Upload checkpoint from step 950

.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 +1,97 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\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' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = message.content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (message.content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = message.content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).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' }}
+        {{- message.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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.7.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 40960,
+  "pad_token_id": 151654,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.56.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66618bf4bbeaaca30667d66c41f1bf9de15d683abb76b9b570f3d72978d53a5f
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720f4e1c7a61e3f3e9e28cd9af16240ddc05d175796cb168f399a8c905938404
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4557a045047091576f9a50118b840f468ea683751f77f99403e05560f64ef7c
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ccc1251ffa293d41dd3e05d77bfce91fe96029fd6f5c21b87ddd39fb1c5cf72
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 8190735360,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f772b2bf68cfe8ae9a2c09ce475680ebd33f98e8d810baf70825ec4a668cf3e
+size 32763296520

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf18f7e8ee46120fc5618da558bfc6f30d047897e85a0c36d0c5004216d1b080
+size 1465

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "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": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,984 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.172316063938329,
+  "eval_steps": 500,
+  "global_step": 950,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.401060389354825,
+      "epoch": 0.0018138533046139895,
+      "grad_norm": 0.5078125,
+      "learning_rate": 4.999991783232007e-05,
+      "loss": 0.3909,
+      "mean_token_accuracy": 0.8833676137030124,
+      "num_tokens": 689094.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.35119859240949153,
+      "epoch": 0.003627706609227979,
+      "grad_norm": 0.3515625,
+      "learning_rate": 4.999963379658905e-05,
+      "loss": 0.3488,
+      "mean_token_accuracy": 0.8924659512937069,
+      "num_tokens": 1431066.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.330338497646153,
+      "epoch": 0.005441559913841968,
+      "grad_norm": 0.3359375,
+      "learning_rate": 4.999914688069563e-05,
+      "loss": 0.3263,
+      "mean_token_accuracy": 0.8976220838725567,
+      "num_tokens": 2149722.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.3173067133873701,
+      "epoch": 0.007255413218455958,
+      "grad_norm": 0.37109375,
+      "learning_rate": 4.9998457088591286e-05,
+      "loss": 0.3126,
+      "mean_token_accuracy": 0.900362791121006,
+      "num_tokens": 2839517.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.3035059319809079,
+      "epoch": 0.009069266523069946,
+      "grad_norm": 0.37890625,
+      "learning_rate": 4.999756442587392e-05,
+      "loss": 0.2985,
+      "mean_token_accuracy": 0.9043247863650322,
+      "num_tokens": 3562428.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.31549433059990406,
+      "epoch": 0.010883119827683935,
+      "grad_norm": 0.447265625,
+      "learning_rate": 4.999646889978778e-05,
+      "loss": 0.3119,
+      "mean_token_accuracy": 0.9018740214407444,
+      "num_tokens": 679264.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.3051564427092671,
+      "epoch": 0.012696973132297925,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.99951705192234e-05,
+      "loss": 0.3007,
+      "mean_token_accuracy": 0.9044437751173973,
+      "num_tokens": 1386187.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.29480861593037844,
+      "epoch": 0.014510826436911916,
+      "grad_norm": 0.35546875,
+      "learning_rate": 4.999366929471757e-05,
+      "loss": 0.2925,
+      "mean_token_accuracy": 0.9076969392597676,
+      "num_tokens": 2069407.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.29471962377429006,
