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 +1,85 @@
+{%- 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 message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- 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>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- 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 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "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": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:239055f3b8c0ef203a0b3fe1697d5e7e8775d2cf0f396050e75a0d4bc478307c
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12b672ddee6182e38a9cf7b5fedc97478295ea368f59d9bbf877207fc06b0e9a
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 196096,
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

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": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,895 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2474,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.008085299914093689,
+      "grad_norm": 1.7893829836216715,
+      "learning_rate": 3.830645161290323e-06,
+      "loss": 0.4938,
+      "step": 20
+    },
+    {
+      "epoch": 0.016170599828187377,
+      "grad_norm": 1.544145448548272,
+      "learning_rate": 7.862903225806451e-06,
+      "loss": 0.4366,
+      "step": 40
+    },
+    {
+      "epoch": 0.024255899742281064,
+      "grad_norm": 1.5679306059971794,
+      "learning_rate": 1.1895161290322582e-05,
+      "loss": 0.4118,
+      "step": 60
+    },
+    {
+      "epoch": 0.032341199656374754,
+      "grad_norm": 1.395964355237053,
+      "learning_rate": 1.592741935483871e-05,
+      "loss": 0.4251,
+      "step": 80
+    },
+    {
+      "epoch": 0.04042649957046844,
+      "grad_norm": 1.3199581670369915,
+      "learning_rate": 1.995967741935484e-05,
+      "loss": 0.4003,
+      "step": 100
+    },
+    {
+      "epoch": 0.04851179948456213,
+      "grad_norm": 1.208480802915807,
+      "learning_rate": 2.3991935483870968e-05,
+      "loss": 0.4006,
+      "step": 120
+    },
+    {
+      "epoch": 0.05659709939865582,
+      "grad_norm": 1.1298545768045016,
+      "learning_rate": 2.8024193548387097e-05,
+      "loss": 0.4189,
+      "step": 140
+    },
+    {
+      "epoch": 0.06468239931274951,
+      "grad_norm": 1.1666261970423883,
+      "learning_rate": 3.205645161290323e-05,
+      "loss": 0.4503,
+      "step": 160
+    },
+    {
+      "epoch": 0.0727676992268432,
+      "grad_norm": 0.9707198547224671,
+      "learning_rate": 3.608870967741936e-05,
+      "loss": 0.4518,
+      "step": 180
+    },
+    {
+      "epoch": 0.08085299914093688,
+      "grad_norm": 0.9077078784165401,
+      "learning_rate": 4.0120967741935485e-05,
+      "loss": 0.4568,
+      "step": 200
+    },
+    {
+      "epoch": 0.08893829905503058,
+      "grad_norm": 1.1533412194423165,
+      "learning_rate": 4.415322580645162e-05,
+      "loss": 0.4513,
+      "step": 220
+    },
+    {
+      "epoch": 0.09702359896912426,
+      "grad_norm": 0.9729124530590224,
+      "learning_rate": 4.818548387096775e-05,
+      "loss": 0.4733,
+      "step": 240
+    },
+    {
+      "epoch": 0.10510889888321795,
+      "grad_norm": 0.8740160088683773,
+      "learning_rate": 4.999698743735772e-05,
+      "loss": 0.4758,
+      "step": 260
+    },
+    {
+      "epoch": 0.11319419879731164,
+      "grad_norm": 0.9664220859409508,
+      "learning_rate": 4.997607711513815e-05,
+      "loss": 0.4948,
+      "step": 280
+    },
+    {
+      "epoch": 0.12127949871140532,
+      "grad_norm": 0.9046563007004271,
+      "learning_rate": 4.99352690044939e-05,
+      "loss": 0.4909,
+      "step": 300
+    },
+    {
+      "epoch": 0.12936479862549902,
+      "grad_norm": 1.0102916306305423,
+      "learning_rate": 4.987459561618109e-05,
+      "loss": 0.4813,
+      "step": 320
+    },
+    {
