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 +1,110 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- else %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
+                <|vision_start|><|image_pad|><|vision_end|>
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
+                <|vision_start|><|video_pad|><|vision_end|>
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{%- endmacro %}
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- render_content(messages[0].content, false) + '\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' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false) %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, True) %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and 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' }}
+        {{- content }}
+        {{- '\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<think>\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen3VLForConditionalGeneration"
+  ],
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "image_token_id": 151655,
+  "model_type": "qwen3_vl",
+  "pad_token_id": 151643,
+  "text_config": {
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "bos_token_id": 151643,
+    "dtype": "bfloat16",
+    "eos_token_id": 151645,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 4096,
+    "initializer_range": 0.02,
+    "intermediate_size": 12288,
+    "max_position_embeddings": 262144,
+    "model_type": "qwen3_vl_text",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 36,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": {
+      "mrope_interleaved": true,
+      "mrope_section": [
+        24,
+        20,
+        20
+      ],
+      "rope_type": "default"
+    },
+    "rope_theta": 5000000,
+    "use_cache": false,
+    "vocab_size": 151936
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "video_token_id": 151656,
+  "vision_config": {
+    "deepstack_visual_indexes": [
+      8,
+      16,
+      24
+    ],
+    "depth": 27,
+    "dtype": "bfloat16",
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_size": 1152,
+    "in_channels": 3,
+    "initializer_range": 0.02,
+    "intermediate_size": 4304,
+    "model_type": "qwen3_vl",
+    "num_heads": 16,
+    "num_position_embeddings": 2304,
+    "out_hidden_size": 4096,
+    "patch_size": 16,
+    "spatial_merge_size": 2,
+    "temporal_patch_size": 2
+  },
+  "vision_end_token_id": 151653,
+  "vision_start_token_id": 151652
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fb5a15766061dfc2db47f93ca53d34794135e9f46e48a772940c096846764f1
+size 4998056552

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:538d3f36e96871cacabb6ade27b63d6ba76e29981d21e2534eb49fdea613dbf0
+size 4915962464

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf653df3006f00bd1fc3e9cbf8c4dba3d0d98edc8ad66c2acbdae4da21cf35ca
+size 4915962496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b86205b3cbca7833475fce32f6ece92bb249bcca9a9726d04afb6ed83f1df57f
+size 2704357976

model.safetensors.index.json

@@ -0,0 +1,758 @@
+{
+  "metadata": {
+    "total_parameters": 8767123696,
+    "total_size": 17534247392
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
+    "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.language_model.norm.weight": "model-00004-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
+    "model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
+    "model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
+    "model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
+  }
+}

preprocessor_config.json

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

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,2266 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.956175298804781,
+  "eval_steps": 500,
+  "global_step": 186,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01593625498007968,
+      "grad_norm": 3.265625,
+      "learning_rate": 0.0,
+      "loss": 1.1802,
+      "memory/device_reserved (GiB)": 62.1,
+      "memory/max_active (GiB)": 50.46,
+      "memory/max_allocated (GiB)": 50.46,
+      "step": 1,
+      "tokens_per_second_per_gpu": 4078.9,
+      "total_tokens": 187960
+    },
+    {
+      "epoch": 0.03187250996015936,
+      "grad_norm": 3.53125,
+      "learning_rate": 1.111111111111111e-07,
+      "loss": 1.2461,
+      "memory/device_reserved (GiB)": 77.62,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 2,
+      "tokens_per_second_per_gpu": 5600.28,
+      "total_tokens": 380007
+    },
+    {
+      "epoch": 0.04780876494023904,
+      "grad_norm": 3.5625,
+      "learning_rate": 2.222222222222222e-07,
+      "loss": 1.3145,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 3,
+      "tokens_per_second_per_gpu": 5504.25,
+      "total_tokens": 566579
+    },
+    {
+      "epoch": 0.06374501992031872,
+      "grad_norm": 3.625,
+      "learning_rate": 3.333333333333333e-07,
+      "loss": 1.2505,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 4,
+      "tokens_per_second_per_gpu": 5678.77,
+      "total_tokens": 754678
+    },
+    {
+      "epoch": 0.0796812749003984,
+      "grad_norm": 3.46875,
+      "learning_rate": 4.444444444444444e-07,
+      "loss": 1.2344,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 5,
+      "tokens_per_second_per_gpu": 5644.44,
+      "total_tokens": 935084
+    },
+    {
+      "epoch": 0.09561752988047809,
+      "grad_norm": 3.71875,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 1.334,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 6,
+      "tokens_per_second_per_gpu": 5488.37,
+      "total_tokens": 1114037
+    },
+    {
+      "epoch": 0.11155378486055777,
+      "grad_norm": 3.4375,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 1.1704,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 7,
+      "tokens_per_second_per_gpu": 5468.62,
+      "total_tokens": 1302175
+    },
+    {
+      "epoch": 0.12749003984063745,
+      "grad_norm": 3.484375,
+      "learning_rate": 7.777777777777778e-07,
+      "loss": 1.2471,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 8,
+      "tokens_per_second_per_gpu": 5412.64,
+      "total_tokens": 1483342
+    },
+    {
+      "epoch": 0.14342629482071714,
+      "grad_norm": 3.375,
+      "learning_rate": 8.888888888888888e-07,
+      "loss": 1.2354,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 9,
+      "tokens_per_second_per_gpu": 5455.54,
+      "total_tokens": 1667332
+    },
+    {
+      "epoch": 0.1593625498007968,
+      "grad_norm": 3.546875,
+      "learning_rate": 1e-06,
+      "loss": 1.3232,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 10,
+      "tokens_per_second_per_gpu": 5574.32,
+      "total_tokens": 1849357
+    },
+    {
+      "epoch": 0.1752988047808765,
+      "grad_norm": 3.671875,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.3232,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 11,
+      "tokens_per_second_per_gpu": 5321.58,
+      "total_tokens": 2026853
+    },
+    {
+      "epoch": 0.19123505976095617,
+      "grad_norm": 3.359375,
+      "learning_rate": 1.2222222222222223e-06,
