Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,27 @@ 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
+epoch_1/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_1/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_1/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_1/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_1/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_2/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_2/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_2/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_2/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_2/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_3/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_3/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_3/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_3/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_3/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_4/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_4/checkpoint-150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_4/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_4/checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_4/checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+epoch_4/tokenizer.json filter=lfs diff=lfs merge=lfs -text

epoch_1/README.md

@@ -0,0 +1,59 @@
+---
+library_name: transformers
+license: other
+base_model: /projects/ai_safe/cuongdc/adaptive_3B_low/epoch_3
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: epoch_1
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# epoch_1
+
+This model is a fine-tuned version of [/projects/ai_safe/cuongdc/adaptive_3B_low/epoch_3](https://huggingface.co//projects/ai_safe/cuongdc/adaptive_3B_low/epoch_3) on the 3B_high dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1.25e-06
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- total_train_batch_size: 2
+- total_eval_batch_size: 16
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.56.2
+- Pytorch 2.7.1+cu126
+- Datasets 4.0.0
+- Tokenizers 0.22.1

epoch_1/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

epoch_1/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 473506775040.0,
+    "train_loss": 0.13181804982200265,
+    "train_runtime": 287.1762,
+    "train_samples_per_second": 1.741,
+    "train_steps_per_second": 0.871
+}

epoch_1/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

epoch_1/checkpoint-100/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

epoch_1/checkpoint-100/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

epoch_1/checkpoint-100/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "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": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

epoch_1/checkpoint-100/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.56.2"
+}

epoch_1/checkpoint-100/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1628140ad80add877b3b542cd4948be19f21ace3445ef89770ed2916b097104
+size 4957560304

epoch_1/checkpoint-100/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e967d36970daff6cfff467c81396c1cad1000af167728c8f72db5cc0a353a786
+size 1214366696

epoch_1/checkpoint-100/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_parameters": 241664,
+    "total_size": 6171877376
+  },
+  "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-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_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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"
+  }
+}

epoch_1/checkpoint-100/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
+  }
+}

epoch_1/checkpoint-100/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

epoch_1/checkpoint-100/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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
+}

epoch_1/checkpoint-100/trainer_state.json

@@ -0,0 +1,734 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004,
+      "grad_norm": 4.017385483397232,
+      "learning_rate": 1.25e-06,
+      "loss": 0.1413,
+      "step": 1
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 3.8449675966687606,
+      "learning_rate": 1.2499506526273853e-06,
+      "loss": 0.1328,
+      "step": 2
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 2.1638363967847223,
+      "learning_rate": 1.2498026183020626e-06,
+      "loss": 0.086,
+      "step": 3
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 3.3743604139964436,
+      "learning_rate": 1.2495559204003684e-06,
+      "loss": 0.1365,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.288840036724382,
+      "learning_rate": 1.2492105978787612e-06,
+      "loss": 0.1513,
+      "step": 5
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 7.595431480390665,
+      "learning_rate": 1.2487667052676699e-06,
+      "loss": 0.1987,
+      "step": 6
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 3.2413826920628166,
+      "learning_rate": 1.2482243126628838e-06,
+      "loss": 0.1202,
+      "step": 7
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 4.883733594707665,
+      "learning_rate": 1.247583505714483e-06,
+      "loss": 0.1799,
+      "step": 8
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 4.508245483958065,
+      "learning_rate": 1.2468443856133129e-06,
+      "loss": 0.1619,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.906984422165932,
+      "learning_rate": 1.2460070690750053e-06,
+      "loss": 0.167,
+      "step": 10
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 3.6964749714214906,
+      "learning_rate": 1.245071688321549e-06,
+      "loss": 0.1187,
+      "step": 11
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 2.979347665997292,
+      "learning_rate": 1.2440383910604071e-06,
+      "loss": 0.1668,
+      "step": 12
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 2.954570728851493,
+      "learning_rate": 1.2429073404611962e-06,
+      "loss": 0.0828,
+      "step": 13
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 6.636874452245697,
+      "learning_rate": 1.2416787151299176e-06,
+      "loss": 0.2631,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.091490024239134,
+      "learning_rate": 1.2403527090807535e-06,
+      "loss": 0.1144,
+      "step": 15
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.2323669367718386,
+      "learning_rate": 1.2389295317054306e-06,
+      "loss": 0.0631,
+      "step": 16
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 4.4396327514278795,
+      "learning_rate": 1.2374094077401545e-06,
+      "loss": 0.194,
+      "step": 17
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 3.8264637726466115,
+      "learning_rate": 1.235792577230121e-06,
+      "loss": 0.1736,
+      "step": 18
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 2.999135242898612,
+      "learning_rate": 1.2340792954916109e-06,
+      "loss": 0.1339,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.1527155068441246,
+      "learning_rate": 1.2322698330716713e-06,
+      "loss": 0.0834,
+      "step": 20
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 4.0286126176650185,
+      "learning_rate": 1.2303644757053945e-06,
+      "loss": 0.1841,
+      "step": 21
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 3.9156121312517786,
+      "learning_rate": 1.2283635242707962e-06,
+      "loss": 0.1142,
+      "step": 22
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 4.245160129433801,
+      "learning_rate": 1.2262672947413037e-06,
+      "loss": 0.1251,
+      "step": 23
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 5.309528123667374,
+      "learning_rate": 1.22407611813586e-06,
+      "loss": 0.1602,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.485877801658527,
+      "learning_rate": 1.221790340466652e-06,
+      "loss": 0.1733,
+      "step": 25
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.96261019219239,
+      "learning_rate": 1.2194103226844711e-06,
+      "loss": 0.1113,
+      "step": 26
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 5.128545078967028,
+      "learning_rate": 1.2169364406217154e-06,
+      "loss": 0.146,
+      "step": 27
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 4.463994053430229,
+      "learning_rate": 1.2143690849330405e-06,
+      "loss": 0.1564,
+      "step": 28
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 3.344393653898428,
+      "learning_rate": 1.2117086610336714e-06,
+      "loss": 0.103,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.176137249160477,
+      "learning_rate": 1.2089555890353826e-06,
+      "loss": 0.0477,
+      "step": 30
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 3.051441040807267,
+      "learning_rate": 1.2061103036801573e-06,
+      "loss": 0.0949,
+      "step": 31
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 3.5084777203708444,
+      "learning_rate": 1.2031732542715363e-06,
+      "loss": 0.1001,
+      "step": 32
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 3.060808348393298,
+      "learning_rate": 1.2001449046036692e-06,
+      "loss": 0.1111,
+      "step": 33
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 3.6047867168659997,
+      "learning_rate": 1.1970257328880735e-06,
+      "loss": 0.0838,
+      "step": 34
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.605944823640285,
+      "learning_rate": 1.1938162316781223e-06,
+      "loss": 0.1047,
+      "step": 35
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 3.642604507481262,
+      "learning_rate": 1.1905169077912623e-06,
+      "loss": 0.1691,
+      "step": 36
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 2.977794754734627,
+      "learning_rate": 1.187128282228982e-06,
+      "loss": 0.1335,
+      "step": 37
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 3.597549271855966,
+      "learning_rate": 1.18365089009454e-06,
+      "loss": 0.1307,
+      "step": 38
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 3.3649862888593303,
