Upload merged Qwen3-4B-Instruct-2507 model (auto-generated README)

.gitattributes

@@ -33,3 +33,6 @@ 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-1100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1162/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,69 @@
+---
+base_model: Qwen/Qwen3-4B-Instruct-2507
+datasets:
+- u-10bei/sft_alfworld_trajectory_dataset_v5
+- u-10bei/dbbench_sft_dataset_react_v4
+language:
+- en
+license: apache-2.0
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- lora
+- agent
+- tool-use
+- alfworld
+- dbbench
+---
+
+# Qwen3-4B ALFWorld+DBBench Mixed LoRA Adapter (r=64)
+
+This repository provides a **LoRA adapter** fine-tuned from
+**Qwen/Qwen3-4B-Instruct-2507** using **LoRA + Unsloth**.
+
+This repository contains **LoRA adapter weights only**.
+The base model must be loaded separately.
+
+## Training Objective
+
+This adapter is trained to improve **multi-turn agent task performance**
+on ALFWorld (household tasks) and DBBench (database operations).
+
+Loss is applied to **all assistant turns** in the multi-turn trajectory,
+enabling the model to learn environment observation, action selection,
+tool use, and recovery from errors.
+
+## Training Configuration
+
+- Base model: Qwen/Qwen3-4B-Instruct-2507
+- Method: LoRA (full precision base)
+- Max sequence length: 4096
+- Epochs: 3
+- Learning rate: 2e-04
+- LoRA: r=64, alpha=128
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from peft import PeftModel
+import torch
+
+base = "Qwen/Qwen3-4B-Instruct-2507"
+adapter = "your_id/your-repo"
+
+tokenizer = AutoTokenizer.from_pretrained(base)
+model = AutoModelForCausalLM.from_pretrained(
+    base,
+    torch_dtype=torch.float16,
+    device_map="auto",
+)
+model = PeftModel.from_pretrained(model, adapter)
+```
+
+## Sources & Terms (IMPORTANT)
+
+Training data: u-10bei/sft_alfworld_trajectory_dataset_v5 + u-10bei/dbbench_sft_dataset_react_v4
+
+Dataset License: MIT License. This dataset is used and distributed under the terms of the MIT License.
+Compliance: Users must comply with the MIT license (including copyright notice) and the base model's original terms of use.

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a1d31d17384133f04ead482a00de00fc0e6eee7662ec25fbefb1a97ec78ac6
+size 528550256

added_tokens.json

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

chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1100/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

checkpoint-1100/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1100/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aea867929fcb593af6c54177c530455b22d007de7d888ed952f8401fa3f54293
+size 528550256

checkpoint-1100/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-1100/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1100/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:231ec7e9974ebd189e67e77bdf218fefeed535977d7197d85f7c4426206132df
+size 1057397963

checkpoint-1100/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:720e48fa1b729d3d6ae48fc4f1f79e62eb75b8edef9a96abf51ddb5f8c030287
+size 14645

checkpoint-1100/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ab80f50a5442bb1ce7e5c40ef041db326e376f2e4222d8ee804dc248f9d172
+size 1465

checkpoint-1100/special_tokens_map.json

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

checkpoint-1100/tokenizer.json

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

checkpoint-1100/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1100/trainer_state.json