+      "epoch": 0.016324679741525905,
+      "grad_norm": 0.392578125,
+      "learning_rate": 4.999196523845322e-05,
+      "loss": 0.2822,
+      "mean_token_accuracy": 0.9081305578351021,
+      "num_tokens": 2751799.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.2778853852301836,
+      "epoch": 0.018138533046139892,
+      "grad_norm": 0.390625,
+      "learning_rate": 4.9990058364259315e-05,
+      "loss": 0.2757,
+      "mean_token_accuracy": 0.9112294614315033,
+      "num_tokens": 3432327.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.2759243570268154,
+      "epoch": 0.019952386350753883,
+      "grad_norm": 0.33984375,
+      "learning_rate": 4.998794868761076e-05,
+      "loss": 0.2709,
+      "mean_token_accuracy": 0.9125727131962776,
+      "num_tokens": 4120004.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.2782453015446663,
+      "epoch": 0.02176623965536787,
+      "grad_norm": 0.3515625,
+      "learning_rate": 4.9985636225628276e-05,
+      "loss": 0.2707,
+      "mean_token_accuracy": 0.9114268697798252,
+      "num_tokens": 4818399.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.28113641776144505,
+      "epoch": 0.023580092959981862,
+      "grad_norm": 0.318359375,
+      "learning_rate": 4.998312099707823e-05,
+      "loss": 0.2816,
+      "mean_token_accuracy": 0.9110292144119739,
+      "num_tokens": 5530113.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.2701249118894339,
+      "epoch": 0.02539394626459585,
+      "grad_norm": 0.384765625,
+      "learning_rate": 4.998040302237253e-05,
+      "loss": 0.2633,
+      "mean_token_accuracy": 0.9143483161926269,
+      "num_tokens": 6202520.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.26040864232927563,
+      "epoch": 0.02720779956920984,
+      "grad_norm": 0.376953125,
+      "learning_rate": 4.997748232356841e-05,
+      "loss": 0.2595,
+      "mean_token_accuracy": 0.9160367086529732,
+      "num_tokens": 6897257.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.26147676482796667,
+      "epoch": 0.02902165287382383,
+      "grad_norm": 0.37890625,
+      "learning_rate": 4.997435892436832e-05,
+      "loss": 0.2607,
+      "mean_token_accuracy": 0.9158791072666645,
+      "num_tokens": 7596780.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.2591979356482625,
+      "epoch": 0.03083550617843782,
+      "grad_norm": 0.333984375,
+      "learning_rate": 4.997103285011964e-05,
+      "loss": 0.2498,
+      "mean_token_accuracy": 0.917728378623724,
+      "num_tokens": 8327856.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.262632866948843,
+      "epoch": 0.03264935948305181,
+      "grad_norm": 0.35546875,
+      "learning_rate": 4.996750412781454e-05,
+      "loss": 0.2615,
+      "mean_token_accuracy": 0.9157723136246204,
+      "num_tokens": 9035609.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.2631745539605618,
+      "epoch": 0.0344632127876658,
+      "grad_norm": 0.392578125,
+      "learning_rate": 4.996377278608977e-05,
+      "loss": 0.2632,
+      "mean_token_accuracy": 0.9168937481939793,
+      "num_tokens": 9761489.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.2691297778859735,
+      "epoch": 0.036277066092279785,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.995983885522636e-05,
+      "loss": 0.267,
+      "mean_token_accuracy": 0.9136621370911598,
+      "num_tokens": 10480790.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.2528717964887619,
+      "epoch": 0.038090919396893776,
+      "grad_norm": 0.3671875,
+      "learning_rate": 4.995570236714945e-05,
+      "loss": 0.2457,
+      "mean_token_accuracy": 0.9190806046128273,
+      "num_tokens": 11166729.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.25353531800210477,
+      "epoch": 0.03990477270150777,
+      "grad_norm": 0.48046875,
+      "learning_rate": 4.995136335542799e-05,
+      "loss": 0.2538,
+      "mean_token_accuracy": 0.9182398840785027,
+      "num_tokens": 11883461.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.2523710783571005,
+      "epoch": 0.04171862600612176,
+      "grad_norm": 0.380859375,
+      "learning_rate": 4.9946821855274475e-05,
+      "loss": 0.2471,
+      "mean_token_accuracy": 0.9204144366085529,