+      "epoch": 0.1374500985395927,
+      "grad_norm": 0.7964130200362666,
+      "learning_rate": 4.979410528710377e-05,
+      "loss": 0.4657,
+      "step": 340
+    },
+    {
+      "epoch": 0.1455353984536864,
+      "grad_norm": 3.4749268002378666,
+      "learning_rate": 4.969386214180523e-05,
+      "loss": 0.4769,
+      "step": 360
+    },
+    {
+      "epoch": 0.15362069836778008,
+      "grad_norm": 0.9409849930897388,
+      "learning_rate": 4.957394604138165e-05,
+      "loss": 0.4611,
+      "step": 380
+    },
+    {
+      "epoch": 0.16170599828187376,
+      "grad_norm": 0.7527126720894318,
+      "learning_rate": 4.94344525198588e-05,
+      "loss": 0.4733,
+      "step": 400
+    },
+    {
+      "epoch": 0.16979129819596744,
+      "grad_norm": 0.9209239697756653,
+      "learning_rate": 4.9275492708082604e-05,
+      "loss": 0.4829,
+      "step": 420
+    },
+    {
+      "epoch": 0.17787659811006115,
+      "grad_norm": 0.9136833504109678,
+      "learning_rate": 4.909719324518412e-05,
+      "loss": 0.4751,
+      "step": 440
+    },
+    {
+      "epoch": 0.18596189802415483,
+      "grad_norm": 0.8981636505844758,
+      "learning_rate": 4.8899696177689404e-05,
+      "loss": 0.4874,
+      "step": 460
+    },
+    {
+      "epoch": 0.1940471979382485,
+      "grad_norm": 0.8300876947503312,
+      "learning_rate": 4.8683158846354786e-05,
+      "loss": 0.4618,
+      "step": 480
+    },
+    {
+      "epoch": 0.20213249785234222,
+      "grad_norm": 0.8242465855991236,
+      "learning_rate": 4.84477537608176e-05,
+      "loss": 0.4893,
+      "step": 500
+    },
+    {
+      "epoch": 0.2102177977664359,
+      "grad_norm": 0.800700567006772,
+      "learning_rate": 4.819366846216224e-05,
+      "loss": 0.4726,
+      "step": 520
+    },
+    {
+      "epoch": 0.21830309768052958,
+      "grad_norm": 0.779146282903641,
+      "learning_rate": 4.792110537351109e-05,
+      "loss": 0.468,
+      "step": 540
+    },
+    {
+      "epoch": 0.2263883975946233,
+      "grad_norm": 0.7743872804155105,
+      "learning_rate": 4.763028163875928e-05,
+      "loss": 0.4624,
+      "step": 560
+    },
+    {
+      "epoch": 0.23447369750871697,
+      "grad_norm": 1.288690581905525,
+      "learning_rate": 4.7321428949581885e-05,
+      "loss": 0.442,
+      "step": 580
+    },
+    {
+      "epoch": 0.24255899742281065,
+      "grad_norm": 0.7215163472877574,
+      "learning_rate": 4.699479336085113e-05,
+      "loss": 0.4782,
+      "step": 600
+    },
+    {
+      "epoch": 0.25064429733690435,
+      "grad_norm": 0.7069830331678881,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 0.4534,
+      "step": 620
+    },
+    {
+      "epoch": 0.25872959725099803,
+      "grad_norm": 0.8227398911837543,
+      "learning_rate": 4.6289228332764924e-05,
+      "loss": 0.4706,
+      "step": 640
+    },
+    {
+      "epoch": 0.2668148971650917,
+      "grad_norm": 0.80160540139322,
+      "learning_rate": 4.5910860998642566e-05,
+      "loss": 0.4784,
+      "step": 660
+    },
+    {
+      "epoch": 0.2749001970791854,
+      "grad_norm": 0.8392100792211208,
+      "learning_rate": 4.551583452761849e-05,
+      "loss": 0.4676,
+      "step": 680
+    },
+    {
+      "epoch": 0.2829854969932791,
+      "grad_norm": 1.3191462108675702,
+      "learning_rate": 4.510446362696664e-05,
+      "loss": 0.4679,
+      "step": 700
+    },
+    {
+      "epoch": 0.2910707969073728,
+      "grad_norm": 0.7565884365460607,
+      "learning_rate": 4.467707602514122e-05,
+      "loss": 0.4496,
+      "step": 720
+    },
+    {
+      "epoch": 0.2991560968214665,
+      "grad_norm": 0.7086008790878013,
+      "learning_rate": 4.4234012210684026e-05,
+      "loss": 0.4316,
+      "step": 740
+    },
+    {
+      "epoch": 0.30724139673556017,
+      "grad_norm": 0.699596566391461,
+      "learning_rate": 4.377562516096607e-05,
+      "loss": 0.4558,