@@ -0,0 +1,1092 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8936719758932417,
+  "eval_steps": 30,
+  "global_step": 1100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017219113215669393,
+      "grad_norm": 8.32422161102295,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 2.589,
+      "step": 10
+    },
+    {
+      "epoch": 0.034438226431338786,
+      "grad_norm": 0.8107045292854309,
+      "learning_rate": 3.247863247863248e-05,
+      "loss": 0.9674,
+      "step": 20
+    },
+    {
+      "epoch": 0.05165733964700818,
+      "grad_norm": 0.7474735379219055,
+      "learning_rate": 4.9572649572649575e-05,
+      "loss": 0.5896,
+      "step": 30
+    },
+    {
+      "epoch": 0.05165733964700818,
+      "eval_loss": 0.5013840198516846,
+      "eval_runtime": 53.9761,
+      "eval_samples_per_second": 4.539,
+      "eval_steps_per_second": 4.539,
+      "step": 30
+    },
+    {
+      "epoch": 0.06887645286267757,
+      "grad_norm": 0.5421889424324036,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.439,
+      "step": 40
+    },
+    {
+      "epoch": 0.08609556607834697,
+      "grad_norm": 0.5523178577423096,
+      "learning_rate": 8.376068376068377e-05,
+      "loss": 0.334,
+      "step": 50
+    },
+    {
+      "epoch": 0.10331467929401636,
+      "grad_norm": 0.5268102884292603,
+      "learning_rate": 0.00010085470085470086,
+      "loss": 0.2835,
+      "step": 60
+    },
+    {
+      "epoch": 0.10331467929401636,
+      "eval_loss": 0.2452857494354248,
+      "eval_runtime": 53.6208,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 4.569,
+      "step": 60
+    },
+    {
+      "epoch": 0.12053379250968575,
+      "grad_norm": 0.4393221437931061,
+      "learning_rate": 0.00011794871794871796,
+      "loss": 0.2366,
+      "step": 70
+    },
+    {
+      "epoch": 0.13775290572535515,
+      "grad_norm": 0.5775641202926636,
+      "learning_rate": 0.00013504273504273505,
+      "loss": 0.2218,
+      "step": 80
+    },
+    {
+      "epoch": 0.15497201894102453,
+      "grad_norm": 0.4302266240119934,
+      "learning_rate": 0.00015213675213675214,
+      "loss": 0.1986,
+      "step": 90
+    },
+    {
+      "epoch": 0.15497201894102453,
+      "eval_loss": 0.1793452501296997,
+      "eval_runtime": 53.5304,
+      "eval_samples_per_second": 4.577,
+      "eval_steps_per_second": 4.577,
+      "step": 90
+    },
+    {
+      "epoch": 0.17219113215669393,
+      "grad_norm": 0.39770159125328064,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.186,
+      "step": 100
+    },
+    {
+      "epoch": 0.1894102453723633,
+      "grad_norm": 0.4006386399269104,
+      "learning_rate": 0.00018632478632478634,
+      "loss": 0.1708,
+      "step": 110
+    },
+    {
+      "epoch": 0.20662935858803272,
+      "grad_norm": 0.4491441547870636,
+      "learning_rate": 0.00019999819242697418,
+      "loss": 0.1712,
+      "step": 120
+    },
+    {
+      "epoch": 0.20662935858803272,
+      "eval_loss": 0.15836507081985474,
+      "eval_runtime": 53.6179,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 4.569,
+      "step": 120
+    },
+    {
+      "epoch": 0.2238484718037021,
+      "grad_norm": 0.33016568422317505,
+      "learning_rate": 0.00019993493423217814,
+      "loss": 0.1638,
+      "step": 130
+    },
+    {
+      "epoch": 0.2410675850193715,
+      "grad_norm": 0.22399674355983734,
+      "learning_rate": 0.00019978136272187747,
+      "loss": 0.1533,
+      "step": 140
+    },
+    {
+      "epoch": 0.2582866982350409,
+      "grad_norm": 0.2746177911758423,
+      "learning_rate": 0.0001995376166818969,
