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 +1,86 @@
+{%- 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 message.content is string 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.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,31 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151644,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151645,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 151644,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "pad_token_id": 151643,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f51fe92bc7b81e824d154bd8ba41c75f5b2979903fd4913e82634ab1df80bd
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7a2859705f97a655832e7c289c8cca468d46a3bd7d3473c354a5d6f5edace96
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "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 +1,20 @@
+{
+  "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": "<|im_start|>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "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": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1282 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 177,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01694915254237288,
+      "grad_norm": 11.399982724065612,
+      "learning_rate": 0.0,
+      "loss": 0.5723,
+      "step": 1
+    },
+    {
+      "epoch": 0.03389830508474576,
+      "grad_norm": 15.996953522086482,
+      "learning_rate": 6.25e-07,
+      "loss": 0.6919,
+      "step": 2
+    },
+    {
+      "epoch": 0.05084745762711865,
+      "grad_norm": 12.017237167498154,
+      "learning_rate": 1.25e-06,
+      "loss": 0.5464,
+      "step": 3
+    },
+    {
+      "epoch": 0.06779661016949153,
+      "grad_norm": 9.524531515096024,
+      "learning_rate": 1.8750000000000003e-06,
+      "loss": 0.4571,
+      "step": 4
+    },
+    {
+      "epoch": 0.0847457627118644,
+      "grad_norm": 10.11840992474023,
+      "learning_rate": 2.5e-06,
+      "loss": 0.512,
+      "step": 5
+    },
+    {
+      "epoch": 0.1016949152542373,
+      "grad_norm": 8.291307792118173,
+      "learning_rate": 3.125e-06,
+      "loss": 0.4744,
+      "step": 6
+    },
+    {
+      "epoch": 0.11864406779661017,
+      "grad_norm": 4.947811089030161,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.4064,
+      "step": 7
+    },
+    {
+      "epoch": 0.13559322033898305,
+      "grad_norm": 3.957348877914598,
+      "learning_rate": 4.3750000000000005e-06,
+      "loss": 0.4147,
+      "step": 8
+    },
+    {
+      "epoch": 0.15254237288135594,
+      "grad_norm": 1.878974520193955,
+      "learning_rate": 5e-06,
+      "loss": 0.3625,
+      "step": 9
+    },
+    {
+      "epoch": 0.1694915254237288,
+      "grad_norm": 1.685893632116404,
+      "learning_rate": 4.999568059583401e-06,
+      "loss": 0.3652,
+      "step": 10
+    },
+    {
+      "epoch": 0.1864406779661017,
+      "grad_norm": 0.8038396125458356,
+      "learning_rate": 4.998272387591625e-06,
+      "loss": 0.2205,
+      "step": 11
+    },
+    {
+      "epoch": 0.2033898305084746,
+      "grad_norm": 1.1469245810216282,
+      "learning_rate": 4.99611343174715e-06,
+      "loss": 0.3542,
+      "step": 12
+    },
+    {
+      "epoch": 0.22033898305084745,
+      "grad_norm": 1.1786630363061648,
+      "learning_rate": 4.993091938082206e-06,
+      "loss": 0.3458,
+      "step": 13
+    },
+    {
+      "epoch": 0.23728813559322035,
+      "grad_norm": 1.1958089208385483,
+      "learning_rate": 4.989208950680979e-06,
+      "loss": 0.3565,
+      "step": 14
+    },
+    {
+      "epoch": 0.2542372881355932,
+      "grad_norm": 0.9163324740544867,
+      "learning_rate": 4.984465811318826e-06,
+      "loss": 0.3015,
+      "step": 15
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 0.7719232841825565,
+      "learning_rate": 4.97886415899862e-06,
+      "loss": 0.3175,
+      "step": 16
+    },
+    {
+      "epoch": 0.288135593220339,
+      "grad_norm": 0.7319081785361947,
+      "learning_rate": 4.972405929384391e-06,
+      "loss": 0.3195,
+      "step": 17
+    },
+    {
+      "epoch": 0.3050847457627119,
