Upload folder using huggingface_hub

.gitattributes

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

added_tokens.json

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

chat_template.jinja

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

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "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",
+  "use_cache": false,
+  "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_step40

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a542f2d6ce5947d7145c409441d79417a10bebe65251fba59896f9e803d748b
+size 4990497880

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15736deefce18773e243fedede593c37aae1635f0e35d50309eb48e434517378
+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": null,
+  "merge_size": 2,
+  "min_pixels": null,
+  "pad_size": null,
+  "patch_size": 16,
+  "processor_class": "Qwen3VLProcessor",
+  "resample": 3,
+  "rescale_factor": 0.00392156862745098,
+  "return_tensors": null,
+  "size": {
+    "longest_edge": 16777216,
+    "shortest_edge": 65536
+  },
+  "temporal_patch_size": 2
+}

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a452b2ea3db00380e8fdeb9266f4c42ee14e8e00b83bd7d6a4ee5fa7a778325c
+size 16389

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e8c94a7d8b1c87f5b9f5046b384b095346801ff674b05e90e1a28e362ed5f57
+size 16389

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7eadb93f5d62ae91726102a593830fc5ed98db986f2faaa34360fe03d399ce9
+size 16389

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d6877b68a79d88617afcef990b89f04ee3f034980d10d8104139b02dded82f2
+size 16389

rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61a980e88ec1c7125d5bc5d528b10df9f19b61b7202d8384c3bb8201191d631f
+size 16389

rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee8a7eb177d72f01b3e79d22cf98cac2fbe62476f923155a1c78a60e44c3caee
+size 16389

rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:252aaea316903a59daa65816cf2720907bb191aebf4faae2a8823a60a3fadecb
+size 16389

rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2be2a13e44fa197adb417e6056a073cacf18361f0ca3ee2010857ef29f78d290
+size 16325

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b3168962445ab6564ad4b1b7eb51e33d9167a11a0d74565a2942309a4825e4c
+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:f54b55fa0c3aba0c91ce09ea79ae4e62da24e2a1a630f96c4bae34aba25e234a
+size 11422822