+      "loss": 0.158,
+      "step": 150
+    },
+    {
+      "epoch": 0.2582866982350409,
+      "eval_loss": 0.14334778487682343,
+      "eval_runtime": 53.578,
+      "eval_samples_per_second": 4.573,
+      "eval_steps_per_second": 4.573,
+      "step": 150
+    },
+    {
+      "epoch": 0.2755058114507103,
+      "grad_norm": 0.2805308699607849,
+      "learning_rate": 0.00019920391639069242,
+      "loss": 0.1509,
+      "step": 160
+    },
+    {
+      "epoch": 0.29272492466637967,
+      "grad_norm": 0.4730603098869324,
+      "learning_rate": 0.00019878056342028102,
+      "loss": 0.1496,
+      "step": 170
+    },
+    {
+      "epoch": 0.30994403788204905,
+      "grad_norm": 0.23217393457889557,
+      "learning_rate": 0.00019826794036370362,
+      "loss": 0.1472,
+      "step": 180
+    },
+    {
+      "epoch": 0.30994403788204905,
+      "eval_loss": 0.13477234542369843,
+      "eval_runtime": 53.4805,
+      "eval_samples_per_second": 4.581,
+      "eval_steps_per_second": 4.581,
+      "step": 180
+    },
+    {
+      "epoch": 0.3271631510977185,
+      "grad_norm": 0.28313347697257996,
+      "learning_rate": 0.0001976665104892678,
+      "loss": 0.147,
+      "step": 190
+    },
+    {
+      "epoch": 0.34438226431338786,
+      "grad_norm": 0.15724846720695496,
+      "learning_rate": 0.00019697681732188218,
+      "loss": 0.1426,
+      "step": 200
+    },
+    {
+      "epoch": 0.36160137752905724,
+      "grad_norm": 0.24457155168056488,
+      "learning_rate": 0.00019619948415186173,
+      "loss": 0.1397,
+      "step": 210
+    },
+    {
+      "epoch": 0.36160137752905724,
+      "eval_loss": 0.13591289520263672,
+      "eval_runtime": 53.3683,
+      "eval_samples_per_second": 4.591,
+      "eval_steps_per_second": 4.591,
+      "step": 210
+    },
+    {
+      "epoch": 0.3788204907447266,
+      "grad_norm": 0.25315046310424805,
+      "learning_rate": 0.00019533521347164687,
+      "loss": 0.1454,
+      "step": 220
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 0.20438989996910095,
+      "learning_rate": 0.00019438478634094638,
+      "loss": 0.1404,
+      "step": 230
+    },
+    {
+      "epoch": 0.41325871717606544,
+      "grad_norm": 0.3646264672279358,
+      "learning_rate": 0.00019334906168087698,
+      "loss": 0.1371,
+      "step": 240
+    },
+    {
+      "epoch": 0.41325871717606544,
+      "eval_loss": 0.12897279858589172,
+      "eval_runtime": 53.3855,
+      "eval_samples_per_second": 4.589,
+      "eval_steps_per_second": 4.589,
+      "step": 240
+    },
+    {
+      "epoch": 0.4304778303917348,
+      "grad_norm": 0.24957729876041412,
+      "learning_rate": 0.00019222897549773848,
+      "loss": 0.1489,
+      "step": 250
+    },
+    {
+      "epoch": 0.4476969436074042,
+      "grad_norm": 0.17658768594264984,
+      "learning_rate": 0.00019102554003712466,
+      "loss": 0.1221,
+      "step": 260
+    },
+    {
+      "epoch": 0.46491605682307363,
+      "grad_norm": 0.26017439365386963,
+      "learning_rate": 0.00018973984286913584,
+      "loss": 0.1364,
+      "step": 270
+    },
+    {
+      "epoch": 0.46491605682307363,
+      "eval_loss": 0.12664556503295898,
+      "eval_runtime": 53.4534,
+      "eval_samples_per_second": 4.583,
+      "eval_steps_per_second": 4.583,
+      "step": 270
+    },
+    {
+      "epoch": 0.482135170038743,
+      "grad_norm": 0.13661746680736542,
+      "learning_rate": 0.0001883730459055186,
+      "loss": 0.128,
+      "step": 280
+    },
+    {
+      "epoch": 0.4993542832544124,
+      "grad_norm": 0.20260806381702423,