+      "num_tokens": 12586996.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.24951837193220855,
+      "epoch": 0.04353247931073574,
+      "grad_norm": 0.375,
+      "learning_rate": 4.994207790354464e-05,
+      "loss": 0.2439,
+      "mean_token_accuracy": 0.9190732814371586,
+      "num_tokens": 13294833.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.2435963459312916,
+      "epoch": 0.04534633261534973,
+      "grad_norm": 0.361328125,
+      "learning_rate": 4.993713153873721e-05,
+      "loss": 0.2387,
+      "mean_token_accuracy": 0.9220220901072025,
+      "num_tokens": 13964074.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.24172000139951705,
+      "epoch": 0.047160185919963724,
+      "grad_norm": 0.36328125,
+      "learning_rate": 4.9931982800993535e-05,
+      "loss": 0.2409,
+      "mean_token_accuracy": 0.9220294274389744,
+      "num_tokens": 14699210.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.24300440158694983,
+      "epoch": 0.048974039224577715,
+      "grad_norm": 0.3828125,
+      "learning_rate": 4.992663173209732e-05,
+      "loss": 0.2383,
+      "mean_token_accuracy": 0.9216976344585419,
+      "num_tokens": 15397171.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.23483966048806906,
+      "epoch": 0.0507878925291917,
+      "grad_norm": 0.412109375,
+      "learning_rate": 4.992107837547419e-05,
+      "loss": 0.2312,
+      "mean_token_accuracy": 0.9239355817437171,
+      "num_tokens": 16084594.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.22807897245511413,
+      "epoch": 0.05260174583380569,
+      "grad_norm": 0.4296875,
+      "learning_rate": 4.991532277619149e-05,
+      "loss": 0.225,
+      "mean_token_accuracy": 0.9266773730516433,
+      "num_tokens": 16814512.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.23185804225504397,
+      "epoch": 0.05441559913841968,
+      "grad_norm": 0.396484375,
+      "learning_rate": 4.9909364980957735e-05,
+      "loss": 0.227,
+      "mean_token_accuracy": 0.9256549589335918,
+      "num_tokens": 17530989.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.227366485260427,
+      "epoch": 0.05622945244303367,
+      "grad_norm": 0.392578125,
+      "learning_rate": 4.99032050381224e-05,
+      "loss": 0.2258,
+      "mean_token_accuracy": 0.9261060066521167,
+      "num_tokens": 18206500.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.2307612099684775,
+      "epoch": 0.05804330574764766,
+      "grad_norm": 0.369140625,
+      "learning_rate": 4.989684299767541e-05,
+      "loss": 0.2252,
+      "mean_token_accuracy": 0.9251494728028774,
+      "num_tokens": 18876031.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.23350342214107514,
+      "epoch": 0.059857159052261646,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.9890278911246805e-05,
+      "loss": 0.2307,
+      "mean_token_accuracy": 0.9253196962177753,
+      "num_tokens": 19628445.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.22912344289943576,
+      "epoch": 0.06167101235687564,
+      "grad_norm": 0.365234375,
+      "learning_rate": 4.9883512832106286e-05,
+      "loss": 0.2253,
+      "mean_token_accuracy": 0.926545312255621,
+      "num_tokens": 20323150.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.22221376914530994,
+      "epoch": 0.06348486566148963,
+      "grad_norm": 0.404296875,
+      "learning_rate": 4.987654481516276e-05,
+      "loss": 0.2179,
+      "mean_token_accuracy": 0.92796630859375,
+      "num_tokens": 21008346.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.220701056253165,
+      "epoch": 0.06529871896610362,
+      "grad_norm": 0.38671875,
+      "learning_rate": 4.9869374916963983e-05,
+      "loss": 0.2147,
+      "mean_token_accuracy": 0.9299234464764595,
+      "num_tokens": 21709970.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.2218360759317875,
+      "epoch": 0.06711257227071761,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.9862003195696e-05,
+      "loss": 0.2175,
+      "mean_token_accuracy": 0.9282336570322514,
+      "num_tokens": 22414407.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.21832106141373514,
+      "epoch": 0.0689264255753316,
+      "grad_norm": 0.388671875,