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,1154 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.017014036580178648,
+  "eval_steps": 500,
+  "global_step": 40,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 313.0,
+      "completions/mean_length": 169.875,
+      "completions/mean_terminated_length": 158.8386993408203,
+      "completions/min_length": 95.0,
+      "completions/min_terminated_length": 95.0,
+      "epoch": 0.0004253509145044662,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 4.363935947418213,
+      "kl": 0.0003229373978683725,
+      "learning_rate": 0.0,
+      "loss": 0.0073,
+      "num_tokens": 81770.0,
+      "reward": 2.789294719696045,
+      "reward_std": 0.13441388309001923,
+      "rewards/format_hoi_key_reward/mean": 0.8359375,
+      "rewards/format_hoi_key_reward/std": 0.2847406268119812,
+      "rewards/format_hoi_object_label_reward/mean": 0.7421875,
+      "rewards/format_hoi_object_label_reward/std": 0.3625374734401703,
+      "rewards/format_hoi_verb_label_reward/mean": 0.5434027910232544,
+      "rewards/format_hoi_verb_label_reward/std": 0.38580045104026794,
+      "rewards/hoi_iou_reward/mean": 0.6677669286727905,
+      "rewards/hoi_iou_reward/std": 0.27127814292907715,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 468.0,
+      "completions/max_terminated_length": 468.0,
+      "completions/mean_length": 172.28125,
+      "completions/mean_terminated_length": 172.28125,
+      "completions/min_length": 125.0,
+      "completions/min_terminated_length": 125.0,
+      "epoch": 0.0008507018290089324,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.752140760421753,
+      "kl": 0.000335300101141911,
+      "learning_rate": 7.042253521126761e-08,
+      "loss": -0.0022,
+      "num_tokens": 163613.0,
+      "reward": 2.4476234912872314,
+      "reward_std": 0.17685432732105255,
+      "rewards/format_hoi_key_reward/mean": 0.7478471994400024,
+      "rewards/format_hoi_key_reward/std": 0.3051668405532837,
+      "rewards/format_hoi_object_label_reward/mean": 0.6697916984558105,
+      "rewards/format_hoi_object_label_reward/std": 0.34505072236061096,
+      "rewards/format_hoi_verb_label_reward/mean": 0.39635416865348816,
+      "rewards/format_hoi_verb_label_reward/std": 0.2153073251247406,
+      "rewards/hoi_iou_reward/mean": 0.6336303353309631,
+      "rewards/hoi_iou_reward/std": 0.3029536306858063,
+      "step": 2
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 487.0,
+      "completions/mean_length": 186.03125,
+      "completions/mean_terminated_length": 175.51612854003906,
+      "completions/min_length": 91.0,
+      "completions/min_terminated_length": 91.0,
+      "epoch": 0.0012760527435133986,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.0201789140701294,
+      "kl": 0.0003579963668016717,
+      "learning_rate": 1.4084507042253522e-07,
+      "loss": -0.0078,
+      "num_tokens": 245910.0,
+      "reward": 2.2469096183776855,
+      "reward_std": 0.21650519967079163,
+      "rewards/format_hoi_key_reward/mean": 0.7998958826065063,
+      "rewards/format_hoi_key_reward/std": 0.2879995107650757,
+      "rewards/format_hoi_object_label_reward/mean": 0.4833333492279053,
+      "rewards/format_hoi_object_label_reward/std": 0.4311150908470154,
+      "rewards/format_hoi_verb_label_reward/mean": 0.44062501192092896,
+      "rewards/format_hoi_verb_label_reward/std": 0.39745914936065674,
+      "rewards/hoi_iou_reward/mean": 0.5230554342269897,
+      "rewards/hoi_iou_reward/std": 0.3132159411907196,
+      "step": 3
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 457.0,
+      "completions/max_terminated_length": 457.0,
+      "completions/mean_length": 186.4375,
+      "completions/mean_terminated_length": 186.4375,
+      "completions/min_length": 95.0,
+      "completions/min_terminated_length": 95.0,
+      "epoch": 0.0017014036580178648,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.2351148128509521,
+      "kl": 0.0003153797151753679,
+      "learning_rate": 2.1126760563380284e-07,
+      "loss": 0.0413,
+      "num_tokens": 328192.0,
+      "reward": 3.0791516304016113,
+      "reward_std": 0.1785963922739029,
+      "rewards/format_hoi_key_reward/mean": 0.8968750238418579,
+      "rewards/format_hoi_key_reward/std": 0.19876126945018768,
+      "rewards/format_hoi_object_label_reward/mean": 0.8411458730697632,
+      "rewards/format_hoi_object_label_reward/std": 0.30258694291114807,
+      "rewards/format_hoi_verb_label_reward/mean": 0.5755208730697632,
+      "rewards/format_hoi_verb_label_reward/std": 0.3113258183002472,
+      "rewards/hoi_iou_reward/mean": 0.7656100392341614,
+      "rewards/hoi_iou_reward/std": 0.240717351436615,
+      "step": 4
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 336.0,
+      "completions/mean_length": 191.0,
+      "completions/mean_terminated_length": 180.64515686035156,
+      "completions/min_length": 92.0,
+      "completions/min_terminated_length": 92.0,
+      "epoch": 0.002126754572522331,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.201839566230774,
+      "kl": 0.00034184849937446415,
+      "learning_rate": 2.8169014084507043e-07,
+      "loss": 0.0003,
+      "num_tokens": 410578.0,
+      "reward": 2.123943328857422,
+      "reward_std": 0.16979998350143433,
+      "rewards/format_hoi_key_reward/mean": 0.6126735806465149,
+      "rewards/format_hoi_key_reward/std": 0.3427790701389313,
+      "rewards/format_hoi_object_label_reward/mean": 0.6137152910232544,
+      "rewards/format_hoi_object_label_reward/std": 0.3750321567058563,
+      "rewards/format_hoi_verb_label_reward/mean": 0.36812394857406616,
+      "rewards/format_hoi_verb_label_reward/std": 0.27230551838874817,
+      "rewards/hoi_iou_reward/mean": 0.5294303297996521,
+      "rewards/hoi_iou_reward/std": 0.3228149712085724,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 230.0,
+      "completions/max_terminated_length": 230.0,
+      "completions/mean_length": 157.15625,
+      "completions/mean_terminated_length": 157.15625,
+      "completions/min_length": 88.0,
+      "completions/min_terminated_length": 88.0,
+      "epoch": 0.002552105487026797,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.502875566482544,
+      "kl": 0.00034246582072228193,
+      "learning_rate": 3.521126760563381e-07,
+      "loss": -0.0042,
+      "num_tokens": 491951.0,
+      "reward": 2.6239867210388184,
+      "reward_std": 0.3057432472705841,
+      "rewards/format_hoi_key_reward/mean": 0.8656250238418579,
+      "rewards/format_hoi_key_reward/std": 0.23455658555030823,
+      "rewards/format_hoi_object_label_reward/mean": 0.6927083730697632,