+      "grad_norm": 0.7002551472674452,
+      "learning_rate": 4.965093354132451e-06,
+      "loss": 0.3074,
+      "step": 18
+    },
+    {
+      "epoch": 0.3220338983050847,
+      "grad_norm": 0.6366390198837392,
+      "learning_rate": 4.9569289601202405e-06,
+      "loss": 0.287,
+      "step": 19
+    },
+    {
+      "epoch": 0.3389830508474576,
+      "grad_norm": 0.48511268745049707,
+      "learning_rate": 4.9479155685731595e-06,
+      "loss": 0.2634,
+      "step": 20
+    },
+    {
+      "epoch": 0.3559322033898305,
+      "grad_norm": 0.5725593300080952,
+      "learning_rate": 4.938056294089689e-06,
+      "loss": 0.2718,
+      "step": 21
+    },
+    {
+      "epoch": 0.3728813559322034,
+      "grad_norm": 0.5881100232575105,
+      "learning_rate": 4.927354543565131e-06,
+      "loss": 0.2813,
+      "step": 22
+    },
+    {
+      "epoch": 0.3898305084745763,
+      "grad_norm": 0.6954472249924972,
+      "learning_rate": 4.915814015014349e-06,
+      "loss": 0.2829,
+      "step": 23
+    },
+    {
+      "epoch": 0.4067796610169492,
+      "grad_norm": 1.7773763839304515,
+      "learning_rate": 4.90343869629391e-06,
+      "loss": 0.2961,
+      "step": 24
+    },
+    {
+      "epoch": 0.423728813559322,
+      "grad_norm": 0.7136095313835628,
+      "learning_rate": 4.890232863724075e-06,
+      "loss": 0.314,
+      "step": 25
+    },
+    {
+      "epoch": 0.4406779661016949,
+      "grad_norm": 0.5965674482281343,
+      "learning_rate": 4.8762010806111e-06,
+      "loss": 0.305,
+      "step": 26
+    },
+    {
+      "epoch": 0.4576271186440678,
+      "grad_norm": 0.5426262579836809,
+      "learning_rate": 4.861348195670381e-06,
+      "loss": 0.2904,
+      "step": 27
+    },
+    {
+      "epoch": 0.4745762711864407,
+      "grad_norm": 0.6232000750718879,
+      "learning_rate": 4.845679341350963e-06,
+      "loss": 0.3194,
+      "step": 28
+    },
+    {
+      "epoch": 0.4915254237288136,
+      "grad_norm": 0.5521136750290783,
+      "learning_rate": 4.8291999320620185e-06,
+      "loss": 0.3016,
+      "step": 29
+    },
+    {
+      "epoch": 0.5084745762711864,
+      "grad_norm": 0.5746062885940153,
+      "learning_rate": 4.811915662301877e-06,
+      "loss": 0.2648,
+      "step": 30
+    },
+    {
+      "epoch": 0.5254237288135594,
+      "grad_norm": 0.607102290977902,
+      "learning_rate": 4.793832504690283e-06,
+      "loss": 0.299,
+      "step": 31
+    },
+    {
+      "epoch": 0.5423728813559322,
+      "grad_norm": 0.49962250759355686,
+      "learning_rate": 4.774956707904542e-06,
+      "loss": 0.2515,
+      "step": 32
+    },
+    {
+      "epoch": 0.559322033898305,
+      "grad_norm": 0.4701577356569123,
+      "learning_rate": 4.755294794520277e-06,
+      "loss": 0.2491,
+      "step": 33
+    },
+    {
+      "epoch": 0.576271186440678,
+      "grad_norm": 0.7858423854608445,
+      "learning_rate": 4.734853558757534e-06,
+      "loss": 0.2827,
+      "step": 34
+    },
+    {
+      "epoch": 0.5932203389830508,
+      "grad_norm": 0.49539465146154066,
+      "learning_rate": 4.7136400641330245e-06,
+      "loss": 0.2844,
+      "step": 35
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "grad_norm": 0.4775787849669313,
+      "learning_rate": 4.691661641019316e-06,
+      "loss": 0.2587,
+      "step": 36
+    },
+    {
+      "epoch": 0.6271186440677966,
+      "grad_norm": 0.6390518183116327,
+      "learning_rate": 4.6689258841117946e-06,
+      "loss": 0.2926,
+      "step": 37
+    },
+    {
+      "epoch": 0.6440677966101694,
+      "grad_norm": 0.5314073848549145,
+      "learning_rate": 4.64544064980431e-06,
+      "loss": 0.2485,
+      "step": 38
+    },
+    {
+      "epoch": 0.6610169491525424,
+      "grad_norm": 0.4020113800366879,
+      "learning_rate": 4.621214053474374e-06,
+      "loss": 0.2132,
+      "step": 39
+    },
+    {
+      "epoch": 0.6779661016949152,
+      "grad_norm": 0.5353215315551882,
+      "learning_rate": 4.596254466678877e-06,
+      "loss": 0.2788,
+      "step": 40
+    },
+    {
+      "epoch": 0.6949152542372882,
+      "grad_norm": 0.4769490074416754,