+      "loss": 1.2529,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 12,
+      "tokens_per_second_per_gpu": 5847.85,
+      "total_tokens": 2213285
+    },
+    {
+      "epoch": 0.20717131474103587,
+      "grad_norm": 3.328125,
+      "learning_rate": 1.3333333333333332e-06,
+      "loss": 1.2559,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 13,
+      "tokens_per_second_per_gpu": 5613.77,
+      "total_tokens": 2400076
+    },
+    {
+      "epoch": 0.22310756972111553,
+      "grad_norm": 3.15625,
+      "learning_rate": 1.4444444444444443e-06,
+      "loss": 1.2129,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 14,
+      "tokens_per_second_per_gpu": 5571.51,
+      "total_tokens": 2593112
+    },
+    {
+      "epoch": 0.23904382470119523,
+      "grad_norm": 3.125,
+      "learning_rate": 1.5555555555555556e-06,
+      "loss": 1.2153,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 15,
+      "tokens_per_second_per_gpu": 5626.56,
+      "total_tokens": 2782327
+    },
+    {
+      "epoch": 0.2549800796812749,
+      "grad_norm": 3.3125,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.2598,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 16,
+      "tokens_per_second_per_gpu": 5731.24,
+      "total_tokens": 2966947
+    },
+    {
+      "epoch": 0.27091633466135456,
+      "grad_norm": 3.09375,
+      "learning_rate": 1.7777777777777775e-06,
+      "loss": 1.1714,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 17,
+      "tokens_per_second_per_gpu": 6088.78,
+      "total_tokens": 3161163
+    },
+    {
+      "epoch": 0.2868525896414343,
+      "grad_norm": 3.234375,
+      "learning_rate": 1.8888888888888888e-06,
+      "loss": 1.2402,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 18,
+      "tokens_per_second_per_gpu": 5499.3,
+      "total_tokens": 3343301
+    },
+    {
+      "epoch": 0.30278884462151395,
+      "grad_norm": 3.171875,
+      "learning_rate": 2e-06,
+      "loss": 1.2158,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 19,
+      "tokens_per_second_per_gpu": 5505.1,
+      "total_tokens": 3527203
+    },
+    {
+      "epoch": 0.3187250996015936,
+      "grad_norm": 3.21875,
+      "learning_rate": 1.9998251609127463e-06,
+      "loss": 1.2446,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 20,
+      "tokens_per_second_per_gpu": 5441.06,
+      "total_tokens": 3710228
+    },
+    {
+      "epoch": 0.3346613545816733,
+      "grad_norm": 2.875,
+      "learning_rate": 1.9993007047883984e-06,
+      "loss": 1.1895,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 21,
+      "tokens_per_second_per_gpu": 5817.48,
+      "total_tokens": 3903090
+    },
+    {
+      "epoch": 0.350597609561753,
+      "grad_norm": 3.078125,
+      "learning_rate": 1.9984268150178167e-06,
+      "loss": 1.209,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 22,
+      "tokens_per_second_per_gpu": 5823.26,
+      "total_tokens": 4085213
+    },
+    {
+      "epoch": 0.3665338645418327,
+      "grad_norm": 2.71875,
+      "learning_rate": 1.9972037971811797e-06,
+      "loss": 1.1602,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 23,
+      "tokens_per_second_per_gpu": 5595.44,
+      "total_tokens": 4271930
+    },
+    {
+      "epoch": 0.38247011952191234,
+      "grad_norm": 2.625,
+      "learning_rate": 1.9956320789411338e-06,
+      "loss": 1.1587,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 24,
+      "tokens_per_second_per_gpu": 5470.25,
+      "total_tokens": 4458282
+    },
+    {
+      "epoch": 0.398406374501992,
+      "grad_norm": 2.96875,
+      "learning_rate": 1.9937122098932426e-06,
+      "loss": 1.2295,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 25,
+      "tokens_per_second_per_gpu": 5381.09,
+      "total_tokens": 4638920
+    },
+    {
+      "epoch": 0.41434262948207173,
+      "grad_norm": 2.765625,
+      "learning_rate": 1.9914448613738106e-06,
+      "loss": 1.2695,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 26,
+      "tokens_per_second_per_gpu": 5413.01,
+      "total_tokens": 4823256
+    },
+    {
+      "epoch": 0.4302788844621514,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.9888308262251284e-06,
+      "loss": 1.2412,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 27,
+      "tokens_per_second_per_gpu": 5555.69,
+      "total_tokens": 5004546
+    },
+    {
+      "epoch": 0.44621513944223107,
+      "grad_norm": 2.703125,
+      "learning_rate": 1.9858710185182355e-06,
+      "loss": 1.2666,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 28,
+      "tokens_per_second_per_gpu": 5321.57,
+      "total_tokens": 5180916
+    },
+    {
+      "epoch": 0.46215139442231074,
+      "grad_norm": 2.5625,
+      "learning_rate": 1.9825664732332882e-06,
+      "loss": 1.207,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 29,
+      "tokens_per_second_per_gpu": 5507.08,
+      "total_tokens": 5362870
+    },
+    {
+      "epoch": 0.47808764940239046,
+      "grad_norm": 2.671875,
+      "learning_rate": 1.9789183458976484e-06,
+      "loss": 1.1904,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 30,
+      "tokens_per_second_per_gpu": 5788.71,
+      "total_tokens": 5548692
+    },
+    {
+      "epoch": 0.4940239043824701,
+      "grad_norm": 2.4375,
+      "learning_rate": 1.9749279121818236e-06,
+      "loss": 1.1865,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 31,
+      "tokens_per_second_per_gpu": 5411.35,
+      "total_tokens": 5734611
+    },
+    {
+      "epoch": 0.5099601593625498,
+      "grad_norm": 2.5,
+      "learning_rate": 1.970596567453391e-06,
+      "loss": 1.1953,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 32,
+      "tokens_per_second_per_gpu": 5568.61,
+      "total_tokens": 5915483
+    },
+    {
+      "epoch": 0.5258964143426295,
+      "grad_norm": 2.328125,
+      "learning_rate": 1.965925826289068e-06,
+      "loss": 1.1885,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 33,
+      "tokens_per_second_per_gpu": 5527.28,
+      "total_tokens": 6103887
+    },
+    {
+      "epoch": 0.5418326693227091,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.9609173219450997e-06,
+      "loss": 1.2578,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 34,
+      "tokens_per_second_per_gpu": 5786.79,
+      "total_tokens": 6291053
+    },
+    {
+      "epoch": 0.5577689243027888,
+      "grad_norm": 2.390625,
+      "learning_rate": 1.955572805786141e-06,
+      "loss": 1.2656,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 35,
+      "tokens_per_second_per_gpu": 5616.39,
+      "total_tokens": 6476080
+    },
+    {
+      "epoch": 0.5737051792828686,
+      "grad_norm": 2.40625,
+      "learning_rate": 1.9498941466728456e-06,
+      "loss": 1.2285,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 36,
+      "tokens_per_second_per_gpu": 5446.88,
+      "total_tokens": 6654173
+    },
+    {
+      "epoch": 0.5896414342629482,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.9438833303083674e-06,
+      "loss": 1.2314,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 37,