+      "rewards/format_hoi_object_label_reward/std": 0.38824430108070374,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3932291567325592,
+      "rewards/format_hoi_verb_label_reward/std": 0.3944879472255707,
+      "rewards/hoi_iou_reward/mean": 0.6724243760108948,
+      "rewards/hoi_iou_reward/std": 0.2741568088531494,
+      "step": 6
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 310.0,
+      "completions/mean_length": 179.71875,
+      "completions/mean_terminated_length": 157.56668090820312,
+      "completions/min_length": 119.0,
+      "completions/min_terminated_length": 119.0,
+      "epoch": 0.0029774564015312634,
+      "frac_reward_zero_std": 0.0625,
+      "grad_norm": 1.2773802280426025,
+      "kl": 0.00039098386332625523,
+      "learning_rate": 4.225352112676057e-07,
+      "loss": 0.021,
+      "num_tokens": 574042.0,
+      "reward": 2.446112632751465,
+      "reward_std": 0.2966364324092865,
+      "rewards/format_hoi_key_reward/mean": 0.8067708015441895,
+      "rewards/format_hoi_key_reward/std": 0.31369173526763916,
+      "rewards/format_hoi_object_label_reward/mean": 0.6536458730697632,
+      "rewards/format_hoi_object_label_reward/std": 0.4338444769382477,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3489583432674408,
+      "rewards/format_hoi_verb_label_reward/std": 0.3668850064277649,
+      "rewards/hoi_iou_reward/mean": 0.6367375254631042,
+      "rewards/hoi_iou_reward/std": 0.2808148264884949,
+      "step": 7
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 420.0,
+      "completions/mean_length": 241.1875,
+      "completions/mean_terminated_length": 223.1333465576172,
+      "completions/min_length": 125.0,
+      "completions/min_terminated_length": 125.0,
+      "epoch": 0.0034028073160357296,
+      "frac_reward_zero_std": 0.0625,
+      "grad_norm": 1.0549662113189697,
+      "kl": 0.0003542311387718655,
+      "learning_rate": 4.929577464788733e-07,
+      "loss": -0.027,
+      "num_tokens": 658152.0,
+      "reward": 2.2133703231811523,
+      "reward_std": 0.4084068238735199,
+      "rewards/format_hoi_key_reward/mean": 0.6832291483879089,
+      "rewards/format_hoi_key_reward/std": 0.29706627130508423,
+      "rewards/format_hoi_object_label_reward/mean": 0.5901042222976685,
+      "rewards/format_hoi_object_label_reward/std": 0.34433093667030334,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4224702715873718,
+      "rewards/format_hoi_verb_label_reward/std": 0.32381853461265564,
+      "rewards/hoi_iou_reward/mean": 0.5175668001174927,
+      "rewards/hoi_iou_reward/std": 0.26935523748397827,
+      "step": 8
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 339.0,
+      "completions/mean_length": 196.46875,
+      "completions/mean_terminated_length": 175.433349609375,
+      "completions/min_length": 93.0,
+      "completions/min_terminated_length": 93.0,
+      "epoch": 0.0038281582305401958,
+      "frac_reward_zero_std": 0.0625,
+      "grad_norm": 1.110564112663269,
+      "kl": 0.0004391309848870151,
+      "learning_rate": 5.633802816901409e-07,
+      "loss": -0.0017,
+      "num_tokens": 740859.0,
+      "reward": 2.465003728866577,
+      "reward_std": 0.0937172994017601,
+      "rewards/format_hoi_key_reward/mean": 0.7511160373687744,
+      "rewards/format_hoi_key_reward/std": 0.32644686102867126,
+      "rewards/format_hoi_object_label_reward/mean": 0.6443452835083008,
+      "rewards/format_hoi_object_label_reward/std": 0.4073486030101776,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4927455186843872,
+      "rewards/format_hoi_verb_label_reward/std": 0.3828698992729187,
+      "rewards/hoi_iou_reward/mean": 0.5767968893051147,
+      "rewards/hoi_iou_reward/std": 0.30675631761550903,
+      "step": 9
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 347.0,
+      "completions/max_terminated_length": 347.0,
+      "completions/mean_length": 172.09375,
+      "completions/mean_terminated_length": 172.09375,
+      "completions/min_length": 93.0,
+      "completions/min_terminated_length": 93.0,
+      "epoch": 0.004253509145044662,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 2.442121982574463,
+      "kl": 0.00042213514825562015,
+      "learning_rate": 6.338028169014085e-07,
+      "loss": -0.0037,
+      "num_tokens": 822690.0,
+      "reward": 2.751133441925049,
+      "reward_std": 0.33584073185920715,
+      "rewards/format_hoi_key_reward/mean": 0.8541666269302368,
+      "rewards/format_hoi_key_reward/std": 0.21394065022468567,
+      "rewards/format_hoi_object_label_reward/mean": 0.7239583730697632,
+      "rewards/format_hoi_object_label_reward/std": 0.3409331738948822,
+      "rewards/format_hoi_verb_label_reward/mean": 0.5394965410232544,
+      "rewards/format_hoi_verb_label_reward/std": 0.3380621373653412,
+      "rewards/hoi_iou_reward/mean": 0.6335119009017944,
+      "rewards/hoi_iou_reward/std": 0.2383546382188797,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 254.0,
+      "completions/max_terminated_length": 254.0,
+      "completions/mean_length": 144.0625,
+      "completions/mean_terminated_length": 144.0625,
+      "completions/min_length": 92.0,
+      "completions/min_terminated_length": 92.0,
+      "epoch": 0.004678860059549128,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.577789545059204,
+      "kl": 0.0003447915078140795,
+      "learning_rate": 7.042253521126762e-07,
+      "loss": 0.0014,
+      "num_tokens": 903614.0,
+      "reward": 2.294086456298828,
+      "reward_std": 0.05743589997291565,
+      "rewards/format_hoi_key_reward/mean": 0.7256410121917725,
+      "rewards/format_hoi_key_reward/std": 0.3094317615032196,
+      "rewards/format_hoi_object_label_reward/mean": 0.6041666865348816,
+      "rewards/format_hoi_object_label_reward/std": 0.39372313022613525,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3736979365348816,
+      "rewards/format_hoi_verb_label_reward/std": 0.3025956153869629,
+      "rewards/hoi_iou_reward/mean": 0.5905807614326477,
+      "rewards/hoi_iou_reward/std": 0.29480627179145813,
+      "step": 11
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.09375,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 441.0,
+      "completions/mean_length": 208.03125,
+      "completions/mean_terminated_length": 176.58621215820312,
+      "completions/min_length": 97.0,
+      "completions/min_terminated_length": 97.0,
+      "epoch": 0.005104210974053594,
+      "frac_reward_zero_std": 0.0625,
+      "grad_norm": 0.8127485513687134,
+      "kl": 0.0003554098366294056,
+      "learning_rate": 7.746478873239437e-07,
+      "loss": -0.0117,