+      "learning_rate": 0.00018692638434962143,
+      "loss": 0.1341,
+      "step": 290
+    },
+    {
+      "epoch": 0.5165733964700818,
+      "grad_norm": 0.14534738659858704,
+      "learning_rate": 0.0001854011655801157,
+      "loss": 0.1393,
+      "step": 300
+    },
+    {
+      "epoch": 0.5165733964700818,
+      "eval_loss": 0.12330517172813416,
+      "eval_runtime": 53.8347,
+      "eval_samples_per_second": 4.551,
+      "eval_steps_per_second": 4.551,
+      "step": 300
+    },
+    {
+      "epoch": 0.5337925096857512,
+      "grad_norm": 0.15992437303066254,
+      "learning_rate": 0.0001837987679694894,
+      "loss": 0.1344,
+      "step": 310
+    },
+    {
+      "epoch": 0.5510116229014206,
+      "grad_norm": 0.17435793578624725,
+      "learning_rate": 0.0001821206396383831,
+      "loss": 0.1326,
+      "step": 320
+    },
+    {
+      "epoch": 0.56823073611709,
+      "grad_norm": 0.12753354012966156,
+      "learning_rate": 0.00018036829714689252,
+      "loss": 0.1265,
+      "step": 330
+    },
+    {
+      "epoch": 0.56823073611709,
+      "eval_loss": 0.12111596018075943,
+      "eval_runtime": 53.8413,
+      "eval_samples_per_second": 4.55,
+      "eval_steps_per_second": 4.55,
+      "step": 330
+    },
+    {
+      "epoch": 0.5854498493327593,
+      "grad_norm": 0.17733751237392426,
+      "learning_rate": 0.00017854332412402108,
+      "loss": 0.1321,
+      "step": 340
+    },
+    {
+      "epoch": 0.6026689625484287,
+      "grad_norm": 0.18490831553936005,
+      "learning_rate": 0.00017664736983652088,
+      "loss": 0.1336,
+      "step": 350
+    },
+    {
+      "epoch": 0.6198880757640981,
+      "grad_norm": 0.16691215336322784,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 0.1286,
+      "step": 360
+    },
+    {
+      "epoch": 0.6198880757640981,
+      "eval_loss": 0.1179625391960144,
+      "eval_runtime": 53.9361,
+      "eval_samples_per_second": 4.542,
+      "eval_steps_per_second": 4.542,
+      "step": 360
+    },
+    {
+      "epoch": 0.6371071889797676,
+      "grad_norm": 0.1389610469341278,
+      "learning_rate": 0.000172649433722551,
+      "loss": 0.123,
+      "step": 370
+    },
+    {
+      "epoch": 0.654326302195437,
+      "grad_norm": 0.12287218123674393,
+      "learning_rate": 0.00017055106491557645,
+      "loss": 0.1264,
+      "step": 380
+    },
+    {
+      "epoch": 0.6715454154111064,
+      "grad_norm": 0.13567915558815002,
+      "learning_rate": 0.00016838893761780127,
+      "loss": 0.1258,
+      "step": 390
+    },
+    {
+      "epoch": 0.6715454154111064,
+      "eval_loss": 0.11948917806148529,
+      "eval_runtime": 53.9271,
+      "eval_samples_per_second": 4.543,
+      "eval_steps_per_second": 4.543,
+      "step": 390
+    },
+    {
+      "epoch": 0.6887645286267757,
+      "grad_norm": 0.1640617996454239,
+      "learning_rate": 0.00016616500578943273,
+      "loss": 0.1233,
+      "step": 400
+    },
+    {
+      "epoch": 0.7059836418424451,
+      "grad_norm": 0.10329368710517883,
+      "learning_rate": 0.0001638812792447406,
+      "loss": 0.1275,
+      "step": 410
+    },
+    {
+      "epoch": 0.7232027550581145,
+      "grad_norm": 0.11142633855342865,
+      "learning_rate": 0.0001615398218357457,
+      "loss": 0.132,
+      "step": 420
+    },
+    {
+      "epoch": 0.7232027550581145,
+      "eval_loss": 0.11622682213783264,
+      "eval_runtime": 53.961,
+      "eval_samples_per_second": 4.54,
+      "eval_steps_per_second": 4.54,
+      "step": 420
+    },
+    {
+      "epoch": 0.7404218682737839,
