Upload trained Qwen-4B model on Hyperswitch data

.gitattributes

@@ -33,3 +33,7 @@ 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
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-324/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+emergency_checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,48 @@
+---
+license: apache-2.0
+base_model: Qwen/Qwen3-4B
+tags:
+- code
+- hyperswitch
+- pretrained
+- qwen
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# qwen-14b-hyperswitch-v1
+
+qwen14
+
+## Model Details
+
+- **Base Model**: Qwen/Qwen3-4B
+- **Training Data**: Hyperswitch repository code
+- **Final Training Loss**: 0.4966
+- **Training Progress**: 92% complete (excellent results)
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+import torch
+
+model = AutoModelForCausalLM.from_pretrained(
+    "archit11/qwen-14b-hyperswitch-v1",
+    torch_dtype=torch.float16,
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("archit11/qwen-14b-hyperswitch-v1")
+
+# Generate code
+prompt = "use crate::"
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(**inputs, max_length=150, temperature=0.3)
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(result)
+```
+
+## Training Details
+
+This model was fine-tuned on the Hyperswitch codebase to improve code completion and generation for Rust payment processing systems.

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-200/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-200/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-200/config.json

@@ -0,0 +1,72 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-200/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.56.1"
+}

checkpoint-200/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:072af4e8108e7ee2acab88da7efb128c7fd8e51f8ce6f9818906be57f625ac1a
+size 4984780720

checkpoint-200/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:021c4625731b6621cf89b188e6c860dffb8c59bc151c00a5bc7e7239209a11c6
+size 4980891968

checkpoint-200/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e6709a27edc8a92c8a50fc81f829280997d911c9636da9a8e7df3ca21dfa731
+size 4928485016

checkpoint-200/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7de7935642af11c825cd9334ee5341d7ef260ffb14a0e6225d9ea5ff901a066
+size 4980892032

checkpoint-200/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6069d453f7f82f6384f099922f186d18f4ef4ad20225bb324dde86a702319e63
+size 4928485016

checkpoint-200/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:223a86f95a2702bcb0e5a26c3732bbf8742773538adbb6b1c66f8724ef2ffd15
+size 4733130456

checkpoint-200/model.safetensors.index.json

@@ -0,0 +1,451 @@
+{
+  "metadata": {
+    "total_parameters": 14768307200,
+    "total_size": 29536614400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

checkpoint-200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62ba0b88893083bf46683675866763debef6ea8fb21f4facf7fa0ee31faa4683
+size 59073623712

checkpoint-200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c15d10da233568de54180256b227cfe26dea6eaac6df08048357111de9ef60d
+size 14645

checkpoint-200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df35dfa383765c61d3756802588956c1c2bc4a51a62badb582b0aeeea1191e49
+size 1465

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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-200/tokenizer.json