+      "num_tokens": 986589.0,
+      "reward": 2.294464349746704,
+      "reward_std": 0.20235002040863037,
+      "rewards/format_hoi_key_reward/mean": 0.7207965850830078,
+      "rewards/format_hoi_key_reward/std": 0.35986757278442383,
+      "rewards/format_hoi_object_label_reward/mean": 0.5450674295425415,
+      "rewards/format_hoi_object_label_reward/std": 0.42823418974876404,
+      "rewards/format_hoi_verb_label_reward/mean": 0.44454658031463623,
+      "rewards/format_hoi_verb_label_reward/std": 0.4109439253807068,
+      "rewards/hoi_iou_reward/mean": 0.5840538144111633,
+      "rewards/hoi_iou_reward/std": 0.35957613587379456,
+      "step": 12
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 299.0,
+      "completions/max_terminated_length": 299.0,
+      "completions/mean_length": 172.75,
+      "completions/mean_terminated_length": 172.75,
+      "completions/min_length": 116.0,
+      "completions/min_terminated_length": 116.0,
+      "epoch": 0.00552956188855806,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.269765019416809,
+      "kl": 0.00036870952317258343,
+      "learning_rate": 8.450704225352114e-07,
+      "loss": -0.0155,
+      "num_tokens": 1068533.0,
+      "reward": 2.4297869205474854,
+      "reward_std": 0.2929306924343109,
+      "rewards/format_hoi_key_reward/mean": 0.796875,
+      "rewards/format_hoi_key_reward/std": 0.2455495446920395,
+      "rewards/format_hoi_object_label_reward/mean": 0.5703125,
+      "rewards/format_hoi_object_label_reward/std": 0.4022279679775238,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4661458432674408,
+      "rewards/format_hoi_verb_label_reward/std": 0.33458054065704346,
+      "rewards/hoi_iou_reward/mean": 0.5964536070823669,
+      "rewards/hoi_iou_reward/std": 0.2549525201320648,
+      "step": 13
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.15625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 441.0,
+      "completions/mean_length": 233.03125,
+      "completions/mean_terminated_length": 181.37037658691406,
+      "completions/min_length": 92.0,
+      "completions/min_terminated_length": 92.0,
+      "epoch": 0.005954912803062527,
+      "frac_reward_zero_std": 0.125,
+      "grad_norm": 0.9530596733093262,
+      "kl": 0.00036477607500273734,
+      "learning_rate": 9.154929577464789e-07,
+      "loss": 0.0057,
+      "num_tokens": 1152368.0,
+      "reward": 2.0490849018096924,
+      "reward_std": 0.3710783123970032,
+      "rewards/format_hoi_key_reward/mean": 0.6766666173934937,
+      "rewards/format_hoi_key_reward/std": 0.3744644820690155,
+      "rewards/format_hoi_object_label_reward/mean": 0.5354166626930237,
+      "rewards/format_hoi_object_label_reward/std": 0.4118267297744751,
+      "rewards/format_hoi_verb_label_reward/mean": 0.30980902910232544,
+      "rewards/format_hoi_verb_label_reward/std": 0.3180212080478668,
+      "rewards/hoi_iou_reward/mean": 0.5271925330162048,
+      "rewards/hoi_iou_reward/std": 0.33255496621131897,
+      "step": 14
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 332.0,
+      "completions/mean_length": 183.96875,
+      "completions/mean_terminated_length": 173.3870849609375,
+      "completions/min_length": 93.0,
+      "completions/min_terminated_length": 93.0,
+      "epoch": 0.0063802637175669925,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.3094820976257324,
+      "kl": 0.0003903634860762395,
+      "learning_rate": 9.859154929577465e-07,
+      "loss": -0.0348,
+      "num_tokens": 1234625.0,
+      "reward": 2.416910171508789,
+      "reward_std": 0.39547234773635864,
+      "rewards/format_hoi_key_reward/mean": 0.8177083730697632,
+      "rewards/format_hoi_key_reward/std": 0.25537019968032837,
+      "rewards/format_hoi_object_label_reward/mean": 0.703125,
+      "rewards/format_hoi_object_label_reward/std": 0.3103194534778595,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3838541507720947,
+      "rewards/format_hoi_verb_label_reward/std": 0.3097499907016754,
+      "rewards/hoi_iou_reward/mean": 0.5122226476669312,
+      "rewards/hoi_iou_reward/std": 0.2652962803840637,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 510.0,
+      "completions/mean_length": 191.9375,
+      "completions/mean_terminated_length": 181.61289978027344,
+      "completions/min_length": 111.0,
+      "completions/min_terminated_length": 111.0,
+      "epoch": 0.006805614632071459,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.2858763933181763,
+      "kl": 0.00034383483580313623,
+      "learning_rate": 1.0563380281690142e-06,
+      "loss": 0.0097,
+      "num_tokens": 1317153.0,
+      "reward": 2.2493948936462402,
+      "reward_std": 0.25483453273773193,
+      "rewards/format_hoi_key_reward/mean": 0.7226041555404663,
+      "rewards/format_hoi_key_reward/std": 0.266787588596344,
+      "rewards/format_hoi_object_label_reward/mean": 0.5197916626930237,
+      "rewards/format_hoi_object_label_reward/std": 0.395753413438797,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4555555582046509,
+      "rewards/format_hoi_verb_label_reward/std": 0.34589242935180664,
+      "rewards/hoi_iou_reward/mean": 0.5514433979988098,
+      "rewards/hoi_iou_reward/std": 0.31066155433654785,
+      "step": 16
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 273.0,
+      "completions/max_terminated_length": 273.0,
+      "completions/mean_length": 143.3125,
+      "completions/mean_terminated_length": 143.3125,
+      "completions/min_length": 94.0,
+      "completions/min_terminated_length": 94.0,
+      "epoch": 0.007230965546575925,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.596779704093933,
+      "kl": 0.00033400646498193964,
+      "learning_rate": 1.1267605633802817e-06,
+      "loss": 0.0058,
+      "num_tokens": 1398085.0,
+      "reward": 2.553602695465088,
+      "reward_std": 0.11417173594236374,
+      "rewards/format_hoi_key_reward/mean": 0.8300297856330872,
+      "rewards/format_hoi_key_reward/std": 0.3036980926990509,
+      "rewards/format_hoi_object_label_reward/mean": 0.710565447807312,
+      "rewards/format_hoi_object_label_reward/std": 0.3981569707393646,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3980654776096344,
+      "rewards/format_hoi_verb_label_reward/std": 0.3377469480037689,
+      "rewards/hoi_iou_reward/mean": 0.6149418354034424,
+      "rewards/hoi_iou_reward/std": 0.28151780366897583,
+      "step": 17
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 202.0,
+      "completions/mean_length": 150.15625,
+      "completions/mean_terminated_length": 138.48387145996094,
+      "completions/min_length": 90.0,
+      "completions/min_terminated_length": 90.0,