+      "learning_rate": 1.1800852805084655e-06,
+      "loss": 0.062,
+      "step": 39
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.183766887602216,
+      "learning_rate": 1.176432016521846e-06,
+      "loss": 0.1588,
+      "step": 40
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 3.7163992206687726,
+      "learning_rate": 1.1726916750274148e-06,
+      "loss": 0.0954,
+      "step": 41
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.40910896062220287,
+      "learning_rate": 1.1688648466684537e-06,
+      "loss": 0.0136,
+      "step": 42
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 5.295089388122023,
+      "learning_rate": 1.1649521357455222e-06,
+      "loss": 0.2147,
+      "step": 43
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 2.576423141532492,
+      "learning_rate": 1.1609541601210329e-06,
+      "loss": 0.1033,
+      "step": 44
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.312566919509821,
+      "learning_rate": 1.1568715511216826e-06,
+      "loss": 0.1621,
+      "step": 45
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 5.7157490385942085,
+      "learning_rate": 1.1527049534387595e-06,
+      "loss": 0.2664,
+      "step": 46
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 4.642925524228082,
+      "learning_rate": 1.1484550250263388e-06,
+      "loss": 0.152,
+      "step": 47
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 6.3866757968856485,
+      "learning_rate": 1.144122436997383e-06,
+      "loss": 0.1785,
+      "step": 48
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 4.874612191099983,
+      "learning_rate": 1.1397078735177673e-06,
+      "loss": 0.217,
+      "step": 49
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.4575745000644247,
+      "learning_rate": 1.13521203169824e-06,
+      "loss": 0.13,
+      "step": 50
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 6.292533852396203,
+      "learning_rate": 1.1306356214843423e-06,
+      "loss": 0.1678,
+      "step": 51
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 4.188127391211228,
+      "learning_rate": 1.125979365544298e-06,
+      "loss": 0.1346,
+      "step": 52
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 3.404139570651294,
+      "learning_rate": 1.1212439991548971e-06,
+      "loss": 0.1136,
+      "step": 53
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 3.7842612979712187,
+      "learning_rate": 1.1164302700853868e-06,
+      "loss": 0.1024,
+      "step": 54
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.3939355583645425,
+      "learning_rate": 1.1115389384793898e-06,
+      "loss": 0.1253,
+      "step": 55
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 5.245180376439613,
+      "learning_rate": 1.1065707767348684e-06,
+      "loss": 0.1256,
+      "step": 56
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.5729530986310555,
+      "learning_rate": 1.101526569382155e-06,
+      "loss": 0.0234,
+      "step": 57
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 3.2118514205891486,
+      "learning_rate": 1.096407112960065e-06,
+      "loss": 0.0853,
+      "step": 58
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 2.106270697781548,
+      "learning_rate": 1.091213215890114e-06,
+      "loss": 0.0717,
+      "step": 59
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.349587278976827,
+      "learning_rate": 1.0859456983488588e-06,
+      "loss": 0.089,
+      "step": 60
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 7.876301970845418,
+      "learning_rate": 1.0806053921383823e-06,
+      "loss": 0.2699,
+      "step": 61
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 2.531190836425024,
+      "learning_rate": 1.0751931405549419e-06,
+      "loss": 0.1106,
+      "step": 62
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 5.5346145359497205,
+      "learning_rate": 1.0697097982558036e-06,
+      "loss": 0.1247,
+      "step": 63
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 5.142622243461298,
+      "learning_rate": 1.064156231124281e-06,
+      "loss": 0.1363,
+      "step": 64
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.11593080424434,
+      "learning_rate": 1.058533316133003e-06,
+      "loss": 0.0876,
+      "step": 65
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 5.967188720796784,
+      "learning_rate": 1.0528419412054306e-06,
+      "loss": 0.1276,
+      "step": 66
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 3.9076222868719577,
+      "learning_rate": 1.0470830050756402e-06,
+      "loss": 0.1199,
+      "step": 67
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 4.5469221847786905,
+      "learning_rate": 1.0412574171464074e-06,
+      "loss": 0.1236,
+      "step": 68
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 3.2424285022940356,
+      "learning_rate": 1.035366097345598e-06,
+      "loss": 0.0848,
+      "step": 69
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.322304043916362,
+      "learning_rate": 1.0294099759809028e-06,
+      "loss": 0.2061,
+      "step": 70
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 3.832594763604789,
+      "learning_rate": 1.0233899935929311e-06,
+      "loss": 0.1614,
+      "step": 71
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 2.4467957912337166,
+      "learning_rate": 1.0173071008066878e-06,
+      "loss": 0.0921,
+      "step": 72
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 2.8598136356378525,
+      "learning_rate": 1.011162258181459e-06,
+      "loss": 0.0752,
+      "step": 73
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 4.0019435362793905,
+      "learning_rate": 1.0049564360591285e-06,
+      "loss": 0.1029,
+      "step": 74
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.2212138974769413,
+      "learning_rate": 9.986906144109494e-07,
+      "loss": 0.0987,
+      "step": 75
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 4.522211217403667,
+      "learning_rate": 9.923657826827958e-07,
+      "loss": 0.1602,
+      "step": 76
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 3.376245985310258,
+      "learning_rate": 9.859829396389172e-07,
+      "loss": 0.1176,
+      "step": 77
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 6.073368961666502,
+      "learning_rate": 9.79543093204223e-07,
+      "loss": 0.1807,
+      "step": 78
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 7.706860943134537,
+      "learning_rate": 9.730472603051175e-07,
+      "loss": 0.149,
+      "step": 79
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.81425757189223,
+      "learning_rate": 9.664964667089184e-07,
+      "loss": 0.0606,
+      "step": 80
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 3.1034608925705465,
+      "learning_rate": 9.59891746861873e-07,
+      "loss": 0.1235,
+      "step": 81
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 5.4593767606269745,
+      "learning_rate": 9.532341437258099e-07,
+      "loss": 0.1292,
+      "step": 82
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 3.35883770074761,
+      "learning_rate": 9.465247086134416e-07,
+      "loss": 0.1196,
+      "step": 83
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 5.458524887235343,
+      "learning_rate": 9.397645010223506e-07,
+      "loss": 0.2082,
+      "step": 84
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.345193079077953,
+      "learning_rate": 9.329545884676823e-07,
+      "loss": 0.2584,
+      "step": 85
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 3.4245431779216946,
+      "learning_rate": 9.260960463135721e-07,
+      "loss": 0.1003,
+      "step": 86
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 4.046815164804643,
+      "learning_rate": 9.191899576033331e-07,
+      "loss": 0.127,
+      "step": 87
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 4.551196552703828,
+      "learning_rate": 9.122374128884301e-07,
+      "loss": 0.2096,
+      "step": 88
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 3.3977880693097093,
+      "learning_rate": 9.052395100562704e-07,
+      "loss": 0.1034,
+      "step": 89
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5277523583283517,
+      "learning_rate": 8.981973541568331e-07,
+      "loss": 0.0185,
+      "step": 90
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 3.715550434329015,
+      "learning_rate": 8.911120572281705e-07,
+      "loss": 0.1184,
+      "step": 91
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 2.2115026803492053,
+      "learning_rate": 8.839847381208027e-07,
+      "loss": 0.0669,
+      "step": 92
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 3.5200936151406346,
+      "learning_rate": 8.768165223210393e-07,
+      "loss": 0.0676,
+      "step": 93
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 2.6500028260333464,
+      "learning_rate": 8.696085417732517e-07,
+      "loss": 0.0601,
+      "step": 94
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.676896418632736,
+      "learning_rate": 8.623619347011259e-07,
+      "loss": 0.1151,
+      "step": 95
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 4.125582103259355,
+      "learning_rate": 8.550778454279239e-07,
+      "loss": 0.1375,
+      "step": 96
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 4.002370086986581,
+      "learning_rate": 8.477574241957817e-07,
+      "loss": 0.1177,
+      "step": 97
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 3.3858392990737753,
+      "learning_rate": 8.404018269840731e-07,
+      "loss": 0.077,
+      "step": 98
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 3.0438174129534703,
+      "learning_rate": 8.330122153268668e-07,
+      "loss": 0.1303,
+      "step": 99
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.0043982911779907,
+      "learning_rate": 8.255897561295059e-07,
+      "loss": 0.0558,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 192882671616.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