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

checkpoint-200/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,1434 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.6184770003865481,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0030923850019327404,
+      "grad_norm": 1.7919921875,
+      "learning_rate": 0.0,
+      "loss": 0.5969,
+      "step": 1
+    },
+    {
+      "epoch": 0.006184770003865481,
+      "grad_norm": 1.9970703125,
+      "learning_rate": 6.666666666666667e-08,
+      "loss": 0.6202,
+      "step": 2
+    },
+    {
+      "epoch": 0.009277155005798222,
+      "grad_norm": 1.6474609375,
+      "learning_rate": 1.3333333333333334e-07,
+      "loss": 0.7447,
+      "step": 3
+    },
+    {
+      "epoch": 0.012369540007730962,
+      "grad_norm": 1.7734375,
+      "learning_rate": 2e-07,
+      "loss": 0.8834,
+      "step": 4
+    },
+    {
+      "epoch": 0.015461925009663703,
+      "grad_norm": 1.52734375,
+      "learning_rate": 2.6666666666666667e-07,
+      "loss": 0.7299,
+      "step": 5
+    },
+    {
+      "epoch": 0.018554310011596443,
+      "grad_norm": 1.623046875,
+      "learning_rate": 3.333333333333333e-07,
+      "loss": 0.7126,
+      "step": 6
+    },
+    {
+      "epoch": 0.021646695013529185,
+      "grad_norm": 2.2890625,
+      "learning_rate": 4e-07,
+      "loss": 0.8068,
+      "step": 7
+    },
+    {
+      "epoch": 0.024739080015461924,
+      "grad_norm": 3.50390625,
+      "learning_rate": 4.6666666666666666e-07,
+      "loss": 0.5119,
+      "step": 8
+    },
+    {
+      "epoch": 0.027831465017394665,
+      "grad_norm": 3.953125,
+      "learning_rate": 5.333333333333333e-07,
+      "loss": 0.413,
+      "step": 9
+    },
+    {
+      "epoch": 0.030923850019327407,
+      "grad_norm": 136.375,
+      "learning_rate": 6e-07,
+      "loss": 4.7449,
+      "step": 10
+    },
+    {
+      "epoch": 0.034016235021260145,
+      "grad_norm": 185.625,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 7.8581,
+      "step": 11
+    },
+    {
+      "epoch": 0.03710862002319289,
+      "grad_norm": 254.875,
+      "learning_rate": 7.333333333333332e-07,
+      "loss": 11.5138,
+      "step": 12
+    },
+    {
+      "epoch": 0.04020100502512563,
+      "grad_norm": 250.5,
+      "learning_rate": 8e-07,
+      "loss": 11.6085,
+      "step": 13
+    },
+    {
+      "epoch": 0.04329339002705837,
+      "grad_norm": 199.625,
+      "learning_rate": 8.666666666666667e-07,
+      "loss": 11.0929,
+      "step": 14
+    },
+    {
+      "epoch": 0.04638577502899111,
+      "grad_norm": 164.375,
+      "learning_rate": 9.333333333333333e-07,
+      "loss": 9.0069,
+      "step": 15
+    },
+    {
+      "epoch": 0.04947816003092385,
+      "grad_norm": 191.125,
+      "learning_rate": 1e-06,
+      "loss": 10.9254,
+      "step": 16
+    },
+    {
+      "epoch": 0.05257054503285659,
+      "grad_norm": 226.0,
+      "learning_rate": 9.99974158420562e-07,
+      "loss": 10.8139,
+      "step": 17
+    },
+    {
+      "epoch": 0.05566293003478933,
+      "grad_norm": 291.5,
+      "learning_rate": 9.99896636353397e-07,
+      "loss": 9.8274,
+      "step": 18
+    },
+    {
+      "epoch": 0.05875531503672207,
+      "grad_norm": 245.5,
+      "learning_rate": 9.997674418116758e-07,
+      "loss": 7.577,
+      "step": 19
+    },
+    {
+      "epoch": 0.061847700038654814,
+      "grad_norm": 246.25,
+      "learning_rate": 9.99586588149762e-07,
+      "loss": 6.5899,
+      "step": 20
+    },
+    {
+      "epoch": 0.06494008504058756,
+      "grad_norm": 112.0,
+      "learning_rate": 9.993540940618332e-07,
+      "loss": 4.777,
+      "step": 21
+    },
+    {
+      "epoch": 0.06803247004252029,
+      "grad_norm": 132.625,
+      "learning_rate": 9.990699835799469e-07,
+      "loss": 5.0894,
+      "step": 22
+    },
+    {
+      "epoch": 0.07112485504445304,
+      "grad_norm": 110.5,
+      "learning_rate": 9.987342860715575e-07,
+      "loss": 4.3164,
+      "step": 23
+    },
+    {
+      "epoch": 0.07421724004638577,
+      "grad_norm": 80.1875,
+      "learning_rate": 9.983470362364801e-07,
+      "loss": 4.1167,
+      "step": 24
+    },
+    {
+      "epoch": 0.07730962504831851,
+      "grad_norm": 36.03125,
+      "learning_rate": 9.979082741033045e-07,
+      "loss": 2.8033,
+      "step": 25
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 32.15625,
+      "learning_rate": 9.97418045025257e-07,
+      "loss": 3.3556,
+      "step": 26
+    },
+    {
+      "epoch": 0.08349439505218399,
+      "grad_norm": 32.96875,
+      "learning_rate": 9.968763996755115e-07,
+      "loss": 3.8153,
+      "step": 27
+    },
+    {
+      "epoch": 0.08658678005411674,
+      "grad_norm": 26.3125,
+      "learning_rate": 9.96283394041954e-07,
+      "loss": 2.8114,
+      "step": 28
+    },
+    {
+      "epoch": 0.08967916505604948,
+      "grad_norm": 24.125,
+      "learning_rate": 9.956390894213928e-07,
+      "loss": 2.7601,
+      "step": 29
+    },
+    {
+      "epoch": 0.09277155005798222,
+      "grad_norm": 24.359375,
+      "learning_rate": 9.949435524132244e-07,
+      "loss": 2.8906,
+      "step": 30
+    },
+    {
+      "epoch": 0.09586393505991496,
+      "grad_norm": 19.28125,
+      "learning_rate": 9.94196854912548e-07,
+      "loss": 2.3873,
+      "step": 31
+    },
+    {
+      "epoch": 0.0989563200618477,
+      "grad_norm": 18.71875,
+      "learning_rate": 9.933990741027348e-07,
+      "loss": 2.4901,
+      "step": 32
+    },
+    {
+      "epoch": 0.10204870506378044,
+      "grad_norm": 25.375,
+      "learning_rate": 9.925502924474493e-07,
+      "loss": 2.3877,
+      "step": 33
+    },
+    {
+      "epoch": 0.10514109006571318,
+      "grad_norm": 20.1875,
+      "learning_rate": 9.91650597682126e-07,
+      "loss": 2.0152,
+      "step": 34
+    },
+    {
+      "epoch": 0.10823347506764593,
+      "grad_norm": 18.453125,
+      "learning_rate": 9.907000828049e-07,
+      "loss": 1.624,
+      "step": 35
+    },
+    {
+      "epoch": 0.11132586006957866,
+      "grad_norm": 18.90625,
+      "learning_rate": 9.896988460669938e-07,
+      "loss": 2.1227,
+      "step": 36
+    },
+    {
+      "epoch": 0.11441824507151141,
+      "grad_norm": 17.421875,
+      "learning_rate": 9.886469909625622e-07,
+      "loss": 1.6674,
+      "step": 37
+    },
+    {
+      "epoch": 0.11751063007344414,
+      "grad_norm": 11.125,
+      "learning_rate": 9.875446262179947e-07,
+      "loss": 1.0941,
+      "step": 38
+    },
+    {
+      "epoch": 0.12060301507537688,
+      "grad_norm": 12.90625,
+      "learning_rate": 9.863918657806751e-07,
+      "loss": 1.6579,
+      "step": 39
+    },
+    {
+      "epoch": 0.12369540007730963,
+      "grad_norm": 18.0625,
+      "learning_rate": 9.851888288072053e-07,
+      "loss": 1.183,
+      "step": 40
+    },
+    {
+      "epoch": 0.12678778507924238,
+      "grad_norm": 29.65625,
+      "learning_rate": 9.839356396510874e-07,
+      "loss": 1.4809,
+      "step": 41
+    },
+    {
+      "epoch": 0.1298801700811751,
+      "grad_norm": 26.4375,
+      "learning_rate": 9.826324278498698e-07,
+      "loss": 1.5772,
+      "step": 42
+    },
+    {
+      "epoch": 0.13297255508310785,
+      "grad_norm": 16.390625,
+      "learning_rate": 9.81279328111758e-07,
+      "loss": 1.2533,
+      "step": 43
+    },
+    {
+      "epoch": 0.13606494008504058,
+      "grad_norm": 12.4453125,
+      "learning_rate": 9.79876480301689e-07,
+      "loss": 1.2557,
+      "step": 44
+    },
+    {
+      "epoch": 0.13915732508697332,
+      "grad_norm": 8.9765625,
+      "learning_rate": 9.784240294268754e-07,
+      "loss": 1.3086,
+      "step": 45
+    },
+    {
+      "epoch": 0.14224971008890608,
+      "grad_norm": 6.34765625,
+      "learning_rate": 9.769221256218162e-07,
+      "loss": 1.2175,
+      "step": 46
+    },
+    {
+      "epoch": 0.1453420950908388,
+      "grad_norm": 4.5234375,
+      "learning_rate": 9.753709241327773e-07,
+      "loss": 1.1835,
+      "step": 47
+    },
+    {
+      "epoch": 0.14843448009277155,
+      "grad_norm": 3.810546875,
+      "learning_rate": 9.73770585301744e-07,
+      "loss": 1.1484,
+      "step": 48
+    },
+    {
+      "epoch": 0.15152686509470428,
+      "grad_norm": 3.814453125,
+      "learning_rate": 9.721212745498492e-07,
+      "loss": 1.2048,
+      "step": 49
+    },
+    {
+      "epoch": 0.15461925009663702,
+      "grad_norm": 3.79296875,
+      "learning_rate": 9.70423162360272e-07,
+      "loss": 1.2032,
+      "step": 50
+    },
+    {
+      "epoch": 0.15771163509856978,
+      "grad_norm": 3.427734375,
+      "learning_rate": 9.686764242606163e-07,
+      "loss": 1.0343,
+      "step": 51
+    },
+    {
+      "epoch": 0.16080402010050251,
+      "grad_norm": 3.875,
+      "learning_rate": 9.668812408047678e-07,
+      "loss": 1.0729,
+      "step": 52
+    },
+    {
+      "epoch": 0.16389640510243525,
+      "grad_norm": 3.544921875,
+      "learning_rate": 9.650377975542296e-07,
+      "loss": 0.9213,
+      "step": 53
+    },
+    {
+      "epoch": 0.16698879010436798,
+      "grad_norm": 3.51171875,
+      "learning_rate": 9.631462850589431e-07,
+      "loss": 1.0332,
+      "step": 54
+    },
+    {
+      "epoch": 0.17008117510630075,
+      "grad_norm": 2.197265625,
+      "learning_rate": 9.612068988375896e-07,
+      "loss": 0.6052,
+      "step": 55
+    },
+    {
+      "epoch": 0.17317356010823348,
+      "grad_norm": 3.966796875,
+      "learning_rate": 9.592198393573816e-07,
+      "loss": 0.8506,
+      "step": 56
+    },
+    {
+      "epoch": 0.17626594511016622,
+      "grad_norm": 9.140625,
+      "learning_rate": 9.571853120133403e-07,
+      "loss": 1.291,
+      "step": 57
+    },
+    {
+      "epoch": 0.17935833011209895,
+      "grad_norm": 5.25,
+      "learning_rate": 9.551035271070664e-07,
+      "loss": 0.7823,
+      "step": 58
+    },
+    {
+      "epoch": 0.1824507151140317,
+      "grad_norm": 7.38671875,
+      "learning_rate": 9.529746998249992e-07,
+      "loss": 0.743,
+      "step": 59
+    },
+    {
+      "epoch": 0.18554310011596445,
+      "grad_norm": 5.23828125,
+      "learning_rate": 9.507990502161767e-07,
+      "loss": 0.8768,
+      "step": 60
+    },
+    {
+      "epoch": 0.18863548511789718,
+      "grad_norm": 3.9375,
+      "learning_rate": 9.485768031694871e-07,
+      "loss": 1.1133,
+      "step": 61
+    },
+    {
+      "epoch": 0.19172787011982992,
+      "grad_norm": 3.298828125,
+      "learning_rate": 9.46308188390425e-07,
+      "loss": 1.2435,
+      "step": 62
+    },
+    {
+      "epoch": 0.19482025512176265,
+      "grad_norm": 2.3046875,
+      "learning_rate": 9.439934403773466e-07,
+      "loss": 0.6786,
+      "step": 63
+    },
+    {
+      "epoch": 0.1979126401236954,
+      "grad_norm": 10.265625,
+      "learning_rate": 9.416327983972303e-07,
+      "loss": 1.1159,
+      "step": 64
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 2.861328125,
+      "learning_rate": 9.392265064609453e-07,
+      "loss": 0.7327,
+      "step": 65
+    },
+    {
+      "epoch": 0.20409741012756089,
+      "grad_norm": 3.681640625,
+      "learning_rate": 9.367748132980285e-07,
+      "loss": 0.9711,
+      "step": 66
+    },
+    {
+      "epoch": 0.20718979512949362,
+      "grad_norm": 2.857421875,
+      "learning_rate": 9.342779723309743e-07,
+      "loss": 0.6344,
+      "step": 67
+    },
+    {
+      "epoch": 0.21028218013142636,
+      "grad_norm": 4.12890625,
+      "learning_rate": 9.317362416490395e-07,
+      "loss": 1.0897,
+      "step": 68
+    },
+    {
+      "epoch": 0.2133745651333591,
+      "grad_norm": 3.03125,
+      "learning_rate": 9.291498839815655e-07,
+      "loss": 0.9388,
+      "step": 69
+    },
+    {
+      "epoch": 0.21646695013529185,
+      "grad_norm": 4.79296875,
+      "learning_rate": 9.265191666708208e-07,
+      "loss": 0.8255,
+      "step": 70
+    },
+    {
+      "epoch": 0.2195593351372246,
+      "grad_norm": 3.376953125,
+      "learning_rate": 9.238443616443665e-07,
+      "loss": 0.7494,
+      "step": 71
+    },
+    {
+      "epoch": 0.22265172013915732,
+      "grad_norm": 3.1640625,
+      "learning_rate": 9.211257453869493e-07,
+      "loss": 0.9806,
+      "step": 72
+    },
+    {
+      "epoch": 0.22574410514109006,
+      "grad_norm": 3.29296875,
+      "learning_rate": 9.183635989119209e-07,
+      "loss": 0.5427,
+      "step": 73
+    },
+    {
+      "epoch": 0.22883649014302282,
+      "grad_norm": 2.98828125,
+      "learning_rate": 9.155582077321917e-07,
+      "loss": 1.3904,
+      "step": 74
+    },
+    {
+      "epoch": 0.23192887514495555,
+      "grad_norm": 2.70703125,
+      "learning_rate": 9.127098618307177e-07,
+      "loss": 0.8491,
+      "step": 75
+    },
+    {
+      "epoch": 0.2350212601468883,
+      "grad_norm": 1.6318359375,
+      "learning_rate": 9.098188556305262e-07,
+      "loss": 0.5332,
+      "step": 76
+    },
+    {
+      "epoch": 0.23811364514882102,
+      "grad_norm": 1.794921875,
+      "learning_rate": 9.068854879642831e-07,
+      "loss": 0.8511,
+      "step": 77
+    },
+    {
+      "epoch": 0.24120603015075376,
+      "grad_norm": 1.3857421875,
+      "learning_rate": 9.039100620434024e-07,
+      "loss": 0.6289,
+      "step": 78
+    },
+    {
+      "epoch": 0.24429841515268652,
+      "grad_norm": 1.3076171875,
+      "learning_rate": 9.008928854267053e-07,
+      "loss": 0.6155,
+      "step": 79
+    },
+    {
+      "epoch": 0.24739080015461926,
+      "grad_norm": 3.12890625,
+      "learning_rate": 8.978342699886288e-07,
+      "loss": 0.9333,
+      "step": 80
+    },
+    {
+      "epoch": 0.250483185156552,
+      "grad_norm": 1.375,
+      "learning_rate": 8.947345318869881e-07,
+      "loss": 0.4149,
+      "step": 81
+    },
+    {
+      "epoch": 0.25357557015848475,
+      "grad_norm": 1.5517578125,
+      "learning_rate": 8.915939915302968e-07,
+      "loss": 0.6882,
+      "step": 82
+    },
+    {
+      "epoch": 0.25666795516041746,
+      "grad_norm": 2.533203125,
+      "learning_rate": 8.88412973544647e-07,
+      "loss": 0.904,
+      "step": 83
+    },
+    {
+      "epoch": 0.2597603401623502,
+      "grad_norm": 1.849609375,
+      "learning_rate": 8.851918067401551e-07,
+      "loss": 0.6705,
+      "step": 84
+    },
+    {
+      "epoch": 0.26285272516428293,
+      "grad_norm": 1.1474609375,
+      "learning_rate": 8.819308240769724e-07,
+      "loss": 0.4361,
+      "step": 85
+    },
+    {
+      "epoch": 0.2659451101662157,
+      "grad_norm": 1.720703125,
+      "learning_rate": 8.786303626308688e-07,
+      "loss": 0.6259,
+      "step": 86
+    },
+    {
+      "epoch": 0.26903749516814845,
+      "grad_norm": 1.3369140625,
+      "learning_rate": 8.752907635583911e-07,
+      "loss": 0.372,
+      "step": 87
+    },
+    {
+      "epoch": 0.27212988017008116,
+      "grad_norm": 1.1396484375,
+      "learning_rate": 8.71912372061598e-07,
+      "loss": 0.3766,
+      "step": 88
+    },
+    {
+      "epoch": 0.2752222651720139,
+      "grad_norm": 1.3701171875,
+      "learning_rate": 8.684955373523786e-07,
+      "loss": 0.5947,
+      "step": 89
+    },
+    {
+      "epoch": 0.27831465017394663,
+      "grad_norm": 1.0537109375,
+      "learning_rate": 8.650406126163551e-07,
+      "loss": 0.5538,
+      "step": 90
+    },
+    {
+      "epoch": 0.2814070351758794,
+      "grad_norm": 1.43359375,
+      "learning_rate": 8.615479549763755e-07,
+      "loss": 0.5618,
+      "step": 91
+    },
+    {
+      "epoch": 0.28449942017781216,
+      "grad_norm": 1.248046875,
+      "learning_rate": 8.580179254555994e-07,
+      "loss": 0.5608,
+      "step": 92
+    },
+    {
+      "epoch": 0.28759180517974486,
+      "grad_norm": 1.14453125,
+      "learning_rate": 8.544508889401798e-07,
+      "loss": 0.5199,
+      "step": 93
+    },
+    {
+      "epoch": 0.2906841901816776,
+      "grad_norm": 0.95263671875,
+      "learning_rate": 8.508472141415465e-07,
+      "loss": 0.3945,
+      "step": 94
+    },
+    {
+      "epoch": 0.29377657518361033,
+      "grad_norm": 1.07421875,
+      "learning_rate": 8.472072735582941e-07,
+      "loss": 0.5235,
+      "step": 95
+    },
+    {
+      "epoch": 0.2968689601855431,
+      "grad_norm": 2.25,
+      "learning_rate": 8.435314434376773e-07,
+      "loss": 0.5098,
+      "step": 96
+    },
+    {
+      "epoch": 0.29996134518747586,
+      "grad_norm": 1.0419921875,
+      "learning_rate": 8.398201037367201e-07,
+      "loss": 0.5901,
+      "step": 97
+    },
+    {
+      "epoch": 0.30305373018940857,
+      "grad_norm": 1.197265625,
+      "learning_rate": 8.360736380829418e-07,
+      "loss": 0.6208,
+      "step": 98
+    },
+    {
+      "epoch": 0.30614611519134133,
+      "grad_norm": 1.2783203125,
+      "learning_rate": 8.322924337347015e-07,
+      "loss": 0.6289,
+      "step": 99
+    },
+    {
+      "epoch": 0.30923850019327404,
+      "grad_norm": 2.18359375,
+      "learning_rate": 8.284768815411691e-07,
+      "loss": 0.7223,
+      "step": 100
+    },
+    {
+      "epoch": 0.3123308851952068,
+      "grad_norm": 3.375,
+      "learning_rate": 8.246273759019251e-07,
+      "loss": 0.8717,
+      "step": 101
+    },
+    {