+      "epoch": 0.0076563164610803916,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 2.1925482749938965,
+      "kl": 0.0003761410553124733,
+      "learning_rate": 1.1971830985915492e-06,
+      "loss": 0.0275,
+      "num_tokens": 1479104.0,
+      "reward": 2.4335920810699463,
+      "reward_std": 0.24886168539524078,
+      "rewards/format_hoi_key_reward/mean": 0.7729166746139526,
+      "rewards/format_hoi_key_reward/std": 0.3151136040687561,
+      "rewards/format_hoi_object_label_reward/mean": 0.6536458134651184,
+      "rewards/format_hoi_object_label_reward/std": 0.4061078131198883,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4140625,
+      "rewards/format_hoi_verb_label_reward/std": 0.34423333406448364,
+      "rewards/hoi_iou_reward/mean": 0.59296715259552,
+      "rewards/hoi_iou_reward/std": 0.3096284866333008,
+      "step": 18
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 447.0,
+      "completions/mean_length": 217.34375,
+      "completions/mean_terminated_length": 197.70001220703125,
+      "completions/min_length": 118.0,
+      "completions/min_terminated_length": 118.0,
+      "epoch": 0.008081667375584857,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 2.192422389984131,
+      "kl": 0.0004282266672817059,
+      "learning_rate": 1.267605633802817e-06,
+      "loss": 0.0079,
+      "num_tokens": 1562405.0,
+      "reward": 2.197598457336426,
+      "reward_std": 0.26950523257255554,
+      "rewards/format_hoi_key_reward/mean": 0.6578124761581421,
+      "rewards/format_hoi_key_reward/std": 0.3557007312774658,
+      "rewards/format_hoi_object_label_reward/mean": 0.59375,
+      "rewards/format_hoi_object_label_reward/std": 0.3958510160446167,
+      "rewards/format_hoi_verb_label_reward/mean": 0.41914063692092896,
+      "rewards/format_hoi_verb_label_reward/std": 0.334130197763443,
+      "rewards/hoi_iou_reward/mean": 0.52689528465271,
+      "rewards/hoi_iou_reward/std": 0.31697896122932434,
+      "step": 19
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 456.0,
+      "completions/mean_length": 167.5625,
+      "completions/mean_terminated_length": 156.4516143798828,
+      "completions/min_length": 91.0,
+      "completions/min_terminated_length": 91.0,
+      "epoch": 0.008507018290089324,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 9.545456886291504,
+      "kl": 0.0003430663564358838,
+      "learning_rate": 1.3380281690140844e-06,
+      "loss": 0.0305,
+      "num_tokens": 1644081.0,
+      "reward": 2.449803590774536,
+      "reward_std": 0.3938855230808258,
+      "rewards/format_hoi_key_reward/mean": 0.7368229031562805,
+      "rewards/format_hoi_key_reward/std": 0.29059892892837524,
+      "rewards/format_hoi_object_label_reward/mean": 0.676562488079071,
+      "rewards/format_hoi_object_label_reward/std": 0.3538031578063965,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4554687738418579,
+      "rewards/format_hoi_verb_label_reward/std": 0.31711632013320923,
+      "rewards/hoi_iou_reward/mean": 0.5809494853019714,
+      "rewards/hoi_iou_reward/std": 0.25384804606437683,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 236.0,
+      "completions/max_terminated_length": 236.0,
+      "completions/mean_length": 153.0625,
+      "completions/mean_terminated_length": 153.0625,
+      "completions/min_length": 104.0,
+      "completions/min_terminated_length": 104.0,
+      "epoch": 0.00893236920459379,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.9242279529571533,
+      "kl": 0.00033866508601931855,
+      "learning_rate": 1.4084507042253523e-06,
+      "loss": -0.0036,
+      "num_tokens": 1725353.0,
+      "reward": 2.697577476501465,
+      "reward_std": 0.22112613916397095,
+      "rewards/format_hoi_key_reward/mean": 0.8525000214576721,
+      "rewards/format_hoi_key_reward/std": 0.22024911642074585,
+      "rewards/format_hoi_object_label_reward/mean": 0.6875,
+      "rewards/format_hoi_object_label_reward/std": 0.3544646203517914,
+      "rewards/format_hoi_verb_label_reward/mean": 0.5083333253860474,
+      "rewards/format_hoi_verb_label_reward/std": 0.3730144500732422,
+      "rewards/hoi_iou_reward/mean": 0.6492440104484558,
+      "rewards/hoi_iou_reward/std": 0.2220328450202942,
+      "step": 21
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 466.0,
+      "completions/max_terminated_length": 466.0,
+      "completions/mean_length": 199.53125,
+      "completions/mean_terminated_length": 199.53125,
+      "completions/min_length": 117.0,
+      "completions/min_terminated_length": 117.0,
+      "epoch": 0.009357720119098255,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 2.485565662384033,
+      "kl": 0.0004189620740362443,
+      "learning_rate": 1.4788732394366198e-06,
+      "loss": -0.0042,
+      "num_tokens": 1808072.0,
+      "reward": 2.559481143951416,
+      "reward_std": 0.10840541124343872,
+      "rewards/format_hoi_key_reward/mean": 0.8031938076019287,
+      "rewards/format_hoi_key_reward/std": 0.27561086416244507,
+      "rewards/format_hoi_object_label_reward/mean": 0.6789750456809998,
+      "rewards/format_hoi_object_label_reward/std": 0.39399468898773193,
+      "rewards/format_hoi_verb_label_reward/mean": 0.45625001192092896,
+      "rewards/format_hoi_verb_label_reward/std": 0.32801535725593567,
+      "rewards/hoi_iou_reward/mean": 0.6210623979568481,
+      "rewards/hoi_iou_reward/std": 0.300423264503479,
+      "step": 22
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 456.0,
+      "completions/max_terminated_length": 456.0,
+      "completions/mean_length": 190.40625,
+      "completions/mean_terminated_length": 190.40625,
+      "completions/min_length": 114.0,
+      "completions/min_terminated_length": 114.0,
+      "epoch": 0.009783071033602722,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.3170195817947388,
+      "kl": 0.000440634525148198,
+      "learning_rate": 1.5492957746478873e-06,
+      "loss": 0.0079,
+      "num_tokens": 1890443.0,
+      "reward": 2.659435510635376,
+      "reward_std": 0.15746591985225677,
+      "rewards/format_hoi_key_reward/mean": 0.8373958468437195,
+      "rewards/format_hoi_key_reward/std": 0.26145681738853455,
+      "rewards/format_hoi_object_label_reward/mean": 0.6739583611488342,
+      "rewards/format_hoi_object_label_reward/std": 0.437386691570282,
+      "rewards/format_hoi_verb_label_reward/mean": 0.504687488079071,
+      "rewards/format_hoi_verb_label_reward/std": 0.35861727595329285,
+      "rewards/hoi_iou_reward/mean": 0.6433938145637512,
+      "rewards/hoi_iou_reward/std": 0.31976941227912903,
+      "step": 23