+      "step": 760
+    },
+    {
+      "epoch": 0.31532669664965385,
+      "grad_norm": 1.0631183317034627,
+      "learning_rate": 4.330228006097979e-05,
+      "loss": 0.4497,
+      "step": 780
+    },
+    {
+      "epoch": 0.32341199656374753,
+      "grad_norm": 0.7860971712287887,
+      "learning_rate": 4.281435401240563e-05,
+      "loss": 0.473,
+      "step": 800
+    },
+    {
+      "epoch": 0.3314972964778412,
+      "grad_norm": 0.8091591439036853,
+      "learning_rate": 4.231223573318504e-05,
+      "loss": 0.4435,
+      "step": 820
+    },
+    {
+      "epoch": 0.3395825963919349,
+      "grad_norm": 0.6418471132042838,
+      "learning_rate": 4.179632524783899e-05,
+      "loss": 0.4605,
+      "step": 840
+    },
+    {
+      "epoch": 0.3476678963060286,
+      "grad_norm": 0.6675200504051455,
+      "learning_rate": 4.126703356877893e-05,
+      "loss": 0.4386,
+      "step": 860
+    },
+    {
+      "epoch": 0.3557531962201223,
+      "grad_norm": 0.8350300201126641,
+      "learning_rate": 4.072478236886392e-05,
+      "loss": 0.44,
+      "step": 880
+    },
+    {
+      "epoch": 0.363838496134216,
+      "grad_norm": 0.7065809423140008,
+      "learning_rate": 4.017000364546484e-05,
+      "loss": 0.4585,
+      "step": 900
+    },
+    {
+      "epoch": 0.37192379604830966,
+      "grad_norm": 0.7805666899810452,
+      "learning_rate": 3.96031393763034e-05,
+      "loss": 0.4333,
+      "step": 920
+    },
+    {
+      "epoch": 0.38000909596240334,
+      "grad_norm": 0.8177836753419291,
+      "learning_rate": 3.902464116734003e-05,
+      "loss": 0.4471,
+      "step": 940
+    },
+    {
+      "epoch": 0.388094395876497,
+      "grad_norm": 0.7575936626356954,
+      "learning_rate": 3.84349698929912e-05,
+      "loss": 0.4373,
+      "step": 960
+    },
+    {
+      "epoch": 0.39617969579059076,
+      "grad_norm": 0.7492067475736178,
+      "learning_rate": 3.7834595328962794e-05,
+      "loss": 0.4497,
+      "step": 980
+    },
+    {
+      "epoch": 0.40426499570468444,
+      "grad_norm": 0.7908131728874307,
+      "learning_rate": 3.72239957779921e-05,
+      "loss": 0.449,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4123502956187781,
+      "grad_norm": 0.6640701333672742,
+      "learning_rate": 3.6603657688796465e-05,
+      "loss": 0.4345,
+      "step": 1020
+    },
+    {
+      "epoch": 0.4204355955328718,
+      "grad_norm": 0.7662918750682771,
+      "learning_rate": 3.597407526853235e-05,
+      "loss": 0.4276,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4285208954469655,
+      "grad_norm": 0.7191116615450338,
+      "learning_rate": 3.533575008907338e-05,
+      "loss": 0.4291,
+      "step": 1060
+    },
+    {
+      "epoch": 0.43660619536105916,
+      "grad_norm": 0.6538640833264813,
+      "learning_rate": 3.468919068742113e-05,
+      "loss": 0.4271,
+      "step": 1080
+    },
+    {
+      "epoch": 0.44469149527515284,
+      "grad_norm": 0.84633760406372,
+      "learning_rate": 3.403491216056695e-05,
+      "loss": 0.441,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4527767951892466,
+      "grad_norm": 0.6956037005349539,
+      "learning_rate": 3.337343575512768e-05,
+      "loss": 0.433,
+      "step": 1120
+    },
+    {
+      "epoch": 0.46086209510334025,
+      "grad_norm": 0.6833758980525753,
+      "learning_rate": 3.270528845208207e-05,
+      "loss": 0.412,
+      "step": 1140
+    },
+    {
+      "epoch": 0.46894739501743393,
+      "grad_norm": 1.4679545429292338,
+      "learning_rate": 3.203100254693878e-05,
+      "loss": 0.4256,
+      "step": 1160
+    },
+    {
+      "epoch": 0.4770326949315276,
+      "grad_norm": 0.7006335987685887,
+      "learning_rate": 3.135111522567048e-05,
+      "loss": 0.4396,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4851179948456213,
+      "grad_norm": 0.7567851300681356,