epoch_1/checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1b9bdac6c229a95edd8b52f2e6ad8ad316ae8b086598f08733c34e3e7848b4
+size 8145

epoch_1/checkpoint-150/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

epoch_1/checkpoint-150/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

epoch_1/checkpoint-150/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "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": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

epoch_1/checkpoint-150/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.56.2"
+}

epoch_1/checkpoint-150/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27174856b5c4ebc3a03dc0bafb4eb033cdbc71a75b923f50d5b52663e0778b50
+size 4957560304

epoch_1/checkpoint-150/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a6af988d416dd2e6055b1d9bf1108dd2563c2690cff27e585b5f732ace26ddd
+size 1214366696

epoch_1/checkpoint-150/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_parameters": 241664,
+    "total_size": 6171877376
+  },
+  "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-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_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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"
+  }
+}

epoch_1/checkpoint-150/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
+  }
+}

epoch_1/checkpoint-150/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

epoch_1/checkpoint-150/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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
+}

epoch_1/checkpoint-150/trainer_state.json

@@ -0,0 +1,1084 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6,
+  "eval_steps": 500,
+  "global_step": 150,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004,
+      "grad_norm": 4.017385483397232,
+      "learning_rate": 1.25e-06,
+      "loss": 0.1413,
+      "step": 1
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 3.8449675966687606,
+      "learning_rate": 1.2499506526273853e-06,
+      "loss": 0.1328,
+      "step": 2
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 2.1638363967847223,
+      "learning_rate": 1.2498026183020626e-06,
+      "loss": 0.086,
+      "step": 3
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 3.3743604139964436,
+      "learning_rate": 1.2495559204003684e-06,
+      "loss": 0.1365,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.288840036724382,
+      "learning_rate": 1.2492105978787612e-06,
+      "loss": 0.1513,
+      "step": 5
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 7.595431480390665,
+      "learning_rate": 1.2487667052676699e-06,
+      "loss": 0.1987,
+      "step": 6
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 3.2413826920628166,
+      "learning_rate": 1.2482243126628838e-06,
+      "loss": 0.1202,
+      "step": 7
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 4.883733594707665,
+      "learning_rate": 1.247583505714483e-06,
+      "loss": 0.1799,
+      "step": 8
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 4.508245483958065,
+      "learning_rate": 1.2468443856133129e-06,
+      "loss": 0.1619,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.906984422165932,
+      "learning_rate": 1.2460070690750053e-06,
+      "loss": 0.167,
+      "step": 10
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 3.6964749714214906,
+      "learning_rate": 1.245071688321549e-06,
+      "loss": 0.1187,
+      "step": 11
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 2.979347665997292,
+      "learning_rate": 1.2440383910604071e-06,
+      "loss": 0.1668,
+      "step": 12
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 2.954570728851493,
+      "learning_rate": 1.2429073404611962e-06,
+      "loss": 0.0828,
+      "step": 13
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 6.636874452245697,
+      "learning_rate": 1.2416787151299176e-06,
+      "loss": 0.2631,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.091490024239134,
+      "learning_rate": 1.2403527090807535e-06,
+      "loss": 0.1144,
+      "step": 15
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.2323669367718386,
+      "learning_rate": 1.2389295317054306e-06,
+      "loss": 0.0631,
+      "step": 16
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 4.4396327514278795,
+      "learning_rate": 1.2374094077401545e-06,
+      "loss": 0.194,
+      "step": 17
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 3.8264637726466115,
+      "learning_rate": 1.235792577230121e-06,
+      "loss": 0.1736,
+      "step": 18
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 2.999135242898612,
+      "learning_rate": 1.2340792954916109e-06,
+      "loss": 0.1339,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.1527155068441246,
+      "learning_rate": 1.2322698330716713e-06,
+      "loss": 0.0834,
+      "step": 20
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 4.0286126176650185,
+      "learning_rate": 1.2303644757053945e-06,
+      "loss": 0.1841,
+      "step": 21
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 3.9156121312517786,
+      "learning_rate": 1.2283635242707962e-06,
+      "loss": 0.1142,
+      "step": 22
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 4.245160129433801,
+      "learning_rate": 1.2262672947413037e-06,
+      "loss": 0.1251,
+      "step": 23
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 5.309528123667374,
+      "learning_rate": 1.22407611813586e-06,
+      "loss": 0.1602,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.485877801658527,
+      "learning_rate": 1.221790340466652e-06,
+      "loss": 0.1733,
+      "step": 25
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.96261019219239,
+      "learning_rate": 1.2194103226844711e-06,
+      "loss": 0.1113,
+      "step": 26
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 5.128545078967028,
+      "learning_rate": 1.2169364406217154e-06,
+      "loss": 0.146,
+      "step": 27
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 4.463994053430229,
+      "learning_rate": 1.2143690849330405e-06,
+      "loss": 0.1564,
+      "step": 28
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 3.344393653898428,
+      "learning_rate": 1.2117086610336714e-06,
+      "loss": 0.103,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.176137249160477,
+      "learning_rate": 1.2089555890353826e-06,
+      "loss": 0.0477,
+      "step": 30
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 3.051441040807267,
+      "learning_rate": 1.2061103036801573e-06,
+      "loss": 0.0949,
+      "step": 31
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 3.5084777203708444,
+      "learning_rate": 1.2031732542715363e-06,
+      "loss": 0.1001,
+      "step": 32
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 3.060808348393298,
+      "learning_rate": 1.2001449046036692e-06,
+      "loss": 0.1111,
+      "step": 33
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 3.6047867168659997,
+      "learning_rate": 1.1970257328880735e-06,
+      "loss": 0.0838,
+      "step": 34
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.605944823640285,
+      "learning_rate": 1.1938162316781223e-06,
+      "loss": 0.1047,
+      "step": 35
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 3.642604507481262,
+      "learning_rate": 1.1905169077912623e-06,
+      "loss": 0.1691,
+      "step": 36
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 2.977794754734627,
+      "learning_rate": 1.187128282228982e-06,
+      "loss": 0.1335,
+      "step": 37
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 3.597549271855966,
+      "learning_rate": 1.18365089009454e-06,
+      "loss": 0.1307,
+      "step": 38
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 3.3649862888593303,
+      "learning_rate": 1.1800852805084655e-06,
+      "loss": 0.062,
+      "step": 39
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.183766887602216,
+      "learning_rate": 1.176432016521846e-06,
+      "loss": 0.1588,
+      "step": 40
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 3.7163992206687726,
+      "learning_rate": 1.1726916750274148e-06,
+      "loss": 0.0954,
+      "step": 41
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.40910896062220287,
+      "learning_rate": 1.1688648466684537e-06,
+      "loss": 0.0136,
+      "step": 42
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 5.295089388122023,
+      "learning_rate": 1.1649521357455222e-06,
+      "loss": 0.2147,
+      "step": 43
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 2.576423141532492,
+      "learning_rate": 1.1609541601210329e-06,
+      "loss": 0.1033,
+      "step": 44
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.312566919509821,
+      "learning_rate": 1.1568715511216826e-06,
+      "loss": 0.1621,
+      "step": 45
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 5.7157490385942085,
+      "learning_rate": 1.1527049534387595e-06,
+      "loss": 0.2664,
+      "step": 46
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 4.642925524228082,
+      "learning_rate": 1.1484550250263388e-06,
+      "loss": 0.152,
+      "step": 47
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 6.3866757968856485,
+      "learning_rate": 1.144122436997383e-06,
+      "loss": 0.1785,
+      "step": 48
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 4.874612191099983,
+      "learning_rate": 1.1397078735177673e-06,
+      "loss": 0.217,
+      "step": 49
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.4575745000644247,
+      "learning_rate": 1.13521203169824e-06,
+      "loss": 0.13,
+      "step": 50
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 6.292533852396203,
+      "learning_rate": 1.1306356214843423e-06,
+      "loss": 0.1678,
+      "step": 51
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 4.188127391211228,
+      "learning_rate": 1.125979365544298e-06,
+      "loss": 0.1346,
+      "step": 52
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 3.404139570651294,
+      "learning_rate": 1.1212439991548971e-06,
+      "loss": 0.1136,
+      "step": 53
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 3.7842612979712187,
+      "learning_rate": 1.1164302700853868e-06,
+      "loss": 0.1024,
+      "step": 54
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.3939355583645425,
+      "learning_rate": 1.1115389384793898e-06,
+      "loss": 0.1253,
+      "step": 55
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 5.245180376439613,
+      "learning_rate": 1.1065707767348684e-06,
+      "loss": 0.1256,
+      "step": 56
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.5729530986310555,
+      "learning_rate": 1.101526569382155e-06,
+      "loss": 0.0234,
+      "step": 57
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 3.2118514205891486,
+      "learning_rate": 1.096407112960065e-06,
+      "loss": 0.0853,
+      "step": 58
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 2.106270697781548,
+      "learning_rate": 1.091213215890114e-06,
+      "loss": 0.0717,
+      "step": 59
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.349587278976827,
+      "learning_rate": 1.0859456983488588e-06,
+      "loss": 0.089,
+      "step": 60
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 7.876301970845418,
+      "learning_rate": 1.0806053921383823e-06,
+      "loss": 0.2699,
+      "step": 61
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 2.531190836425024,
+      "learning_rate": 1.0751931405549419e-06,
+      "loss": 0.1106,
+      "step": 62
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 5.5346145359497205,
+      "learning_rate": 1.0697097982558036e-06,
+      "loss": 0.1247,
+      "step": 63
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 5.142622243461298,
+      "learning_rate": 1.064156231124281e-06,
+      "loss": 0.1363,
+      "step": 64
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.11593080424434,
+      "learning_rate": 1.058533316133003e-06,
+      "loss": 0.0876,
+      "step": 65
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 5.967188720796784,
+      "learning_rate": 1.0528419412054306e-06,
+      "loss": 0.1276,
+      "step": 66
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 3.9076222868719577,
+      "learning_rate": 1.0470830050756402e-06,
+      "loss": 0.1199,
+      "step": 67
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 4.5469221847786905,
+      "learning_rate": 1.0412574171464074e-06,
+      "loss": 0.1236,
+      "step": 68
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 3.2424285022940356,
+      "learning_rate": 1.035366097345598e-06,
+      "loss": 0.0848,
+      "step": 69
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.322304043916362,
+      "learning_rate": 1.0294099759809028e-06,
+      "loss": 0.2061,
+      "step": 70
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 3.832594763604789,