+      "epoch": 0.31542327019713956,
+      "grad_norm": 1.150390625,
+      "learning_rate": 8.207443147261929e-07,
+      "loss": 0.7932,
+      "step": 102
+    },
+    {
+      "epoch": 0.31851565519907227,
+      "grad_norm": 1.1240234375,
+      "learning_rate": 8.168280993917076e-07,
+      "loss": 0.6476,
+      "step": 103
+    },
+    {
+      "epoch": 0.32160804020100503,
+      "grad_norm": 0.880859375,
+      "learning_rate": 8.128791347032278e-07,
+      "loss": 0.4536,
+      "step": 104
+    },
+    {
+      "epoch": 0.3247004252029378,
+      "grad_norm": 0.8720703125,
+      "learning_rate": 8.088978288506923e-07,
+      "loss": 0.5822,
+      "step": 105
+    },
+    {
+      "epoch": 0.3277928102048705,
+      "grad_norm": 1.150390625,
+      "learning_rate": 8.048845933670271e-07,
+      "loss": 0.5383,
+      "step": 106
+    },
+    {
+      "epoch": 0.33088519520680326,
+      "grad_norm": 1.0673828125,
+      "learning_rate": 8.008398430856063e-07,
+      "loss": 0.64,
+      "step": 107
+    },
+    {
+      "epoch": 0.33397758020873597,
+      "grad_norm": 1.1337890625,
+      "learning_rate": 7.967639960973726e-07,
+      "loss": 0.6862,
+      "step": 108
+    },
+    {
+      "epoch": 0.33706996521066873,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.92657473707621e-07,
+      "loss": 0.867,
+      "step": 109
+    },
+    {
+      "epoch": 0.3401623502126015,
+      "grad_norm": 0.91455078125,
+      "learning_rate": 7.885207003924497e-07,
+      "loss": 0.464,
+      "step": 110
+    },
+    {
+      "epoch": 0.3432547352145342,
+      "grad_norm": 0.8115234375,
+      "learning_rate": 7.843541037548837e-07,
+      "loss": 0.467,
+      "step": 111
+    },
+    {
+      "epoch": 0.34634712021646696,
+      "grad_norm": 1.9443359375,
+      "learning_rate": 7.801581144806751e-07,
+      "loss": 0.5784,
+      "step": 112
+    },
+    {
+      "epoch": 0.34943950521839967,
+      "grad_norm": 1.2568359375,
+      "learning_rate": 7.75933166293784e-07,
+      "loss": 0.7382,
+      "step": 113
+    },
+    {
+      "epoch": 0.35253189022033243,
+      "grad_norm": 1.126953125,
+      "learning_rate": 7.716796959115477e-07,
+      "loss": 0.4922,
+      "step": 114
+    },
+    {
+      "epoch": 0.3556242752222652,
+      "grad_norm": 1.033203125,
+      "learning_rate": 7.673981429995371e-07,
+      "loss": 0.4763,
+      "step": 115
+    },
+    {
+      "epoch": 0.3587166602241979,
+      "grad_norm": 0.59765625,
+      "learning_rate": 7.630889501261108e-07,
+      "loss": 0.2734,
+      "step": 116
+    },
+    {
+      "epoch": 0.36180904522613067,
+      "grad_norm": 1.6201171875,
+      "learning_rate": 7.58752562716669e-07,
+      "loss": 1.0264,
+      "step": 117
+    },
+    {
+      "epoch": 0.3649014302280634,
+      "grad_norm": 1.8515625,
+      "learning_rate": 7.543894290076103e-07,
+      "loss": 0.6039,
+      "step": 118
+    },
+    {
+      "epoch": 0.36799381522999614,
+      "grad_norm": 0.9951171875,
+      "learning_rate": 7.5e-07,
+      "loss": 0.5836,
+      "step": 119
+    },
+    {
+      "epoch": 0.3710862002319289,
+      "grad_norm": 0.8935546875,
+      "learning_rate": 7.455847294129518e-07,
+      "loss": 0.3714,
+      "step": 120
+    },
+    {
+      "epoch": 0.3741785852338616,
+      "grad_norm": 0.73193359375,
+      "learning_rate": 7.41144073636728e-07,
+      "loss": 0.3868,
+      "step": 121
+    },
+    {
+      "epoch": 0.37727097023579437,
+      "grad_norm": 0.8701171875,
+      "learning_rate": 7.366784916855649e-07,
+      "loss": 0.4043,
+      "step": 122
+    },
+    {
+      "epoch": 0.3803633552377271,
+      "grad_norm": 1.0478515625,
+      "learning_rate": 7.321884451502252e-07,
+      "loss": 0.8025,
+      "step": 123
+    },
+    {
+      "epoch": 0.38345574023965984,
+      "grad_norm": 0.78662109375,
+      "learning_rate": 7.276743981502855e-07,
+      "loss": 0.5009,
+      "step": 124
+    },
+    {
+      "epoch": 0.3865481252415926,
+      "grad_norm": 1.09765625,
+      "learning_rate": 7.231368172861629e-07,
+      "loss": 0.6254,
+      "step": 125
+    },
+    {
+      "epoch": 0.3896405102435253,
+      "grad_norm": 1.568359375,
+      "learning_rate": 7.185761715908825e-07,
+      "loss": 0.6705,
+      "step": 126
+    },
+    {
+      "epoch": 0.39273289524545807,
+      "grad_norm": 0.97802734375,
+      "learning_rate": 7.139929324815964e-07,
+      "loss": 0.5675,
+      "step": 127
+    },
+    {
+      "epoch": 0.3958252802473908,
+      "grad_norm": 1.107421875,
+      "learning_rate": 7.093875737108548e-07,
+      "loss": 0.5836,
+      "step": 128
+    },
+    {
+      "epoch": 0.39891766524932354,
+      "grad_norm": 0.943359375,
+      "learning_rate": 7.047605713176359e-07,
+      "loss": 0.4119,
+      "step": 129
+    },
+    {
+      "epoch": 0.4020100502512563,
+      "grad_norm": 1.0400390625,
+      "learning_rate": 7.001124035781389e-07,
+      "loss": 0.4852,
+      "step": 130
+    },
+    {
+      "epoch": 0.405102435253189,
+      "grad_norm": 0.7646484375,
+      "learning_rate": 6.954435509563477e-07,
+      "loss": 0.5633,
+      "step": 131
+    },
+    {
+      "epoch": 0.40819482025512177,
+      "grad_norm": 1.0126953125,
+      "learning_rate": 6.907544960543658e-07,
+      "loss": 0.7201,
+      "step": 132
+    },
+    {
+      "epoch": 0.4112872052570545,
+      "grad_norm": 0.74560546875,
+      "learning_rate": 6.860457235625321e-07,
+      "loss": 0.6064,
+      "step": 133
+    },
+    {
+      "epoch": 0.41437959025898724,
+      "grad_norm": 0.83984375,
+      "learning_rate": 6.813177202093202e-07,
+      "loss": 0.5591,
+      "step": 134
+    },
+    {
+      "epoch": 0.41747197526092,
+      "grad_norm": 1.1630859375,
+      "learning_rate": 6.765709747110273e-07,
+      "loss": 0.6987,
+      "step": 135
+    },
+    {
+      "epoch": 0.4205643602628527,
+      "grad_norm": 0.66796875,
+      "learning_rate": 6.718059777212565e-07,
+      "loss": 0.3856,
+      "step": 136
+    },
+    {
+      "epoch": 0.4236567452647855,
+      "grad_norm": 1.01953125,
+      "learning_rate": 6.67023221780201e-07,
+      "loss": 0.6259,
+      "step": 137
+    },
+    {
+      "epoch": 0.4267491302667182,
+      "grad_norm": 3.798828125,
+      "learning_rate": 6.62223201263731e-07,
+      "loss": 0.4784,
+      "step": 138
+    },
+    {
+      "epoch": 0.42984151526865094,
+      "grad_norm": 1.5576171875,
+      "learning_rate": 6.574064123322924e-07,
+      "loss": 0.8581,
+      "step": 139
+    },
+    {
+      "epoch": 0.4329339002705837,
+      "grad_norm": 1.9697265625,
+      "learning_rate": 6.525733528796206e-07,
+      "loss": 0.6919,
+      "step": 140
+    },
+    {
+      "epoch": 0.4360262852725164,
+      "grad_norm": 2.140625,
+      "learning_rate": 6.477245224812746e-07,
+      "loss": 0.3518,
+      "step": 141
+    },
+    {
+      "epoch": 0.4391186702744492,
+      "grad_norm": 0.97314453125,
+      "learning_rate": 6.428604223429979e-07,
+      "loss": 0.3641,
+      "step": 142
+    },
+    {
+      "epoch": 0.44221105527638194,
+      "grad_norm": 0.87158203125,
+      "learning_rate": 6.379815552489112e-07,
+      "loss": 0.454,
+      "step": 143
+    },
+    {
+      "epoch": 0.44530344027831464,
+      "grad_norm": 0.611328125,
+      "learning_rate": 6.330884255095408e-07,
+      "loss": 0.2737,
+      "step": 144
+    },
+    {
+      "epoch": 0.4483958252802474,
+      "grad_norm": 1.1591796875,
+      "learning_rate": 6.281815389096901e-07,
+      "loss": 0.5939,
+      "step": 145
+    },
+    {
+      "epoch": 0.4514882102821801,
+      "grad_norm": 0.65380859375,
+      "learning_rate": 6.232614026561586e-07,
+      "loss": 0.3116,
+      "step": 146
+    },
+    {
+      "epoch": 0.4545805952841129,
+      "grad_norm": 2.357421875,
+      "learning_rate": 6.183285253253134e-07,
+      "loss": 0.7887,
+      "step": 147
+    },
+    {
+      "epoch": 0.45767298028604564,
+      "grad_norm": 0.93896484375,
+      "learning_rate": 6.133834168105205e-07,
+      "loss": 0.4022,
+      "step": 148
+    },
+    {
+      "epoch": 0.46076536528797835,
+      "grad_norm": 5.015625,
+      "learning_rate": 6.084265882694378e-07,
+      "loss": 0.8508,
+      "step": 149
+    },
+    {
+      "epoch": 0.4638577502899111,
+      "grad_norm": 1.6611328125,
+      "learning_rate": 6.034585520711792e-07,
+      "loss": 0.6777,
+      "step": 150
+    },
+    {
+      "epoch": 0.4669501352918438,
+      "grad_norm": 0.9248046875,
+      "learning_rate": 5.984798217433531e-07,
+      "loss": 0.5893,
+      "step": 151
+    },
+    {
+      "epoch": 0.4700425202937766,
+      "grad_norm": 0.83251953125,
+      "learning_rate": 5.934909119189805e-07,
+      "loss": 0.43,
+      "step": 152
+    },
+    {
+      "epoch": 0.47313490529570934,
+      "grad_norm": 1.37109375,
+      "learning_rate": 5.884923382832996e-07,
+      "loss": 0.6694,
+      "step": 153
+    },
+    {
+      "epoch": 0.47622729029764205,
+      "grad_norm": 0.85595703125,
+      "learning_rate": 5.834846175204611e-07,
+      "loss": 0.5568,
+      "step": 154
+    },
+    {
+      "epoch": 0.4793196752995748,
+      "grad_norm": 0.88671875,
+      "learning_rate": 5.784682672601207e-07,
+      "loss": 0.382,
+      "step": 155
+    },
+    {
+      "epoch": 0.4824120603015075,
+      "grad_norm": 1.1953125,
+      "learning_rate": 5.734438060239331e-07,
+      "loss": 0.5373,
+      "step": 156
+    },
+    {
+      "epoch": 0.4855044453034403,
+      "grad_norm": 1.171875,
+      "learning_rate": 5.684117531719551e-07,
+      "loss": 0.3352,
+      "step": 157
+    },
+    {
+      "epoch": 0.48859683030537304,
+      "grad_norm": 0.6845703125,
+      "learning_rate": 5.633726288489609e-07,
+      "loss": 0.3523,
+      "step": 158
+    },
+    {
+      "epoch": 0.49168921530730575,
+      "grad_norm": 1.75,
+      "learning_rate": 5.583269539306762e-07,
+      "loss": 0.3556,
+      "step": 159
+    },
+    {
+      "epoch": 0.4947816003092385,
+      "grad_norm": 0.869140625,
+      "learning_rate": 5.53275249969938e-07,
+      "loss": 0.3313,
+      "step": 160
+    },
+    {
+      "epoch": 0.4978739853111712,
+      "grad_norm": 1.05859375,
+      "learning_rate": 5.482180391427833e-07,
+      "loss": 0.609,
+      "step": 161
+    },
+    {
+      "epoch": 0.500966370313104,
+      "grad_norm": 0.85546875,
+      "learning_rate": 5.43155844194473e-07,
+      "loss": 0.393,
+      "step": 162
+    },
+    {
+      "epoch": 0.5040587553150367,
+      "grad_norm": 0.84326171875,
+      "learning_rate": 5.38089188385459e-07,
+      "loss": 0.388,
+      "step": 163
+    },
+    {
+      "epoch": 0.5071511403169695,
+      "grad_norm": 0.92041015625,
+      "learning_rate": 5.330185954372954e-07,
+      "loss": 0.5085,
+      "step": 164
+    },
+    {
+      "epoch": 0.5102435253189022,
+      "grad_norm": 2.18359375,
+      "learning_rate": 5.279445894785041e-07,
+      "loss": 0.4846,
+      "step": 165
+    },
+    {
+      "epoch": 0.5133359103208349,
+      "grad_norm": 6.39453125,
+      "learning_rate": 5.228676949903973e-07,
+      "loss": 0.9367,
+      "step": 166
+    },
+    {
+      "epoch": 0.5164282953227677,
+      "grad_norm": 1.0673828125,
+      "learning_rate": 5.177884367528637e-07,
+      "loss": 0.599,
+      "step": 167
+    },
+    {
+      "epoch": 0.5195206803247004,
+      "grad_norm": 0.64111328125,
+      "learning_rate": 5.127073397901247e-07,
+      "loss": 0.4471,
+      "step": 168
+    },
+    {
+      "epoch": 0.5226130653266332,
+      "grad_norm": 0.58349609375,
+      "learning_rate": 5.07624929316463e-07,
+      "loss": 0.2312,
+      "step": 169
+    },
+    {
+      "epoch": 0.5257054503285659,
+      "grad_norm": 0.59130859375,
+      "learning_rate": 5.025417306819347e-07,
+      "loss": 0.3372,
+      "step": 170
+    },
+    {
+      "epoch": 0.5287978353304986,
+      "grad_norm": 2.068359375,
+      "learning_rate": 4.974582693180651e-07,
+      "loss": 0.4175,
+      "step": 171
+    },
+    {
+      "epoch": 0.5318902203324314,
+      "grad_norm": 0.8701171875,
+      "learning_rate": 4.923750706835371e-07,
+      "loss": 0.7236,
+      "step": 172
+    },
+    {
+      "epoch": 0.5349826053343641,
+      "grad_norm": 3.009765625,
+      "learning_rate": 4.872926602098754e-07,
+      "loss": 0.4879,
+      "step": 173
+    },
+    {
+      "epoch": 0.5380749903362969,
+      "grad_norm": 0.9619140625,
+      "learning_rate": 4.822115632471362e-07,
+      "loss": 0.4472,
+      "step": 174
+    },
+    {
+      "epoch": 0.5411673753382296,
+      "grad_norm": 0.86669921875,
+      "learning_rate": 4.771323050096027e-07,
+      "loss": 0.6425,
+      "step": 175
+    },
+    {
+      "epoch": 0.5442597603401623,
+      "grad_norm": 0.90283203125,
+      "learning_rate": 4.7205541052149604e-07,
+      "loss": 0.4621,
+      "step": 176
+    },
+    {
+      "epoch": 0.5473521453420951,
+      "grad_norm": 1.419921875,
+      "learning_rate": 4.6698140456270455e-07,
+      "loss": 0.2652,
+      "step": 177
+    },
+    {
+      "epoch": 0.5504445303440278,
+      "grad_norm": 0.5361328125,
+      "learning_rate": 4.6191081161454105e-07,
+      "loss": 0.3136,
+      "step": 178
+    },
+    {
+      "epoch": 0.5535369153459606,
+      "grad_norm": 4.40234375,
+      "learning_rate": 4.5684415580552705e-07,
+      "loss": 0.6098,
+      "step": 179
+    },
+    {
+      "epoch": 0.5566293003478933,
+      "grad_norm": 1.5966796875,
+      "learning_rate": 4.517819608572167e-07,
+      "loss": 0.3585,
+      "step": 180
+    },
+    {
+      "epoch": 0.559721685349826,
+      "grad_norm": 2.55078125,
+      "learning_rate": 4.46724750030062e-07,
+      "loss": 0.4844,
+      "step": 181
+    },
+    {
+      "epoch": 0.5628140703517588,
+      "grad_norm": 1.9521484375,
+      "learning_rate": 4.4167304606932387e-07,
+      "loss": 0.4035,
+      "step": 182
+    },
+    {
+      "epoch": 0.5659064553536916,
+      "grad_norm": 1.388671875,
+      "learning_rate": 4.366273711510392e-07,
+      "loss": 0.4476,
+      "step": 183
+    },
+    {
+      "epoch": 0.5689988403556243,
+      "grad_norm": 1.3515625,
+      "learning_rate": 4.3158824682804496e-07,
+      "loss": 0.5406,
+      "step": 184
+    },
+    {
+      "epoch": 0.572091225357557,
+      "grad_norm": 0.96630859375,
+      "learning_rate": 4.26556193976067e-07,
+      "loss": 0.4346,
+      "step": 185
+    },
+    {
+      "epoch": 0.5751836103594897,
+      "grad_norm": 0.6376953125,
+      "learning_rate": 4.215317327398794e-07,
+      "loss": 0.4279,
+      "step": 186
+    },
+    {
+      "epoch": 0.5782759953614225,
+      "grad_norm": 9.0703125,
+      "learning_rate": 4.1651538247953897e-07,
+      "loss": 0.4792,
+      "step": 187
+    },
+    {
+      "epoch": 0.5813683803633553,
+      "grad_norm": 1.244140625,
+      "learning_rate": 4.1150766171670035e-07,
+      "loss": 0.4545,
+      "step": 188
+    },
+    {
+      "epoch": 0.584460765365288,
+      "grad_norm": 4.0703125,
+      "learning_rate": 4.065090880810196e-07,
+      "loss": 0.604,
+      "step": 189
+    },
+    {
+      "epoch": 0.5875531503672207,
+      "grad_norm": 0.93212890625,
+      "learning_rate": 4.015201782566471e-07,
+      "loss": 0.4786,
+      "step": 190
+    },
+    {
+      "epoch": 0.5906455353691534,
+      "grad_norm": 1.796875,
+      "learning_rate": 3.9654144792882084e-07,
+      "loss": 0.3736,
+      "step": 191
+    },
+    {
+      "epoch": 0.5937379203710862,
+      "grad_norm": 1.001953125,
+      "learning_rate": 3.9157341173056236e-07,
+      "loss": 0.4834,
+      "step": 192
+    },
+    {
+      "epoch": 0.596830305373019,
+      "grad_norm": 1.076171875,
+      "learning_rate": 3.866165831894795e-07,
+      "loss": 0.4159,
+      "step": 193
+    },
+    {
+      "epoch": 0.5999226903749517,
+      "grad_norm": 0.81005859375,
+      "learning_rate": 3.8167147467468647e-07,
+      "loss": 0.4358,
+      "step": 194
+    },
+    {
+      "epoch": 0.6030150753768844,
+      "grad_norm": 0.82470703125,
+      "learning_rate": 3.767385973438415e-07,
+      "loss": 0.492,
+      "step": 195
+    },
+    {
+      "epoch": 0.6061074603788171,
+      "grad_norm": 1.3232421875,
+      "learning_rate": 3.7181846109031e-07,
+      "loss": 0.3175,
+      "step": 196
+    },
+    {
+      "epoch": 0.6091998453807499,
+      "grad_norm": 0.5888671875,
+      "learning_rate": 3.669115744904591e-07,
+      "loss": 0.3646,
+      "step": 197
+    },
+    {
+      "epoch": 0.6122922303826827,
+      "grad_norm": 0.873046875,
+      "learning_rate": 3.6201844475108876e-07,
+      "loss": 0.4751,
+      "step": 198
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.5419921875,
+      "learning_rate": 3.571395776570022e-07,
+      "loss": 0.3102,
+      "step": 199
+    },
+    {
+      "epoch": 0.6184770003865481,
+      "grad_norm": 2.56640625,
+      "learning_rate": 3.5227547751872544e-07,
+      "loss": 0.5683,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 324,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.663267681861632e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3063dc7c82841c5e87ffd4a20e3c05dd2f41b6eeb229102eecabe2f040f07c57
+size 5841