+      "learning_rate": 4.570570514261272e-06,
+      "loss": 0.2703,
+      "step": 41
+    },
+    {
+      "epoch": 0.711864406779661,
+      "grad_norm": 0.5249549778546513,
+      "learning_rate": 4.544171071371246e-06,
+      "loss": 0.2701,
+      "step": 42
+    },
+    {
+      "epoch": 0.7288135593220338,
+      "grad_norm": 0.5163626189073403,
+      "learning_rate": 4.517065260397887e-06,
+      "loss": 0.2864,
+      "step": 43
+    },
+    {
+      "epoch": 0.7457627118644068,
+      "grad_norm": 0.5413634640003411,
+      "learning_rate": 4.489262447817421e-06,
+      "loss": 0.2568,
+      "step": 44
+    },
+    {
+      "epoch": 0.7627118644067796,
+      "grad_norm": 0.5149640991984162,
+      "learning_rate": 4.460772240956609e-06,
+      "loss": 0.2525,
+      "step": 45
+    },
+    {
+      "epoch": 0.7796610169491526,
+      "grad_norm": 0.445354494671823,
+      "learning_rate": 4.431604484672905e-06,
+      "loss": 0.2172,
+      "step": 46
+    },
+    {
+      "epoch": 0.7966101694915254,
+      "grad_norm": 0.5009716150531464,
+      "learning_rate": 4.401769257952551e-06,
+      "loss": 0.2624,
+      "step": 47
+    },
+    {
+      "epoch": 0.8135593220338984,
+      "grad_norm": 0.5140310721121815,
+      "learning_rate": 4.3712768704277535e-06,
+      "loss": 0.2781,
+      "step": 48
+    },
+    {
+      "epoch": 0.8305084745762712,
+      "grad_norm": 0.5467147233990847,
+      "learning_rate": 4.340137858814168e-06,
+      "loss": 0.244,
+      "step": 49
+    },
+    {
+      "epoch": 0.847457627118644,
+      "grad_norm": 0.4862542975816897,
+      "learning_rate": 4.308362983269916e-06,
+      "loss": 0.226,
+      "step": 50
+    },
+    {
+      "epoch": 0.864406779661017,
+      "grad_norm": 0.5701344768833954,
+      "learning_rate": 4.275963223677379e-06,
+      "loss": 0.3184,
+      "step": 51
+    },
+    {
+      "epoch": 0.8813559322033898,
+      "grad_norm": 0.5680722480199585,
+      "learning_rate": 4.242949775849083e-06,
+      "loss": 0.2723,
+      "step": 52
+    },
+    {
+      "epoch": 0.8983050847457628,
+      "grad_norm": 0.6081264789001348,
+      "learning_rate": 4.209334047658956e-06,
+      "loss": 0.2686,
+      "step": 53
+    },
+    {
+      "epoch": 0.9152542372881356,
+      "grad_norm": 0.46308625878084975,
+      "learning_rate": 4.175127655100306e-06,
+      "loss": 0.2763,
+      "step": 54
+    },
+    {
+      "epoch": 0.9322033898305084,
+      "grad_norm": 0.41899355255330367,
+      "learning_rate": 4.140342418271897e-06,
+      "loss": 0.2555,
+      "step": 55
+    },
+    {
+      "epoch": 0.9491525423728814,
+      "grad_norm": 0.5677964936366232,
+      "learning_rate": 4.104990357293478e-06,
+      "loss": 0.2808,
+      "step": 56
+    },
+    {
+      "epoch": 0.9661016949152542,
+      "grad_norm": 0.5450969329455534,
+      "learning_rate": 4.069083688152206e-06,
+      "loss": 0.2464,
+      "step": 57
+    },
+    {
+      "epoch": 0.9830508474576272,
+      "grad_norm": 0.49742989815197775,
+      "learning_rate": 4.032634818481382e-06,
+      "loss": 0.2435,
+      "step": 58
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.47791981816360296,
+      "learning_rate": 3.995656343272969e-06,
+      "loss": 0.2431,
+      "step": 59
+    },
+    {
+      "epoch": 1.0169491525423728,
+      "grad_norm": 0.5336552382444577,
+      "learning_rate": 3.958161040525354e-06,
+      "loss": 0.2608,
+      "step": 60
+    },
+    {
+      "epoch": 1.0338983050847457,
+      "grad_norm": 0.6255845843539747,
+      "learning_rate": 3.92016186682789e-06,
+      "loss": 0.2718,
+      "step": 61
+    },
+    {
+      "epoch": 1.0508474576271187,
+      "grad_norm": 0.5386071690484918,
+      "learning_rate": 3.88167195288371e-06,
+      "loss": 0.2472,
+      "step": 62
+    },
+    {
+      "epoch": 1.0677966101694916,
+      "grad_norm": 0.4610208030538615,
+      "learning_rate": 3.842704598972384e-06,
+      "loss": 0.2711,
+      "step": 63
+    },
+    {
+      "epoch": 1.0847457627118644,
+      "grad_norm": 0.5005083514691049,
+      "learning_rate": 3.80327327035398e-06,
+      "loss": 0.243,
+      "step": 64