+      "learning_rate": 4.985442971118273e-05,
+      "loss": 0.2154,
+      "mean_token_accuracy": 0.9296296700835228,
+      "num_tokens": 23105526.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.22634686436504126,
+      "epoch": 0.07074027887994558,
+      "grad_norm": 0.41796875,
+      "learning_rate": 4.984665452488545e-05,
+      "loss": 0.2291,
+      "mean_token_accuracy": 0.9264358282089233,
+      "num_tokens": 23783734.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.21892870962619781,
+      "epoch": 0.07255413218455957,
+      "grad_norm": 0.361328125,
+      "learning_rate": 4.983867769990233e-05,
+      "loss": 0.2138,
+      "mean_token_accuracy": 0.929813839495182,
+      "num_tokens": 24499302.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.20870111417025328,
+      "epoch": 0.07436798548917356,
+      "grad_norm": 0.373046875,
+      "learning_rate": 4.9830499300967924e-05,
+      "loss": 0.2059,
+      "mean_token_accuracy": 0.9323622785508633,
+      "num_tokens": 25187005.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.2046168447472155,
+      "epoch": 0.07618183879378755,
+      "grad_norm": 0.35546875,
+      "learning_rate": 4.9822119394452575e-05,
+      "loss": 0.2022,
+      "mean_token_accuracy": 0.9341225482523441,
+      "num_tokens": 25894789.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.21055085053667427,
+      "epoch": 0.07799569209840154,
+      "grad_norm": 0.3984375,
+      "learning_rate": 4.981353804836196e-05,
+      "loss": 0.2088,
+      "mean_token_accuracy": 0.9323237225413322,
+      "num_tokens": 26605837.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.22691676011309028,
+      "epoch": 0.07980954540301553,
+      "grad_norm": 0.3828125,
+      "learning_rate": 4.98047553323365e-05,
+      "loss": 0.2232,
+      "mean_token_accuracy": 0.9282535433769226,
+      "num_tokens": 27306059.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.21169109037145972,
+      "epoch": 0.08162339870762952,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.979577131765079e-05,
+      "loss": 0.2094,
+      "mean_token_accuracy": 0.9311828054487705,
+      "num_tokens": 28027405.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.21191262369975447,
+      "epoch": 0.08343725201224352,
+      "grad_norm": 0.408203125,
+      "learning_rate": 4.978658607721301e-05,
+      "loss": 0.2076,
+      "mean_token_accuracy": 0.9319212548434734,
+      "num_tokens": 28717583.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.20386602552607655,
+      "epoch": 0.08525110531685749,
+      "grad_norm": 0.498046875,
+      "learning_rate": 4.977719968556441e-05,
+      "loss": 0.1973,
+      "mean_token_accuracy": 0.9341823615133762,
+      "num_tokens": 29415356.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.21132566928863525,
+      "epoch": 0.08706495862147148,
+      "grad_norm": 0.400390625,
+      "learning_rate": 4.976761221887859e-05,
+      "loss": 0.2095,
+      "mean_token_accuracy": 0.9307463005185127,
+      "num_tokens": 30130018.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.2104976624250412,
+      "epoch": 0.08887881192608547,
+      "grad_norm": 0.3359375,
+      "learning_rate": 4.975782375496098e-05,
+      "loss": 0.2057,
+      "mean_token_accuracy": 0.9317945875227451,
+      "num_tokens": 30871597.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.20463952338322997,
+      "epoch": 0.09069266523069947,
+      "grad_norm": 0.392578125,
+      "learning_rate": 4.974783437324812e-05,
+      "loss": 0.203,
+      "mean_token_accuracy": 0.934221388399601,
+      "num_tokens": 31571911.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.20768251903355123,
+      "epoch": 0.09250651853531346,
+      "grad_norm": 0.376953125,
+      "learning_rate": 4.9737644154807126e-05,
+      "loss": 0.2058,
+      "mean_token_accuracy": 0.9322210021317006,
+      "num_tokens": 32245409.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.20007140738889576,
+      "epoch": 0.09432037183992745,
+      "grad_norm": 0.3984375,
+      "learning_rate": 4.972725318233492e-05,
+      "loss": 0.1977,
+      "mean_token_accuracy": 0.9346926286816597,
+      "num_tokens": 32960743.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.20683543616905808,