+      "tokens_per_second_per_gpu": 5411.99,
+      "total_tokens": 6838496
+    },
+    {
+      "epoch": 0.6055776892430279,
+      "grad_norm": 2.140625,
+      "learning_rate": 1.937542458543999e-06,
+      "loss": 1.1685,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 38,
+      "tokens_per_second_per_gpu": 5285.57,
+      "total_tokens": 7020101
+    },
+    {
+      "epoch": 0.6215139442231076,
+      "grad_norm": 2.09375,
+      "learning_rate": 1.930873748644204e-06,
+      "loss": 1.1489,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 39,
+      "tokens_per_second_per_gpu": 5909.97,
+      "total_tokens": 7209728
+    },
+    {
+      "epoch": 0.6374501992031872,
+      "grad_norm": 2.21875,
+      "learning_rate": 1.9238795325112867e-06,
+      "loss": 1.1924,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 40,
+      "tokens_per_second_per_gpu": 5668.7,
+      "total_tokens": 7392542
+    },
+    {
+      "epoch": 0.6533864541832669,
+      "grad_norm": 2.1875,
+      "learning_rate": 1.916562255869976e-06,
+      "loss": 1.21,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 41,
+      "tokens_per_second_per_gpu": 5187.81,
+      "total_tokens": 7570380
+    },
+    {
+      "epoch": 0.6693227091633466,
+      "grad_norm": 2.03125,
+      "learning_rate": 1.908924477412211e-06,
+      "loss": 1.1787,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 42,
+      "tokens_per_second_per_gpu": 5502.78,
+      "total_tokens": 7753287
+    },
+    {
+      "epoch": 0.6852589641434262,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.9009688679024189e-06,
+      "loss": 1.1504,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 43,
+      "tokens_per_second_per_gpu": 5664.86,
+      "total_tokens": 7942863
+    },
+    {
+      "epoch": 0.701195219123506,
+      "grad_norm": 1.9921875,
+      "learning_rate": 1.8926982092436114e-06,
+      "loss": 1.2075,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 44,
+      "tokens_per_second_per_gpu": 5493.62,
+      "total_tokens": 8127398
+    },
+    {
+      "epoch": 0.7171314741035857,
+      "grad_norm": 1.9140625,
+      "learning_rate": 1.8841153935046096e-06,
+      "loss": 1.1484,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 45,
+      "tokens_per_second_per_gpu": 5847.74,
+      "total_tokens": 8312603
+    },
+    {
+      "epoch": 0.7330677290836654,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.8752234219087537e-06,
+      "loss": 1.167,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 46,
+      "tokens_per_second_per_gpu": 5502.76,
+      "total_tokens": 8497383
+    },
+    {
+      "epoch": 0.749003984063745,
+      "grad_norm": 1.8828125,
+      "learning_rate": 1.8660254037844386e-06,
+      "loss": 1.147,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 47,
+      "tokens_per_second_per_gpu": 5615.32,
+      "total_tokens": 8688166
+    },
+    {
+      "epoch": 0.7649402390438247,
+      "grad_norm": 1.9453125,
+      "learning_rate": 1.8565245554778515e-06,
+      "loss": 1.1992,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 48,
+      "tokens_per_second_per_gpu": 5767.9,
+      "total_tokens": 8874386
+    },
+    {
+      "epoch": 0.7808764940239044,
+      "grad_norm": 1.90625,
+      "learning_rate": 1.8467241992282841e-06,
+      "loss": 1.1475,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 49,
+      "tokens_per_second_per_gpu": 5789.02,
+      "total_tokens": 9059229
+    },
+    {
+      "epoch": 0.796812749003984,
+      "grad_norm": 1.75,
+      "learning_rate": 1.8366277620064197e-06,
+      "loss": 1.0986,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 50,
+      "tokens_per_second_per_gpu": 5192.74,
+      "total_tokens": 9255532
+    },
+    {
+      "epoch": 0.8127490039840638,
+      "grad_norm": 1.7578125,
+      "learning_rate": 1.8262387743159948e-06,
+      "loss": 1.0908,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 51,
+      "tokens_per_second_per_gpu": 5522.43,
+      "total_tokens": 9446438
+    },
+    {
+      "epoch": 0.8286852589641435,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.8155608689592601e-06,
+      "loss": 1.1084,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 52,
+      "tokens_per_second_per_gpu": 5467.0,
+      "total_tokens": 9632510
+    },
+    {
+      "epoch": 0.8446215139442231,
+      "grad_norm": 1.6171875,
+      "learning_rate": 1.8045977797666683e-06,
+      "loss": 1.0781,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 53,
+      "tokens_per_second_per_gpu": 5831.19,
+      "total_tokens": 9824144
+    },
+    {
+      "epoch": 0.8605577689243028,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.7933533402912351e-06,
+      "loss": 1.1533,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 54,
+      "tokens_per_second_per_gpu": 5705.42,
+      "total_tokens": 10010140
+    },
+    {
+      "epoch": 0.8764940239043825,
+      "grad_norm": 1.7734375,
+      "learning_rate": 1.7818314824680298e-06,
+      "loss": 1.1689,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 55,
+      "tokens_per_second_per_gpu": 5696.79,
+      "total_tokens": 10195855
+    },
+    {
+      "epoch": 0.8924302788844621,
+      "grad_norm": 1.6796875,
+      "learning_rate": 1.770036235239263e-06,
+      "loss": 1.1182,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 56,
+      "tokens_per_second_per_gpu": 6045.85,
+      "total_tokens": 10381589
+    },
+    {
+      "epoch": 0.9083665338645418,
+      "grad_norm": 1.6875,
+      "learning_rate": 1.7579717231454529e-06,
+      "loss": 1.1738,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 57,
+      "tokens_per_second_per_gpu": 5658.53,
+      "total_tokens": 10573779
+    },
+    {
+      "epoch": 0.9243027888446215,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.7456421648831654e-06,
+      "loss": 1.1553,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 58,
+      "tokens_per_second_per_gpu": 5601.69,
+      "total_tokens": 10762764
+    },
+    {
+      "epoch": 0.9402390438247012,
+      "grad_norm": 1.7109375,
+      "learning_rate": 1.733051871829826e-06,
+      "loss": 1.1416,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 59,
+      "tokens_per_second_per_gpu": 5873.82,
+      "total_tokens": 10948310
+    },
+    {
+      "epoch": 0.9561752988047809,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.7202052465361266e-06,
+      "loss": 1.1514,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 60,
+      "tokens_per_second_per_gpu": 5552.06,
+      "total_tokens": 11134379
+    },
+    {
+      "epoch": 0.9721115537848606,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.7071067811865474e-06,
+      "loss": 1.1243,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 61,
+      "tokens_per_second_per_gpu": 5016.43,
+      "total_tokens": 11320025
+    },
+    {
+      "epoch": 0.9880478087649402,
+      "grad_norm": 1.4921875,
+      "learning_rate": 1.6937610560285416e-06,
+      "loss": 1.0957,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 62,
+      "tokens_per_second_per_gpu": 5350.32,