+      "learning_rate": 3.0666168136751776e-05,
+      "loss": 0.4204,
+      "step": 1200
+    },
+    {
+      "epoch": 0.49320329475971497,
+      "grad_norm": 0.7039630629968385,
+      "learning_rate": 2.997670695964204e-05,
+      "loss": 0.4149,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5012885946738087,
+      "grad_norm": 0.6801686276783195,
+      "learning_rate": 2.9283280970056826e-05,
+      "loss": 0.4213,
+      "step": 1240
+    },
+    {
+      "epoch": 0.5093738945879024,
+      "grad_norm": 0.5702376498270392,
+      "learning_rate": 2.8586442602374246e-05,
+      "loss": 0.4107,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5174591945019961,
+      "grad_norm": 0.5903215734392792,
+      "learning_rate": 2.788674700952495e-05,
+      "loss": 0.426,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5255444944160897,
+      "grad_norm": 0.7072289573693732,
+      "learning_rate": 2.7184751620716254e-05,
+      "loss": 0.4166,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5336297943301834,
+      "grad_norm": 0.7528995772779531,
+      "learning_rate": 2.648101569734286e-05,
+      "loss": 0.4088,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5417150942442771,
+      "grad_norm": 0.7990855433501134,
+      "learning_rate": 2.5776099887437906e-05,
+      "loss": 0.4167,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5498003941583708,
+      "grad_norm": 0.6292477887263497,
+      "learning_rate": 2.5070565779019316e-05,
+      "loss": 0.422,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5578856940724645,
+      "grad_norm": 0.7554555570744919,
+      "learning_rate": 2.43649754526873e-05,
+      "loss": 0.4155,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5659709939865581,
+      "grad_norm": 0.7699820762080785,
+      "learning_rate": 2.365989103382942e-05,
+      "loss": 0.4286,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5740562939006518,
+      "grad_norm": 0.7266763971520528,
+      "learning_rate": 2.2955874244789934e-05,
+      "loss": 0.4158,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5821415938147456,
+      "grad_norm": 0.7740051062605608,
+      "learning_rate": 2.2253485957360336e-05,
+      "loss": 0.4223,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5902268937288393,
+      "grad_norm": 0.6515042328015387,
+      "learning_rate": 2.1553285745947393e-05,
+      "loss": 0.4032,
+      "step": 1460
+    },
+    {
+      "epoch": 0.598312193642933,
+      "grad_norm": 0.6585346292648555,
+      "learning_rate": 2.0855831441774858e-05,
+      "loss": 0.4097,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6063974935570267,
+      "grad_norm": 0.7026076918363772,
+      "learning_rate": 2.0161678688473902e-05,
+      "loss": 0.4102,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6144827934711203,
+      "grad_norm": 0.6988836739982369,
+      "learning_rate": 1.947138049941629e-05,
+      "loss": 0.4144,
+      "step": 1520
+    },
+    {
+      "epoch": 0.622568093385214,
+      "grad_norm": 0.7005776385652717,
+      "learning_rate": 1.878548681714317e-05,
+      "loss": 0.412,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6306533932993077,
+      "grad_norm": 0.6745885622939958,
+      "learning_rate": 1.8104544075240086e-05,
+      "loss": 0.4038,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6387386932134014,
+      "grad_norm": 0.6945027772851639,
+      "learning_rate": 1.742909476300773e-05,
+      "loss": 0.392,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6468239931274951,
+      "grad_norm": 0.7034384881922375,
+      "learning_rate": 1.6759676993274804e-05,
+      "loss": 0.4212,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6549092930415887,
+      "grad_norm": 0.7064404152869979,
+      "learning_rate": 1.609682407369761e-05,
+      "loss": 0.3931,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6629945929556824,