+      "epoch": 0.09613422514454144,
+      "grad_norm": 0.376953125,
+      "learning_rate": 4.971666154015762e-05,
+      "loss": 0.2034,
+      "mean_token_accuracy": 0.9335305042564869,
+      "num_tokens": 33657841.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.2172858018428087,
+      "epoch": 0.09794807844915543,
+      "grad_norm": 0.451171875,
+      "learning_rate": 4.970586931422985e-05,
+      "loss": 0.2102,
+      "mean_token_accuracy": 0.9308790504932404,
+      "num_tokens": 34304617.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.19533313820138573,
+      "epoch": 0.09976193175376942,
+      "grad_norm": 0.443359375,
+      "learning_rate": 4.969487659213404e-05,
+      "loss": 0.1942,
+      "mean_token_accuracy": 0.9365381173789501,
+      "num_tokens": 35002676.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.19501794883981347,
+      "epoch": 0.1015757850583834,
+      "grad_norm": 0.396484375,
+      "learning_rate": 4.9683683463079716e-05,
+      "loss": 0.194,
+      "mean_token_accuracy": 0.9368167445063591,
+      "num_tokens": 35721130.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.19730768594890832,
+      "epoch": 0.10338963836299739,
+      "grad_norm": 0.4375,
+      "learning_rate": 4.967229001790275e-05,
+      "loss": 0.1912,
+      "mean_token_accuracy": 0.9373390160501003,
+      "num_tokens": 36452825.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.20269922027364373,
+      "epoch": 0.10520349166761138,
+      "grad_norm": 0.416015625,
+      "learning_rate": 4.966069634906465e-05,
+      "loss": 0.1976,
+      "mean_token_accuracy": 0.9344136849045753,
+      "num_tokens": 37150583.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.1830467650666833,
+      "epoch": 0.10701734497222537,
+      "grad_norm": 0.36328125,
+      "learning_rate": 4.964890255065182e-05,
+      "loss": 0.1813,
+      "mean_token_accuracy": 0.9408909261226654,
+      "num_tokens": 37856958.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.18502615857869387,
+      "epoch": 0.10883119827683936,
+      "grad_norm": 0.38671875,
+      "learning_rate": 4.9636908718374776e-05,
+      "loss": 0.1811,
+      "mean_token_accuracy": 0.9401354268193245,
+      "num_tokens": 38557749.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.17543947864323856,
+      "epoch": 0.11064505158145335,
+      "grad_norm": 0.3828125,
+      "learning_rate": 4.962471494956736e-05,
+      "loss": 0.1742,
+      "mean_token_accuracy": 0.9421761430799961,
+      "num_tokens": 39302134.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.18896188419312238,
+      "epoch": 0.11245890488606734,
+      "grad_norm": 0.376953125,
+      "learning_rate": 4.961232134318597e-05,
+      "loss": 0.1848,
+      "mean_token_accuracy": 0.9393556989729405,
+      "num_tokens": 40012713.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.19227341655641794,
+      "epoch": 0.11427275819068133,
+      "grad_norm": 0.408203125,
+      "learning_rate": 4.9599727999808776e-05,
+      "loss": 0.1813,
+      "mean_token_accuracy": 0.9380827076733113,
+      "num_tokens": 40728293.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.17786815362051128,
+      "epoch": 0.11608661149529532,
+      "grad_norm": 0.75,
+      "learning_rate": 4.9586935021634835e-05,
+      "loss": 0.1764,
+      "mean_token_accuracy": 0.9420537509024143,
+      "num_tokens": 41434153.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.18211883958429098,
+      "epoch": 0.1179004647999093,
+      "grad_norm": 0.412109375,
+      "learning_rate": 4.957394251248334e-05,
+      "loss": 0.1771,
+      "mean_token_accuracy": 0.9409064181149006,
+      "num_tokens": 42140372.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.1796271875500679,
+      "epoch": 0.11971431810452329,
+      "grad_norm": 0.41796875,
+      "learning_rate": 4.9560750577792715e-05,
+      "loss": 0.1747,
+      "mean_token_accuracy": 0.942291560024023,
+      "num_tokens": 42838039.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.17686794362962246,
+      "epoch": 0.12152817140913728,
+      "grad_norm": 0.388671875,
+      "learning_rate": 4.954735932461982e-05,
+      "loss": 0.1741,