+      "total_tokens": 11504140
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.609375,
+      "learning_rate": 1.6801727377709191e-06,
+      "loss": 1.1582,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 63,
+      "tokens_per_second_per_gpu": 4173.22,
+      "total_tokens": 11627371
+    },
+    {
+      "epoch": 1.0159362549800797,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.6663465779520037e-06,
+      "loss": 1.0864,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 64,
+      "tokens_per_second_per_gpu": 5530.73,
+      "total_tokens": 11815331
+    },
+    {
+      "epoch": 1.0318725099601593,
+      "grad_norm": 1.6015625,
+      "learning_rate": 1.6522874112781212e-06,
+      "loss": 1.1445,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 65,
+      "tokens_per_second_per_gpu": 5941.29,
+      "total_tokens": 12007378
+    },
+    {
+      "epoch": 1.047808764940239,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.6380001539330085e-06,
+      "loss": 1.209,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 66,
+      "tokens_per_second_per_gpu": 5598.11,
+      "total_tokens": 12193950
+    },
+    {
+      "epoch": 1.0637450199203187,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.6234898018587336e-06,
+      "loss": 1.1421,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 67,
+      "tokens_per_second_per_gpu": 5671.24,
+      "total_tokens": 12382049
+    },
+    {
+      "epoch": 1.0796812749003983,
+      "grad_norm": 1.5,
+      "learning_rate": 1.6087614290087205e-06,
+      "loss": 1.1323,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 68,
+      "tokens_per_second_per_gpu": 5627.89,
+      "total_tokens": 12562455
+    },
+    {
+      "epoch": 1.095617529880478,
+      "grad_norm": 1.5859375,
+      "learning_rate": 1.5938201855735014e-06,
+      "loss": 1.2207,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 69,
+      "tokens_per_second_per_gpu": 5368.43,
+      "total_tokens": 12741408
+    },
+    {
+      "epoch": 1.1115537848605577,
+      "grad_norm": 1.46875,
+      "learning_rate": 1.578671296179806e-06,
+      "loss": 1.0659,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 70,
+      "tokens_per_second_per_gpu": 5466.98,
+      "total_tokens": 12929546
+    },
+    {
+      "epoch": 1.1274900398406373,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.563320058063622e-06,
+      "loss": 1.1416,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 71,
+      "tokens_per_second_per_gpu": 5509.23,
+      "total_tokens": 13110713
+    },
+    {
+      "epoch": 1.1434262948207172,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.5477718392178713e-06,
+      "loss": 1.1318,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 72,
+      "tokens_per_second_per_gpu": 5553.33,
+      "total_tokens": 13294703
+    },
+    {
+      "epoch": 1.159362549800797,
+      "grad_norm": 1.484375,
+      "learning_rate": 1.5320320765153365e-06,
+      "loss": 1.2129,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 73,
+      "tokens_per_second_per_gpu": 5457.5,
+      "total_tokens": 13476728
+    },
+    {
+      "epoch": 1.1752988047808766,
+      "grad_norm": 1.5,
+      "learning_rate": 1.5161062738075065e-06,
+      "loss": 1.2109,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 74,
+      "tokens_per_second_per_gpu": 5229.94,
+      "total_tokens": 13654224
+    },
+    {
+      "epoch": 1.1912350597609562,
+      "grad_norm": 1.3671875,
+      "learning_rate": 1.5e-06,
+      "loss": 1.1475,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 75,
+      "tokens_per_second_per_gpu": 5856.14,
+      "total_tokens": 13840656
+    },
+    {
+      "epoch": 1.207171314741036,
+      "grad_norm": 1.3984375,
+      "learning_rate": 1.4837188871052397e-06,
+      "loss": 1.1494,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 76,
+      "tokens_per_second_per_gpu": 5621.93,
+      "total_tokens": 14027447
+    },
+    {
+      "epoch": 1.2231075697211156,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.467268628273062e-06,
+      "loss": 1.1133,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 77,
+      "tokens_per_second_per_gpu": 5678.9,
+      "total_tokens": 14220483
+    },
+    {
+      "epoch": 1.2390438247011952,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.4506549757999453e-06,
+      "loss": 1.1182,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 78,
+      "tokens_per_second_per_gpu": 5610.92,
+      "total_tokens": 14409698
+    },
+    {
+      "epoch": 1.254980079681275,
+      "grad_norm": 1.4296875,
+      "learning_rate": 1.433883739117558e-06,
+      "loss": 1.1582,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 79,
+      "tokens_per_second_per_gpu": 5624.06,
+      "total_tokens": 14594318
+    },
+    {
+      "epoch": 1.2709163346613546,
+      "grad_norm": 1.328125,
+      "learning_rate": 1.4169607827613282e-06,
+      "loss": 1.0762,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 80,
+      "tokens_per_second_per_gpu": 6081.02,
+      "total_tokens": 14788534
+    },
+    {
+      "epoch": 1.2868525896414342,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.3998920243197408e-06,
+      "loss": 1.1372,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 81,
+      "tokens_per_second_per_gpu": 5511.47,
+      "total_tokens": 14970672
+    },
+    {
+      "epoch": 1.302788844621514,
+      "grad_norm": 1.3671875,
+      "learning_rate": 1.3826834323650898e-06,
+      "loss": 1.1167,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 82,
+      "tokens_per_second_per_gpu": 5614.12,
+      "total_tokens": 15154574
+    },
+    {
+      "epoch": 1.3187250996015936,
+      "grad_norm": 1.390625,
+      "learning_rate": 1.3653410243663951e-06,
+      "loss": 1.1455,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 83,
+      "tokens_per_second_per_gpu": 5438.76,
+      "total_tokens": 15337599
+    },
+    {
+      "epoch": 1.3346613545816732,
+      "grad_norm": 1.234375,
+      "learning_rate": 1.347870864585227e-06,
+      "loss": 1.103,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 84,
+      "tokens_per_second_per_gpu": 5795.88,
+      "total_tokens": 15530461
+    },
+    {
+      "epoch": 1.3505976095617531,
+      "grad_norm": 1.3515625,
+      "learning_rate": 1.3302790619551672e-06,
+      "loss": 1.1162,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 85,
+      "tokens_per_second_per_gpu": 5723.72,
+      "total_tokens": 15712584
+    },
+    {
+      "epoch": 1.3665338645418328,
+      "grad_norm": 1.2265625,
+      "learning_rate": 1.3125717679456444e-06,
+      "loss": 1.0786,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 86,
+      "tokens_per_second_per_gpu": 5598.4,
+      "total_tokens": 15899301
+    },
+    {
+      "epoch": 1.3824701195219125,
+      "grad_norm": 1.1875,
+      "learning_rate": 1.2947551744109043e-06,
+      "loss": 1.082,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 87,
+      "tokens_per_second_per_gpu": 5458.74,
+      "total_tokens": 16085653
+    },
+    {
+      "epoch": 1.3984063745019921,