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 280.0,
+      "completions/max_terminated_length": 280.0,
+      "completions/mean_length": 157.5,
+      "completions/mean_terminated_length": 157.5,
+      "completions/min_length": 108.0,
+      "completions/min_terminated_length": 108.0,
+      "epoch": 0.010208421948107189,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.0314154624938965,
+      "kl": 0.00044616637751460075,
+      "learning_rate": 1.6197183098591552e-06,
+      "loss": -0.0025,
+      "num_tokens": 1971841.0,
+      "reward": 2.6582393646240234,
+      "reward_std": 0.18655748665332794,
+      "rewards/format_hoi_key_reward/mean": 0.84375,
+      "rewards/format_hoi_key_reward/std": 0.25374436378479004,
+      "rewards/format_hoi_object_label_reward/mean": 0.6328125,
+      "rewards/format_hoi_object_label_reward/std": 0.4136229455471039,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4991319477558136,
+      "rewards/format_hoi_verb_label_reward/std": 0.35674116015434265,
+      "rewards/hoi_iou_reward/mean": 0.6825448274612427,
+      "rewards/hoi_iou_reward/std": 0.2595166563987732,
+      "step": 24
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 339.0,
+      "completions/mean_length": 180.28125,
+      "completions/mean_terminated_length": 158.1666717529297,
+      "completions/min_length": 116.0,
+      "completions/min_terminated_length": 116.0,
+      "epoch": 0.010633772862611655,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 11.281386375427246,
+      "kl": 0.0005614817346213385,
+      "learning_rate": 1.6901408450704227e-06,
+      "loss": 0.0657,
+      "num_tokens": 2053992.0,
+      "reward": 2.5150856971740723,
+      "reward_std": 0.24478863179683685,
+      "rewards/format_hoi_key_reward/mean": 0.809374988079071,
+      "rewards/format_hoi_key_reward/std": 0.3469045162200928,
+      "rewards/format_hoi_object_label_reward/mean": 0.70703125,
+      "rewards/format_hoi_object_label_reward/std": 0.4348819851875305,
+      "rewards/format_hoi_verb_label_reward/mean": 0.38359373807907104,
+      "rewards/format_hoi_verb_label_reward/std": 0.3953370153903961,
+      "rewards/hoi_iou_reward/mean": 0.6150857210159302,
+      "rewards/hoi_iou_reward/std": 0.3287210464477539,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 348.0,
+      "completions/max_terminated_length": 348.0,
+      "completions/mean_length": 151.59375,
+      "completions/mean_terminated_length": 151.59375,
+      "completions/min_length": 96.0,
+      "completions/min_terminated_length": 96.0,
+      "epoch": 0.01105912377711612,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.4701417684555054,
+      "kl": 0.0005035337235312909,
+      "learning_rate": 1.7605633802816902e-06,
+      "loss": 0.0044,
+      "num_tokens": 2135251.0,
+      "reward": 2.886725902557373,
+      "reward_std": 0.2123258411884308,
+      "rewards/format_hoi_key_reward/mean": 0.8578125238418579,
+      "rewards/format_hoi_key_reward/std": 0.2075624167919159,
+      "rewards/format_hoi_object_label_reward/mean": 0.7526041865348816,
+      "rewards/format_hoi_object_label_reward/std": 0.3613770306110382,
+      "rewards/format_hoi_verb_label_reward/mean": 0.5438988208770752,
+      "rewards/format_hoi_verb_label_reward/std": 0.3702835440635681,
+      "rewards/hoi_iou_reward/mean": 0.7324104309082031,
+      "rewards/hoi_iou_reward/std": 0.2421286553144455,
+      "step": 26
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 334.0,
+      "completions/mean_length": 167.8125,
+      "completions/mean_terminated_length": 156.7096710205078,
+      "completions/min_length": 93.0,
+      "completions/min_terminated_length": 93.0,
+      "epoch": 0.011484474691620587,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.1934653520584106,
+      "kl": 0.0005954405351076275,
+      "learning_rate": 1.8309859154929579e-06,
+      "loss": -0.032,
+      "num_tokens": 2216967.0,
+      "reward": 2.394422769546509,
+      "reward_std": 0.42784780263900757,
+      "rewards/format_hoi_key_reward/mean": 0.761805534362793,
+      "rewards/format_hoi_key_reward/std": 0.296843022108078,
+      "rewards/format_hoi_object_label_reward/mean": 0.6618055701255798,
+      "rewards/format_hoi_object_label_reward/std": 0.4076228737831116,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3853406012058258,
+      "rewards/format_hoi_verb_label_reward/std": 0.3449983298778534,
+      "rewards/hoi_iou_reward/mean": 0.5854711532592773,
+      "rewards/hoi_iou_reward/std": 0.2725910246372223,
+      "step": 27
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 473.0,
+      "completions/mean_length": 178.34375,
+      "completions/mean_terminated_length": 167.5806427001953,
+      "completions/min_length": 116.0,
+      "completions/min_terminated_length": 116.0,
+      "epoch": 0.011909825606125054,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.208022952079773,
+      "kl": 0.0006310369935818017,
+      "learning_rate": 1.9014084507042254e-06,
+      "loss": -0.034,
+      "num_tokens": 2299060.0,
+      "reward": 2.214604377746582,
+      "reward_std": 0.31437236070632935,
+      "rewards/format_hoi_key_reward/mean": 0.7563762664794922,
+      "rewards/format_hoi_key_reward/std": 0.346075177192688,
+      "rewards/format_hoi_object_label_reward/mean": 0.4952651560306549,
+      "rewards/format_hoi_object_label_reward/std": 0.47521334886550903,
+      "rewards/format_hoi_verb_label_reward/mean": 0.40388256311416626,
+      "rewards/format_hoi_verb_label_reward/std": 0.3852638006210327,
+      "rewards/hoi_iou_reward/mean": 0.5590803623199463,
+      "rewards/hoi_iou_reward/std": 0.3093617558479309,
+      "step": 28
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 450.0,
+      "completions/max_terminated_length": 450.0,
+      "completions/mean_length": 174.78125,
+      "completions/mean_terminated_length": 174.78125,
+      "completions/min_length": 96.0,
+      "completions/min_terminated_length": 96.0,
+      "epoch": 0.01233517652062952,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.393183946609497,
+      "kl": 0.0007882892386987805,
+      "learning_rate": 1.971830985915493e-06,
+      "loss": -0.024,
+      "num_tokens": 2380987.0,
+      "reward": 2.2392172813415527,
+      "reward_std": 0.3153127431869507,
+      "rewards/format_hoi_key_reward/mean": 0.7479861378669739,
+      "rewards/format_hoi_key_reward/std": 0.3090425729751587,
+      "rewards/format_hoi_object_label_reward/mean": 0.5729166865348816,
+      "rewards/format_hoi_object_label_reward/std": 0.4102790057659149,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3237847089767456,