+    },
+    {
+      "epoch": 1.1016949152542372,
+      "grad_norm": 0.5256738643041071,
+      "learning_rate": 3.763391592616104e-06,
+      "loss": 0.2304,
+      "step": 65
+    },
+    {
+      "epoch": 1.11864406779661,
+      "grad_norm": 0.4461147519625525,
+      "learning_rate": 3.7230733469655554e-06,
+      "loss": 0.257,
+      "step": 66
+    },
+    {
+      "epoch": 1.1355932203389831,
+      "grad_norm": 0.5616719506601695,
+      "learning_rate": 3.6823324654661923e-06,
+      "loss": 0.2695,
+      "step": 67
+    },
+    {
+      "epoch": 1.152542372881356,
+      "grad_norm": 0.5267858101125528,
+      "learning_rate": 3.6411830262246755e-06,
+      "loss": 0.2626,
+      "step": 68
+    },
+    {
+      "epoch": 1.1694915254237288,
+      "grad_norm": 0.44572869985154356,
+      "learning_rate": 3.599639248525749e-06,
+      "loss": 0.2314,
+      "step": 69
+    },
+    {
+      "epoch": 1.1864406779661016,
+      "grad_norm": 0.4743820453627211,
+      "learning_rate": 3.5577154879187286e-06,
+      "loss": 0.2524,
+      "step": 70
+    },
+    {
+      "epoch": 1.2033898305084745,
+      "grad_norm": 0.4795920562830289,
+      "learning_rate": 3.5154262312569134e-06,
+      "loss": 0.2272,
+      "step": 71
+    },
+    {
+      "epoch": 1.2203389830508475,
+      "grad_norm": 0.4454617572461806,
+      "learning_rate": 3.4727860916916143e-06,
+      "loss": 0.2192,
+      "step": 72
+    },
+    {
+      "epoch": 1.2372881355932204,
+      "grad_norm": 0.45505003053894033,
+      "learning_rate": 3.429809803622551e-06,
+      "loss": 0.2222,
+      "step": 73
+    },
+    {
+      "epoch": 1.2542372881355932,
+      "grad_norm": 0.5092981797760533,
+      "learning_rate": 3.386512217606339e-06,
+      "loss": 0.2221,
+      "step": 74
+    },
+    {
+      "epoch": 1.271186440677966,
+      "grad_norm": 0.45652766088591107,
+      "learning_rate": 3.342908295224854e-06,
+      "loss": 0.2115,
+      "step": 75
+    },
+    {
+      "epoch": 1.288135593220339,
+      "grad_norm": 0.5773859878970916,
+      "learning_rate": 3.299013103915214e-06,
+      "loss": 0.2735,
+      "step": 76
+    },
+    {
+      "epoch": 1.305084745762712,
+      "grad_norm": 0.5403811470495191,
+      "learning_rate": 3.2548418117631952e-06,
+      "loss": 0.2248,
+      "step": 77
+    },
+    {
+      "epoch": 1.3220338983050848,
+      "grad_norm": 0.6646747594835315,
+      "learning_rate": 3.2104096822618657e-06,
+      "loss": 0.2554,
+      "step": 78
+    },
+    {
+      "epoch": 1.3389830508474576,
+      "grad_norm": 0.44285218067378557,
+      "learning_rate": 3.1657320690372464e-06,
+      "loss": 0.1984,
+      "step": 79
+    },
+    {
+      "epoch": 1.3559322033898304,
+      "grad_norm": 0.48055286049444484,
+      "learning_rate": 3.120824410542833e-06,
+      "loss": 0.2187,
+      "step": 80
+    },
+    {
+      "epoch": 1.3728813559322033,
+      "grad_norm": 0.5320390743973299,
+      "learning_rate": 3.0757022247248e-06,
+      "loss": 0.2232,
+      "step": 81
+    },
+    {
+      "epoch": 1.3898305084745763,
+      "grad_norm": 0.4807624431716425,
+      "learning_rate": 3.0303811036597395e-06,
+      "loss": 0.2403,
+      "step": 82
+    },
+    {
+      "epoch": 1.4067796610169492,
+      "grad_norm": 0.4244464101592162,
+      "learning_rate": 2.9848767081667823e-06,
+      "loss": 0.2213,
+      "step": 83
+    },
+    {
+      "epoch": 1.423728813559322,
+      "grad_norm": 0.49236319422304126,
+      "learning_rate": 2.9392047623959653e-06,
+      "loss": 0.2375,
+      "step": 84
+    },
+    {
+      "epoch": 1.4406779661016949,
+      "grad_norm": 0.46784645507056544,
+      "learning_rate": 2.8933810483947156e-06,
+      "loss": 0.2219,
+      "step": 85
+    },
+    {
+      "epoch": 1.457627118644068,
+      "grad_norm": 0.48973007159992155,
+      "learning_rate": 2.8474214006543255e-06,
+      "loss": 0.2166,
+      "step": 86
+    },
+    {
+      "epoch": 1.4745762711864407,
+      "grad_norm": 0.3510113111902409,
+      "learning_rate": 2.8013417006383078e-06,
+      "loss": 0.1943,
+      "step": 87
+    },
+    {