+      "grad_norm": 1.3515625,
+      "learning_rate": 1.2768355114248492e-06,
+      "loss": 1.1436,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 88,
+      "tokens_per_second_per_gpu": 5579.84,
+      "total_tokens": 16266291
+    },
+    {
+      "epoch": 1.4143426294820718,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.2588190451025207e-06,
+      "loss": 1.1914,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 89,
+      "tokens_per_second_per_gpu": 5336.85,
+      "total_tokens": 16450627
+    },
+    {
+      "epoch": 1.4302788844621515,
+      "grad_norm": 1.25,
+      "learning_rate": 1.240712075408973e-06,
+      "loss": 1.167,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 90,
+      "tokens_per_second_per_gpu": 5445.98,
+      "total_tokens": 16631917
+    },
+    {
+      "epoch": 1.4462151394422311,
+      "grad_norm": 1.265625,
+      "learning_rate": 1.2225209339563143e-06,
+      "loss": 1.1895,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 91,
+      "tokens_per_second_per_gpu": 5330.92,
+      "total_tokens": 16808287
+    },
+    {
+      "epoch": 1.4621513944223108,
+      "grad_norm": 1.25,
+      "learning_rate": 1.2042519817896804e-06,
+      "loss": 1.1357,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 92,
+      "tokens_per_second_per_gpu": 5515.76,
+      "total_tokens": 16990241
+    },
+    {
+      "epoch": 1.4780876494023905,
+      "grad_norm": 1.328125,
+      "learning_rate": 1.1859116071629147e-06,
+      "loss": 1.1187,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 93,
+      "tokens_per_second_per_gpu": 5890.54,
+      "total_tokens": 17176063
+    },
+    {
+      "epoch": 1.4940239043824701,
+      "grad_norm": 1.2265625,
+      "learning_rate": 1.1675062233047363e-06,
+      "loss": 1.1211,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 94,
+      "tokens_per_second_per_gpu": 5413.95,
+      "total_tokens": 17361982
+    },
+    {
+      "epoch": 1.5099601593625498,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.1490422661761743e-06,
+      "loss": 1.1294,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 95,
+      "tokens_per_second_per_gpu": 5447.34,
+      "total_tokens": 17542854
+    },
+    {
+      "epoch": 1.5258964143426295,
+      "grad_norm": 1.1875,
+      "learning_rate": 1.1305261922200517e-06,
+      "loss": 1.125,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 96,
+      "tokens_per_second_per_gpu": 5531.41,
+      "total_tokens": 17731258
+    },
+    {
+      "epoch": 1.5418326693227091,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.1119644761033077e-06,
+      "loss": 1.1963,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 97,
+      "tokens_per_second_per_gpu": 5812.79,
+      "total_tokens": 17918424
+    },
+    {
+      "epoch": 1.5577689243027888,
+      "grad_norm": 1.203125,
+      "learning_rate": 1.0933636084529506e-06,
+      "loss": 1.2041,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 98,
+      "tokens_per_second_per_gpu": 5613.31,
+      "total_tokens": 18103451
+    },
+    {
+      "epoch": 1.5737051792828685,
+      "grad_norm": 1.2578125,
+      "learning_rate": 1.0747300935864243e-06,
+      "loss": 1.168,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 99,
+      "tokens_per_second_per_gpu": 5555.4,
+      "total_tokens": 18281544
+    },
+    {
+      "epoch": 1.5896414342629481,
+      "grad_norm": 1.171875,
+      "learning_rate": 1.0560704472371917e-06,
+      "loss": 1.1768,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 100,
+      "tokens_per_second_per_gpu": 5413.52,
+      "total_tokens": 18465867
+    },
+    {
+      "epoch": 1.6055776892430278,
+      "grad_norm": 1.15625,
+      "learning_rate": 1.037391194276326e-06,
+      "loss": 1.1162,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 101,
+      "tokens_per_second_per_gpu": 5209.56,
+      "total_tokens": 18647472
+    },
+    {
+      "epoch": 1.6215139442231075,
+      "grad_norm": 1.1328125,
+      "learning_rate": 1.0186988664309022e-06,
+      "loss": 1.0986,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 102,
+      "tokens_per_second_per_gpu": 5913.8,
+      "total_tokens": 18837099
+    },
+    {
+      "epoch": 1.6374501992031871,
+      "grad_norm": 1.21875,
+      "learning_rate": 1e-06,
+      "loss": 1.1392,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 103,
+      "tokens_per_second_per_gpu": 5669.98,
+      "total_tokens": 19019913
+    },
+    {
+      "epoch": 1.6533864541832668,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.81301133569098e-07,
+      "loss": 1.1582,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 104,
+      "tokens_per_second_per_gpu": 5370.41,
+      "total_tokens": 19197751
+    },
+    {
+      "epoch": 1.6693227091633465,
+      "grad_norm": 1.1796875,
+      "learning_rate": 9.626088057236744e-07,
+      "loss": 1.1318,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 105,
+      "tokens_per_second_per_gpu": 5391.77,
+      "total_tokens": 19380658
+    },
+    {
+      "epoch": 1.6852589641434261,
+      "grad_norm": 1.09375,
+      "learning_rate": 9.43929552762808e-07,
+      "loss": 1.1084,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 106,
+      "tokens_per_second_per_gpu": 5564.12,
+      "total_tokens": 19570234
+    },
+    {
+      "epoch": 1.701195219123506,
+      "grad_norm": 1.1640625,
+      "learning_rate": 9.252699064135758e-07,
+      "loss": 1.1616,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 107,
+      "tokens_per_second_per_gpu": 5485.18,
+      "total_tokens": 19754769
+    },
+    {
+      "epoch": 1.7171314741035857,
+      "grad_norm": 1.1328125,
+      "learning_rate": 9.066363915470494e-07,
+      "loss": 1.106,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 108,
+      "tokens_per_second_per_gpu": 5839.07,
+      "total_tokens": 19939974
+    },
+    {
+      "epoch": 1.7330677290836654,
+      "grad_norm": 1.1328125,
+      "learning_rate": 8.880355238966921e-07,
+      "loss": 1.125,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 109,
+      "tokens_per_second_per_gpu": 5601.59,
+      "total_tokens": 20124754
+    },
+    {
+      "epoch": 1.749003984063745,
+      "grad_norm": 1.15625,
+      "learning_rate": 8.694738077799486e-07,
+      "loss": 1.1084,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 110,
+      "tokens_per_second_per_gpu": 5601.31,
+      "total_tokens": 20315537
+    },
+    {
+      "epoch": 1.7649402390438247,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.509577338238254e-07,
+      "loss": 1.1602,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 111,
+      "tokens_per_second_per_gpu": 5767.0,
+      "total_tokens": 20501757
+    },
+    {
+      "epoch": 1.7808764940239044,
+      "grad_norm": 1.1796875,
+      "learning_rate": 8.324937766952636e-07,
+      "loss": 1.1094,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 112,
+      "tokens_per_second_per_gpu": 5679.05,
+      "total_tokens": 20686600
+    },
+    {
+      "epoch": 1.796812749003984,
+      "grad_norm": 1.1015625,