+      "grad_norm": 0.6741314936898479,
+      "learning_rate": 1.5441064081887762e-05,
+      "loss": 0.412,
+      "step": 1640
+    },
+    {
+      "epoch": 0.6710798928697761,
+      "grad_norm": 0.6489494957365249,
+      "learning_rate": 1.4792919444706531e-05,
+      "loss": 0.3977,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6791651927838698,
+      "grad_norm": 0.6239148906365745,
+      "learning_rate": 1.4152906522061048e-05,
+      "loss": 0.3925,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6872504926979636,
+      "grad_norm": 0.6758196156693772,
+      "learning_rate": 1.3521535195533797e-05,
+      "loss": 0.401,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6953357926120572,
+      "grad_norm": 0.6670657379068383,
+      "learning_rate": 1.2899308462173293e-05,
+      "loss": 0.3964,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7034210925261509,
+      "grad_norm": 0.7080774192825836,
+      "learning_rate": 1.2286722033769493e-05,
+      "loss": 0.3872,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7115063924402446,
+      "grad_norm": 0.78706482596111,
+      "learning_rate": 1.1684263941933116e-05,
+      "loss": 0.3999,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7195916923543383,
+      "grad_norm": 0.6453268176626914,
+      "learning_rate": 1.109241414929365e-05,
+      "loss": 0.3839,
+      "step": 1780
+    },
+    {
+      "epoch": 0.727676992268432,
+      "grad_norm": 0.7743809381350635,
+      "learning_rate": 1.0511644167125611e-05,
+      "loss": 0.403,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7357622921825256,
+      "grad_norm": 0.5812286294961497,
+      "learning_rate": 9.94241667970785e-06,
+      "loss": 0.4051,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7438475920966193,
+      "grad_norm": 0.6627529924806566,
+      "learning_rate": 9.385185175715067e-06,
+      "loss": 0.3878,
+      "step": 1840
+    },
+    {
+      "epoch": 0.751932892010713,
+      "grad_norm": 0.5787935835133774,
+      "learning_rate": 8.840393586935228e-06,
+      "loss": 0.3879,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7600181919248067,
+      "grad_norm": 0.5575588303157542,
+      "learning_rate": 8.30847593460069e-06,
+      "loss": 0.3799,
+      "step": 1880
+    },
+    {
+      "epoch": 0.7681034918389004,
+      "grad_norm": 0.6937350938930752,
+      "learning_rate": 7.789855983614826e-06,
+      "loss": 0.3981,
+      "step": 1900
+    },
+    {
+      "epoch": 0.776188791752994,
+      "grad_norm": 0.6705779864961804,
+      "learning_rate": 7.2849469049496216e-06,
+      "loss": 0.3982,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7842740916670877,
+      "grad_norm": 0.6247131470946646,
+      "learning_rate": 6.794150946483091e-06,
+      "loss": 0.3894,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7923593915811815,
+      "grad_norm": 0.7527011970876276,
+      "learning_rate": 6.317859112538943e-06,
+      "loss": 0.3933,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8004446914952752,
+      "grad_norm": 0.70959890519849,
+      "learning_rate": 5.856450852383627e-06,
+      "loss": 0.4001,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8085299914093689,
+      "grad_norm": 0.7637107619681417,
+      "learning_rate": 5.410293757929027e-06,
+      "loss": 0.3825,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8166152913234626,
+      "grad_norm": 0.6687923533892048,
+      "learning_rate": 4.979743270881559e-06,
+      "loss": 0.4063,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8247005912375562,
+      "grad_norm": 0.6751152707749739,
+      "learning_rate": 4.56514239957109e-06,
+      "loss": 0.4046,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8327858911516499,
+      "grad_norm": 0.6861920430003902,
+      "learning_rate": 4.166821445685087e-06,