+      "learning_rate": 1.0233899935929311e-06,
+      "loss": 0.1614,
+      "step": 71
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 2.4467957912337166,
+      "learning_rate": 1.0173071008066878e-06,
+      "loss": 0.0921,
+      "step": 72
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 2.8598136356378525,
+      "learning_rate": 1.011162258181459e-06,
+      "loss": 0.0752,
+      "step": 73
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 4.0019435362793905,
+      "learning_rate": 1.0049564360591285e-06,
+      "loss": 0.1029,
+      "step": 74
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.2212138974769413,
+      "learning_rate": 9.986906144109494e-07,
+      "loss": 0.0987,
+      "step": 75
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 4.522211217403667,
+      "learning_rate": 9.923657826827958e-07,
+      "loss": 0.1602,
+      "step": 76
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 3.376245985310258,
+      "learning_rate": 9.859829396389172e-07,
+      "loss": 0.1176,
+      "step": 77
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 6.073368961666502,
+      "learning_rate": 9.79543093204223e-07,
+      "loss": 0.1807,
+      "step": 78
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 7.706860943134537,
+      "learning_rate": 9.730472603051175e-07,
+      "loss": 0.149,
+      "step": 79
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.81425757189223,
+      "learning_rate": 9.664964667089184e-07,
+      "loss": 0.0606,
+      "step": 80
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 3.1034608925705465,
+      "learning_rate": 9.59891746861873e-07,
+      "loss": 0.1235,
+      "step": 81
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 5.4593767606269745,
+      "learning_rate": 9.532341437258099e-07,
+      "loss": 0.1292,
+      "step": 82
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 3.35883770074761,
+      "learning_rate": 9.465247086134416e-07,
+      "loss": 0.1196,
+      "step": 83
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 5.458524887235343,
+      "learning_rate": 9.397645010223506e-07,
+      "loss": 0.2082,
+      "step": 84
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.345193079077953,
+      "learning_rate": 9.329545884676823e-07,
+      "loss": 0.2584,
+      "step": 85
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 3.4245431779216946,
+      "learning_rate": 9.260960463135721e-07,
+      "loss": 0.1003,
+      "step": 86
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 4.046815164804643,
+      "learning_rate": 9.191899576033331e-07,
+      "loss": 0.127,
+      "step": 87
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 4.551196552703828,
+      "learning_rate": 9.122374128884301e-07,
+      "loss": 0.2096,
+      "step": 88
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 3.3977880693097093,
+      "learning_rate": 9.052395100562704e-07,
+      "loss": 0.1034,
+      "step": 89
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5277523583283517,
+      "learning_rate": 8.981973541568331e-07,
+      "loss": 0.0185,
+      "step": 90
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 3.715550434329015,
+      "learning_rate": 8.911120572281705e-07,
+      "loss": 0.1184,
+      "step": 91
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 2.2115026803492053,
+      "learning_rate": 8.839847381208027e-07,
+      "loss": 0.0669,
+      "step": 92
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 3.5200936151406346,
+      "learning_rate": 8.768165223210393e-07,
+      "loss": 0.0676,
+      "step": 93
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 2.6500028260333464,
+      "learning_rate": 8.696085417732517e-07,
+      "loss": 0.0601,
+      "step": 94
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.676896418632736,
+      "learning_rate": 8.623619347011259e-07,
+      "loss": 0.1151,
+      "step": 95
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 4.125582103259355,
+      "learning_rate": 8.550778454279239e-07,
+      "loss": 0.1375,
+      "step": 96
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 4.002370086986581,
+      "learning_rate": 8.477574241957817e-07,
+      "loss": 0.1177,
+      "step": 97
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 3.3858392990737753,
+      "learning_rate": 8.404018269840731e-07,
+      "loss": 0.077,
+      "step": 98
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 3.0438174129534703,
+      "learning_rate": 8.330122153268668e-07,
+      "loss": 0.1303,
+      "step": 99
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.0043982911779907,
+      "learning_rate": 8.255897561295059e-07,
+      "loss": 0.0558,
+      "step": 100
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 3.908268142779911,
+      "learning_rate": 8.181356214843422e-07,
+      "loss": 0.1988,
+      "step": 101
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 2.562662931219627,
+      "learning_rate": 8.106509884856469e-07,
+      "loss": 0.0558,
+      "step": 102
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 5.9781104173538715,
+      "learning_rate": 8.031370390437352e-07,
+      "loss": 0.2385,
+      "step": 103
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 2.4126656649906333,
+      "learning_rate": 7.955949596983284e-07,
+      "loss": 0.1026,
+      "step": 104
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.672796222838684,
+      "learning_rate": 7.880259414311857e-07,
+      "loss": 0.1316,
+      "step": 105
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 3.588897224218465,
+      "learning_rate": 7.804311794780345e-07,
+      "loss": 0.1586,
+      "step": 106
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 3.5642760730996934,
+      "learning_rate": 7.728118731398281e-07,
+      "loss": 0.1325,
+      "step": 107
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 2.849326457820366,
+      "learning_rate": 7.651692255933634e-07,
+      "loss": 0.1072,
+      "step": 108
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 7.160268721443933,
+      "learning_rate": 7.575044437012844e-07,
+      "loss": 0.212,
+      "step": 109
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.51867195731136,
+      "learning_rate": 7.498187378215044e-07,
+      "loss": 0.0868,
+      "step": 110
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 5.33044270549408,
+      "learning_rate": 7.421133216160781e-07,
+      "loss": 0.11,
+      "step": 111
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 3.7800629114651776,
+      "learning_rate": 7.343894118595477e-07,
+      "loss": 0.1271,
+      "step": 112
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 3.3562639092242406,
+      "learning_rate": 7.266482282468024e-07,
+      "loss": 0.1037,
+      "step": 113
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 2.676228500418713,
+      "learning_rate": 7.188909932004733e-07,
+      "loss": 0.0674,
+      "step": 114
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.46204350887125,
+      "learning_rate": 7.111189316778988e-07,
+      "loss": 0.1317,
+      "step": 115
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 5.208156619949427,
+      "learning_rate": 7.033332709776902e-07,
+      "loss": 0.1565,
+      "step": 116
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 4.253140685795728,
+      "learning_rate": 6.955352405459261e-07,
+      "loss": 0.1173,
+      "step": 117
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 2.1409973511035663,
+      "learning_rate": 6.877260717820093e-07,
+      "loss": 0.0894,
+      "step": 118
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 2.636844618416736,
+      "learning_rate": 6.799069978442147e-07,
+      "loss": 0.0794,
+      "step": 119
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.0790955874335193,
+      "learning_rate": 6.72079253454958e-07,
+      "loss": 0.072,
+      "step": 120
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 5.470329539821142,
+      "learning_rate": 6.642440747058209e-07,
+      "loss": 0.1631,
+      "step": 121
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 2.9616163814022767,
+      "learning_rate": 6.56402698862356e-07,
+      "loss": 0.1343,
+      "step": 122
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 2.6774812765668528,
+      "learning_rate": 6.485563641687093e-07,
+      "loss": 0.1067,
+      "step": 123
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 3.546931596203205,
+      "learning_rate": 6.407063096520861e-07,
+      "loss": 0.1099,
+      "step": 124
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.957398392343282,
+      "learning_rate": 6.328537749270955e-07,
+      "loss": 0.1128,
+      "step": 125
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 3.1585121573793913,
+      "learning_rate": 6.25e-07,
+      "loss": 0.1311,
+      "step": 126
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 5.993701817302737,
+      "learning_rate": 6.171462250729046e-07,
+      "loss": 0.2228,
+      "step": 127
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 3.059251333266507,
+      "learning_rate": 6.092936903479141e-07,
+      "loss": 0.1377,
+      "step": 128
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 2.7050519202831773,
+      "learning_rate": 6.014436358312909e-07,
+      "loss": 0.0669,
+      "step": 129
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.8139156307086175,
+      "learning_rate": 5.935973011376441e-07,
+      "loss": 0.0689,
+      "step": 130
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 4.439701739697846,
+      "learning_rate": 5.857559252941792e-07,
+      "loss": 0.1976,
+      "step": 131
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 3.825102266906039,
+      "learning_rate": 5.779207465450422e-07,
+      "loss": 0.1406,
+      "step": 132
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 1.9701757945162446,
+      "learning_rate": 5.700930021557855e-07,
+      "loss": 0.0711,
+      "step": 133
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 4.622445287004756,
+      "learning_rate": 5.622739282179907e-07,
+      "loss": 0.1108,
+      "step": 134
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.503076971686029,
+      "learning_rate": 5.544647594540739e-07,
+      "loss": 0.2497,
+      "step": 135
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 4.029937986134255,
+      "learning_rate": 5.466667290223098e-07,
+      "loss": 0.1739,
+      "step": 136
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 3.9748792359783676,
+      "learning_rate": 5.388810683221013e-07,
+      "loss": 0.1316,
+      "step": 137
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 4.756036320737784,
+      "learning_rate": 5.311090067995268e-07,
+      "loss": 0.0975,
+      "step": 138
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 3.167102420161004,
+      "learning_rate": 5.233517717531978e-07,
+      "loss": 0.1049,
+      "step": 139
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.9601077878796214,
+      "learning_rate": 5.156105881404524e-07,
+      "loss": 0.0927,
+      "step": 140
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 3.6670426901017867,
+      "learning_rate": 5.07886678383922e-07,
+      "loss": 0.1055,
+      "step": 141
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 2.44582710953066,
+      "learning_rate": 5.001812621784957e-07,
+      "loss": 0.1004,
+      "step": 142
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 3.3343903580284855,
+      "learning_rate": 4.92495556298716e-07,
+      "loss": 0.1558,
+      "step": 143
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 4.207281714783421,
+      "learning_rate": 4.848307744066369e-07,
+      "loss": 0.121,
+      "step": 144
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.6177447522900485,
+      "learning_rate": 4.771881268601722e-07,
+      "loss": 0.078,
+      "step": 145
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 3.042351199477721,
+      "learning_rate": 4.695688205219659e-07,
+      "loss": 0.1287,
+      "step": 146
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 3.2625168137168057,
+      "learning_rate": 4.619740585688146e-07,
+      "loss": 0.1401,
+      "step": 147
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 3.119233422265635,
+      "learning_rate": 4.5440504030167185e-07,
+      "loss": 0.0755,
+      "step": 148
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 2.551277447962574,
+      "learning_rate": 4.4686296095626495e-07,
+      "loss": 0.1041,
+      "step": 149
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.65142155374999,
+      "learning_rate": 4.3934901151435333e-07,
+      "loss": 0.0987,
+      "step": 150
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 284266463232.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