+      "learning_rate": 8.140883928370854e-07,
+      "loss": 1.0659,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 113,
+      "tokens_per_second_per_gpu": 5176.17,
+      "total_tokens": 20882903
+    },
+    {
+      "epoch": 1.812749003984064,
+      "grad_norm": 1.109375,
+      "learning_rate": 7.957480182103197e-07,
+      "loss": 1.0562,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 114,
+      "tokens_per_second_per_gpu": 5609.67,
+      "total_tokens": 21073809
+    },
+    {
+      "epoch": 1.8286852589641436,
+      "grad_norm": 1.09375,
+      "learning_rate": 7.774790660436857e-07,
+      "loss": 1.0747,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 115,
+      "tokens_per_second_per_gpu": 5480.8,
+      "total_tokens": 21259881
+    },
+    {
+      "epoch": 1.8446215139442232,
+      "grad_norm": 1.0390625,
+      "learning_rate": 7.592879245910272e-07,
+      "loss": 1.0459,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 116,
+      "tokens_per_second_per_gpu": 5854.74,
+      "total_tokens": 21451515
+    },
+    {
+      "epoch": 1.860557768924303,
+      "grad_norm": 1.1484375,
+      "learning_rate": 7.411809548974791e-07,
+      "loss": 1.1191,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 117,
+      "tokens_per_second_per_gpu": 5607.88,
+      "total_tokens": 21637511
+    },
+    {
+      "epoch": 1.8764940239043826,
+      "grad_norm": 1.1328125,
+      "learning_rate": 7.231644885751507e-07,
+      "loss": 1.1377,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 118,
+      "tokens_per_second_per_gpu": 5697.72,
+      "total_tokens": 21823226
+    },
+    {
+      "epoch": 1.8924302788844622,
+      "grad_norm": 1.1171875,
+      "learning_rate": 7.052448255890957e-07,
+      "loss": 1.0869,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 119,
+      "tokens_per_second_per_gpu": 6034.6,
+      "total_tokens": 22008960
+    },
+    {
+      "epoch": 1.908366533864542,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6.874282320543556e-07,
+      "loss": 1.144,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 120,
+      "tokens_per_second_per_gpu": 5668.36,
+      "total_tokens": 22201150
+    },
+    {
+      "epoch": 1.9243027888446216,
+      "grad_norm": 1.0859375,
+      "learning_rate": 6.697209380448332e-07,
+      "loss": 1.1255,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 121,
+      "tokens_per_second_per_gpu": 5720.74,
+      "total_tokens": 22390135
+    },
+    {
+      "epoch": 1.9402390438247012,
+      "grad_norm": 1.15625,
+      "learning_rate": 6.521291354147726e-07,
+      "loss": 1.1104,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 122,
+      "tokens_per_second_per_gpu": 5870.28,
+      "total_tokens": 22575681
+    },
+    {
+      "epoch": 1.956175298804781,
+      "grad_norm": 1.0625,
+      "learning_rate": 6.34658975633605e-07,
+      "loss": 1.1221,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 123,
+      "tokens_per_second_per_gpu": 5453.27,
+      "total_tokens": 22761750
+    },
+    {
+      "epoch": 1.9721115537848606,
+      "grad_norm": 1.0859375,
+      "learning_rate": 6.173165676349102e-07,
+      "loss": 1.0967,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 124,
+      "tokens_per_second_per_gpu": 4989.67,
+      "total_tokens": 22947396
+    },
+    {
+      "epoch": 1.9880478087649402,
+      "grad_norm": 1.0390625,
+      "learning_rate": 6.001079756802592e-07,
+      "loss": 1.0703,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 125,
+      "tokens_per_second_per_gpu": 5385.24,
+      "total_tokens": 23131511
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.140625,
+      "learning_rate": 5.830392172386722e-07,
+      "loss": 1.1328,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 126,
+      "tokens_per_second_per_gpu": 4540.27,
+      "total_tokens": 23254742
+    },
+    {
+      "epoch": 2.0159362549800797,
+      "grad_norm": 1.03125,
+      "learning_rate": 5.661162608824419e-07,
+      "loss": 1.061,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 127,
+      "tokens_per_second_per_gpu": 5523.13,
+      "total_tokens": 23442702
+    },
+    {
+      "epoch": 2.0318725099601593,
+      "grad_norm": 1.140625,
+      "learning_rate": 5.493450242000546e-07,
+      "loss": 1.1201,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 128,
+      "tokens_per_second_per_gpu": 5699.3,
+      "total_tokens": 23634749
+    },
+    {
+      "epoch": 2.047808764940239,
+      "grad_norm": 1.109375,
+      "learning_rate": 5.327313717269379e-07,
+      "loss": 1.1875,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 129,
+      "tokens_per_second_per_gpu": 5607.25,
+      "total_tokens": 23821321
+    },
+    {
+      "epoch": 2.0637450199203187,
+      "grad_norm": 1.15625,
+      "learning_rate": 5.162811128947602e-07,
+      "loss": 1.1191,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 130,
+      "tokens_per_second_per_gpu": 5781.65,
+      "total_tokens": 24009420
+    },
+    {
+      "epoch": 2.0796812749003983,
+      "grad_norm": 1.1015625,
+      "learning_rate": 5.000000000000002e-07,
+      "loss": 1.1104,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 131,
+      "tokens_per_second_per_gpu": 5505.55,
+      "total_tokens": 24189826
+    },
+    {
+      "epoch": 2.095617529880478,
+      "grad_norm": 1.1796875,
+      "learning_rate": 4.838937261924933e-07,
+      "loss": 1.1973,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 132,
+      "tokens_per_second_per_gpu": 5512.31,
+      "total_tokens": 24368779
+    },
+    {
+      "epoch": 2.1115537848605577,
+      "grad_norm": 1.1015625,
+      "learning_rate": 4.6796792348466353e-07,
+      "loss": 1.0444,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 133,
+      "tokens_per_second_per_gpu": 5465.08,
+      "total_tokens": 24556917
+    },
+    {
+      "epoch": 2.1274900398406373,
+      "grad_norm": 1.1015625,
+      "learning_rate": 4.522281607821288e-07,
+      "loss": 1.1206,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 134,
+      "tokens_per_second_per_gpu": 5419.8,
+      "total_tokens": 24738084
+    },
+    {
+      "epoch": 2.143426294820717,
+      "grad_norm": 1.03125,
+      "learning_rate": 4.366799419363779e-07,
+      "loss": 1.1143,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 135,
+      "tokens_per_second_per_gpu": 5539.41,
+      "total_tokens": 24922074
+    },
+    {
+      "epoch": 2.1593625498007967,
+      "grad_norm": 1.1328125,
+      "learning_rate": 4.2132870382019427e-07,
+      "loss": 1.1924,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 136,
+      "tokens_per_second_per_gpu": 5444.42,
+      "total_tokens": 25104099
+    },
+    {
+      "epoch": 2.1752988047808763,
+      "grad_norm": 1.1328125,
+      "learning_rate": 4.061798144264985e-07,
+      "loss": 1.1885,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 137,
+      "tokens_per_second_per_gpu": 5332.72,
+      "total_tokens": 25281595
+    },
+    {
+      "epoch": 2.191235059760956,
+      "grad_norm": 1.0703125,