+      "mean_token_accuracy": 0.942273823171854,
+      "num_tokens": 43550368.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.18043181113898754,
+      "epoch": 0.12334202471375127,
+      "grad_norm": 0.458984375,
+      "learning_rate": 4.9533768861639016e-05,
+      "loss": 0.1758,
+      "mean_token_accuracy": 0.9421767868101597,
+      "num_tokens": 44249323.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.17555835144594312,
+      "epoch": 0.12515587801836525,
+      "grad_norm": 0.453125,
+      "learning_rate": 4.951997929914135e-05,
+      "loss": 0.1712,
+      "mean_token_accuracy": 0.9432690389454365,
+      "num_tokens": 44934599.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.1881471230648458,
+      "epoch": 0.12696973132297926,
+      "grad_norm": 0.44921875,
+      "learning_rate": 4.9505990749033596e-05,
+      "loss": 0.1814,
+      "mean_token_accuracy": 0.9401827119290829,
+      "num_tokens": 45627988.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.1738990875892341,
+      "epoch": 0.12878358462759323,
+      "grad_norm": 0.396484375,
+      "learning_rate": 4.9491803324837394e-05,
+      "loss": 0.1669,
+      "mean_token_accuracy": 0.9448154501616954,
+      "num_tokens": 46344816.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.1657118304632604,
+      "epoch": 0.13059743793220724,
+      "grad_norm": 0.39453125,
+      "learning_rate": 4.94774171416883e-05,
+      "loss": 0.1635,
+      "mean_token_accuracy": 0.9460572391748429,
+      "num_tokens": 47031930.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.17199594508856536,
+      "epoch": 0.13241129123682122,
+      "grad_norm": 0.3828125,
+      "learning_rate": 4.946283231633488e-05,
+      "loss": 0.1677,
+      "mean_token_accuracy": 0.9447118684649467,
+      "num_tokens": 47700276.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.17147760968655348,
+      "epoch": 0.13422514454143522,
+      "grad_norm": 0.380859375,
+      "learning_rate": 4.944804896713773e-05,
+      "loss": 0.1699,
+      "mean_token_accuracy": 0.9442392319440842,
+      "num_tokens": 48399953.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.16508059948682785,
+      "epoch": 0.1360389978460492,
+      "grad_norm": 0.400390625,
+      "learning_rate": 4.943306721406854e-05,
+      "loss": 0.1605,
+      "mean_token_accuracy": 0.9466995656490326,
+      "num_tokens": 49117167.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.1752813272178173,
+      "epoch": 0.1378528511506632,
+      "grad_norm": 0.39453125,
+      "learning_rate": 4.941788717870912e-05,
+      "loss": 0.1733,
+      "mean_token_accuracy": 0.9437988288700581,
+      "num_tokens": 49824093.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.17272874722257256,
+      "epoch": 0.13966670445527718,
+      "grad_norm": 0.431640625,
+      "learning_rate": 4.940250898425039e-05,
+      "loss": 0.1678,
+      "mean_token_accuracy": 0.9446949861943722,
+      "num_tokens": 50511512.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.16612791642546654,
+      "epoch": 0.14148055775989116,
+      "grad_norm": 0.421875,
+      "learning_rate": 4.93869327554914e-05,
+      "loss": 0.1624,
+      "mean_token_accuracy": 0.9459903188049793,
+      "num_tokens": 51215026.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.16376803433522583,
+      "epoch": 0.14329441106450516,
+      "grad_norm": 0.369140625,
+      "learning_rate": 4.937115861883831e-05,
+      "loss": 0.1604,
+      "mean_token_accuracy": 0.9473146192729474,
+      "num_tokens": 51929249.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.1707521677017212,
+      "epoch": 0.14510826436911914,
+      "grad_norm": 0.359375,
+      "learning_rate": 4.935518670230339e-05,
+      "loss": 0.1664,
+      "mean_token_accuracy": 0.9445839419960975,
+      "num_tokens": 52626389.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.15680131250992418,
+      "epoch": 0.14692211767373314,
+      "grad_norm": 0.345703125,
+      "learning_rate": 4.933901713550391e-05,
+      "loss": 0.1565,
+      "mean_token_accuracy": 0.9488645300269127,
+      "num_tokens": 53324625.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.16342241717502476,
+      "epoch": 0.14873597097834712,