checkpoint-324/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-324/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-324/config.json

@@ -0,0 +1,72 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-324/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "eos_token_id": [
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.56.1"
+}

checkpoint-324/model-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7156400408457e9a45049bb01956c01c7c6b0600b3a786fd6881fe09f6da83b8
+size 4984780720

checkpoint-324/model-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9290499bce25e4c3f78b03f45769fa2300e43ea8e376d1ebca282ffeba02fcba
+size 4980891968

checkpoint-324/model-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8973f1992eb3e99a9c7357201dc19f2a778a9fc4577d25eff34cbd30175d39bc
+size 4928485016

checkpoint-324/model-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d9a39e1d4849ffb79ad4deb1bb14c4ca77f1429fa895054aecee0461f5b5ba
+size 4980892032

checkpoint-324/model-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62d734e14556d0ec39834d3acf74b365140dbb09ddf39ff4940eefe8b738a000
+size 4928485016

checkpoint-324/model-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c00aefce412b3d8e84c8b0cb8b4efe1befc527eb9d35d3febb98b7d19f37a086
+size 4733130456

checkpoint-324/model.safetensors.index.json

@@ -0,0 +1,451 @@
+{
+  "metadata": {
+    "total_parameters": 14768307200,
+    "total_size": 29536614400
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00006-of-00006.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_norm.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
+    "model.norm.weight": "model-00006-of-00006.safetensors"
+  }
+}

checkpoint-324/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9aa76d8414125f3040f92359980df277e51fe2346b4bfd1bf84a4d84262cbda9
+size 59073623712

checkpoint-324/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c15d10da233568de54180256b227cfe26dea6eaac6df08048357111de9ef60d
+size 14645

checkpoint-324/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09e03b81011dc1cef5580d5ee78cde9dbd9dba5180b190a51d74210acbcae067
+size 1465

checkpoint-324/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-324/tokenizer.json

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

checkpoint-324/tokenizer_config.json

@@ -0,0 +1,239 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-324/trainer_state.json