+      "epoch": 1.4915254237288136,
+      "grad_norm": 0.44578327104858334,
+      "learning_rate": 2.755157871294521e-06,
+      "loss": 0.234,
+      "step": 88
+    },
+    {
+      "epoch": 1.5084745762711864,
+      "grad_norm": 0.7165659629002311,
+      "learning_rate": 2.708885871552954e-06,
+      "loss": 0.2447,
+      "step": 89
+    },
+    {
+      "epoch": 1.5254237288135593,
+      "grad_norm": 0.45065744754362286,
+      "learning_rate": 2.6625416908110825e-06,
+      "loss": 0.2284,
+      "step": 90
+    },
+    {
+      "epoch": 1.542372881355932,
+      "grad_norm": 0.41704260341071947,
+      "learning_rate": 2.616141343408696e-06,
+      "loss": 0.2237,
+      "step": 91
+    },
+    {
+      "epoch": 1.559322033898305,
+      "grad_norm": 0.5042304558688149,
+      "learning_rate": 2.569700863094104e-06,
+      "loss": 0.2219,
+      "step": 92
+    },
+    {
+      "epoch": 1.576271186440678,
+      "grad_norm": 0.5190696344795624,
+      "learning_rate": 2.5232362974836394e-06,
+      "loss": 0.2321,
+      "step": 93
+    },
+    {
+      "epoch": 1.5932203389830508,
+      "grad_norm": 0.5279441416014571,
+      "learning_rate": 2.4767637025163614e-06,
+      "loss": 0.2715,
+      "step": 94
+    },
+    {
+      "epoch": 1.6101694915254239,
+      "grad_norm": 0.5147780575565639,
+      "learning_rate": 2.4302991369058963e-06,
+      "loss": 0.2445,
+      "step": 95
+    },
+    {
+      "epoch": 1.6271186440677967,
+      "grad_norm": 0.4916874716282566,
+      "learning_rate": 2.3838586565913053e-06,
+      "loss": 0.2045,
+      "step": 96
+    },
+    {
+      "epoch": 1.6440677966101696,
+      "grad_norm": 0.4829870763326134,
+      "learning_rate": 2.3374583091889188e-06,
+      "loss": 0.2154,
+      "step": 97
+    },
+    {
+      "epoch": 1.6610169491525424,
+      "grad_norm": 0.5093333087244544,
+      "learning_rate": 2.2911141284470466e-06,
+      "loss": 0.2453,
+      "step": 98
+    },
+    {
+      "epoch": 1.6779661016949152,
+      "grad_norm": 0.6588755855029546,
+      "learning_rate": 2.2448421287054794e-06,
+      "loss": 0.2668,
+      "step": 99
+    },
+    {
+      "epoch": 1.694915254237288,
+      "grad_norm": 0.49865992979225093,
+      "learning_rate": 2.1986582993616926e-06,
+      "loss": 0.2283,
+      "step": 100
+    },
+    {
+      "epoch": 1.711864406779661,
+      "grad_norm": 0.37695864859441414,
+      "learning_rate": 2.1525785993456753e-06,
+      "loss": 0.2057,
+      "step": 101
+    },
+    {
+      "epoch": 1.7288135593220337,
+      "grad_norm": 0.548172589959634,
+      "learning_rate": 2.1066189516052848e-06,
+      "loss": 0.2558,
+      "step": 102
+    },
+    {
+      "epoch": 1.7457627118644068,
+      "grad_norm": 0.7296309615305285,
+      "learning_rate": 2.0607952376040355e-06,
+      "loss": 0.2707,
+      "step": 103
+    },
+    {
+      "epoch": 1.7627118644067796,
+      "grad_norm": 0.6191305523245286,
+      "learning_rate": 2.0151232918332186e-06,
+      "loss": 0.216,
+      "step": 104
+    },
+    {
+      "epoch": 1.7796610169491527,
+      "grad_norm": 0.4275148733512332,
+      "learning_rate": 1.9696188963402613e-06,
+      "loss": 0.2016,
+      "step": 105
+    },
+    {
+      "epoch": 1.7966101694915255,
+      "grad_norm": 0.5433825312095228,
+      "learning_rate": 1.9242977752752006e-06,
+      "loss": 0.2463,
+      "step": 106
+    },
+    {
+      "epoch": 1.8135593220338984,
+      "grad_norm": 0.6146764112328339,
+      "learning_rate": 1.879175589457168e-06,
+      "loss": 0.217,
+      "step": 107
+    },
+    {
+      "epoch": 1.8305084745762712,
+      "grad_norm": 0.4492249547863865,
+      "learning_rate": 1.8342679309627545e-06,
+      "loss": 0.2112,
+      "step": 108
+    },
+    {
+      "epoch": 1.847457627118644,
+      "grad_norm": 0.45112403138122764,
+      "learning_rate": 1.7895903177381351e-06,
+      "loss": 0.2213,
+      "step": 109
+    },
+    {
+      "epoch": 1.8644067796610169,
+      "grad_norm": 0.6114123860260355,
+      "learning_rate": 1.7451581882368052e-06,
+      "loss": 0.2067,
+      "step": 110
+    },
+    {
+      "epoch": 1.8813559322033897,