epoch_1/checkpoint-150/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1b9bdac6c229a95edd8b52f2e6ad8ad316ae8b086598f08733c34e3e7848b4
+size 8145

epoch_1/checkpoint-200/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

epoch_1/checkpoint-200/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

epoch_1/checkpoint-200/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "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": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

epoch_1/checkpoint-200/generation_config.json

@@ -0,0 +1,13 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.56.2"
+}

epoch_1/checkpoint-200/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23819a8e54c80fe69993f6a781e00ae15b90598b330879390532d35ba986fbd3
+size 4957560304

epoch_1/checkpoint-200/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cca804dbd306ab00e374fa7e5312c620485ddc89753e85d4e0145038cd0d615
+size 1214366696

epoch_1/checkpoint-200/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_parameters": 241664,
+    "total_size": 6171877376
+  },
+  "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-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-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "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_proj.bias": "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.bias": "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-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-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_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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_proj.bias": "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_proj.bias": "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.bias": "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"
+  }
+}

epoch_1/checkpoint-200/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
+  }
+}

epoch_1/checkpoint-200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

epoch_1/checkpoint-200/tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "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
+    }
+  },
+  "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
+}

epoch_1/checkpoint-200/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004,
+      "grad_norm": 4.017385483397232,
+      "learning_rate": 1.25e-06,
+      "loss": 0.1413,
+      "step": 1
+    },
+    {
+      "epoch": 0.008,
+      "grad_norm": 3.8449675966687606,
+      "learning_rate": 1.2499506526273853e-06,
+      "loss": 0.1328,
+      "step": 2
+    },
+    {
+      "epoch": 0.012,
+      "grad_norm": 2.1638363967847223,
+      "learning_rate": 1.2498026183020626e-06,
+      "loss": 0.086,
+      "step": 3
+    },
+    {
+      "epoch": 0.016,
+      "grad_norm": 3.3743604139964436,
+      "learning_rate": 1.2495559204003684e-06,
+      "loss": 0.1365,
+      "step": 4
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 3.288840036724382,
+      "learning_rate": 1.2492105978787612e-06,
+      "loss": 0.1513,
+      "step": 5
+    },
+    {
+      "epoch": 0.024,
+      "grad_norm": 7.595431480390665,
+      "learning_rate": 1.2487667052676699e-06,
+      "loss": 0.1987,
+      "step": 6
+    },
+    {
+      "epoch": 0.028,
+      "grad_norm": 3.2413826920628166,
+      "learning_rate": 1.2482243126628838e-06,
+      "loss": 0.1202,
+      "step": 7
+    },
+    {
+      "epoch": 0.032,
+      "grad_norm": 4.883733594707665,
+      "learning_rate": 1.247583505714483e-06,
+      "loss": 0.1799,
+      "step": 8
+    },
+    {
+      "epoch": 0.036,
+      "grad_norm": 4.508245483958065,
+      "learning_rate": 1.2468443856133129e-06,
+      "loss": 0.1619,
+      "step": 9
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 4.906984422165932,
+      "learning_rate": 1.2460070690750053e-06,
+      "loss": 0.167,
+      "step": 10
+    },
+    {
+      "epoch": 0.044,
+      "grad_norm": 3.6964749714214906,
+      "learning_rate": 1.245071688321549e-06,
+      "loss": 0.1187,
+      "step": 11
+    },
+    {
+      "epoch": 0.048,
+      "grad_norm": 2.979347665997292,
+      "learning_rate": 1.2440383910604071e-06,
+      "loss": 0.1668,
+      "step": 12
+    },
+    {
+      "epoch": 0.052,
+      "grad_norm": 2.954570728851493,
+      "learning_rate": 1.2429073404611962e-06,
+      "loss": 0.0828,
+      "step": 13
+    },
+    {
+      "epoch": 0.056,
+      "grad_norm": 6.636874452245697,
+      "learning_rate": 1.2416787151299176e-06,
+      "loss": 0.2631,
+      "step": 14
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 3.091490024239134,
+      "learning_rate": 1.2403527090807535e-06,
+      "loss": 0.1144,
+      "step": 15
+    },
+    {
+      "epoch": 0.064,
+      "grad_norm": 2.2323669367718386,
+      "learning_rate": 1.2389295317054306e-06,
+      "loss": 0.0631,
+      "step": 16
+    },
+    {
+      "epoch": 0.068,
+      "grad_norm": 4.4396327514278795,
+      "learning_rate": 1.2374094077401545e-06,
+      "loss": 0.194,
+      "step": 17
+    },
+    {
+      "epoch": 0.072,
+      "grad_norm": 3.8264637726466115,
+      "learning_rate": 1.235792577230121e-06,
+      "loss": 0.1736,
+      "step": 18
+    },
+    {
+      "epoch": 0.076,
+      "grad_norm": 2.999135242898612,
+      "learning_rate": 1.2340792954916109e-06,
+      "loss": 0.1339,
+      "step": 19
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 2.1527155068441246,
+      "learning_rate": 1.2322698330716713e-06,
+      "loss": 0.0834,
+      "step": 20
+    },
+    {
+      "epoch": 0.084,
+      "grad_norm": 4.0286126176650185,
+      "learning_rate": 1.2303644757053945e-06,
+      "loss": 0.1841,
+      "step": 21
+    },
+    {
+      "epoch": 0.088,
+      "grad_norm": 3.9156121312517786,
+      "learning_rate": 1.2283635242707962e-06,
+      "loss": 0.1142,
+      "step": 22
+    },
+    {
+      "epoch": 0.092,
+      "grad_norm": 4.245160129433801,
+      "learning_rate": 1.2262672947413037e-06,
+      "loss": 0.1251,
+      "step": 23
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 5.309528123667374,
+      "learning_rate": 1.22407611813586e-06,
+      "loss": 0.1602,
+      "step": 24
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 6.485877801658527,
+      "learning_rate": 1.221790340466652e-06,
+      "loss": 0.1733,
+      "step": 25
+    },
+    {
+      "epoch": 0.104,
+      "grad_norm": 2.96261019219239,
+      "learning_rate": 1.2194103226844711e-06,
+      "loss": 0.1113,
+      "step": 26
+    },
+    {
+      "epoch": 0.108,
+      "grad_norm": 5.128545078967028,
+      "learning_rate": 1.2169364406217154e-06,
+      "loss": 0.146,
+      "step": 27
+    },
+    {
+      "epoch": 0.112,
+      "grad_norm": 4.463994053430229,
+      "learning_rate": 1.2143690849330405e-06,
+      "loss": 0.1564,
+      "step": 28
+    },
+    {
+      "epoch": 0.116,
+      "grad_norm": 3.344393653898428,
+      "learning_rate": 1.2117086610336714e-06,
+      "loss": 0.103,
+      "step": 29
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 2.176137249160477,
+      "learning_rate": 1.2089555890353826e-06,
+      "loss": 0.0477,
+      "step": 30
+    },
+    {
+      "epoch": 0.124,
+      "grad_norm": 3.051441040807267,
+      "learning_rate": 1.2061103036801573e-06,
+      "loss": 0.0949,
+      "step": 31
+    },
+    {
+      "epoch": 0.128,
+      "grad_norm": 3.5084777203708444,
+      "learning_rate": 1.2031732542715363e-06,
+      "loss": 0.1001,
+      "step": 32
+    },
+    {
+      "epoch": 0.132,
+      "grad_norm": 3.060808348393298,
+      "learning_rate": 1.2001449046036692e-06,
+      "loss": 0.1111,
+      "step": 33
+    },
+    {
+      "epoch": 0.136,
+      "grad_norm": 3.6047867168659997,
+      "learning_rate": 1.1970257328880735e-06,
+      "loss": 0.0838,
+      "step": 34
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 2.605944823640285,
+      "learning_rate": 1.1938162316781223e-06,
+      "loss": 0.1047,
+      "step": 35
+    },
+    {
+      "epoch": 0.144,
+      "grad_norm": 3.642604507481262,
+      "learning_rate": 1.1905169077912623e-06,
+      "loss": 0.1691,
+      "step": 36
+    },
+    {
+      "epoch": 0.148,
+      "grad_norm": 2.977794754734627,
+      "learning_rate": 1.187128282228982e-06,
+      "loss": 0.1335,
+      "step": 37
+    },
+    {
+      "epoch": 0.152,
+      "grad_norm": 3.597549271855966,
+      "learning_rate": 1.18365089009454e-06,
+      "loss": 0.1307,
+      "step": 38
+    },
+    {
+      "epoch": 0.156,
+      "grad_norm": 3.3649862888593303,
+      "learning_rate": 1.1800852805084655e-06,
+      "loss": 0.062,
+      "step": 39
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.183766887602216,
+      "learning_rate": 1.176432016521846e-06,
+      "loss": 0.1588,
+      "step": 40
+    },
+    {
+      "epoch": 0.164,
+      "grad_norm": 3.7163992206687726,
+      "learning_rate": 1.1726916750274148e-06,
+      "loss": 0.0954,
+      "step": 41
+    },
+    {
+      "epoch": 0.168,
+      "grad_norm": 0.40910896062220287,