@@ -0,0 +1,2302 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 324,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0030923850019327404,
+      "grad_norm": 1.7919921875,
+      "learning_rate": 0.0,
+      "loss": 0.5969,
+      "step": 1
+    },
+    {
+      "epoch": 0.006184770003865481,
+      "grad_norm": 1.9970703125,
+      "learning_rate": 6.666666666666667e-08,
+      "loss": 0.6202,
+      "step": 2
+    },
+    {
+      "epoch": 0.009277155005798222,
+      "grad_norm": 1.6474609375,
+      "learning_rate": 1.3333333333333334e-07,
+      "loss": 0.7447,
+      "step": 3
+    },
+    {
+      "epoch": 0.012369540007730962,
+      "grad_norm": 1.7734375,
+      "learning_rate": 2e-07,
+      "loss": 0.8834,
+      "step": 4
+    },
+    {
+      "epoch": 0.015461925009663703,
+      "grad_norm": 1.52734375,
+      "learning_rate": 2.6666666666666667e-07,
+      "loss": 0.7299,
+      "step": 5
+    },
+    {
+      "epoch": 0.018554310011596443,
+      "grad_norm": 1.623046875,
+      "learning_rate": 3.333333333333333e-07,
+      "loss": 0.7126,
+      "step": 6
+    },
+    {
+      "epoch": 0.021646695013529185,
+      "grad_norm": 2.2890625,
+      "learning_rate": 4e-07,
+      "loss": 0.8068,
+      "step": 7
+    },
+    {
+      "epoch": 0.024739080015461924,
+      "grad_norm": 3.50390625,
+      "learning_rate": 4.6666666666666666e-07,
+      "loss": 0.5119,
+      "step": 8
+    },
+    {
+      "epoch": 0.027831465017394665,
+      "grad_norm": 3.953125,
+      "learning_rate": 5.333333333333333e-07,
+      "loss": 0.413,
+      "step": 9
+    },
+    {
+      "epoch": 0.030923850019327407,
+      "grad_norm": 136.375,
+      "learning_rate": 6e-07,
+      "loss": 4.7449,
+      "step": 10
+    },
+    {
+      "epoch": 0.034016235021260145,
+      "grad_norm": 185.625,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 7.8581,
+      "step": 11
+    },
+    {
+      "epoch": 0.03710862002319289,
+      "grad_norm": 254.875,
+      "learning_rate": 7.333333333333332e-07,
+      "loss": 11.5138,
+      "step": 12
+    },
+    {
+      "epoch": 0.04020100502512563,
+      "grad_norm": 250.5,
+      "learning_rate": 8e-07,
+      "loss": 11.6085,
+      "step": 13
+    },
+    {
+      "epoch": 0.04329339002705837,
+      "grad_norm": 199.625,
+      "learning_rate": 8.666666666666667e-07,
+      "loss": 11.0929,
+      "step": 14
+    },
+    {
+      "epoch": 0.04638577502899111,
+      "grad_norm": 164.375,
+      "learning_rate": 9.333333333333333e-07,
+      "loss": 9.0069,
+      "step": 15
+    },
+    {
+      "epoch": 0.04947816003092385,
+      "grad_norm": 191.125,
+      "learning_rate": 1e-06,
+      "loss": 10.9254,
+      "step": 16
+    },
+    {
+      "epoch": 0.05257054503285659,
+      "grad_norm": 226.0,
+      "learning_rate": 9.99974158420562e-07,
+      "loss": 10.8139,
+      "step": 17
+    },
+    {
+      "epoch": 0.05566293003478933,
+      "grad_norm": 291.5,
+      "learning_rate": 9.99896636353397e-07,
+      "loss": 9.8274,
+      "step": 18
+    },
+    {
+      "epoch": 0.05875531503672207,
+      "grad_norm": 245.5,
+      "learning_rate": 9.997674418116758e-07,
+      "loss": 7.577,
+      "step": 19
+    },
+    {
+      "epoch": 0.061847700038654814,
+      "grad_norm": 246.25,
+      "learning_rate": 9.99586588149762e-07,
+      "loss": 6.5899,
+      "step": 20
+    },
+    {
+      "epoch": 0.06494008504058756,
+      "grad_norm": 112.0,
+      "learning_rate": 9.993540940618332e-07,
+      "loss": 4.777,
+      "step": 21
+    },
+    {
+      "epoch": 0.06803247004252029,
+      "grad_norm": 132.625,
+      "learning_rate": 9.990699835799469e-07,
+      "loss": 5.0894,
+      "step": 22
+    },
+    {
+      "epoch": 0.07112485504445304,
+      "grad_norm": 110.5,
+      "learning_rate": 9.987342860715575e-07,
+      "loss": 4.3164,
+      "step": 23
+    },
+    {
+      "epoch": 0.07421724004638577,
+      "grad_norm": 80.1875,
+      "learning_rate": 9.983470362364801e-07,
+      "loss": 4.1167,
+      "step": 24
+    },
+    {
+      "epoch": 0.07730962504831851,
+      "grad_norm": 36.03125,
+      "learning_rate": 9.979082741033045e-07,
+      "loss": 2.8033,
+      "step": 25
+    },
+    {
+      "epoch": 0.08040201005025126,
+      "grad_norm": 32.15625,
+      "learning_rate": 9.97418045025257e-07,
+      "loss": 3.3556,
+      "step": 26
+    },
+    {
+      "epoch": 0.08349439505218399,
+      "grad_norm": 32.96875,
+      "learning_rate": 9.968763996755115e-07,
+      "loss": 3.8153,
+      "step": 27
+    },
+    {
+      "epoch": 0.08658678005411674,
+      "grad_norm": 26.3125,
+      "learning_rate": 9.96283394041954e-07,
+      "loss": 2.8114,
+      "step": 28
+    },
+    {
+      "epoch": 0.08967916505604948,
+      "grad_norm": 24.125,
+      "learning_rate": 9.956390894213928e-07,
+      "loss": 2.7601,
+      "step": 29
+    },
+    {
+      "epoch": 0.09277155005798222,
+      "grad_norm": 24.359375,
+      "learning_rate": 9.949435524132244e-07,
+      "loss": 2.8906,
+      "step": 30
+    },
+    {
+      "epoch": 0.09586393505991496,
+      "grad_norm": 19.28125,
+      "learning_rate": 9.94196854912548e-07,
+      "loss": 2.3873,
+      "step": 31
+    },
+    {
+      "epoch": 0.0989563200618477,
+      "grad_norm": 18.71875,
+      "learning_rate": 9.933990741027348e-07,
+      "loss": 2.4901,
+      "step": 32
+    },
+    {
+      "epoch": 0.10204870506378044,
+      "grad_norm": 25.375,
+      "learning_rate": 9.925502924474493e-07,
+      "loss": 2.3877,
+      "step": 33
+    },
+    {
+      "epoch": 0.10514109006571318,
+      "grad_norm": 20.1875,
+      "learning_rate": 9.91650597682126e-07,
+      "loss": 2.0152,
+      "step": 34
+    },
+    {
+      "epoch": 0.10823347506764593,
+      "grad_norm": 18.453125,
+      "learning_rate": 9.907000828049e-07,
+      "loss": 1.624,
+      "step": 35
+    },
+    {
+      "epoch": 0.11132586006957866,
+      "grad_norm": 18.90625,
+      "learning_rate": 9.896988460669938e-07,
+      "loss": 2.1227,
+      "step": 36
+    },
+    {
+      "epoch": 0.11441824507151141,
+      "grad_norm": 17.421875,
+      "learning_rate": 9.886469909625622e-07,
+      "loss": 1.6674,
+      "step": 37
+    },
+    {
+      "epoch": 0.11751063007344414,
+      "grad_norm": 11.125,
+      "learning_rate": 9.875446262179947e-07,
+      "loss": 1.0941,
+      "step": 38
+    },
+    {
+      "epoch": 0.12060301507537688,
+      "grad_norm": 12.90625,
+      "learning_rate": 9.863918657806751e-07,
+      "loss": 1.6579,
+      "step": 39
+    },
+    {
+      "epoch": 0.12369540007730963,
+      "grad_norm": 18.0625,
+      "learning_rate": 9.851888288072053e-07,
+      "loss": 1.183,
+      "step": 40
+    },
+    {
+      "epoch": 0.12678778507924238,
+      "grad_norm": 29.65625,
+      "learning_rate": 9.839356396510874e-07,
+      "loss": 1.4809,
+      "step": 41
+    },
+    {
+      "epoch": 0.1298801700811751,
+      "grad_norm": 26.4375,
+      "learning_rate": 9.826324278498698e-07,
+      "loss": 1.5772,
+      "step": 42
+    },
+    {
+      "epoch": 0.13297255508310785,
+      "grad_norm": 16.390625,
+      "learning_rate": 9.81279328111758e-07,
+      "loss": 1.2533,
+      "step": 43
+    },
+    {
+      "epoch": 0.13606494008504058,
+      "grad_norm": 12.4453125,
+      "learning_rate": 9.79876480301689e-07,
+      "loss": 1.2557,
+      "step": 44
+    },
+    {
+      "epoch": 0.13915732508697332,
+      "grad_norm": 8.9765625,
+      "learning_rate": 9.784240294268754e-07,
+      "loss": 1.3086,
+      "step": 45
+    },
+    {
+      "epoch": 0.14224971008890608,
+      "grad_norm": 6.34765625,
+      "learning_rate": 9.769221256218162e-07,
+      "loss": 1.2175,
+      "step": 46
+    },
+    {
+      "epoch": 0.1453420950908388,
+      "grad_norm": 4.5234375,
+      "learning_rate": 9.753709241327773e-07,
+      "loss": 1.1835,
+      "step": 47
+    },
+    {
+      "epoch": 0.14843448009277155,
+      "grad_norm": 3.810546875,
+      "learning_rate": 9.73770585301744e-07,
+      "loss": 1.1484,
+      "step": 48
+    },
+    {
+      "epoch": 0.15152686509470428,
+      "grad_norm": 3.814453125,
+      "learning_rate": 9.721212745498492e-07,
+      "loss": 1.2048,
+      "step": 49
+    },
+    {
+      "epoch": 0.15461925009663702,
+      "grad_norm": 3.79296875,
+      "learning_rate": 9.70423162360272e-07,
+      "loss": 1.2032,
+      "step": 50
+    },
+    {
+      "epoch": 0.15771163509856978,
+      "grad_norm": 3.427734375,
+      "learning_rate": 9.686764242606163e-07,
+      "loss": 1.0343,
+      "step": 51
+    },
+    {
+      "epoch": 0.16080402010050251,
+      "grad_norm": 3.875,
+      "learning_rate": 9.668812408047678e-07,
+      "loss": 1.0729,
+      "step": 52
+    },
+    {
+      "epoch": 0.16389640510243525,
+      "grad_norm": 3.544921875,
+      "learning_rate": 9.650377975542296e-07,
+      "loss": 0.9213,
+      "step": 53
+    },
+    {
+      "epoch": 0.16698879010436798,
+      "grad_norm": 3.51171875,
+      "learning_rate": 9.631462850589431e-07,
+      "loss": 1.0332,
+      "step": 54
+    },
+    {
+      "epoch": 0.17008117510630075,
+      "grad_norm": 2.197265625,
+      "learning_rate": 9.612068988375896e-07,
+      "loss": 0.6052,
+      "step": 55
+    },
+    {
+      "epoch": 0.17317356010823348,
+      "grad_norm": 3.966796875,
+      "learning_rate": 9.592198393573816e-07,
+      "loss": 0.8506,
+      "step": 56
+    },
+    {
+      "epoch": 0.17626594511016622,
+      "grad_norm": 9.140625,
+      "learning_rate": 9.571853120133403e-07,
+      "loss": 1.291,
+      "step": 57
+    },
+    {
+      "epoch": 0.17935833011209895,
+      "grad_norm": 5.25,
+      "learning_rate": 9.551035271070664e-07,
+      "loss": 0.7823,
+      "step": 58
+    },
+    {
+      "epoch": 0.1824507151140317,
+      "grad_norm": 7.38671875,
+      "learning_rate": 9.529746998249992e-07,
+      "loss": 0.743,
+      "step": 59
+    },
+    {
+      "epoch": 0.18554310011596445,
+      "grad_norm": 5.23828125,
+      "learning_rate": 9.507990502161767e-07,
+      "loss": 0.8768,
+      "step": 60
+    },
+    {
+      "epoch": 0.18863548511789718,
+      "grad_norm": 3.9375,
+      "learning_rate": 9.485768031694871e-07,
+      "loss": 1.1133,
+      "step": 61
+    },
+    {
+      "epoch": 0.19172787011982992,
+      "grad_norm": 3.298828125,
+      "learning_rate": 9.46308188390425e-07,
+      "loss": 1.2435,
+      "step": 62
+    },
+    {
+      "epoch": 0.19482025512176265,
+      "grad_norm": 2.3046875,
+      "learning_rate": 9.439934403773466e-07,
+      "loss": 0.6786,
+      "step": 63
+    },
+    {
+      "epoch": 0.1979126401236954,
+      "grad_norm": 10.265625,
+      "learning_rate": 9.416327983972303e-07,
+      "loss": 1.1159,
+      "step": 64
+    },
+    {
+      "epoch": 0.20100502512562815,
+      "grad_norm": 2.861328125,
+      "learning_rate": 9.392265064609453e-07,
+      "loss": 0.7327,
+      "step": 65
+    },
+    {
+      "epoch": 0.20409741012756089,
+      "grad_norm": 3.681640625,
+      "learning_rate": 9.367748132980285e-07,
+      "loss": 0.9711,
+      "step": 66
+    },
+    {
+      "epoch": 0.20718979512949362,
+      "grad_norm": 2.857421875,
+      "learning_rate": 9.342779723309743e-07,
+      "loss": 0.6344,
+      "step": 67
+    },
+    {
+      "epoch": 0.21028218013142636,
+      "grad_norm": 4.12890625,
+      "learning_rate": 9.317362416490395e-07,
+      "loss": 1.0897,
+      "step": 68
+    },
+    {
+      "epoch": 0.2133745651333591,
+      "grad_norm": 3.03125,
+      "learning_rate": 9.291498839815655e-07,
+      "loss": 0.9388,
+      "step": 69
+    },
+    {
+      "epoch": 0.21646695013529185,
+      "grad_norm": 4.79296875,
+      "learning_rate": 9.265191666708208e-07,
+      "loss": 0.8255,
+      "step": 70
+    },
+    {
+      "epoch": 0.2195593351372246,
+      "grad_norm": 3.376953125,
+      "learning_rate": 9.238443616443665e-07,
+      "loss": 0.7494,
+      "step": 71
+    },
+    {
+      "epoch": 0.22265172013915732,
+      "grad_norm": 3.1640625,
+      "learning_rate": 9.211257453869493e-07,
+      "loss": 0.9806,
+      "step": 72
+    },
+    {
+      "epoch": 0.22574410514109006,
+      "grad_norm": 3.29296875,
+      "learning_rate": 9.183635989119209e-07,
+      "loss": 0.5427,
+      "step": 73
+    },
+    {
+      "epoch": 0.22883649014302282,
+      "grad_norm": 2.98828125,
+      "learning_rate": 9.155582077321917e-07,
+      "loss": 1.3904,
+      "step": 74
+    },
+    {
+      "epoch": 0.23192887514495555,
+      "grad_norm": 2.70703125,
+      "learning_rate": 9.127098618307177e-07,
+      "loss": 0.8491,
+      "step": 75
+    },
+    {
+      "epoch": 0.2350212601468883,
+      "grad_norm": 1.6318359375,
+      "learning_rate": 9.098188556305262e-07,
+      "loss": 0.5332,
+      "step": 76
+    },
+    {
+      "epoch": 0.23811364514882102,
+      "grad_norm": 1.794921875,
+      "learning_rate": 9.068854879642831e-07,
+      "loss": 0.8511,
+      "step": 77
+    },
+    {
+      "epoch": 0.24120603015075376,
+      "grad_norm": 1.3857421875,
+      "learning_rate": 9.039100620434024e-07,
+      "loss": 0.6289,
+      "step": 78
+    },
+    {
+      "epoch": 0.24429841515268652,
+      "grad_norm": 1.3076171875,
+      "learning_rate": 9.008928854267053e-07,
+      "loss": 0.6155,
+      "step": 79
+    },
+    {
+      "epoch": 0.24739080015461926,
+      "grad_norm": 3.12890625,
+      "learning_rate": 8.978342699886288e-07,
+      "loss": 0.9333,
+      "step": 80
+    },
+    {
+      "epoch": 0.250483185156552,
+      "grad_norm": 1.375,
+      "learning_rate": 8.947345318869881e-07,
+      "loss": 0.4149,
+      "step": 81
+    },
+    {
+      "epoch": 0.25357557015848475,
+      "grad_norm": 1.5517578125,
+      "learning_rate": 8.915939915302968e-07,
+      "loss": 0.6882,
+      "step": 82
+    },
+    {
+      "epoch": 0.25666795516041746,
+      "grad_norm": 2.533203125,
+      "learning_rate": 8.88412973544647e-07,
+      "loss": 0.904,
+      "step": 83
+    },
+    {
+      "epoch": 0.2597603401623502,
+      "grad_norm": 1.849609375,