+      "loss": 0.3964,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8408711910657436,
+      "grad_norm": 0.6621186149402191,
+      "learning_rate": 3.7850977411259705e-06,
+      "loss": 0.3753,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8489564909798373,
+      "grad_norm": 0.6470208514078205,
+      "learning_rate": 3.420275395201014e-06,
+      "loss": 0.3818,
+      "step": 2100
+    },
+    {
+      "epoch": 0.857041790893931,
+      "grad_norm": 0.6610917416320168,
+      "learning_rate": 3.0726450523464208e-06,
+      "loss": 0.3844,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8651270908080246,
+      "grad_norm": 0.6756461162410473,
+      "learning_rate": 2.74248366057851e-06,
+      "loss": 0.3757,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8732123907221183,
+      "grad_norm": 0.6961821177637604,
+      "learning_rate": 2.430054250856412e-06,
+      "loss": 0.3803,
+      "step": 2160
+    },
+    {
+      "epoch": 0.881297690636212,
+      "grad_norm": 0.7418320454835176,
+      "learning_rate": 2.1356057275322417e-06,
+      "loss": 0.3869,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8893829905503057,
+      "grad_norm": 0.6584153523981158,
+      "learning_rate": 1.8593726700554342e-06,
+      "loss": 0.3806,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8974682904643995,
+      "grad_norm": 0.6627761573934713,
+      "learning_rate": 1.6015751460894762e-06,
+      "loss": 0.399,
+      "step": 2220
+    },
+    {
+      "epoch": 0.9055535903784931,
+      "grad_norm": 0.5659307004910596,
+      "learning_rate": 1.3624185361897135e-06,
+      "loss": 0.3806,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9136388902925868,
+      "grad_norm": 0.6155894884801492,
+      "learning_rate": 1.1420933701820347e-06,
+      "loss": 0.3897,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9217241902066805,
+      "grad_norm": 0.5448653880194827,
+      "learning_rate": 9.407751753727323e-07,
+      "loss": 0.4017,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9298094901207742,
+      "grad_norm": 0.6080654098190524,
+      "learning_rate": 7.586243367104894e-07,
+      "loss": 0.3767,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9378947900348679,
+      "grad_norm": 0.7569388927738113,
+      "learning_rate": 5.95785969011875e-07,
+      "loss": 0.3919,
+      "step": 2320
+    },
+    {
+      "epoch": 0.9459800899489615,
+      "grad_norm": 0.9500614354033146,
+      "learning_rate": 4.52389801352146e-07,
+      "loss": 0.3918,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9540653898630552,
+      "grad_norm": 0.6408282025966349,
+      "learning_rate": 3.285500737135072e-07,
+      "loss": 0.3778,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9621506897771489,
+      "grad_norm": 0.7007941767466861,
+      "learning_rate": 2.2436544597307652e-07,
+      "loss": 0.3788,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9702359896912426,
+      "grad_norm": 0.6363318157541741,
+      "learning_rate": 1.399189193031475e-07,
+      "loss": 0.383,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9783212896053363,
+      "grad_norm": 0.6023554877318151,
+      "learning_rate": 7.527777004632253e-08,
+      "loss": 0.3832,
+      "step": 2420
+    },
+    {
+      "epoch": 0.9864065895194299,
+      "grad_norm": 0.7881624086353561,
+      "learning_rate": 3.049349611820851e-08,
+      "loss": 0.3751,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9944918894335236,
+      "grad_norm": 0.6497592434119226,
+      "learning_rate": 5.601775980371149e-09,
+      "loss": 0.3836,
+      "step": 2460
+    }
+  ],
+  "logging_steps": 20,
+  "max_steps": 2474,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 600,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 40816993337344.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf4acec142521cc1c0359ac88d9d0888f2f8999cbccfa04cd12baf54224d7462
+size 8145