+      "grad_norm": 0.47090009128241844,
+      "learning_rate": 1.700986896084787e-06,
+      "loss": 0.23,
+      "step": 111
+    },
+    {
+      "epoch": 1.8983050847457628,
+      "grad_norm": 0.4641120289884631,
+      "learning_rate": 1.6570917047751465e-06,
+      "loss": 0.2385,
+      "step": 112
+    },
+    {
+      "epoch": 1.9152542372881356,
+      "grad_norm": 0.6393272872227032,
+      "learning_rate": 1.613487782393661e-06,
+      "loss": 0.2196,
+      "step": 113
+    },
+    {
+      "epoch": 1.9322033898305084,
+      "grad_norm": 0.41826816207678297,
+      "learning_rate": 1.5701901963774504e-06,
+      "loss": 0.2031,
+      "step": 114
+    },
+    {
+      "epoch": 1.9491525423728815,
+      "grad_norm": 0.43623407997620883,
+      "learning_rate": 1.5272139083083865e-06,
+      "loss": 0.2168,
+      "step": 115
+    },
+    {
+      "epoch": 1.9661016949152543,
+      "grad_norm": 0.5121666691791417,
+      "learning_rate": 1.4845737687430875e-06,
+      "loss": 0.2476,
+      "step": 116
+    },
+    {
+      "epoch": 1.9830508474576272,
+      "grad_norm": 0.4875537170599579,
+      "learning_rate": 1.4422845120812718e-06,
+      "loss": 0.1885,
+      "step": 117
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.6170831997594528,
+      "learning_rate": 1.400360751474253e-06,
+      "loss": 0.2491,
+      "step": 118
+    },
+    {
+      "epoch": 2.016949152542373,
+      "grad_norm": 0.4472827280319739,
+      "learning_rate": 1.3588169737753258e-06,
+      "loss": 0.1855,
+      "step": 119
+    },
+    {
+      "epoch": 2.0338983050847457,
+      "grad_norm": 0.5413068643010572,
+      "learning_rate": 1.3176675345338085e-06,
+      "loss": 0.2188,
+      "step": 120
+    },
+    {
+      "epoch": 2.0508474576271185,
+      "grad_norm": 0.428707546016933,
+      "learning_rate": 1.276926653034444e-06,
+      "loss": 0.2248,
+      "step": 121
+    },
+    {
+      "epoch": 2.0677966101694913,
+      "grad_norm": 0.5858749588254089,
+      "learning_rate": 1.2366084073838963e-06,
+      "loss": 0.2598,
+      "step": 122
+    },
+    {
+      "epoch": 2.084745762711864,
+      "grad_norm": 0.44846382451641165,
+      "learning_rate": 1.1967267296460208e-06,
+      "loss": 0.1837,
+      "step": 123
+    },
+    {
+      "epoch": 2.1016949152542375,
+      "grad_norm": 0.48106733288396136,
+      "learning_rate": 1.157295401027616e-06,
+      "loss": 0.2265,
+      "step": 124
+    },
+    {
+      "epoch": 2.1186440677966103,
+      "grad_norm": 0.5527311526391787,
+      "learning_rate": 1.1183280471162916e-06,
+      "loss": 0.2181,
+      "step": 125
+    },
+    {
+      "epoch": 2.135593220338983,
+      "grad_norm": 0.4955616787413392,
+      "learning_rate": 1.079838133172111e-06,
+      "loss": 0.2234,
+      "step": 126
+    },
+    {
+      "epoch": 2.152542372881356,
+      "grad_norm": 0.43338578262654337,
+      "learning_rate": 1.0418389594746462e-06,
+      "loss": 0.214,
+      "step": 127
+    },
+    {
+      "epoch": 2.169491525423729,
+      "grad_norm": 0.3669554740937264,
+      "learning_rate": 1.0043436567270313e-06,
+      "loss": 0.1856,
+      "step": 128
+    },
+    {
+      "epoch": 2.1864406779661016,
+      "grad_norm": 0.4089136976273204,
+      "learning_rate": 9.673651815186186e-07,
+      "loss": 0.181,
+      "step": 129
+    },
+    {
+      "epoch": 2.2033898305084745,
+      "grad_norm": 0.5094068860196916,
+      "learning_rate": 9.309163118477954e-07,
+      "loss": 0.232,
+      "step": 130
+    },
+    {
+      "epoch": 2.2203389830508473,
+      "grad_norm": 0.6111829159014325,
+      "learning_rate": 8.950096427065232e-07,
+      "loss": 0.256,
+      "step": 131
+    },
+    {
+      "epoch": 2.23728813559322,
+      "grad_norm": 0.5499628769610874,
+      "learning_rate": 8.596575817281036e-07,
+      "loss": 0.263,
+      "step": 132
+    },
+    {
+      "epoch": 2.2542372881355934,
+      "grad_norm": 0.472315352129982,
+      "learning_rate": 8.248723448996942e-07,
+      "loss": 0.2025,
+      "step": 133
+    },
+    {
+      "epoch": 2.2711864406779663,
+      "grad_norm": 0.44621416461066526,