+      "learning_rate": 8.851918067401551e-07,
+      "loss": 0.6705,
+      "step": 84
+    },
+    {
+      "epoch": 0.26285272516428293,
+      "grad_norm": 1.1474609375,
+      "learning_rate": 8.819308240769724e-07,
+      "loss": 0.4361,
+      "step": 85
+    },
+    {
+      "epoch": 0.2659451101662157,
+      "grad_norm": 1.720703125,
+      "learning_rate": 8.786303626308688e-07,
+      "loss": 0.6259,
+      "step": 86
+    },
+    {
+      "epoch": 0.26903749516814845,
+      "grad_norm": 1.3369140625,
+      "learning_rate": 8.752907635583911e-07,
+      "loss": 0.372,
+      "step": 87
+    },
+    {
+      "epoch": 0.27212988017008116,
+      "grad_norm": 1.1396484375,
+      "learning_rate": 8.71912372061598e-07,
+      "loss": 0.3766,
+      "step": 88
+    },
+    {
+      "epoch": 0.2752222651720139,
+      "grad_norm": 1.3701171875,
+      "learning_rate": 8.684955373523786e-07,
+      "loss": 0.5947,
+      "step": 89
+    },
+    {
+      "epoch": 0.27831465017394663,
+      "grad_norm": 1.0537109375,
+      "learning_rate": 8.650406126163551e-07,
+      "loss": 0.5538,
+      "step": 90
+    },
+    {
+      "epoch": 0.2814070351758794,
+      "grad_norm": 1.43359375,
+      "learning_rate": 8.615479549763755e-07,
+      "loss": 0.5618,
+      "step": 91
+    },
+    {
+      "epoch": 0.28449942017781216,
+      "grad_norm": 1.248046875,
+      "learning_rate": 8.580179254555994e-07,
+      "loss": 0.5608,
+      "step": 92
+    },
+    {
+      "epoch": 0.28759180517974486,
+      "grad_norm": 1.14453125,
+      "learning_rate": 8.544508889401798e-07,
+      "loss": 0.5199,
+      "step": 93
+    },
+    {
+      "epoch": 0.2906841901816776,
+      "grad_norm": 0.95263671875,
+      "learning_rate": 8.508472141415465e-07,
+      "loss": 0.3945,
+      "step": 94
+    },
+    {
+      "epoch": 0.29377657518361033,
+      "grad_norm": 1.07421875,
+      "learning_rate": 8.472072735582941e-07,
+      "loss": 0.5235,
+      "step": 95
+    },
+    {
+      "epoch": 0.2968689601855431,
+      "grad_norm": 2.25,
+      "learning_rate": 8.435314434376773e-07,
+      "loss": 0.5098,
+      "step": 96
+    },
+    {
+      "epoch": 0.29996134518747586,
+      "grad_norm": 1.0419921875,
+      "learning_rate": 8.398201037367201e-07,
+      "loss": 0.5901,
+      "step": 97
+    },
+    {
+      "epoch": 0.30305373018940857,
+      "grad_norm": 1.197265625,
+      "learning_rate": 8.360736380829418e-07,
+      "loss": 0.6208,
+      "step": 98
+    },
+    {
+      "epoch": 0.30614611519134133,
+      "grad_norm": 1.2783203125,
+      "learning_rate": 8.322924337347015e-07,
+      "loss": 0.6289,
+      "step": 99
+    },
+    {
+      "epoch": 0.30923850019327404,
+      "grad_norm": 2.18359375,
+      "learning_rate": 8.284768815411691e-07,
+      "loss": 0.7223,
+      "step": 100
+    },
+    {
+      "epoch": 0.3123308851952068,
+      "grad_norm": 3.375,
+      "learning_rate": 8.246273759019251e-07,
+      "loss": 0.8717,
+      "step": 101
+    },
+    {
+      "epoch": 0.31542327019713956,
+      "grad_norm": 1.150390625,
+      "learning_rate": 8.207443147261929e-07,
+      "loss": 0.7932,
+      "step": 102
+    },
+    {
+      "epoch": 0.31851565519907227,
+      "grad_norm": 1.1240234375,
+      "learning_rate": 8.168280993917076e-07,
+      "loss": 0.6476,
+      "step": 103
+    },
+    {
+      "epoch": 0.32160804020100503,
+      "grad_norm": 0.880859375,
+      "learning_rate": 8.128791347032278e-07,
+      "loss": 0.4536,
+      "step": 104
+    },
+    {
+      "epoch": 0.3247004252029378,
+      "grad_norm": 0.8720703125,
+      "learning_rate": 8.088978288506923e-07,
+      "loss": 0.5822,
+      "step": 105
+    },
+    {
+      "epoch": 0.3277928102048705,
+      "grad_norm": 1.150390625,
+      "learning_rate": 8.048845933670271e-07,
+      "loss": 0.5383,
+      "step": 106
+    },
+    {
+      "epoch": 0.33088519520680326,
+      "grad_norm": 1.0673828125,
+      "learning_rate": 8.008398430856063e-07,
+      "loss": 0.64,
+      "step": 107
+    },
+    {
+      "epoch": 0.33397758020873597,
+      "grad_norm": 1.1337890625,
+      "learning_rate": 7.967639960973726e-07,
+      "loss": 0.6862,
+      "step": 108
+    },
+    {
+      "epoch": 0.33706996521066873,
+      "grad_norm": 1.4296875,
+      "learning_rate": 7.92657473707621e-07,
+      "loss": 0.867,
+      "step": 109
+    },
+    {
+      "epoch": 0.3401623502126015,
+      "grad_norm": 0.91455078125,
+      "learning_rate": 7.885207003924497e-07,
+      "loss": 0.464,
+      "step": 110
+    },
+    {
+      "epoch": 0.3432547352145342,
+      "grad_norm": 0.8115234375,
+      "learning_rate": 7.843541037548837e-07,
+      "loss": 0.467,
+      "step": 111
+    },
+    {
+      "epoch": 0.34634712021646696,
+      "grad_norm": 1.9443359375,
+      "learning_rate": 7.801581144806751e-07,
+      "loss": 0.5784,
+      "step": 112
+    },
+    {
+      "epoch": 0.34943950521839967,
+      "grad_norm": 1.2568359375,
+      "learning_rate": 7.75933166293784e-07,
+      "loss": 0.7382,
+      "step": 113
+    },
+    {
+      "epoch": 0.35253189022033243,
+      "grad_norm": 1.126953125,
+      "learning_rate": 7.716796959115477e-07,
+      "loss": 0.4922,
+      "step": 114
+    },
+    {
+      "epoch": 0.3556242752222652,
+      "grad_norm": 1.033203125,
+      "learning_rate": 7.673981429995371e-07,
+      "loss": 0.4763,
+      "step": 115
+    },
+    {
+      "epoch": 0.3587166602241979,
+      "grad_norm": 0.59765625,
+      "learning_rate": 7.630889501261108e-07,
+      "loss": 0.2734,
+      "step": 116
+    },
+    {
+      "epoch": 0.36180904522613067,
+      "grad_norm": 1.6201171875,
+      "learning_rate": 7.58752562716669e-07,
+      "loss": 1.0264,
+      "step": 117
+    },
+    {
+      "epoch": 0.3649014302280634,
+      "grad_norm": 1.8515625,
+      "learning_rate": 7.543894290076103e-07,
+      "loss": 0.6039,
+      "step": 118
+    },
+    {
+      "epoch": 0.36799381522999614,
+      "grad_norm": 0.9951171875,
+      "learning_rate": 7.5e-07,
+      "loss": 0.5836,
+      "step": 119
+    },
+    {
+      "epoch": 0.3710862002319289,
+      "grad_norm": 0.8935546875,
+      "learning_rate": 7.455847294129518e-07,
+      "loss": 0.3714,
+      "step": 120
+    },
+    {
+      "epoch": 0.3741785852338616,
+      "grad_norm": 0.73193359375,
+      "learning_rate": 7.41144073636728e-07,
+      "loss": 0.3868,
+      "step": 121
+    },
+    {
+      "epoch": 0.37727097023579437,
+      "grad_norm": 0.8701171875,
+      "learning_rate": 7.366784916855649e-07,
+      "loss": 0.4043,
+      "step": 122
+    },
+    {
+      "epoch": 0.3803633552377271,
+      "grad_norm": 1.0478515625,
+      "learning_rate": 7.321884451502252e-07,
+      "loss": 0.8025,
+      "step": 123
+    },
+    {
+      "epoch": 0.38345574023965984,
+      "grad_norm": 0.78662109375,
+      "learning_rate": 7.276743981502855e-07,
+      "loss": 0.5009,
+      "step": 124
+    },
+    {
+      "epoch": 0.3865481252415926,
+      "grad_norm": 1.09765625,
+      "learning_rate": 7.231368172861629e-07,
+      "loss": 0.6254,
+      "step": 125
+    },
+    {
+      "epoch": 0.3896405102435253,
+      "grad_norm": 1.568359375,
+      "learning_rate": 7.185761715908825e-07,
+      "loss": 0.6705,
+      "step": 126
+    },
+    {
+      "epoch": 0.39273289524545807,
+      "grad_norm": 0.97802734375,
+      "learning_rate": 7.139929324815964e-07,
+      "loss": 0.5675,
+      "step": 127
+    },
+    {
+      "epoch": 0.3958252802473908,
+      "grad_norm": 1.107421875,
+      "learning_rate": 7.093875737108548e-07,
+      "loss": 0.5836,
+      "step": 128
+    },
+    {
+      "epoch": 0.39891766524932354,
+      "grad_norm": 0.943359375,
+      "learning_rate": 7.047605713176359e-07,
+      "loss": 0.4119,
+      "step": 129
+    },
+    {
+      "epoch": 0.4020100502512563,
+      "grad_norm": 1.0400390625,
+      "learning_rate": 7.001124035781389e-07,
+      "loss": 0.4852,
+      "step": 130
+    },
+    {
+      "epoch": 0.405102435253189,
+      "grad_norm": 0.7646484375,
+      "learning_rate": 6.954435509563477e-07,
+      "loss": 0.5633,
+      "step": 131
+    },
+    {
+      "epoch": 0.40819482025512177,
+      "grad_norm": 1.0126953125,
+      "learning_rate": 6.907544960543658e-07,
+      "loss": 0.7201,
+      "step": 132
+    },
+    {
+      "epoch": 0.4112872052570545,
+      "grad_norm": 0.74560546875,
+      "learning_rate": 6.860457235625321e-07,
+      "loss": 0.6064,
+      "step": 133
+    },
+    {
+      "epoch": 0.41437959025898724,
+      "grad_norm": 0.83984375,
+      "learning_rate": 6.813177202093202e-07,
+      "loss": 0.5591,
+      "step": 134
+    },
+    {
+      "epoch": 0.41747197526092,
+      "grad_norm": 1.1630859375,
+      "learning_rate": 6.765709747110273e-07,
+      "loss": 0.6987,
+      "step": 135
+    },
+    {
+      "epoch": 0.4205643602628527,
+      "grad_norm": 0.66796875,
+      "learning_rate": 6.718059777212565e-07,
+      "loss": 0.3856,
+      "step": 136
+    },
+    {
+      "epoch": 0.4236567452647855,
+      "grad_norm": 1.01953125,
+      "learning_rate": 6.67023221780201e-07,
+      "loss": 0.6259,
+      "step": 137
+    },
+    {
+      "epoch": 0.4267491302667182,
+      "grad_norm": 3.798828125,
+      "learning_rate": 6.62223201263731e-07,
+      "loss": 0.4784,
+      "step": 138
+    },
+    {
+      "epoch": 0.42984151526865094,
+      "grad_norm": 1.5576171875,
+      "learning_rate": 6.574064123322924e-07,
+      "loss": 0.8581,
+      "step": 139
+    },
+    {
+      "epoch": 0.4329339002705837,
+      "grad_norm": 1.9697265625,
+      "learning_rate": 6.525733528796206e-07,
+      "loss": 0.6919,
+      "step": 140
+    },
+    {
+      "epoch": 0.4360262852725164,
+      "grad_norm": 2.140625,
+      "learning_rate": 6.477245224812746e-07,
+      "loss": 0.3518,
+      "step": 141
+    },
+    {
+      "epoch": 0.4391186702744492,
+      "grad_norm": 0.97314453125,
+      "learning_rate": 6.428604223429979e-07,
+      "loss": 0.3641,
+      "step": 142
+    },
+    {
+      "epoch": 0.44221105527638194,
+      "grad_norm": 0.87158203125,
+      "learning_rate": 6.379815552489112e-07,
+      "loss": 0.454,
+      "step": 143
+    },
+    {
+      "epoch": 0.44530344027831464,
+      "grad_norm": 0.611328125,
+      "learning_rate": 6.330884255095408e-07,
+      "loss": 0.2737,
+      "step": 144
+    },
+    {
+      "epoch": 0.4483958252802474,
+      "grad_norm": 1.1591796875,
+      "learning_rate": 6.281815389096901e-07,
+      "loss": 0.5939,
+      "step": 145
+    },
+    {
+      "epoch": 0.4514882102821801,
+      "grad_norm": 0.65380859375,
+      "learning_rate": 6.232614026561586e-07,
+      "loss": 0.3116,
+      "step": 146
+    },
+    {
+      "epoch": 0.4545805952841129,
+      "grad_norm": 2.357421875,
+      "learning_rate": 6.183285253253134e-07,
+      "loss": 0.7887,
+      "step": 147
+    },
+    {
+      "epoch": 0.45767298028604564,
+      "grad_norm": 0.93896484375,
+      "learning_rate": 6.133834168105205e-07,
+      "loss": 0.4022,
+      "step": 148
+    },
+    {
+      "epoch": 0.46076536528797835,
+      "grad_norm": 5.015625,
+      "learning_rate": 6.084265882694378e-07,
+      "loss": 0.8508,
+      "step": 149
+    },
+    {
+      "epoch": 0.4638577502899111,
+      "grad_norm": 1.6611328125,
+      "learning_rate": 6.034585520711792e-07,
+      "loss": 0.6777,
+      "step": 150
+    },
+    {
+      "epoch": 0.4669501352918438,
+      "grad_norm": 0.9248046875,
+      "learning_rate": 5.984798217433531e-07,
+      "loss": 0.5893,
+      "step": 151
+    },
+    {
+      "epoch": 0.4700425202937766,
+      "grad_norm": 0.83251953125,
+      "learning_rate": 5.934909119189805e-07,
+      "loss": 0.43,
+      "step": 152
+    },
+    {
+      "epoch": 0.47313490529570934,
+      "grad_norm": 1.37109375,
+      "learning_rate": 5.884923382832996e-07,
+      "loss": 0.6694,
+      "step": 153
+    },
+    {
+      "epoch": 0.47622729029764205,
+      "grad_norm": 0.85595703125,
+      "learning_rate": 5.834846175204611e-07,
+      "loss": 0.5568,
+      "step": 154
+    },
+    {
+      "epoch": 0.4793196752995748,
+      "grad_norm": 0.88671875,
+      "learning_rate": 5.784682672601207e-07,
+      "loss": 0.382,
+      "step": 155
+    },
+    {
+      "epoch": 0.4824120603015075,
+      "grad_norm": 1.1953125,
+      "learning_rate": 5.734438060239331e-07,
+      "loss": 0.5373,
+      "step": 156
+    },
+    {
+      "epoch": 0.4855044453034403,
+      "grad_norm": 1.171875,
+      "learning_rate": 5.684117531719551e-07,
+      "loss": 0.3352,
+      "step": 157
+    },
+    {
+      "epoch": 0.48859683030537304,
+      "grad_norm": 0.6845703125,
+      "learning_rate": 5.633726288489609e-07,
+      "loss": 0.3523,
+      "step": 158
+    },
+    {
+      "epoch": 0.49168921530730575,
+      "grad_norm": 1.75,
+      "learning_rate": 5.583269539306762e-07,
+      "loss": 0.3556,
+      "step": 159
+    },
+    {
+      "epoch": 0.4947816003092385,
+      "grad_norm": 0.869140625,
+      "learning_rate": 5.53275249969938e-07,
+      "loss": 0.3313,
+      "step": 160
+    },
+    {
+      "epoch": 0.4978739853111712,
+      "grad_norm": 1.05859375,
+      "learning_rate": 5.482180391427833e-07,
+      "loss": 0.609,
+      "step": 161
+    },
+    {
+      "epoch": 0.500966370313104,
+      "grad_norm": 0.85546875,
+      "learning_rate": 5.43155844194473e-07,
+      "loss": 0.393,
+      "step": 162
+    },
+    {
+      "epoch": 0.5040587553150367,
+      "grad_norm": 0.84326171875,
+      "learning_rate": 5.38089188385459e-07,
+      "loss": 0.388,
+      "step": 163
+    },
+    {
+      "epoch": 0.5071511403169695,
+      "grad_norm": 0.92041015625,
+      "learning_rate": 5.330185954372954e-07,
+      "loss": 0.5085,
+      "step": 164
+    },
+    {
+      "epoch": 0.5102435253189022,
+      "grad_norm": 2.18359375,
+      "learning_rate": 5.279445894785041e-07,
+      "loss": 0.4846,
+      "step": 165
+    },
+    {
+      "epoch": 0.5133359103208349,
+      "grad_norm": 6.39453125,
+      "learning_rate": 5.228676949903973e-07,