+      "rewards/format_hoi_verb_label_reward/std": 0.2613273561000824,
+      "rewards/hoi_iou_reward/mean": 0.5945297479629517,
+      "rewards/hoi_iou_reward/std": 0.3360900580883026,
+      "step": 29
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 311.0,
+      "completions/max_terminated_length": 311.0,
+      "completions/mean_length": 157.1875,
+      "completions/mean_terminated_length": 157.1875,
+      "completions/min_length": 95.0,
+      "completions/min_terminated_length": 95.0,
+      "epoch": 0.012760527435133985,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.3999539613723755,
+      "kl": 0.0008022689580684528,
+      "learning_rate": 2.0422535211267608e-06,
+      "loss": -0.0204,
+      "num_tokens": 2462487.0,
+      "reward": 2.1738319396972656,
+      "reward_std": 0.19202688336372375,
+      "rewards/format_hoi_key_reward/mean": 0.7598214149475098,
+      "rewards/format_hoi_key_reward/std": 0.29326102137565613,
+      "rewards/format_hoi_object_label_reward/mean": 0.5598958730697632,
+      "rewards/format_hoi_object_label_reward/std": 0.41382598876953125,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3598484992980957,
+      "rewards/format_hoi_verb_label_reward/std": 0.3271215260028839,
+      "rewards/hoi_iou_reward/mean": 0.49426594376564026,
+      "rewards/hoi_iou_reward/std": 0.2569417953491211,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 492.0,
+      "completions/mean_length": 213.78125,
+      "completions/mean_terminated_length": 204.16128540039062,
+      "completions/min_length": 114.0,
+      "completions/min_terminated_length": 114.0,
+      "epoch": 0.013185878349638452,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 5.476845741271973,
+      "kl": 0.000950784218730405,
+      "learning_rate": 2.1126760563380285e-06,
+      "loss": 0.004,
+      "num_tokens": 2545612.0,
+      "reward": 2.5632033348083496,
+      "reward_std": 0.5354008078575134,
+      "rewards/format_hoi_key_reward/mean": 0.7911458015441895,
+      "rewards/format_hoi_key_reward/std": 0.23706629872322083,
+      "rewards/format_hoi_object_label_reward/mean": 0.7135416865348816,
+      "rewards/format_hoi_object_label_reward/std": 0.32581403851509094,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4348958432674408,
+      "rewards/format_hoi_verb_label_reward/std": 0.3128693997859955,
+      "rewards/hoi_iou_reward/mean": 0.6236201524734497,
+      "rewards/hoi_iou_reward/std": 0.2516784965991974,
+      "step": 31
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 274.0,
+      "completions/mean_length": 174.40625,
+      "completions/mean_terminated_length": 163.51612854003906,
+      "completions/min_length": 113.0,
+      "completions/min_terminated_length": 113.0,
+      "epoch": 0.013611229264142918,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 2.7625715732574463,
+      "kl": 0.001197469318867661,
+      "learning_rate": 2.1830985915492958e-06,
+      "loss": -0.0273,
+      "num_tokens": 2627593.0,
+      "reward": 2.5554096698760986,
+      "reward_std": 0.28477969765663147,
+      "rewards/format_hoi_key_reward/mean": 0.784375011920929,
+      "rewards/format_hoi_key_reward/std": 0.2782413065433502,
+      "rewards/format_hoi_object_label_reward/mean": 0.65625,
+      "rewards/format_hoi_object_label_reward/std": 0.38553017377853394,
+      "rewards/format_hoi_verb_label_reward/mean": 0.49926215410232544,
+      "rewards/format_hoi_verb_label_reward/std": 0.38366368412971497,
+      "rewards/hoi_iou_reward/mean": 0.6155223846435547,
+      "rewards/hoi_iou_reward/std": 0.3186318576335907,
+      "step": 32
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 333.0,
+      "completions/max_terminated_length": 333.0,
+      "completions/mean_length": 167.9375,
+      "completions/mean_terminated_length": 167.9375,
+      "completions/min_length": 109.0,
+      "completions/min_terminated_length": 109.0,
+      "epoch": 0.014036580178647383,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 2.134929656982422,
+      "kl": 0.0012024562747683376,
+      "learning_rate": 2.2535211267605635e-06,
+      "loss": -0.0295,
+      "num_tokens": 2709249.0,
+      "reward": 2.4919838905334473,
+      "reward_std": 0.2809957265853882,
+      "rewards/format_hoi_key_reward/mean": 0.8414583206176758,
+      "rewards/format_hoi_key_reward/std": 0.20066367089748383,
+      "rewards/format_hoi_object_label_reward/mean": 0.6541666984558105,
+      "rewards/format_hoi_object_label_reward/std": 0.40945371985435486,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3828125298023224,
+      "rewards/format_hoi_verb_label_reward/std": 0.28444916009902954,
+      "rewards/hoi_iou_reward/mean": 0.6135461330413818,
+      "rewards/hoi_iou_reward/std": 0.25517329573631287,
+      "step": 33
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 385.0,
+      "completions/mean_length": 204.59375,
+      "completions/mean_terminated_length": 184.10000610351562,
+      "completions/min_length": 93.0,
+      "completions/min_terminated_length": 93.0,
+      "epoch": 0.01446193109315185,
+      "frac_reward_zero_std": 0.125,
+      "grad_norm": 1.4026188850402832,
+      "kl": 0.001380591158522293,
+      "learning_rate": 2.323943661971831e-06,
+      "loss": -0.0124,
+      "num_tokens": 2792274.0,
+      "reward": 2.4142298698425293,
+      "reward_std": 0.3502156734466553,
+      "rewards/format_hoi_key_reward/mean": 0.7880208492279053,
+      "rewards/format_hoi_key_reward/std": 0.28556156158447266,
+      "rewards/format_hoi_object_label_reward/mean": 0.5703125,
+      "rewards/format_hoi_object_label_reward/std": 0.41967159509658813,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4947916865348816,
+      "rewards/format_hoi_verb_label_reward/std": 0.39933720231056213,
+      "rewards/hoi_iou_reward/mean": 0.5611048936843872,
+      "rewards/hoi_iou_reward/std": 0.3223456144332886,
+      "step": 34
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 489.0,
+      "completions/mean_length": 196.3125,
+      "completions/mean_terminated_length": 186.1290283203125,
+      "completions/min_length": 125.0,
+      "completions/min_terminated_length": 125.0,
+      "epoch": 0.014887282007656316,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.316129207611084,
+      "kl": 0.0016481104830745608,
+      "learning_rate": 2.3943661971830984e-06,
+      "loss": -0.0075,
+      "num_tokens": 2874978.0,
+      "reward": 2.8513381481170654,
+      "reward_std": 0.4244565963745117,
+      "rewards/format_hoi_key_reward/mean": 0.8733173608779907,
+      "rewards/format_hoi_key_reward/std": 0.24515916407108307,