+      "learning_rate": 7.906659523410445e-07,
+      "loss": 0.1964,
+      "step": 134
+    },
+    {
+      "epoch": 2.288135593220339,
+      "grad_norm": 0.5438276256045982,
+      "learning_rate": 7.570502241509162e-07,
+      "loss": 0.24,
+      "step": 135
+    },
+    {
+      "epoch": 2.305084745762712,
+      "grad_norm": 0.48076560661191803,
+      "learning_rate": 7.240367763226214e-07,
+      "loss": 0.2522,
+      "step": 136
+    },
+    {
+      "epoch": 2.3220338983050848,
+      "grad_norm": 0.45221392230794627,
+      "learning_rate": 6.916370167300846e-07,
+      "loss": 0.2031,
+      "step": 137
+    },
+    {
+      "epoch": 2.3389830508474576,
+      "grad_norm": 0.6301591765021999,
+      "learning_rate": 6.59862141185832e-07,
+      "loss": 0.2158,
+      "step": 138
+    },
+    {
+      "epoch": 2.3559322033898304,
+      "grad_norm": 0.3952157742860489,
+      "learning_rate": 6.28723129572247e-07,
+      "loss": 0.2078,
+      "step": 139
+    },
+    {
+      "epoch": 2.3728813559322033,
+      "grad_norm": 0.446514287134317,
+      "learning_rate": 5.982307420474501e-07,
+      "loss": 0.1948,
+      "step": 140
+    },
+    {
+      "epoch": 2.389830508474576,
+      "grad_norm": 0.5855904635323722,
+      "learning_rate": 5.683955153270959e-07,
+      "loss": 0.2657,
+      "step": 141
+    },
+    {
+      "epoch": 2.406779661016949,
+      "grad_norm": 0.5583109191195978,
+      "learning_rate": 5.39227759043392e-07,
+      "loss": 0.1933,
+      "step": 142
+    },
+    {
+      "epoch": 2.423728813559322,
+      "grad_norm": 0.47676799585910457,
+      "learning_rate": 5.107375521825791e-07,
+      "loss": 0.2273,
+      "step": 143
+    },
+    {
+      "epoch": 2.440677966101695,
+      "grad_norm": 0.4864750560824795,
+      "learning_rate": 4.829347396021142e-07,
+      "loss": 0.251,
+      "step": 144
+    },
+    {
+      "epoch": 2.457627118644068,
+      "grad_norm": 0.6512251016554255,
+      "learning_rate": 4.5582892862875457e-07,
+      "loss": 0.2521,
+      "step": 145
+    },
+    {
+      "epoch": 2.4745762711864407,
+      "grad_norm": 0.48233660615594676,
+      "learning_rate": 4.294294857387285e-07,
+      "loss": 0.2275,
+      "step": 146
+    },
+    {
+      "epoch": 2.4915254237288136,
+      "grad_norm": 0.6428476684215992,
+      "learning_rate": 4.0374553332112374e-07,
+      "loss": 0.2327,
+      "step": 147
+    },
+    {
+      "epoch": 2.5084745762711864,
+      "grad_norm": 0.5076426403103419,
+      "learning_rate": 3.787859465256258e-07,
+      "loss": 0.1708,
+      "step": 148
+    },
+    {
+      "epoch": 2.5254237288135593,
+      "grad_norm": 0.5026976859156602,
+      "learning_rate": 3.545593501956901e-07,
+      "loss": 0.213,
+      "step": 149
+    },
+    {
+      "epoch": 2.542372881355932,
+      "grad_norm": 0.5662522579882163,
+      "learning_rate": 3.3107411588820527e-07,
+      "loss": 0.1996,
+      "step": 150
+    },
+    {
+      "epoch": 2.559322033898305,
+      "grad_norm": 0.5195058601098169,
+      "learning_rate": 3.083383589806846e-07,
+      "loss": 0.2263,
+      "step": 151
+    },
+    {
+      "epoch": 2.576271186440678,
+      "grad_norm": 0.5200135379990353,
+      "learning_rate": 2.8635993586697555e-07,
+      "loss": 0.2139,
+      "step": 152
+    },
+    {
+      "epoch": 2.593220338983051,
+      "grad_norm": 0.4763652464214379,
+      "learning_rate": 2.6514644124246675e-07,
+      "loss": 0.2229,
+      "step": 153
+    },
+    {
+      "epoch": 2.610169491525424,
+      "grad_norm": 0.49804739846772966,
+      "learning_rate": 2.447052054797233e-07,
+      "loss": 0.217,
+      "step": 154
+    },
+    {
+      "epoch": 2.6271186440677967,
+      "grad_norm": 0.48757701271761317,
+      "learning_rate": 2.2504329209545846e-07,
+      "loss": 0.2081,
+      "step": 155
+    },
+    {
+      "epoch": 2.6440677966101696,
+      "grad_norm": 0.4947797017705308,
+      "learning_rate": 2.0616749530971785e-07,
+      "loss": 0.2351,
+      "step": 156
+    },
+    {
+      "epoch": 2.6610169491525424,
+      "grad_norm": 0.5222467856875551,