+      "loss": 0.9367,
+      "step": 166
+    },
+    {
+      "epoch": 0.5164282953227677,
+      "grad_norm": 1.0673828125,
+      "learning_rate": 5.177884367528637e-07,
+      "loss": 0.599,
+      "step": 167
+    },
+    {
+      "epoch": 0.5195206803247004,
+      "grad_norm": 0.64111328125,
+      "learning_rate": 5.127073397901247e-07,
+      "loss": 0.4471,
+      "step": 168
+    },
+    {
+      "epoch": 0.5226130653266332,
+      "grad_norm": 0.58349609375,
+      "learning_rate": 5.07624929316463e-07,
+      "loss": 0.2312,
+      "step": 169
+    },
+    {
+      "epoch": 0.5257054503285659,
+      "grad_norm": 0.59130859375,
+      "learning_rate": 5.025417306819347e-07,
+      "loss": 0.3372,
+      "step": 170
+    },
+    {
+      "epoch": 0.5287978353304986,
+      "grad_norm": 2.068359375,
+      "learning_rate": 4.974582693180651e-07,
+      "loss": 0.4175,
+      "step": 171
+    },
+    {
+      "epoch": 0.5318902203324314,
+      "grad_norm": 0.8701171875,
+      "learning_rate": 4.923750706835371e-07,
+      "loss": 0.7236,
+      "step": 172
+    },
+    {
+      "epoch": 0.5349826053343641,
+      "grad_norm": 3.009765625,
+      "learning_rate": 4.872926602098754e-07,
+      "loss": 0.4879,
+      "step": 173
+    },
+    {
+      "epoch": 0.5380749903362969,
+      "grad_norm": 0.9619140625,
+      "learning_rate": 4.822115632471362e-07,
+      "loss": 0.4472,
+      "step": 174
+    },
+    {
+      "epoch": 0.5411673753382296,
+      "grad_norm": 0.86669921875,
+      "learning_rate": 4.771323050096027e-07,
+      "loss": 0.6425,
+      "step": 175
+    },
+    {
+      "epoch": 0.5442597603401623,
+      "grad_norm": 0.90283203125,
+      "learning_rate": 4.7205541052149604e-07,
+      "loss": 0.4621,
+      "step": 176
+    },
+    {
+      "epoch": 0.5473521453420951,
+      "grad_norm": 1.419921875,
+      "learning_rate": 4.6698140456270455e-07,
+      "loss": 0.2652,
+      "step": 177
+    },
+    {
+      "epoch": 0.5504445303440278,
+      "grad_norm": 0.5361328125,
+      "learning_rate": 4.6191081161454105e-07,
+      "loss": 0.3136,
+      "step": 178
+    },
+    {
+      "epoch": 0.5535369153459606,
+      "grad_norm": 4.40234375,
+      "learning_rate": 4.5684415580552705e-07,
+      "loss": 0.6098,
+      "step": 179
+    },
+    {
+      "epoch": 0.5566293003478933,
+      "grad_norm": 1.5966796875,
+      "learning_rate": 4.517819608572167e-07,
+      "loss": 0.3585,
+      "step": 180
+    },
+    {
+      "epoch": 0.559721685349826,
+      "grad_norm": 2.55078125,
+      "learning_rate": 4.46724750030062e-07,
+      "loss": 0.4844,
+      "step": 181
+    },
+    {
+      "epoch": 0.5628140703517588,
+      "grad_norm": 1.9521484375,
+      "learning_rate": 4.4167304606932387e-07,
+      "loss": 0.4035,
+      "step": 182
+    },
+    {
+      "epoch": 0.5659064553536916,
+      "grad_norm": 1.388671875,
+      "learning_rate": 4.366273711510392e-07,
+      "loss": 0.4476,
+      "step": 183
+    },
+    {
+      "epoch": 0.5689988403556243,
+      "grad_norm": 1.3515625,
+      "learning_rate": 4.3158824682804496e-07,
+      "loss": 0.5406,
+      "step": 184
+    },
+    {
+      "epoch": 0.572091225357557,
+      "grad_norm": 0.96630859375,
+      "learning_rate": 4.26556193976067e-07,
+      "loss": 0.4346,
+      "step": 185
+    },
+    {
+      "epoch": 0.5751836103594897,
+      "grad_norm": 0.6376953125,
+      "learning_rate": 4.215317327398794e-07,
+      "loss": 0.4279,
+      "step": 186
+    },
+    {
+      "epoch": 0.5782759953614225,
+      "grad_norm": 9.0703125,
+      "learning_rate": 4.1651538247953897e-07,
+      "loss": 0.4792,
+      "step": 187
+    },
+    {
+      "epoch": 0.5813683803633553,
+      "grad_norm": 1.244140625,
+      "learning_rate": 4.1150766171670035e-07,
+      "loss": 0.4545,
+      "step": 188
+    },
+    {
+      "epoch": 0.584460765365288,
+      "grad_norm": 4.0703125,
+      "learning_rate": 4.065090880810196e-07,
+      "loss": 0.604,
+      "step": 189
+    },
+    {
+      "epoch": 0.5875531503672207,
+      "grad_norm": 0.93212890625,
+      "learning_rate": 4.015201782566471e-07,
+      "loss": 0.4786,
+      "step": 190
+    },
+    {
+      "epoch": 0.5906455353691534,
+      "grad_norm": 1.796875,
+      "learning_rate": 3.9654144792882084e-07,
+      "loss": 0.3736,
+      "step": 191
+    },
+    {
+      "epoch": 0.5937379203710862,
+      "grad_norm": 1.001953125,
+      "learning_rate": 3.9157341173056236e-07,
+      "loss": 0.4834,
+      "step": 192
+    },
+    {
+      "epoch": 0.596830305373019,
+      "grad_norm": 1.076171875,
+      "learning_rate": 3.866165831894795e-07,
+      "loss": 0.4159,
+      "step": 193
+    },
+    {
+      "epoch": 0.5999226903749517,
+      "grad_norm": 0.81005859375,
+      "learning_rate": 3.8167147467468647e-07,
+      "loss": 0.4358,
+      "step": 194
+    },
+    {
+      "epoch": 0.6030150753768844,
+      "grad_norm": 0.82470703125,
+      "learning_rate": 3.767385973438415e-07,
+      "loss": 0.492,
+      "step": 195
+    },
+    {
+      "epoch": 0.6061074603788171,
+      "grad_norm": 1.3232421875,
+      "learning_rate": 3.7181846109031e-07,
+      "loss": 0.3175,
+      "step": 196
+    },
+    {
+      "epoch": 0.6091998453807499,
+      "grad_norm": 0.5888671875,
+      "learning_rate": 3.669115744904591e-07,
+      "loss": 0.3646,
+      "step": 197
+    },
+    {
+      "epoch": 0.6122922303826827,
+      "grad_norm": 0.873046875,
+      "learning_rate": 3.6201844475108876e-07,
+      "loss": 0.4751,
+      "step": 198
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.5419921875,
+      "learning_rate": 3.571395776570022e-07,
+      "loss": 0.3102,
+      "step": 199
+    },
+    {
+      "epoch": 0.6184770003865481,
+      "grad_norm": 2.56640625,
+      "learning_rate": 3.5227547751872544e-07,
+      "loss": 0.5683,
+      "step": 200
+    },
+    {
+      "epoch": 0.6215693853884808,
+      "grad_norm": 0.62353515625,
+      "learning_rate": 3.4742664712037936e-07,
+      "loss": 0.2254,
+      "step": 201
+    },
+    {
+      "epoch": 0.6246617703904136,
+      "grad_norm": 1.439453125,
+      "learning_rate": 3.4259358766770764e-07,
+      "loss": 0.5249,
+      "step": 202
+    },
+    {
+      "epoch": 0.6277541553923464,
+      "grad_norm": 0.68310546875,
+      "learning_rate": 3.3777679873626897e-07,
+      "loss": 0.2239,
+      "step": 203
+    },
+    {
+      "epoch": 0.6308465403942791,
+      "grad_norm": 1.341796875,
+      "learning_rate": 3.329767782197991e-07,
+      "loss": 0.4764,
+      "step": 204
+    },
+    {
+      "epoch": 0.6339389253962119,
+      "grad_norm": 0.888671875,
+      "learning_rate": 3.281940222787436e-07,
+      "loss": 0.4993,
+      "step": 205
+    },
+    {
+      "epoch": 0.6370313103981445,
+      "grad_norm": 0.79150390625,
+      "learning_rate": 3.2342902528897274e-07,
+      "loss": 0.4186,
+      "step": 206
+    },
+    {
+      "epoch": 0.6401236954000773,
+      "grad_norm": 3.265625,
+      "learning_rate": 3.186822797906798e-07,
+      "loss": 0.8248,
+      "step": 207
+    },
+    {
+      "epoch": 0.6432160804020101,
+      "grad_norm": 0.61328125,
+      "learning_rate": 3.13954276437468e-07,
+      "loss": 0.4087,
+      "step": 208
+    },
+    {
+      "epoch": 0.6463084654039428,
+      "grad_norm": 0.62451171875,
+      "learning_rate": 3.092455039456343e-07,
+      "loss": 0.3882,
+      "step": 209
+    },
+    {
+      "epoch": 0.6494008504058756,
+      "grad_norm": 0.65576171875,
+      "learning_rate": 3.0455644904365227e-07,
+      "loss": 0.2988,
+      "step": 210
+    },
+    {
+      "epoch": 0.6524932354078082,
+      "grad_norm": 0.7490234375,
+      "learning_rate": 2.9988759642186093e-07,
+      "loss": 0.4568,
+      "step": 211
+    },
+    {
+      "epoch": 0.655585620409741,
+      "grad_norm": 1.8974609375,
+      "learning_rate": 2.952394286823641e-07,
+      "loss": 0.538,
+      "step": 212
+    },
+    {
+      "epoch": 0.6586780054116738,
+      "grad_norm": 0.83642578125,
+      "learning_rate": 2.9061242628914506e-07,
+      "loss": 0.5517,
+      "step": 213
+    },
+    {
+      "epoch": 0.6617703904136065,
+      "grad_norm": 0.681640625,
+      "learning_rate": 2.860070675184036e-07,
+      "loss": 0.3914,
+      "step": 214
+    },
+    {
+      "epoch": 0.6648627754155393,
+      "grad_norm": 0.5283203125,
+      "learning_rate": 2.8142382840911745e-07,
+      "loss": 0.2799,
+      "step": 215
+    },
+    {
+      "epoch": 0.6679551604174719,
+      "grad_norm": 0.83740234375,
+      "learning_rate": 2.7686318271383713e-07,
+      "loss": 0.3534,
+      "step": 216
+    },
+    {
+      "epoch": 0.6710475454194047,
+      "grad_norm": 0.69970703125,
+      "learning_rate": 2.723256018497143e-07,
+      "loss": 0.4005,
+      "step": 217
+    },
+    {
+      "epoch": 0.6741399304213375,
+      "grad_norm": 1.87109375,
+      "learning_rate": 2.6781155484977494e-07,
+      "loss": 0.514,
+      "step": 218
+    },
+    {
+      "epoch": 0.6772323154232702,
+      "grad_norm": 0.94580078125,
+      "learning_rate": 2.633215083144352e-07,
+      "loss": 0.4112,
+      "step": 219
+    },
+    {
+      "epoch": 0.680324700425203,
+      "grad_norm": 0.72900390625,
+      "learning_rate": 2.5885592636327186e-07,
+      "loss": 0.4113,
+      "step": 220
+    },
+    {
+      "epoch": 0.6834170854271356,
+      "grad_norm": 0.546875,
+      "learning_rate": 2.5441527058704827e-07,
+      "loss": 0.312,
+      "step": 221
+    },
+    {
+      "epoch": 0.6865094704290684,
+      "grad_norm": 0.68310546875,
+      "learning_rate": 2.500000000000001e-07,
+      "loss": 0.4087,
+      "step": 222
+    },
+    {
+      "epoch": 0.6896018554310012,
+      "grad_norm": 0.68994140625,
+      "learning_rate": 2.4561057099238967e-07,
+      "loss": 0.4743,
+      "step": 223
+    },
+    {
+      "epoch": 0.6926942404329339,
+      "grad_norm": 1.1025390625,
+      "learning_rate": 2.41247437283331e-07,
+      "loss": 0.4837,
+      "step": 224
+    },
+    {
+      "epoch": 0.6957866254348667,
+      "grad_norm": 0.8369140625,
+      "learning_rate": 2.369110498738892e-07,
+      "loss": 0.6041,
+      "step": 225
+    },
+    {
+      "epoch": 0.6988790104367993,
+      "grad_norm": 0.7314453125,
+      "learning_rate": 2.3260185700046292e-07,
+      "loss": 0.4076,
+      "step": 226
+    },
+    {
+      "epoch": 0.7019713954387321,
+      "grad_norm": 0.755859375,
+      "learning_rate": 2.2832030408845238e-07,
+      "loss": 0.3234,
+      "step": 227
+    },
+    {
+      "epoch": 0.7050637804406649,
+      "grad_norm": 0.53466796875,
+      "learning_rate": 2.2406683370621615e-07,
+      "loss": 0.3365,
+      "step": 228
+    },
+    {
+      "epoch": 0.7081561654425976,
+      "grad_norm": 0.9033203125,
+      "learning_rate": 2.1984188551932508e-07,
+      "loss": 0.4372,
+      "step": 229
+    },
+    {
+      "epoch": 0.7112485504445304,
+      "grad_norm": 0.6357421875,
+      "learning_rate": 2.1564589624511637e-07,
+      "loss": 0.4265,
+      "step": 230
+    },
+    {
+      "epoch": 0.714340935446463,
+      "grad_norm": 0.865234375,
+      "learning_rate": 2.114792996075503e-07,
+      "loss": 0.3074,
+      "step": 231
+    },
+    {
+      "epoch": 0.7174333204483958,
+      "grad_norm": 2.876953125,
+      "learning_rate": 2.0734252629237892e-07,
+      "loss": 0.4653,
+      "step": 232
+    },
+    {
+      "epoch": 0.7205257054503286,
+      "grad_norm": 0.7939453125,
+      "learning_rate": 2.0323600390262742e-07,
+      "loss": 0.3628,
+      "step": 233
+    },
+    {
+      "epoch": 0.7236180904522613,
+      "grad_norm": 0.87744140625,
+      "learning_rate": 1.991601569143938e-07,
+      "loss": 0.4211,
+      "step": 234
+    },
+    {
+      "epoch": 0.7267104754541941,
+      "grad_norm": 0.72607421875,
+      "learning_rate": 1.9511540663297282e-07,
+      "loss": 0.4046,
+      "step": 235
+    },
+    {
+      "epoch": 0.7298028604561267,
+      "grad_norm": 0.5517578125,
+      "learning_rate": 1.9110217114930766e-07,
+      "loss": 0.3374,
+      "step": 236
+    },
+    {
+      "epoch": 0.7328952454580595,
+      "grad_norm": 0.54150390625,
+      "learning_rate": 1.871208652967721e-07,
+      "loss": 0.279,
+      "step": 237
+    },
+    {
+      "epoch": 0.7359876304599923,
+      "grad_norm": 0.65283203125,
+      "learning_rate": 1.831719006082924e-07,
+      "loss": 0.2825,
+      "step": 238
+    },
+    {
+      "epoch": 0.739080015461925,
+      "grad_norm": 0.8046875,
+      "learning_rate": 1.7925568527380713e-07,
+      "loss": 0.4046,
+      "step": 239
+    },
+    {
+      "epoch": 0.7421724004638578,
+      "grad_norm": 0.671875,
+      "learning_rate": 1.7537262409807475e-07,
+      "loss": 0.2117,
+      "step": 240
+    },
+    {
+      "epoch": 0.7452647854657904,
+      "grad_norm": 0.6513671875,
+      "learning_rate": 1.7152311845883094e-07,
+      "loss": 0.2691,
+      "step": 241
+    },
+    {
+      "epoch": 0.7483571704677232,
+      "grad_norm": 0.8837890625,
+      "learning_rate": 1.6770756626529863e-07,
+      "loss": 0.4251,
+      "step": 242
+    },
+    {
+      "epoch": 0.751449555469656,
+      "grad_norm": 0.5244140625,
+      "learning_rate": 1.6392636191705816e-07,
+      "loss": 0.4076,
+      "step": 243
+    },
+    {
+      "epoch": 0.7545419404715887,
+      "grad_norm": 0.7734375,
+      "learning_rate": 1.6017989626327988e-07,
+      "loss": 0.2988,
+      "step": 244
+    },
+    {
+      "epoch": 0.7576343254735215,
+      "grad_norm": 0.6533203125,
+      "learning_rate": 1.5646855656232294e-07,
+      "loss": 0.3373,
+      "step": 245
+    },
+    {
+      "epoch": 0.7607267104754541,
+      "grad_norm": 0.64794921875,
+      "learning_rate": 1.52792726441706e-07,
+      "loss": 0.4431,
+      "step": 246
+    },
+    {
+      "epoch": 0.7638190954773869,
+      "grad_norm": 0.6474609375,
+      "learning_rate": 1.4915278585845347e-07,
+      "loss": 0.3279,
+      "step": 247
+    },
+    {
+      "epoch": 0.7669114804793197,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.455491110598202e-07,