+      "rewards/format_hoi_object_label_reward/mean": 0.7844551205635071,
+      "rewards/format_hoi_object_label_reward/std": 0.3160136938095093,
+      "rewards/format_hoi_verb_label_reward/mean": 0.42851561307907104,
+      "rewards/format_hoi_verb_label_reward/std": 0.32844552397727966,
+      "rewards/hoi_iou_reward/mean": 0.7650501728057861,
+      "rewards/hoi_iou_reward/std": 0.2422105222940445,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0625,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 458.0,
+      "completions/mean_length": 212.78125,
+      "completions/mean_terminated_length": 192.83334350585938,
+      "completions/min_length": 96.0,
+      "completions/min_terminated_length": 96.0,
+      "epoch": 0.015312632922160783,
+      "frac_reward_zero_std": 0.0625,
+      "grad_norm": 1.0710198879241943,
+      "kl": 0.0023336158774327487,
+      "learning_rate": 2.4647887323943666e-06,
+      "loss": 0.0636,
+      "num_tokens": 2957965.0,
+      "reward": 2.45017147064209,
+      "reward_std": 0.37150126695632935,
+      "rewards/format_hoi_key_reward/mean": 0.7733333110809326,
+      "rewards/format_hoi_key_reward/std": 0.2864827811717987,
+      "rewards/format_hoi_object_label_reward/mean": 0.6041666865348816,
+      "rewards/format_hoi_object_label_reward/std": 0.4018549919128418,
+      "rewards/format_hoi_verb_label_reward/mean": 0.4917534589767456,
+      "rewards/format_hoi_verb_label_reward/std": 0.3289114534854889,
+      "rewards/hoi_iou_reward/mean": 0.5809179544448853,
+      "rewards/hoi_iou_reward/std": 0.2540324032306671,
+      "step": 36
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 269.0,
+      "completions/mean_length": 176.375,
+      "completions/mean_terminated_length": 165.5483856201172,
+      "completions/min_length": 114.0,
+      "completions/min_terminated_length": 114.0,
+      "epoch": 0.015737983836665248,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.5639984607696533,
+      "kl": 0.002618325990624726,
+      "learning_rate": 2.535211267605634e-06,
+      "loss": 0.0076,
+      "num_tokens": 3040049.0,
+      "reward": 2.503605365753174,
+      "reward_std": 0.18485644459724426,
+      "rewards/format_hoi_key_reward/mean": 0.7159454822540283,
+      "rewards/format_hoi_key_reward/std": 0.33074691891670227,
+      "rewards/format_hoi_object_label_reward/mean": 0.6513621807098389,
+      "rewards/format_hoi_object_label_reward/std": 0.37841737270355225,
+      "rewards/format_hoi_verb_label_reward/mean": 0.5282986164093018,
+      "rewards/format_hoi_verb_label_reward/std": 0.37431567907333374,
+      "rewards/hoi_iou_reward/mean": 0.6079990863800049,
+      "rewards/hoi_iou_reward/std": 0.28626692295074463,
+      "step": 37
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 488.0,
+      "completions/max_terminated_length": 488.0,
+      "completions/mean_length": 187.28125,
+      "completions/mean_terminated_length": 187.28125,
+      "completions/min_length": 113.0,
+      "completions/min_terminated_length": 113.0,
+      "epoch": 0.016163334751169715,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 3.382786750793457,
+      "kl": 0.003079615533351898,
+      "learning_rate": 2.6056338028169015e-06,
+      "loss": -0.0705,
+      "num_tokens": 3122320.0,
+      "reward": 2.1021814346313477,
+      "reward_std": 0.3316464424133301,
+      "rewards/format_hoi_key_reward/mean": 0.6679166555404663,
+      "rewards/format_hoi_key_reward/std": 0.3353461027145386,
+      "rewards/format_hoi_object_label_reward/mean": 0.5670138597488403,
+      "rewards/format_hoi_object_label_reward/std": 0.4418155550956726,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3420138955116272,
+      "rewards/format_hoi_verb_label_reward/std": 0.37342512607574463,
+      "rewards/hoi_iou_reward/mean": 0.5252367854118347,
+      "rewards/hoi_iou_reward/std": 0.34420183300971985,
+      "step": 38
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 265.0,
+      "completions/max_terminated_length": 265.0,
+      "completions/mean_length": 155.53125,
+      "completions/mean_terminated_length": 155.53125,
+      "completions/min_length": 119.0,
+      "completions/min_terminated_length": 119.0,
+      "epoch": 0.01658868566567418,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 3.260523796081543,
+      "kl": 0.002960343728773296,
+      "learning_rate": 2.676056338028169e-06,
+      "loss": 0.0217,
+      "num_tokens": 3203647.0,
+      "reward": 2.722006320953369,
+      "reward_std": 0.10617414861917496,
+      "rewards/format_hoi_key_reward/mean": 0.8614583015441895,
+      "rewards/format_hoi_key_reward/std": 0.23783813416957855,
+      "rewards/format_hoi_object_label_reward/mean": 0.7364583611488342,
+      "rewards/format_hoi_object_label_reward/std": 0.3555357754230499,
+      "rewards/format_hoi_verb_label_reward/mean": 0.44348961114883423,
+      "rewards/format_hoi_verb_label_reward/std": 0.21557556092739105,
+      "rewards/hoi_iou_reward/mean": 0.6806000471115112,
+      "rewards/hoi_iou_reward/std": 0.24680498242378235,
+      "step": 39
+    },
+    {
+      "clip_ratio": 0.0,
+      "completions/clipped_ratio": 0.03125,
+      "completions/max_length": 512.0,
+      "completions/max_terminated_length": 507.0,
+      "completions/mean_length": 195.375,
+      "completions/mean_terminated_length": 185.16128540039062,
+      "completions/min_length": 116.0,
+      "completions/min_terminated_length": 116.0,
+      "epoch": 0.017014036580178648,
+      "frac_reward_zero_std": 0.0,
+      "grad_norm": 1.774012565612793,
+      "kl": 0.0033842482953332365,
+      "learning_rate": 2.746478873239437e-06,
+      "loss": -0.0124,
+      "num_tokens": 3286303.0,
+      "reward": 2.2706918716430664,
+      "reward_std": 0.18238192796707153,
+      "rewards/format_hoi_key_reward/mean": 0.71370530128479,
+      "rewards/format_hoi_key_reward/std": 0.3266391158103943,
+      "rewards/format_hoi_object_label_reward/mean": 0.5867311954498291,
+      "rewards/format_hoi_object_label_reward/std": 0.3556922376155853,
+      "rewards/format_hoi_verb_label_reward/mean": 0.3763934075832367,
+      "rewards/format_hoi_verb_label_reward/std": 0.3192271590232849,
+      "rewards/hoi_iou_reward/mean": 0.5938619375228882,
+      "rewards/hoi_iou_reward/std": 0.3091049790382385,
+      "step": 40
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 2351,
+  "num_input_tokens_seen": 3286303,
+  "num_train_epochs": 1,
+  "save_steps": 20,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77e703ea414a1dc46c8709364eacc0bbbd42e6cf90e4e0dd5f3b6d3af6632264
+size 9553

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)