+      "learning_rate": 1.1688648466684537e-06,
+      "loss": 0.0136,
+      "step": 42
+    },
+    {
+      "epoch": 0.172,
+      "grad_norm": 5.295089388122023,
+      "learning_rate": 1.1649521357455222e-06,
+      "loss": 0.2147,
+      "step": 43
+    },
+    {
+      "epoch": 0.176,
+      "grad_norm": 2.576423141532492,
+      "learning_rate": 1.1609541601210329e-06,
+      "loss": 0.1033,
+      "step": 44
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 5.312566919509821,
+      "learning_rate": 1.1568715511216826e-06,
+      "loss": 0.1621,
+      "step": 45
+    },
+    {
+      "epoch": 0.184,
+      "grad_norm": 5.7157490385942085,
+      "learning_rate": 1.1527049534387595e-06,
+      "loss": 0.2664,
+      "step": 46
+    },
+    {
+      "epoch": 0.188,
+      "grad_norm": 4.642925524228082,
+      "learning_rate": 1.1484550250263388e-06,
+      "loss": 0.152,
+      "step": 47
+    },
+    {
+      "epoch": 0.192,
+      "grad_norm": 6.3866757968856485,
+      "learning_rate": 1.144122436997383e-06,
+      "loss": 0.1785,
+      "step": 48
+    },
+    {
+      "epoch": 0.196,
+      "grad_norm": 4.874612191099983,
+      "learning_rate": 1.1397078735177673e-06,
+      "loss": 0.217,
+      "step": 49
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 3.4575745000644247,
+      "learning_rate": 1.13521203169824e-06,
+      "loss": 0.13,
+      "step": 50
+    },
+    {
+      "epoch": 0.204,
+      "grad_norm": 6.292533852396203,
+      "learning_rate": 1.1306356214843423e-06,
+      "loss": 0.1678,
+      "step": 51
+    },
+    {
+      "epoch": 0.208,
+      "grad_norm": 4.188127391211228,
+      "learning_rate": 1.125979365544298e-06,
+      "loss": 0.1346,
+      "step": 52
+    },
+    {
+      "epoch": 0.212,
+      "grad_norm": 3.404139570651294,
+      "learning_rate": 1.1212439991548971e-06,
+      "loss": 0.1136,
+      "step": 53
+    },
+    {
+      "epoch": 0.216,
+      "grad_norm": 3.7842612979712187,
+      "learning_rate": 1.1164302700853868e-06,
+      "loss": 0.1024,
+      "step": 54
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.3939355583645425,
+      "learning_rate": 1.1115389384793898e-06,
+      "loss": 0.1253,
+      "step": 55
+    },
+    {
+      "epoch": 0.224,
+      "grad_norm": 5.245180376439613,
+      "learning_rate": 1.1065707767348684e-06,
+      "loss": 0.1256,
+      "step": 56
+    },
+    {
+      "epoch": 0.228,
+      "grad_norm": 0.5729530986310555,
+      "learning_rate": 1.101526569382155e-06,
+      "loss": 0.0234,
+      "step": 57
+    },
+    {
+      "epoch": 0.232,
+      "grad_norm": 3.2118514205891486,
+      "learning_rate": 1.096407112960065e-06,
+      "loss": 0.0853,
+      "step": 58
+    },
+    {
+      "epoch": 0.236,
+      "grad_norm": 2.106270697781548,
+      "learning_rate": 1.091213215890114e-06,
+      "loss": 0.0717,
+      "step": 59
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 2.349587278976827,
+      "learning_rate": 1.0859456983488588e-06,
+      "loss": 0.089,
+      "step": 60
+    },
+    {
+      "epoch": 0.244,
+      "grad_norm": 7.876301970845418,
+      "learning_rate": 1.0806053921383823e-06,
+      "loss": 0.2699,
+      "step": 61
+    },
+    {
+      "epoch": 0.248,
+      "grad_norm": 2.531190836425024,
+      "learning_rate": 1.0751931405549419e-06,
+      "loss": 0.1106,
+      "step": 62
+    },
+    {
+      "epoch": 0.252,
+      "grad_norm": 5.5346145359497205,
+      "learning_rate": 1.0697097982558036e-06,
+      "loss": 0.1247,
+      "step": 63
+    },
+    {
+      "epoch": 0.256,
+      "grad_norm": 5.142622243461298,
+      "learning_rate": 1.064156231124281e-06,
+      "loss": 0.1363,
+      "step": 64
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 3.11593080424434,
+      "learning_rate": 1.058533316133003e-06,
+      "loss": 0.0876,
+      "step": 65
+    },
+    {
+      "epoch": 0.264,
+      "grad_norm": 5.967188720796784,
+      "learning_rate": 1.0528419412054306e-06,
+      "loss": 0.1276,
+      "step": 66
+    },
+    {
+      "epoch": 0.268,
+      "grad_norm": 3.9076222868719577,
+      "learning_rate": 1.0470830050756402e-06,
+      "loss": 0.1199,
+      "step": 67
+    },
+    {
+      "epoch": 0.272,
+      "grad_norm": 4.5469221847786905,
+      "learning_rate": 1.0412574171464074e-06,
+      "loss": 0.1236,
+      "step": 68
+    },
+    {
+      "epoch": 0.276,
+      "grad_norm": 3.2424285022940356,
+      "learning_rate": 1.035366097345598e-06,
+      "loss": 0.0848,
+      "step": 69
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 7.322304043916362,
+      "learning_rate": 1.0294099759809028e-06,
+      "loss": 0.2061,
+      "step": 70
+    },
+    {
+      "epoch": 0.284,
+      "grad_norm": 3.832594763604789,
+      "learning_rate": 1.0233899935929311e-06,
+      "loss": 0.1614,
+      "step": 71
+    },
+    {
+      "epoch": 0.288,
+      "grad_norm": 2.4467957912337166,
+      "learning_rate": 1.0173071008066878e-06,
+      "loss": 0.0921,
+      "step": 72
+    },
+    {
+      "epoch": 0.292,
+      "grad_norm": 2.8598136356378525,
+      "learning_rate": 1.011162258181459e-06,
+      "loss": 0.0752,
+      "step": 73
+    },
+    {
+      "epoch": 0.296,
+      "grad_norm": 4.0019435362793905,
+      "learning_rate": 1.0049564360591285e-06,
+      "loss": 0.1029,
+      "step": 74
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.2212138974769413,
+      "learning_rate": 9.986906144109494e-07,
+      "loss": 0.0987,
+      "step": 75
+    },
+    {
+      "epoch": 0.304,
+      "grad_norm": 4.522211217403667,
+      "learning_rate": 9.923657826827958e-07,
+      "loss": 0.1602,
+      "step": 76
+    },
+    {
+      "epoch": 0.308,
+      "grad_norm": 3.376245985310258,
+      "learning_rate": 9.859829396389172e-07,
+      "loss": 0.1176,
+      "step": 77
+    },
+    {
+      "epoch": 0.312,
+      "grad_norm": 6.073368961666502,
+      "learning_rate": 9.79543093204223e-07,
+      "loss": 0.1807,
+      "step": 78
+    },
+    {
+      "epoch": 0.316,
+      "grad_norm": 7.706860943134537,
+      "learning_rate": 9.730472603051175e-07,
+      "loss": 0.149,
+      "step": 79
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 1.81425757189223,
+      "learning_rate": 9.664964667089184e-07,
+      "loss": 0.0606,
+      "step": 80
+    },
+    {
+      "epoch": 0.324,
+      "grad_norm": 3.1034608925705465,
+      "learning_rate": 9.59891746861873e-07,
+      "loss": 0.1235,
+      "step": 81
+    },
+    {
+      "epoch": 0.328,
+      "grad_norm": 5.4593767606269745,
+      "learning_rate": 9.532341437258099e-07,
+      "loss": 0.1292,
+      "step": 82
+    },
+    {
+      "epoch": 0.332,
+      "grad_norm": 3.35883770074761,
+      "learning_rate": 9.465247086134416e-07,
+      "loss": 0.1196,
+      "step": 83
+    },
+    {
+      "epoch": 0.336,
+      "grad_norm": 5.458524887235343,
+      "learning_rate": 9.397645010223506e-07,
+      "loss": 0.2082,
+      "step": 84
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 4.345193079077953,
+      "learning_rate": 9.329545884676823e-07,
+      "loss": 0.2584,
+      "step": 85
+    },
+    {
+      "epoch": 0.344,
+      "grad_norm": 3.4245431779216946,
+      "learning_rate": 9.260960463135721e-07,
+      "loss": 0.1003,
+      "step": 86
+    },
+    {
+      "epoch": 0.348,
+      "grad_norm": 4.046815164804643,
+      "learning_rate": 9.191899576033331e-07,
+      "loss": 0.127,
+      "step": 87
+    },
+    {
+      "epoch": 0.352,
+      "grad_norm": 4.551196552703828,
+      "learning_rate": 9.122374128884301e-07,
+      "loss": 0.2096,
+      "step": 88
+    },
+    {
+      "epoch": 0.356,
+      "grad_norm": 3.3977880693097093,
+      "learning_rate": 9.052395100562704e-07,
+      "loss": 0.1034,
+      "step": 89
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.5277523583283517,
+      "learning_rate": 8.981973541568331e-07,
+      "loss": 0.0185,
+      "step": 90
+    },
+    {
+      "epoch": 0.364,
+      "grad_norm": 3.715550434329015,
+      "learning_rate": 8.911120572281705e-07,
+      "loss": 0.1184,
+      "step": 91
+    },
+    {
+      "epoch": 0.368,
+      "grad_norm": 2.2115026803492053,
+      "learning_rate": 8.839847381208027e-07,
+      "loss": 0.0669,
+      "step": 92
+    },
+    {
+      "epoch": 0.372,
+      "grad_norm": 3.5200936151406346,
+      "learning_rate": 8.768165223210393e-07,
+      "loss": 0.0676,
+      "step": 93
+    },
+    {
+      "epoch": 0.376,
+      "grad_norm": 2.6500028260333464,
+      "learning_rate": 8.696085417732517e-07,
+      "loss": 0.0601,
+      "step": 94
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 3.676896418632736,
+      "learning_rate": 8.623619347011259e-07,
+      "loss": 0.1151,
+      "step": 95
+    },
+    {
+      "epoch": 0.384,
+      "grad_norm": 4.125582103259355,
+      "learning_rate": 8.550778454279239e-07,
+      "loss": 0.1375,
+      "step": 96
+    },
+    {
+      "epoch": 0.388,
+      "grad_norm": 4.002370086986581,
