+      "mean_token_accuracy": 0.6534523665904999,
+      "num_tokens": 745612891.0,
+      "step": 1920
+    },
+    {
+      "entropy": 1.5098071992397308,
+      "epoch": 0.9135013607857059,
+      "grad_norm": 0.160483717918396,
+      "learning_rate": 2.0595690111112398e-07,
+      "loss": 1.5142,
+      "mean_token_accuracy": 0.6534514829516411,
+      "num_tokens": 749494675.0,
+      "step": 1930
+    },
+    {
+      "entropy": 1.5071230858564377,
+      "epoch": 0.9182345284581707,
+      "grad_norm": 0.15629717707633972,
+      "learning_rate": 1.8431347073888217e-07,
+      "loss": 1.5111,
+      "mean_token_accuracy": 0.6530539333820343,
+      "num_tokens": 753341723.0,
+      "step": 1940
+    },
+    {
+      "entropy": 1.5019009202718734,
+      "epoch": 0.9229676961306355,
+      "grad_norm": 0.15971773862838745,
+      "learning_rate": 1.638499652012754e-07,
+      "loss": 1.5059,
+      "mean_token_accuracy": 0.6544443607330322,
+      "num_tokens": 757233014.0,
+      "step": 1950
+    },
+    {
+      "entropy": 1.5118261843919754,
+      "epoch": 0.9277008638031002,
+      "grad_norm": 0.15779262781143188,
+      "learning_rate": 1.44571398404057e-07,
+      "loss": 1.515,
+      "mean_token_accuracy": 0.6532472312450409,
+      "num_tokens": 761115255.0,
+      "step": 1960
+    },
+    {
+      "entropy": 1.5036541551351548,
+      "epoch": 0.932434031475565,
+      "grad_norm": 0.1535780280828476,
+      "learning_rate": 1.2648249392289925e-07,
+      "loss": 1.5061,
+      "mean_token_accuracy": 0.6545781284570694,
+      "num_tokens": 765028626.0,
+      "step": 1970
+    },
+    {
+      "entropy": 1.50391583442688,
+      "epoch": 0.9371671991480298,
+      "grad_norm": 0.15700839459896088,
+      "learning_rate": 1.095876838460408e-07,
+      "loss": 1.506,
+      "mean_token_accuracy": 0.6557769432663918,
+      "num_tokens": 768939705.0,
+      "step": 1980
+    },
+    {
+      "entropy": 1.5056363612413406,
+      "epoch": 0.9419003668204946,
+      "grad_norm": 0.15855862200260162,
+      "learning_rate": 9.38911076883503e-08,
+      "loss": 1.5082,
+      "mean_token_accuracy": 0.6543473988771439,
+      "num_tokens": 772833689.0,
+      "step": 1990
+    },
+    {
+      "entropy": 1.525366762280464,
+      "epoch": 0.9466335344929594,
+      "grad_norm": 0.15759994089603424,
+      "learning_rate": 7.939661137707167e-08,
+      "loss": 1.5292,
+      "mean_token_accuracy": 0.650723172724247,
+      "num_tokens": 776737000.0,
+      "step": 2000
+    },
+    {
+      "entropy": 1.5107537627220153,
+      "epoch": 0.9513667021654242,
+      "grad_norm": 0.14716793596744537,
+      "learning_rate": 6.610774630951167e-08,
+      "loss": 1.514,
+      "mean_token_accuracy": 0.6538170203566551,
+      "num_tokens": 780623496.0,
+      "step": 2010
+    },
+    {
+      "entropy": 1.510766288638115,
+      "epoch": 0.956099869837889,
+      "grad_norm": 0.15204967558383942,
+      "learning_rate": 5.402776848288216e-08,
+      "loss": 1.5127,
+      "mean_token_accuracy": 0.6531319335103035,
+      "num_tokens": 784511197.0,
+      "step": 2020
+    },
+    {
+      "entropy": 1.5045825749635697,
+      "epoch": 0.9608330375103538,
+      "grad_norm": 0.162211611866951,
+      "learning_rate": 4.315963769652931e-08,
+      "loss": 1.5063,
+      "mean_token_accuracy": 0.6537961974740029,
+      "num_tokens": 788407251.0,
+      "step": 2030
+    },
+    {
+      "entropy": 1.5063252121210098,
+      "epoch": 0.9655662051828185,
+      "grad_norm": 0.15293368697166443,
+      "learning_rate": 3.350601682673094e-08,
+      "loss": 1.5086,
+      "mean_token_accuracy": 0.654248197376728,
+      "num_tokens": 792249083.0,
+      "step": 2040
+    },
+    {
+      "entropy": 1.5172866135835648,
+      "epoch": 0.9702993728552834,
+      "grad_norm": 0.15927255153656006,
+      "learning_rate": 2.5069271174247844e-08,
+      "loss": 1.5187,
+      "mean_token_accuracy": 0.6526034936308861,
+      "num_tokens": 796138376.0,
+      "step": 2050
+    },
+    {
+      "entropy": 1.515240240097046,
+      "epoch": 0.9750325405277482,
+      "grad_norm": 0.15734337270259857,
+      "learning_rate": 1.785146788478298e-08,
+      "loss": 1.5168,
+      "mean_token_accuracy": 0.6522197261452675,
+      "num_tokens": 800048611.0,
+      "step": 2060
+    },
+    {
+      "entropy": 1.505976414680481,
+      "epoch": 0.979765708200213,
+      "grad_norm": 0.15182293951511383,
+      "learning_rate": 1.1854375442498234e-08,
+      "loss": 1.5083,
+      "mean_token_accuracy": 0.653746984899044,
+      "num_tokens": 803953901.0,
+      "step": 2070
+    },
+    {
+      "entropy": 1.5067311346530914,
+      "epoch": 0.9844988758726778,
+      "grad_norm": 0.15344145894050598,
+      "learning_rate": 7.0794632367032765e-09,
+      "loss": 1.5107,
+      "mean_token_accuracy": 0.6533343732357025,
+      "num_tokens": 807795934.0,
+      "step": 2080
+    },
+    {
+      "entropy": 1.5039544194936751,
+      "epoch": 0.9892320435451426,
+      "grad_norm": 0.15625813603401184,
+      "learning_rate": 3.5279012018324397e-09,
+      "loss": 1.5083,
+      "mean_token_accuracy": 0.6547796651721001,
+      "num_tokens": 811672777.0,
+      "step": 2090
+    },
+    {
+      "entropy": 1.5102417439222335,
+      "epoch": 0.9939652112176074,
+      "grad_norm": 0.14735041558742523,
+      "learning_rate": 1.2005595307906792e-09,
+      "loss": 1.5121,
+      "mean_token_accuracy": 0.6533789873123169,
+      "num_tokens": 815540486.0,
+      "step": 2100
+    },
+    {
+      "entropy": 1.5077374666929244,
+      "epoch": 0.9986983788900722,
+      "grad_norm": 0.15531828999519348,
+      "learning_rate": 9.800846173968481e-11,
+      "loss": 1.5117,
+      "mean_token_accuracy": 0.6538635641336441,
+      "num_tokens": 819362988.0,
+      "step": 2110
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2113,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.6414323458230452e+19,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57ae05cf930d7a2b45036327e0bf0a2b89948bc10b3b72ad80403976f79712bf
+size 7569

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"
+}

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if ZERO_STAGE not in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info("Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info("Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)