+      "grad_norm": 0.353515625,
+      "learning_rate": 4.932265004966119e-05,
+      "loss": 0.1582,
+      "mean_token_accuracy": 0.9477129466831684,
+      "num_tokens": 54022972.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.16008385811001064,
+      "epoch": 0.15054982428296113,
+      "grad_norm": 0.46484375,
+      "learning_rate": 4.930608557759945e-05,
+      "loss": 0.1552,
+      "mean_token_accuracy": 0.9485097445547581,
+      "num_tokens": 54705358.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.15298983799293636,
+      "epoch": 0.1523636775875751,
+      "grad_norm": 0.35546875,
+      "learning_rate": 4.928932385374477e-05,
+      "loss": 0.15,
+      "mean_token_accuracy": 0.9502383783459664,
+      "num_tokens": 55415741.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.16001109983772038,
+      "epoch": 0.1541775308921891,
+      "grad_norm": 0.39453125,
+      "learning_rate": 4.927236501412399e-05,
+      "loss": 0.1576,
+      "mean_token_accuracy": 0.9483717873692512,
+      "num_tokens": 56107468.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.15251143919304014,
+      "epoch": 0.15599138419680308,
+      "grad_norm": 0.3828125,
+      "learning_rate": 4.925520919636361e-05,
+      "loss": 0.1469,
+      "mean_token_accuracy": 0.9511617720127106,
+      "num_tokens": 56823057.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.1463920651935041,
+      "epoch": 0.15780523750141706,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.923785653968868e-05,
+      "loss": 0.1465,
+      "mean_token_accuracy": 0.9523930512368679,
+      "num_tokens": 57549593.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.1542105100117624,
+      "epoch": 0.15961909080603107,
+      "grad_norm": 0.388671875,
+      "learning_rate": 4.922030718492166e-05,
+      "loss": 0.1522,
+      "mean_token_accuracy": 0.9503716394305229,
+      "num_tokens": 58266995.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.16295539326965808,
+      "epoch": 0.16143294411064504,
+      "grad_norm": 0.36328125,
+      "learning_rate": 4.920256127448125e-05,
+      "loss": 0.1583,
+      "mean_token_accuracy": 0.9478306032717227,
+      "num_tokens": 58991460.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.16300919009372591,
+      "epoch": 0.16324679741525905,
+      "grad_norm": 0.39453125,
+      "learning_rate": 4.9184618952381314e-05,
+      "loss": 0.161,
+      "mean_token_accuracy": 0.9473481513559818,
+      "num_tokens": 59703569.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.1508354874327779,
+      "epoch": 0.16506065071987303,
+      "grad_norm": 0.357421875,
+      "learning_rate": 4.916648036422962e-05,
+      "loss": 0.1496,
+      "mean_token_accuracy": 0.9515601739287376,
+      "num_tokens": 60396836.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.14858688032254577,
+      "epoch": 0.16687450402448703,
+      "grad_norm": 0.36328125,
+      "learning_rate": 4.914814565722671e-05,
+      "loss": 0.1445,
+      "mean_token_accuracy": 0.9528601355850697,
+      "num_tokens": 61112387.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.15294391922652723,
+      "epoch": 0.168688357329101,
+      "grad_norm": 0.3828125,
+      "learning_rate": 4.91296149801647e-05,
+      "loss": 0.1515,
+      "mean_token_accuracy": 0.9504486098885536,
+      "num_tokens": 61840615.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.16582977958023548,
+      "epoch": 0.17050221063371498,
+      "grad_norm": 0.341796875,
+      "learning_rate": 4.9110888483426075e-05,
+      "loss": 0.1642,
+      "mean_token_accuracy": 0.948068980127573,
+      "num_tokens": 62517757.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.1455585315823555,
+      "epoch": 0.172316063938329,
+      "grad_norm": 0.337890625,
+      "learning_rate": 4.909196631898244e-05,
+      "loss": 0.1438,
+      "mean_token_accuracy": 0.9531501352787017,
+      "num_tokens": 63235939.0,
+      "step": 950
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 11028,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.033342770766072e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d3320605f3a81285438af587e983bfef181c74b93185545ccd0f1d943992a1e
+size 6225