+      "learning_rate": 8.477574241957817e-07,
+      "loss": 0.1177,
+      "step": 97
+    },
+    {
+      "epoch": 0.392,
+      "grad_norm": 3.3858392990737753,
+      "learning_rate": 8.404018269840731e-07,
+      "loss": 0.077,
+      "step": 98
+    },
+    {
+      "epoch": 0.396,
+      "grad_norm": 3.0438174129534703,
+      "learning_rate": 8.330122153268668e-07,
+      "loss": 0.1303,
+      "step": 99
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 2.0043982911779907,
+      "learning_rate": 8.255897561295059e-07,
+      "loss": 0.0558,
+      "step": 100
+    },
+    {
+      "epoch": 0.404,
+      "grad_norm": 3.908268142779911,
+      "learning_rate": 8.181356214843422e-07,
+      "loss": 0.1988,
+      "step": 101
+    },
+    {
+      "epoch": 0.408,
+      "grad_norm": 2.562662931219627,
+      "learning_rate": 8.106509884856469e-07,
+      "loss": 0.0558,
+      "step": 102
+    },
+    {
+      "epoch": 0.412,
+      "grad_norm": 5.9781104173538715,
+      "learning_rate": 8.031370390437352e-07,
+      "loss": 0.2385,
+      "step": 103
+    },
+    {
+      "epoch": 0.416,
+      "grad_norm": 2.4126656649906333,
+      "learning_rate": 7.955949596983284e-07,
+      "loss": 0.1026,
+      "step": 104
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 3.672796222838684,
+      "learning_rate": 7.880259414311857e-07,
+      "loss": 0.1316,
+      "step": 105
+    },
+    {
+      "epoch": 0.424,
+      "grad_norm": 3.588897224218465,
+      "learning_rate": 7.804311794780345e-07,
+      "loss": 0.1586,
+      "step": 106
+    },
+    {
+      "epoch": 0.428,
+      "grad_norm": 3.5642760730996934,
+      "learning_rate": 7.728118731398281e-07,
+      "loss": 0.1325,
+      "step": 107
+    },
+    {
+      "epoch": 0.432,
+      "grad_norm": 2.849326457820366,
+      "learning_rate": 7.651692255933634e-07,
+      "loss": 0.1072,
+      "step": 108
+    },
+    {
+      "epoch": 0.436,
+      "grad_norm": 7.160268721443933,
+      "learning_rate": 7.575044437012844e-07,
+      "loss": 0.212,
+      "step": 109
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 3.51867195731136,
+      "learning_rate": 7.498187378215044e-07,
+      "loss": 0.0868,
+      "step": 110
+    },
+    {
+      "epoch": 0.444,
+      "grad_norm": 5.33044270549408,
+      "learning_rate": 7.421133216160781e-07,
+      "loss": 0.11,
+      "step": 111
+    },
+    {
+      "epoch": 0.448,
+      "grad_norm": 3.7800629114651776,
+      "learning_rate": 7.343894118595477e-07,
+      "loss": 0.1271,
+      "step": 112
+    },
+    {
+      "epoch": 0.452,
+      "grad_norm": 3.3562639092242406,
+      "learning_rate": 7.266482282468024e-07,
+      "loss": 0.1037,
+      "step": 113
+    },
+    {
+      "epoch": 0.456,
+      "grad_norm": 2.676228500418713,
+      "learning_rate": 7.188909932004733e-07,
+      "loss": 0.0674,
+      "step": 114
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.46204350887125,
+      "learning_rate": 7.111189316778988e-07,
+      "loss": 0.1317,
+      "step": 115
+    },
+    {
+      "epoch": 0.464,
+      "grad_norm": 5.208156619949427,
+      "learning_rate": 7.033332709776902e-07,
+      "loss": 0.1565,
+      "step": 116
+    },
+    {
+      "epoch": 0.468,
+      "grad_norm": 4.253140685795728,
+      "learning_rate": 6.955352405459261e-07,
+      "loss": 0.1173,
+      "step": 117
+    },
+    {
+      "epoch": 0.472,
+      "grad_norm": 2.1409973511035663,
+      "learning_rate": 6.877260717820093e-07,
+      "loss": 0.0894,
+      "step": 118
+    },
+    {
+      "epoch": 0.476,
+      "grad_norm": 2.636844618416736,
+      "learning_rate": 6.799069978442147e-07,
+      "loss": 0.0794,
+      "step": 119
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 2.0790955874335193,
+      "learning_rate": 6.72079253454958e-07,
+      "loss": 0.072,
+      "step": 120
+    },
+    {
+      "epoch": 0.484,
+      "grad_norm": 5.470329539821142,
+      "learning_rate": 6.642440747058209e-07,
+      "loss": 0.1631,
+      "step": 121
+    },
+    {
+      "epoch": 0.488,
+      "grad_norm": 2.9616163814022767,
+      "learning_rate": 6.56402698862356e-07,
+      "loss": 0.1343,
+      "step": 122
+    },
+    {
+      "epoch": 0.492,
+      "grad_norm": 2.6774812765668528,
+      "learning_rate": 6.485563641687093e-07,
+      "loss": 0.1067,
+      "step": 123
+    },
+    {
+      "epoch": 0.496,
+      "grad_norm": 3.546931596203205,
+      "learning_rate": 6.407063096520861e-07,
+      "loss": 0.1099,
+      "step": 124
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 2.957398392343282,
+      "learning_rate": 6.328537749270955e-07,
+      "loss": 0.1128,
+      "step": 125
+    },
+    {
+      "epoch": 0.504,
+      "grad_norm": 3.1585121573793913,
+      "learning_rate": 6.25e-07,
+      "loss": 0.1311,
+      "step": 126
+    },
+    {
+      "epoch": 0.508,
+      "grad_norm": 5.993701817302737,
+      "learning_rate": 6.171462250729046e-07,
+      "loss": 0.2228,
+      "step": 127
+    },
+    {
+      "epoch": 0.512,
+      "grad_norm": 3.059251333266507,
+      "learning_rate": 6.092936903479141e-07,
+      "loss": 0.1377,
+      "step": 128
+    },
+    {
+      "epoch": 0.516,
+      "grad_norm": 2.7050519202831773,
+      "learning_rate": 6.014436358312909e-07,
+      "loss": 0.0669,
+      "step": 129
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.8139156307086175,
+      "learning_rate": 5.935973011376441e-07,
+      "loss": 0.0689,
+      "step": 130
+    },
+    {
+      "epoch": 0.524,
+      "grad_norm": 4.439701739697846,
+      "learning_rate": 5.857559252941792e-07,
+      "loss": 0.1976,
+      "step": 131
+    },
+    {
+      "epoch": 0.528,
+      "grad_norm": 3.825102266906039,
+      "learning_rate": 5.779207465450422e-07,
+      "loss": 0.1406,
+      "step": 132
+    },
+    {
+      "epoch": 0.532,
+      "grad_norm": 1.9701757945162446,
+      "learning_rate": 5.700930021557855e-07,
+      "loss": 0.0711,
+      "step": 133
+    },
+    {
+      "epoch": 0.536,
+      "grad_norm": 4.622445287004756,
+      "learning_rate": 5.622739282179907e-07,
+      "loss": 0.1108,
+      "step": 134
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 5.503076971686029,
+      "learning_rate": 5.544647594540739e-07,
+      "loss": 0.2497,
+      "step": 135
+    },
+    {
+      "epoch": 0.544,
+      "grad_norm": 4.029937986134255,
+      "learning_rate": 5.466667290223098e-07,
+      "loss": 0.1739,
+      "step": 136
+    },
+    {
+      "epoch": 0.548,
+      "grad_norm": 3.9748792359783676,
+      "learning_rate": 5.388810683221013e-07,
+      "loss": 0.1316,
+      "step": 137
+    },
+    {
+      "epoch": 0.552,
+      "grad_norm": 4.756036320737784,
+      "learning_rate": 5.311090067995268e-07,
+      "loss": 0.0975,
+      "step": 138
+    },
+    {
+      "epoch": 0.556,
+      "grad_norm": 3.167102420161004,
+      "learning_rate": 5.233517717531978e-07,
+      "loss": 0.1049,
+      "step": 139
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 2.9601077878796214,
+      "learning_rate": 5.156105881404524e-07,
+      "loss": 0.0927,
+      "step": 140
+    },
+    {
+      "epoch": 0.564,
+      "grad_norm": 3.6670426901017867,
+      "learning_rate": 5.07886678383922e-07,
+      "loss": 0.1055,
+      "step": 141
+    },
+    {
+      "epoch": 0.568,
+      "grad_norm": 2.44582710953066,
+      "learning_rate": 5.001812621784957e-07,
+      "loss": 0.1004,
+      "step": 142
+    },
+    {
+      "epoch": 0.572,
+      "grad_norm": 3.3343903580284855,
+      "learning_rate": 4.92495556298716e-07,
+      "loss": 0.1558,
+      "step": 143
+    },
+    {
+      "epoch": 0.576,
+      "grad_norm": 4.207281714783421,
+      "learning_rate": 4.848307744066369e-07,
+      "loss": 0.121,
+      "step": 144
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 2.6177447522900485,
+      "learning_rate": 4.771881268601722e-07,
+      "loss": 0.078,
+      "step": 145
+    },
+    {
+      "epoch": 0.584,
+      "grad_norm": 3.042351199477721,
+      "learning_rate": 4.695688205219659e-07,
+      "loss": 0.1287,
+      "step": 146
+    },
+    {
+      "epoch": 0.588,
+      "grad_norm": 3.2625168137168057,
+      "learning_rate": 4.619740585688146e-07,
+      "loss": 0.1401,
+      "step": 147
+    },
+    {
+      "epoch": 0.592,
+      "grad_norm": 3.119233422265635,
+      "learning_rate": 4.5440504030167185e-07,
+      "loss": 0.0755,
+      "step": 148
+    },
+    {
+      "epoch": 0.596,
+      "grad_norm": 2.551277447962574,
+      "learning_rate": 4.4686296095626495e-07,
+      "loss": 0.1041,
+      "step": 149
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 2.65142155374999,
+      "learning_rate": 4.3934901151435333e-07,
+      "loss": 0.0987,
+      "step": 150
+    },
+    {
+      "epoch": 0.604,
+      "grad_norm": 4.130355895506551,
+      "learning_rate": 4.3186437851565794e-07,
+      "loss": 0.1531,
+      "step": 151
+    },
+    {
+      "epoch": 0.608,