+      "learning_rate": 3.912385709912793e-07,
+      "loss": 1.1318,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 138,
+      "tokens_per_second_per_gpu": 5857.46,
+      "total_tokens": 25468027
+    },
+    {
+      "epoch": 2.2071713147410357,
+      "grad_norm": 1.1015625,
+      "learning_rate": 3.765101981412665e-07,
+      "loss": 1.1328,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 139,
+      "tokens_per_second_per_gpu": 5613.35,
+      "total_tokens": 25654818
+    },
+    {
+      "epoch": 2.2231075697211153,
+      "grad_norm": 1.0390625,
+      "learning_rate": 3.6199984606699153e-07,
+      "loss": 1.0981,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 140,
+      "tokens_per_second_per_gpu": 5586.6,
+      "total_tokens": 25847854
+    },
+    {
+      "epoch": 2.239043824701195,
+      "grad_norm": 1.015625,
+      "learning_rate": 3.477125887218791e-07,
+      "loss": 1.105,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 141,
+      "tokens_per_second_per_gpu": 5723.95,
+      "total_tokens": 26037069
+    },
+    {
+      "epoch": 2.2549800796812747,
+      "grad_norm": 1.15625,
+      "learning_rate": 3.3365342204799606e-07,
+      "loss": 1.1416,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 142,
+      "tokens_per_second_per_gpu": 5609.66,
+      "total_tokens": 26221689
+    },
+    {
+      "epoch": 2.2709163346613543,
+      "grad_norm": 1.0703125,
+      "learning_rate": 3.198272622290804e-07,
+      "loss": 1.0625,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 143,
+      "tokens_per_second_per_gpu": 6065.87,
+      "total_tokens": 26415905
+    },
+    {
+      "epoch": 2.2868525896414345,
+      "grad_norm": 1.0703125,
+      "learning_rate": 3.0623894397145833e-07,
+      "loss": 1.123,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 144,
+      "tokens_per_second_per_gpu": 5513.26,
+      "total_tokens": 26598043
+    },
+    {
+      "epoch": 2.302788844621514,
+      "grad_norm": 1.078125,
+      "learning_rate": 2.9289321881345254e-07,
+      "loss": 1.103,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 145,
+      "tokens_per_second_per_gpu": 5505.93,
+      "total_tokens": 26781945
+    },
+    {
+      "epoch": 2.318725099601594,
+      "grad_norm": 1.140625,
+      "learning_rate": 2.797947534638736e-07,
+      "loss": 1.1348,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 146,
+      "tokens_per_second_per_gpu": 5529.92,
+      "total_tokens": 26964970
+    },
+    {
+      "epoch": 2.3346613545816735,
+      "grad_norm": 1.0234375,
+      "learning_rate": 2.6694812817017387e-07,
+      "loss": 1.0938,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 147,
+      "tokens_per_second_per_gpu": 5703.33,
+      "total_tokens": 27157832
+    },
+    {
+      "epoch": 2.350597609561753,
+      "grad_norm": 1.1640625,
+      "learning_rate": 2.543578351168344e-07,
+      "loss": 1.1045,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 148,
+      "tokens_per_second_per_gpu": 5833.69,
+      "total_tokens": 27339955
+    },
+    {
+      "epoch": 2.366533864541833,
+      "grad_norm": 1.03125,
+      "learning_rate": 2.4202827685454687e-07,
+      "loss": 1.0674,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 149,
+      "tokens_per_second_per_gpu": 5586.43,
+      "total_tokens": 27526672
+    },
+    {
+      "epoch": 2.3824701195219125,
+      "grad_norm": 1.03125,
+      "learning_rate": 2.299637647607372e-07,
+      "loss": 1.0728,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 150,
+      "tokens_per_second_per_gpu": 5369.71,
+      "total_tokens": 27713024
+    },
+    {
+      "epoch": 2.398406374501992,
+      "grad_norm": 1.1640625,
+      "learning_rate": 2.181685175319702e-07,
+      "loss": 1.1318,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 151,
+      "tokens_per_second_per_gpu": 5560.0,
+      "total_tokens": 27893662
+    },
+    {
+      "epoch": 2.414342629482072,
+      "grad_norm": 1.1015625,
+      "learning_rate": 2.0664665970876495e-07,
+      "loss": 1.1807,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 152,
+      "tokens_per_second_per_gpu": 5346.34,
+      "total_tokens": 28077998
+    },
+    {
+      "epoch": 2.4302788844621515,
+      "grad_norm": 1.078125,
+      "learning_rate": 1.9540222023333163e-07,
+      "loss": 1.1572,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 153,
+      "tokens_per_second_per_gpu": 5554.36,
+      "total_tokens": 28259288
+    },
+    {
+      "epoch": 2.446215139442231,
+      "grad_norm": 1.09375,
+      "learning_rate": 1.8443913104073982e-07,
+      "loss": 1.1807,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 154,
+      "tokens_per_second_per_gpu": 5321.03,
+      "total_tokens": 28435658
+    },
+    {
+      "epoch": 2.462151394422311,
+      "grad_norm": 1.1015625,
+      "learning_rate": 1.737612256840053e-07,
+      "loss": 1.127,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 155,
+      "tokens_per_second_per_gpu": 5503.74,
+      "total_tokens": 28617612
+    },
+    {
+      "epoch": 2.4780876494023905,
+      "grad_norm": 1.1640625,
+      "learning_rate": 1.6337223799358024e-07,
+      "loss": 1.1099,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 156,
+      "tokens_per_second_per_gpu": 5737.94,
+      "total_tokens": 28803434
+    },
+    {
+      "epoch": 2.49402390438247,
+      "grad_norm": 1.0859375,
+      "learning_rate": 1.5327580077171588e-07,
+      "loss": 1.1143,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 157,
+      "tokens_per_second_per_gpu": 5419.26,
+      "total_tokens": 28989353
+    },
+    {
+      "epoch": 2.50996015936255,
+      "grad_norm": 1.140625,
+      "learning_rate": 1.4347544452214867e-07,
+      "loss": 1.1216,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 158,
+      "tokens_per_second_per_gpu": 5564.03,
+      "total_tokens": 29170225
+    },
+    {
+      "epoch": 2.5258964143426295,
+      "grad_norm": 1.0703125,
+      "learning_rate": 1.3397459621556128e-07,
+      "loss": 1.1182,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 159,
+      "tokens_per_second_per_gpu": 5533.6,
+      "total_tokens": 29358629
+    },
+    {
+      "epoch": 2.541832669322709,
+      "grad_norm": 1.09375,
+      "learning_rate": 1.2477657809124632e-07,
+      "loss": 1.1895,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 160,
+      "tokens_per_second_per_gpu": 5801.01,
+      "total_tokens": 29545795
+    },
+    {
+      "epoch": 2.557768924302789,
+      "grad_norm": 1.09375,
+      "learning_rate": 1.1588460649539034e-07,
+      "loss": 1.1973,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 161,
+      "tokens_per_second_per_gpu": 5496.74,
+      "total_tokens": 29730822
+    },
+    {
+      "epoch": 2.5737051792828685,
+      "grad_norm": 1.1484375,
+      "learning_rate": 1.0730179075638868e-07,
+      "loss": 1.1611,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 162,
+      "tokens_per_second_per_gpu": 5661.86,
+      "total_tokens": 29908915
+    },
+    {
+      "epoch": 2.589641434262948,
+      "grad_norm": 1.078125,