+      "learning_rate": 1.8808433769812367e-07,
+      "loss": 0.2205,
+      "step": 157
+    },
+    {
+      "epoch": 2.6779661016949152,
+      "grad_norm": 0.4225419072915034,
+      "learning_rate": 1.7080006793798176e-07,
+      "loss": 0.1926,
+      "step": 158
+    },
+    {
+      "epoch": 2.694915254237288,
+      "grad_norm": 0.5691086207780526,
+      "learning_rate": 1.54320658649037e-07,
+      "loss": 0.2317,
+      "step": 159
+    },
+    {
+      "epoch": 2.711864406779661,
+      "grad_norm": 0.3840618595955483,
+      "learning_rate": 1.3865180432961977e-07,
+      "loss": 0.1861,
+      "step": 160
+    },
+    {
+      "epoch": 2.7288135593220337,
+      "grad_norm": 0.43342821320697045,
+      "learning_rate": 1.237989193889e-07,
+      "loss": 0.1841,
+      "step": 161
+    },
+    {
+      "epoch": 2.7457627118644066,
+      "grad_norm": 0.4541304378156735,
+      "learning_rate": 1.0976713627592561e-07,
+      "loss": 0.1838,
+      "step": 162
+    },
+    {
+      "epoch": 2.7627118644067794,
+      "grad_norm": 0.47718407958651254,
+      "learning_rate": 9.656130370609057e-08,
+      "loss": 0.2156,
+      "step": 163
+    },
+    {
+      "epoch": 2.7796610169491527,
+      "grad_norm": 0.4203326388891047,
+      "learning_rate": 8.418598498565217e-08,
+      "loss": 0.198,
+      "step": 164
+    },
+    {
+      "epoch": 2.7966101694915255,
+      "grad_norm": 0.6344933451047076,
+      "learning_rate": 7.264545643486997e-08,
+      "loss": 0.2469,
+      "step": 165
+    },
+    {
+      "epoch": 2.8135593220338984,
+      "grad_norm": 0.5726793839966674,
+      "learning_rate": 6.194370591031174e-08,
+      "loss": 0.2504,
+      "step": 166
+    },
+    {
+      "epoch": 2.830508474576271,
+      "grad_norm": 0.44232201362023676,
+      "learning_rate": 5.208443142684094e-08,
+      "loss": 0.211,
+      "step": 167
+    },
+    {
+      "epoch": 2.847457627118644,
+      "grad_norm": 0.5141286149933719,
+      "learning_rate": 4.307103987976041e-08,
+      "loss": 0.231,
+      "step": 168
+    },
+    {
+      "epoch": 2.864406779661017,
+      "grad_norm": 0.4569119724260856,
+      "learning_rate": 3.4906645867549547e-08,
+      "loss": 0.1939,
+      "step": 169
+    },
+    {
+      "epoch": 2.8813559322033897,
+      "grad_norm": 0.48342076668279055,
+      "learning_rate": 2.7594070615609426e-08,
+      "loss": 0.2043,
+      "step": 170
+    },
+    {
+      "epoch": 2.898305084745763,
+      "grad_norm": 0.34035724769380715,
+      "learning_rate": 2.1135841001380386e-08,
+      "loss": 0.1772,
+      "step": 171
+    },
+    {
+      "epoch": 2.915254237288136,
+      "grad_norm": 0.4608098604477918,
+      "learning_rate": 1.55341886811744e-08,
+      "loss": 0.1966,
+      "step": 172
+    },
+    {
+      "epoch": 2.9322033898305087,
+      "grad_norm": 0.48086970561951203,
+      "learning_rate": 1.0791049319021086e-08,
+      "loss": 0.2193,
+      "step": 173
+    },
+    {
+      "epoch": 2.9491525423728815,
+      "grad_norm": 0.5098124389058276,
+      "learning_rate": 6.908061917794417e-09,
+      "loss": 0.2126,
+      "step": 174
+    },
+    {
+      "epoch": 2.9661016949152543,
+      "grad_norm": 0.4671835659759605,
+      "learning_rate": 3.8865682528504975e-09,
+      "loss": 0.2207,
+      "step": 175
+    },
+    {
+      "epoch": 2.983050847457627,
+      "grad_norm": 1.3155876369197672,
+      "learning_rate": 1.7276124083753788e-09,
+      "loss": 0.2563,
+      "step": 176
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 0.5705208597149767,
+      "learning_rate": 4.3194041659866405e-10,
+      "loss": 0.2054,
+      "step": 177
+    },
+    {
+      "epoch": 3.0,
+      "step": 177,
+      "total_flos": 118937526042624.0,
+      "train_loss": 0.25391180055626367,
+      "train_runtime": 14992.2104,
+      "train_samples_per_second": 0.188,
+      "train_steps_per_second": 0.012
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 177,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 118937526042624.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e17d4d6ff9f57b87907138738135ccc1f950aaa010833c6fc878af1707a1157d
+size 6968