+      "grad_norm": 2.2684979045566465,
+      "learning_rate": 4.244102438704942e-07,
+      "loss": 0.0997,
+      "step": 152
+    },
+    {
+      "epoch": 0.612,
+      "grad_norm": 6.107769430590296,
+      "learning_rate": 4.169877846731334e-07,
+      "loss": 0.1861,
+      "step": 153
+    },
+    {
+      "epoch": 0.616,
+      "grad_norm": 3.7629532551976648,
+      "learning_rate": 4.095981730159269e-07,
+      "loss": 0.1099,
+      "step": 154
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 6.05211783397647,
+      "learning_rate": 4.022425758042184e-07,
+      "loss": 0.1526,
+      "step": 155
+    },
+    {
+      "epoch": 0.624,
+      "grad_norm": 6.34232425065565,
+      "learning_rate": 3.9492215457207634e-07,
+      "loss": 0.1734,
+      "step": 156
+    },
+    {
+      "epoch": 0.628,
+      "grad_norm": 4.59848427107727,
+      "learning_rate": 3.8763806529887443e-07,
+      "loss": 0.1358,
+      "step": 157
+    },
+    {
+      "epoch": 0.632,
+      "grad_norm": 4.770222102495851,
+      "learning_rate": 3.803914582267485e-07,
+      "loss": 0.148,
+      "step": 158
+    },
+    {
+      "epoch": 0.636,
+      "grad_norm": 3.4041753765242118,
+      "learning_rate": 3.7318347767896093e-07,
+      "loss": 0.1623,
+      "step": 159
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 3.5991511368218503,
+      "learning_rate": 3.660152618791975e-07,
+      "loss": 0.1527,
+      "step": 160
+    },
+    {
+      "epoch": 0.644,
+      "grad_norm": 3.657334411571759,
+      "learning_rate": 3.588879427718296e-07,
+      "loss": 0.086,
+      "step": 161
+    },
+    {
+      "epoch": 0.648,
+      "grad_norm": 4.051471747415588,
+      "learning_rate": 3.518026458431671e-07,
+      "loss": 0.1356,
+      "step": 162
+    },
+    {
+      "epoch": 0.652,
+      "grad_norm": 4.793383057458224,
+      "learning_rate": 3.4476048994372996e-07,
+      "loss": 0.1509,
+      "step": 163
+    },
+    {
+      "epoch": 0.656,
+      "grad_norm": 2.1365676277517434,
+      "learning_rate": 3.3776258711157016e-07,
+      "loss": 0.0798,
+      "step": 164
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 3.2273900087686767,
+      "learning_rate": 3.3081004239666715e-07,
+      "loss": 0.1135,
+      "step": 165
+    },
+    {
+      "epoch": 0.664,
+      "grad_norm": 4.809807837379783,
+      "learning_rate": 3.239039536864279e-07,
+      "loss": 0.1287,
+      "step": 166
+    },
+    {
+      "epoch": 0.668,
+      "grad_norm": 5.888085910624194,
+      "learning_rate": 3.170454115323179e-07,
+      "loss": 0.1478,
+      "step": 167
+    },
+    {
+      "epoch": 0.672,
+      "grad_norm": 4.230676768139858,
+      "learning_rate": 3.1023549897764954e-07,
+      "loss": 0.1537,
+      "step": 168
+    },
+    {
+      "epoch": 0.676,
+      "grad_norm": 5.039741042579713,
+      "learning_rate": 3.0347529138655845e-07,
+      "loss": 0.1987,
+      "step": 169
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 3.178464828590722,
+      "learning_rate": 2.9676585627419016e-07,
+      "loss": 0.1145,
+      "step": 170
+    },
+    {
+      "epoch": 0.684,
+      "grad_norm": 3.8148898717720083,
+      "learning_rate": 2.90108253138127e-07,
+      "loss": 0.1138,
+      "step": 171
+    },
+    {
+      "epoch": 0.688,
+      "grad_norm": 4.157270976485161,
+      "learning_rate": 2.835035332910819e-07,
+      "loss": 0.114,
+      "step": 172
+    },
+    {
+      "epoch": 0.692,
+      "grad_norm": 20.048202797184977,
+      "learning_rate": 2.769527396948828e-07,
+      "loss": 0.6356,
+      "step": 173
+    },
+    {
+      "epoch": 0.696,
+      "grad_norm": 4.829166295515264,
+      "learning_rate": 2.7045690679577734e-07,
+      "loss": 0.1435,
+      "step": 174
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 5.0828359611968095,
+      "learning_rate": 2.6401706036108287e-07,
+      "loss": 0.2288,
+      "step": 175
+    },
+    {
+      "epoch": 0.704,
+      "grad_norm": 3.5414989469024105,
+      "learning_rate": 2.5763421731720437e-07,
+      "loss": 0.13,
+      "step": 176
+    },
+    {
+      "epoch": 0.708,
+      "grad_norm": 2.5340319460325724,
+      "learning_rate": 2.5130938558905094e-07,
+      "loss": 0.0857,
+      "step": 177
+    },
+    {
+      "epoch": 0.712,
+      "grad_norm": 2.734460740799023,
+      "learning_rate": 2.450435639408718e-07,
+      "loss": 0.1071,
+      "step": 178
+    },
+    {
+      "epoch": 0.716,
+      "grad_norm": 3.352362451718902,
+      "learning_rate": 2.3883774181854114e-07,
+      "loss": 0.1189,
+      "step": 179
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.7763891778446506,
+      "learning_rate": 2.326928991933123e-07,
+      "loss": 0.112,
+      "step": 180
+    },
+    {
+      "epoch": 0.724,
+      "grad_norm": 2.4440605550029426,
+      "learning_rate": 2.2661000640706893e-07,
+      "loss": 0.0754,
+      "step": 181
+    },
+    {
+      "epoch": 0.728,
+      "grad_norm": 4.031857835325126,
+      "learning_rate": 2.2059002401909752e-07,
+      "loss": 0.1295,
+      "step": 182
+    },
+    {
+      "epoch": 0.732,
+      "grad_norm": 3.8385081642897645,
+      "learning_rate": 2.1463390265440233e-07,
+      "loss": 0.1567,
+      "step": 183
+    },
+    {
+      "epoch": 0.736,
+      "grad_norm": 2.680121298100838,
+      "learning_rate": 2.087425828535928e-07,
+      "loss": 0.0921,
+      "step": 184
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 2.5523520374843502,
+      "learning_rate": 2.0291699492435972e-07,
+      "loss": 0.0799,
+      "step": 185
+    },
+    {
+      "epoch": 0.744,
+      "grad_norm": 2.1929917068003206,
+      "learning_rate": 1.9715805879456955e-07,
+      "loss": 0.1085,
+      "step": 186
+    },
+    {
+      "epoch": 0.748,
+      "grad_norm": 0.6376191244307428,
+      "learning_rate": 1.91466683866997e-07,
+      "loss": 0.0244,
+      "step": 187
+    },
+    {
+      "epoch": 0.752,
+      "grad_norm": 2.989590892102221,
+      "learning_rate": 1.8584376887571934e-07,
+      "loss": 0.0895,
+      "step": 188
+    },
+    {
+      "epoch": 0.756,
+      "grad_norm": 5.449676941662685,
+      "learning_rate": 1.8029020174419669e-07,
+      "loss": 0.2837,
+      "step": 189
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 3.0817912555647586,
+      "learning_rate": 1.748068594450582e-07,
+      "loss": 0.0783,
+      "step": 190
+    },
+    {
+      "epoch": 0.764,
+      "grad_norm": 2.7703640342304037,
+      "learning_rate": 1.6939460786161792e-07,
+      "loss": 0.0988,
+      "step": 191
+    },
+    {
+      "epoch": 0.768,
+      "grad_norm": 2.894586219409546,
+      "learning_rate": 1.6405430165114139e-07,
+      "loss": 0.1094,
+      "step": 192
+    },
+    {
+      "epoch": 0.772,
+      "grad_norm": 4.581321516290858,
+      "learning_rate": 1.587867841098862e-07,
+      "loss": 0.1128,
+      "step": 193
+    },
+    {
+      "epoch": 0.776,
+      "grad_norm": 3.422661784516217,
+      "learning_rate": 1.535928870399351e-07,
+      "loss": 0.0942,
+      "step": 194
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 3.345040791495095,
+      "learning_rate": 1.48473430617845e-07,
+      "loss": 0.1306,
+      "step": 195
+    },
+    {
+      "epoch": 0.784,
+      "grad_norm": 2.9441279129790607,
+      "learning_rate": 1.434292232651318e-07,
+      "loss": 0.0998,
+      "step": 196
+    },
+    {
+      "epoch": 0.788,
+      "grad_norm": 5.881480896938972,
+      "learning_rate": 1.3846106152061043e-07,
+      "loss": 0.2226,
+      "step": 197
+    },
+    {
+      "epoch": 0.792,
+      "grad_norm": 3.90644057826781,
+      "learning_rate": 1.3356972991461317e-07,
+      "loss": 0.0979,
+      "step": 198
+    },
+    {
+      "epoch": 0.796,
+      "grad_norm": 2.3835595988411757,
+      "learning_rate": 1.287560008451029e-07,
+      "loss": 0.0872,
+      "step": 199
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 5.801483313343428,
+      "learning_rate": 1.2402063445570205e-07,
+      "loss": 0.1857,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 250,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 50,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 373028683776.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

epoch_1/checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d1b9bdac6c229a95edd8b52f2e6ad8ad316ae8b086598f08733c34e3e7848b4
+size 8145

epoch_1/checkpoint-250/added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|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
+}

epoch_1/checkpoint-250/chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# 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' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) 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' }}
+{%- endif %}

epoch_1/checkpoint-250/config.json

@@ -0,0 +1,66 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "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": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}