+      "learning_rate": 9.903113209758096e-08,
+      "loss": 1.1709,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 163,
+      "tokens_per_second_per_gpu": 5334.67,
+      "total_tokens": 30093238
+    },
+    {
+      "epoch": 2.605577689243028,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.107552258778905e-08,
+      "loss": 1.1099,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 164,
+      "tokens_per_second_per_gpu": 5276.84,
+      "total_tokens": 30274843
+    },
+    {
+      "epoch": 2.6215139442231075,
+      "grad_norm": 1.046875,
+      "learning_rate": 8.34377441300238e-08,
+      "loss": 1.0933,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 165,
+      "tokens_per_second_per_gpu": 5920.44,
+      "total_tokens": 30464470
+    },
+    {
+      "epoch": 2.637450199203187,
+      "grad_norm": 1.1328125,
+      "learning_rate": 7.612046748871326e-08,
+      "loss": 1.1348,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 166,
+      "tokens_per_second_per_gpu": 5562.69,
+      "total_tokens": 30647284
+    },
+    {
+      "epoch": 2.653386454183267,
+      "grad_norm": 1.1328125,
+      "learning_rate": 6.912625135579586e-08,
+      "loss": 1.1553,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 167,
+      "tokens_per_second_per_gpu": 5381.44,
+      "total_tokens": 30825122
+    },
+    {
+      "epoch": 2.6693227091633465,
+      "grad_norm": 1.078125,
+      "learning_rate": 6.245754145600091e-08,
+      "loss": 1.126,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 168,
+      "tokens_per_second_per_gpu": 5392.77,
+      "total_tokens": 31008029
+    },
+    {
+      "epoch": 2.685258964143426,
+      "grad_norm": 1.03125,
+      "learning_rate": 5.611666969163242e-08,
+      "loss": 1.1025,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 169,
+      "tokens_per_second_per_gpu": 5636.12,
+      "total_tokens": 31197605
+    },
+    {
+      "epoch": 2.7011952191235062,
+      "grad_norm": 1.09375,
+      "learning_rate": 5.0105853327154004e-08,
+      "loss": 1.1572,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 170,
+      "tokens_per_second_per_gpu": 5442.72,
+      "total_tokens": 31382140
+    },
+    {
+      "epoch": 2.717131474103586,
+      "grad_norm": 1.0703125,
+      "learning_rate": 4.442719421385921e-08,
+      "loss": 1.1011,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 171,
+      "tokens_per_second_per_gpu": 5829.11,
+      "total_tokens": 31567345
+    },
+    {
+      "epoch": 2.7330677290836656,
+      "grad_norm": 1.078125,
+      "learning_rate": 3.908267805490051e-08,
+      "loss": 1.123,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 172,
+      "tokens_per_second_per_gpu": 5509.97,
+      "total_tokens": 31752125
+    },
+    {
+      "epoch": 2.7490039840637452,
+      "grad_norm": 1.1015625,
+      "learning_rate": 3.4074173710931796e-08,
+      "loss": 1.105,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 173,
+      "tokens_per_second_per_gpu": 5609.04,
+      "total_tokens": 31942908
+    },
+    {
+      "epoch": 2.764940239043825,
+      "grad_norm": 1.109375,
+      "learning_rate": 2.9403432546609043e-08,
+      "loss": 1.1533,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 174,
+      "tokens_per_second_per_gpu": 5753.07,
+      "total_tokens": 32129128
+    },
+    {
+      "epoch": 2.7808764940239046,
+      "grad_norm": 1.1328125,
+      "learning_rate": 2.507208781817638e-08,
+      "loss": 1.1074,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 175,
+      "tokens_per_second_per_gpu": 5763.07,
+      "total_tokens": 32313971
+    },
+    {
+      "epoch": 2.7968127490039842,
+      "grad_norm": 1.0625,
+      "learning_rate": 2.1081654102351632e-08,
+      "loss": 1.0635,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 176,
+      "tokens_per_second_per_gpu": 5200.76,
+      "total_tokens": 32510274
+    },
+    {
+      "epoch": 2.812749003984064,
+      "grad_norm": 1.078125,
+      "learning_rate": 1.7433526766711725e-08,
+      "loss": 1.0547,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 177,
+      "tokens_per_second_per_gpu": 5511.76,
+      "total_tokens": 32701180
+    },
+    {
+      "epoch": 2.8286852589641436,
+      "grad_norm": 1.0546875,
+      "learning_rate": 1.4128981481764113e-08,
+      "loss": 1.0728,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 178,
+      "tokens_per_second_per_gpu": 5453.23,
+      "total_tokens": 32887252
+    },
+    {
+      "epoch": 2.8446215139442232,
+      "grad_norm": 1.0,
+      "learning_rate": 1.1169173774871477e-08,
+      "loss": 1.0454,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 179,
+      "tokens_per_second_per_gpu": 5831.37,
+      "total_tokens": 33078886
+    },
+    {
+      "epoch": 2.860557768924303,
+      "grad_norm": 1.109375,
+      "learning_rate": 8.555138626189618e-09,
+      "loss": 1.1182,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 180,
+      "tokens_per_second_per_gpu": 5712.45,
+      "total_tokens": 33264882
+    },
+    {
+      "epoch": 2.8764940239043826,
+      "grad_norm": 1.09375,
+      "learning_rate": 6.2877901067573955e-09,
+      "loss": 1.1357,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 181,
+      "tokens_per_second_per_gpu": 5709.15,
+      "total_tokens": 33450597
+    },
+    {
+      "epoch": 2.8924302788844622,
+      "grad_norm": 1.1015625,
+      "learning_rate": 4.367921058866186e-09,
+      "loss": 1.085,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 182,
+      "tokens_per_second_per_gpu": 5923.67,
+      "total_tokens": 33636331
+    },
+    {
+      "epoch": 2.908366533864542,
+      "grad_norm": 1.0859375,
+      "learning_rate": 2.7962028188198706e-09,
+      "loss": 1.1416,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 183,
+      "tokens_per_second_per_gpu": 5643.13,
+      "total_tokens": 33828521
+    },
+    {
+      "epoch": 2.9243027888446216,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.5731849821833953e-09,
+      "loss": 1.1255,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 184,
+      "tokens_per_second_per_gpu": 5703.08,
+      "total_tokens": 34017506
+    },
+    {
+      "epoch": 2.9402390438247012,
+      "grad_norm": 1.1328125,
+      "learning_rate": 6.992952116013917e-10,
+      "loss": 1.1094,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 185,
+      "tokens_per_second_per_gpu": 5872.3,
+      "total_tokens": 34203052
+    },
+    {
+      "epoch": 2.956175298804781,
+      "grad_norm": 1.046875,
+      "learning_rate": 1.7483908725357543e-10,
+      "loss": 1.1221,
+      "memory/device_reserved (GiB)": 77.63,
+      "memory/max_active (GiB)": 65.77,
+      "memory/max_allocated (GiB)": 65.77,
+      "step": 186,
+      "tokens_per_second_per_gpu": 5556.53,
+      "total_tokens": 34389121
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 186,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 62,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.3756016575819284e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

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"
+}