+      "loss": 0.4269,
+      "step": 248
+    },
+    {
+      "epoch": 0.7700038654812524,
+      "grad_norm": 0.85546875,
+      "learning_rate": 1.4198207454440047e-07,
+      "loss": 0.3652,
+      "step": 249
+    },
+    {
+      "epoch": 0.7730962504831852,
+      "grad_norm": 0.61083984375,
+      "learning_rate": 1.384520450236244e-07,
+      "loss": 0.2506,
+      "step": 250
+    },
+    {
+      "epoch": 0.7761886354851179,
+      "grad_norm": 0.6171875,
+      "learning_rate": 1.3495938738364492e-07,
+      "loss": 0.3047,
+      "step": 251
+    },
+    {
+      "epoch": 0.7792810204870506,
+      "grad_norm": 1.380859375,
+      "learning_rate": 1.3150446264762132e-07,
+      "loss": 0.4607,
+      "step": 252
+    },
+    {
+      "epoch": 0.7823734054889834,
+      "grad_norm": 0.576171875,
+      "learning_rate": 1.28087627938402e-07,
+      "loss": 0.3072,
+      "step": 253
+    },
+    {
+      "epoch": 0.7854657904909161,
+      "grad_norm": 0.87646484375,
+      "learning_rate": 1.2470923644160896e-07,
+      "loss": 0.5576,
+      "step": 254
+    },
+    {
+      "epoch": 0.7885581754928489,
+      "grad_norm": 0.425048828125,
+      "learning_rate": 1.2136963736913115e-07,
+      "loss": 0.2187,
+      "step": 255
+    },
+    {
+      "epoch": 0.7916505604947816,
+      "grad_norm": 0.5986328125,
+      "learning_rate": 1.1806917592302761e-07,
+      "loss": 0.1589,
+      "step": 256
+    },
+    {
+      "epoch": 0.7947429454967143,
+      "grad_norm": 0.5537109375,
+      "learning_rate": 1.1480819325984487e-07,
+      "loss": 0.4095,
+      "step": 257
+    },
+    {
+      "epoch": 0.7978353304986471,
+      "grad_norm": 1.091796875,
+      "learning_rate": 1.1158702645535284e-07,
+      "loss": 0.3544,
+      "step": 258
+    },
+    {
+      "epoch": 0.8009277155005798,
+      "grad_norm": 0.7041015625,
+      "learning_rate": 1.0840600846970333e-07,
+      "loss": 0.5995,
+      "step": 259
+    },
+    {
+      "epoch": 0.8040201005025126,
+      "grad_norm": 0.537109375,
+      "learning_rate": 1.0526546811301201e-07,
+      "loss": 0.3507,
+      "step": 260
+    },
+    {
+      "epoch": 0.8071124855044453,
+      "grad_norm": 0.87353515625,
+      "learning_rate": 1.0216573001137125e-07,
+      "loss": 0.3064,
+      "step": 261
+    },
+    {
+      "epoch": 0.810204870506378,
+      "grad_norm": 0.6005859375,
+      "learning_rate": 9.910711457329479e-08,
+      "loss": 0.3378,
+      "step": 262
+    },
+    {
+      "epoch": 0.8132972555083108,
+      "grad_norm": 0.771484375,
+      "learning_rate": 9.608993795659764e-08,
+      "loss": 0.4614,
+      "step": 263
+    },
+    {
+      "epoch": 0.8163896405102435,
+      "grad_norm": 0.7861328125,
+      "learning_rate": 9.311451203571696e-08,
+      "loss": 0.6272,
+      "step": 264
+    },
+    {
+      "epoch": 0.8194820255121763,
+      "grad_norm": 0.8525390625,
+      "learning_rate": 9.018114436947372e-08,
+      "loss": 0.4334,
+      "step": 265
+    },
+    {
+      "epoch": 0.822574410514109,
+      "grad_norm": 1.06640625,
+      "learning_rate": 8.729013816928237e-08,
+      "loss": 0.6624,
+      "step": 266
+    },
+    {
+      "epoch": 0.8256667955160417,
+      "grad_norm": 1.2724609375,
+      "learning_rate": 8.444179226780823e-08,
+      "loss": 0.6581,
+      "step": 267
+    },
+    {
+      "epoch": 0.8287591805179745,
+      "grad_norm": 0.6708984375,
+      "learning_rate": 8.163640108807895e-08,
+      "loss": 0.4066,
+      "step": 268
+    },
+    {
+      "epoch": 0.8318515655199072,
+      "grad_norm": 3.0078125,
+      "learning_rate": 7.887425461305058e-08,
+      "loss": 0.4167,
+      "step": 269
+    },
+    {
+      "epoch": 0.83494395052184,
+      "grad_norm": 0.73974609375,
+      "learning_rate": 7.615563835563338e-08,
+      "loss": 0.3167,
+      "step": 270
+    },
+    {
+      "epoch": 0.8380363355237727,
+      "grad_norm": 0.65234375,
+      "learning_rate": 7.348083332917926e-08,
+      "loss": 0.2428,
+      "step": 271
+    },
+    {
+      "epoch": 0.8411287205257054,
+      "grad_norm": 0.578125,
+      "learning_rate": 7.085011601843437e-08,
+      "loss": 0.3718,
+      "step": 272
+    },
+    {
+      "epoch": 0.8442211055276382,
+      "grad_norm": 0.54150390625,
+      "learning_rate": 6.826375835096038e-08,
+      "loss": 0.2463,
+      "step": 273
+    },
+    {
+      "epoch": 0.847313490529571,
+      "grad_norm": 0.54248046875,
+      "learning_rate": 6.572202766902568e-08,
+      "loss": 0.3427,
+      "step": 274
+    },
+    {
+      "epoch": 0.8504058755315037,
+      "grad_norm": 0.916015625,
+      "learning_rate": 6.322518670197141e-08,
+      "loss": 0.815,
+      "step": 275
+    },
+    {
+      "epoch": 0.8534982605334364,
+      "grad_norm": 0.70068359375,
+      "learning_rate": 6.077349353905464e-08,
+      "loss": 0.5081,
+      "step": 276
+    },
+    {
+      "epoch": 0.8565906455353691,
+      "grad_norm": 0.71240234375,
+      "learning_rate": 5.83672016027697e-08,
+      "loss": 0.2721,
+      "step": 277
+    },
+    {
+      "epoch": 0.8596830305373019,
+      "grad_norm": 0.446044921875,
+      "learning_rate": 5.600655962265344e-08,
+      "loss": 0.2394,
+      "step": 278
+    },
+    {
+      "epoch": 0.8627754155392346,
+      "grad_norm": 0.84130859375,
+      "learning_rate": 5.3691811609574974e-08,
+      "loss": 0.351,
+      "step": 279
+    },
+    {
+      "epoch": 0.8658678005411674,
+      "grad_norm": 0.56689453125,
+      "learning_rate": 5.142319683051299e-08,
+      "loss": 0.4396,
+      "step": 280
+    },
+    {
+      "epoch": 0.8689601855431001,
+      "grad_norm": 0.79345703125,
+      "learning_rate": 4.9200949783823383e-08,
+      "loss": 0.4723,
+      "step": 281
+    },
+    {
+      "epoch": 0.8720525705450328,
+      "grad_norm": 0.6572265625,
+      "learning_rate": 4.702530017500067e-08,
+      "loss": 0.2723,
+      "step": 282
+    },
+    {
+      "epoch": 0.8751449555469656,
+      "grad_norm": 0.7958984375,
+      "learning_rate": 4.489647289293369e-08,
+      "loss": 0.4037,
+      "step": 283
+    },
+    {
+      "epoch": 0.8782373405488983,
+      "grad_norm": 0.56005859375,
+      "learning_rate": 4.281468798665949e-08,
+      "loss": 0.3291,
+      "step": 284
+    },
+    {
+      "epoch": 0.8813297255508311,
+      "grad_norm": 0.6220703125,
+      "learning_rate": 4.078016064261847e-08,
+      "loss": 0.4081,
+      "step": 285
+    },
+    {
+      "epoch": 0.8844221105527639,
+      "grad_norm": 1.3037109375,
+      "learning_rate": 3.879310116241041e-08,
+      "loss": 0.5833,
+      "step": 286
+    },
+    {
+      "epoch": 0.8875144955546965,
+      "grad_norm": 0.72802734375,
+      "learning_rate": 3.685371494105682e-08,
+      "loss": 0.5027,
+      "step": 287
+    },
+    {
+      "epoch": 0.8906068805566293,
+      "grad_norm": 0.46630859375,
+      "learning_rate": 3.496220244577025e-08,
+      "loss": 0.2311,
+      "step": 288
+    },
+    {
+      "epoch": 0.893699265558562,
+      "grad_norm": 0.5966796875,
+      "learning_rate": 3.311875919523227e-08,
+      "loss": 0.4063,
+      "step": 289
+    },
+    {
+      "epoch": 0.8967916505604948,
+      "grad_norm": 0.509765625,
+      "learning_rate": 3.132357573938371e-08,
+      "loss": 0.2633,
+      "step": 290
+    },
+    {
+      "epoch": 0.8998840355624276,
+      "grad_norm": 0.48095703125,
+      "learning_rate": 2.957683763972807e-08,
+      "loss": 0.2012,
+      "step": 291
+    },
+    {
+      "epoch": 0.9029764205643602,
+      "grad_norm": 0.970703125,
+      "learning_rate": 2.7878725450150686e-08,
+      "loss": 0.4094,
+      "step": 292
+    },
+    {
+      "epoch": 0.906068805566293,
+      "grad_norm": 0.66796875,
+      "learning_rate": 2.6229414698255904e-08,
+      "loss": 0.572,
+      "step": 293
+    },
+    {
+      "epoch": 0.9091611905682258,
+      "grad_norm": 0.5888671875,
+      "learning_rate": 2.4629075867222847e-08,
+      "loss": 0.2754,
+      "step": 294
+    },
+    {
+      "epoch": 0.9122535755701585,
+      "grad_norm": 0.5322265625,
+      "learning_rate": 2.3077874378183647e-08,
+      "loss": 0.2989,
+      "step": 295
+    },
+    {
+      "epoch": 0.9153459605720913,
+      "grad_norm": 0.572265625,
+      "learning_rate": 2.1575970573124437e-08,
+      "loss": 0.3489,
+      "step": 296
+    },
+    {
+      "epoch": 0.9184383455740239,
+      "grad_norm": 2.1328125,
+      "learning_rate": 2.0123519698311e-08,
+      "loss": 0.4039,
+      "step": 297
+    },
+    {
+      "epoch": 0.9215307305759567,
+      "grad_norm": 0.51806640625,
+      "learning_rate": 1.8720671888242057e-08,
+      "loss": 0.3504,
+      "step": 298
+    },
+    {
+      "epoch": 0.9246231155778895,
+      "grad_norm": 1.0087890625,
+      "learning_rate": 1.7367572150130128e-08,
+      "loss": 0.2984,
+      "step": 299
+    },
+    {
+      "epoch": 0.9277155005798222,
+      "grad_norm": 0.5478515625,
+      "learning_rate": 1.6064360348912564e-08,
+      "loss": 0.3781,
+      "step": 300
+    },
+    {
+      "epoch": 0.930807885581755,
+      "grad_norm": 0.626953125,
+      "learning_rate": 1.4811171192794624e-08,
+      "loss": 0.323,
+      "step": 301
+    },
+    {
+      "epoch": 0.9339002705836876,
+      "grad_norm": 0.452392578125,
+      "learning_rate": 1.3608134219324885e-08,
+      "loss": 0.1411,
+      "step": 302
+    },
+    {
+      "epoch": 0.9369926555856204,
+      "grad_norm": 0.734375,
+      "learning_rate": 1.245537378200534e-08,
+      "loss": 0.436,
+      "step": 303
+    },
+    {
+      "epoch": 0.9400850405875532,
+      "grad_norm": 0.59765625,
+      "learning_rate": 1.1353009037437522e-08,
+      "loss": 0.4505,
+      "step": 304
+    },
+    {
+      "epoch": 0.9431774255894859,
+      "grad_norm": 0.8798828125,
+      "learning_rate": 1.0301153933006123e-08,
+      "loss": 0.4289,
+      "step": 305
+    },
+    {
+      "epoch": 0.9462698105914187,
+      "grad_norm": 0.69970703125,
+      "learning_rate": 9.299917195099927e-09,
+      "loss": 0.3713,
+      "step": 306
+    },
+    {
+      "epoch": 0.9493621955933513,
+      "grad_norm": 0.61572265625,
+      "learning_rate": 8.349402317873788e-09,
+      "loss": 0.4215,
+      "step": 307
+    },
+    {
+      "epoch": 0.9524545805952841,
+      "grad_norm": 0.419677734375,
+      "learning_rate": 7.449707552550533e-09,
+      "loss": 0.2628,
+      "step": 308
+    },
+    {
+      "epoch": 0.9555469655972169,
+      "grad_norm": 0.68994140625,
+      "learning_rate": 6.600925897265186e-09,
+      "loss": 0.4945,
+      "step": 309
+    },
+    {
+      "epoch": 0.9586393505991496,
+      "grad_norm": 0.77587890625,
+      "learning_rate": 5.803145087451944e-09,
+      "loss": 0.6511,
+      "step": 310
+    },
+    {
+      "epoch": 0.9617317356010824,
+      "grad_norm": 0.41259765625,
+      "learning_rate": 5.056447586775592e-09,
+      "loss": 0.3105,
+      "step": 311
+    },
+    {
+      "epoch": 0.964824120603015,
+      "grad_norm": 0.4443359375,
+      "learning_rate": 4.360910578607158e-09,
+      "loss": 0.2486,
+      "step": 312
+    },
+    {
+      "epoch": 0.9679165056049478,
+      "grad_norm": 0.57373046875,
+      "learning_rate": 3.7166059580460706e-09,
+      "loss": 0.3163,
+      "step": 313
+    },
+    {
+      "epoch": 0.9710088906068806,
+      "grad_norm": 2.029296875,
+      "learning_rate": 3.1236003244884954e-09,
+      "loss": 0.3552,
+      "step": 314
+    },
+    {
+      "epoch": 0.9741012756088133,
+      "grad_norm": 0.60791015625,
+      "learning_rate": 2.5819549747431167e-09,
+      "loss": 0.4722,
+      "step": 315
+    },
+    {
+      "epoch": 0.9771936606107461,
+      "grad_norm": 0.6240234375,
+      "learning_rate": 2.0917258966953734e-09,
+      "loss": 0.3254,
+      "step": 316
+    },
+    {
+      "epoch": 0.9802860456126787,
+      "grad_norm": 0.6259765625,
+      "learning_rate": 1.65296376351981e-09,
+      "loss": 0.3893,
+      "step": 317
+    },
+    {
+      "epoch": 0.9833784306146115,
+      "grad_norm": 0.8466796875,
+      "learning_rate": 1.2657139284425466e-09,
+      "loss": 0.2895,
+      "step": 318
+    },
+    {
+      "epoch": 0.9864708156165443,
+      "grad_norm": 2.890625,
+      "learning_rate": 9.300164200530814e-10,
+      "loss": 0.4493,
+      "step": 319
+    },
+    {
+      "epoch": 0.989563200618477,
+      "grad_norm": 0.69873046875,
+      "learning_rate": 6.459059381667686e-10,
+      "loss": 0.4818,
+      "step": 320
+    },
+    {
+      "epoch": 0.9926555856204098,
+      "grad_norm": 0.64501953125,
+      "learning_rate": 4.1341185023785474e-10,
+      "loss": 0.4492,
+      "step": 321
+    },
+    {
+      "epoch": 0.9957479706223424,
+      "grad_norm": 0.92822265625,
+      "learning_rate": 2.325581883242389e-10,
+      "loss": 0.4671,
+      "step": 322
+    },
+    {
+      "epoch": 0.9988403556242752,
+      "grad_norm": 0.80517578125,
+      "learning_rate": 1.0336364660290531e-10,
+      "loss": 0.3931,
+      "step": 323
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.533203125,
+      "learning_rate": 2.5841579437968497e-11,
+      "loss": 1.0097,
+      "step": 324
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 324,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.6885162763841536e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-324/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3063dc7c82841c5e87ffd4a20e3c05dd2f41b6eeb229102eecabe2f040f07c57
+size 5841

config.json

@@ -0,0 +1,72 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

emergency_checkpoint/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

emergency_checkpoint/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

emergency_checkpoint/config.json

@@ -0,0 +1,72 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "float16",
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 17408,
+  "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",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 40,
+  "model_type": "qwen3",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}