+      "grad_norm": 0.12253064662218094,
+      "learning_rate": 0.0001591427495870729,
+      "loss": 0.1272,
+      "step": 430
+    },
+    {
+      "epoch": 0.7576409814894532,
+      "grad_norm": 0.14540846645832062,
+      "learning_rate": 0.00015669222878365486,
+      "loss": 0.1317,
+      "step": 440
+    },
+    {
+      "epoch": 0.7748600947051227,
+      "grad_norm": 0.10412976145744324,
+      "learning_rate": 0.00015419047401301472,
+      "loss": 0.1317,
+      "step": 450
+    },
+    {
+      "epoch": 0.7748600947051227,
+      "eval_loss": 0.11769552528858185,
+      "eval_runtime": 53.9569,
+      "eval_samples_per_second": 4.541,
+      "eval_steps_per_second": 4.541,
+      "step": 450
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 0.12871715426445007,
+      "learning_rate": 0.0001516397461638962,
+      "loss": 0.129,
+      "step": 460
+    },
+    {
+      "epoch": 0.8092983211364615,
+      "grad_norm": 0.21784746646881104,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 0.1233,
+      "step": 470
+    },
+    {
+      "epoch": 0.8265174343521309,
+      "grad_norm": 0.4632514417171478,
+      "learning_rate": 0.0001464006339920278,
+      "loss": 0.1363,
+      "step": 480
+    },
+    {
+      "epoch": 0.8265174343521309,
+      "eval_loss": 0.11895836144685745,
+      "eval_runtime": 54.1763,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 480
+    },
+    {
+      "epoch": 0.8437365475678003,
+      "grad_norm": 0.15127432346343994,
+      "learning_rate": 0.00014371698436585004,
+      "loss": 0.1265,
+      "step": 490
+    },
+    {
+      "epoch": 0.8609556607834696,
+      "grad_norm": 0.17194333672523499,
+      "learning_rate": 0.0001409938267754926,
+      "loss": 0.13,
+      "step": 500
+    },
+    {
+      "epoch": 0.878174773999139,
+      "grad_norm": 0.15506021678447723,
+      "learning_rate": 0.0001382336221961141,
+      "loss": 0.1274,
+      "step": 510
+    },
+    {
+      "epoch": 0.878174773999139,
+      "eval_loss": 0.11823900789022446,
+      "eval_runtime": 53.9107,
+      "eval_samples_per_second": 4.545,
+      "eval_steps_per_second": 4.545,
+      "step": 510
+    },
+    {
+      "epoch": 0.8953938872148084,
+      "grad_norm": 0.13229945302009583,
+      "learning_rate": 0.00013543886508302148,
+      "loss": 0.1295,
+      "step": 520
+    },
+    {
+      "epoch": 0.9126130004304779,
+      "grad_norm": 0.19207294285297394,
+      "learning_rate": 0.00013261208111737765,
+      "loss": 0.1156,
+      "step": 530
+    },
+    {
+      "epoch": 0.9298321136461473,
+      "grad_norm": 0.20044037699699402,
+      "learning_rate": 0.00012975582492369016,
+      "loss": 0.1198,
+      "step": 540
+    },
+    {
+      "epoch": 0.9298321136461473,
+      "eval_loss": 0.11498646438121796,
+      "eval_runtime": 53.9988,
+      "eval_samples_per_second": 4.537,
+      "eval_steps_per_second": 4.537,
+      "step": 540
+    },
+    {
+      "epoch": 0.9470512268618166,
+      "grad_norm": 0.2503241002559662,
+      "learning_rate": 0.00012687267776114304,
+      "loss": 0.1325,
+      "step": 550
+    },
+    {
+      "epoch": 0.964270340077486,
+      "grad_norm": 0.1304081231355667,
+      "learning_rate": 0.0001239652451908579,
+      "loss": 0.1305,
+      "step": 560
+    },
+    {
+      "epoch": 0.9814894532931554,
+      "grad_norm": 0.17837955057621002,
+      "learning_rate": 0.0001210361547211936,
+      "loss": 0.1105,
+      "step": 570
+    },
+    {
+      "epoch": 0.9814894532931554,
+      "eval_loss": 0.1158880740404129,
+      "eval_runtime": 53.9013,
+      "eval_samples_per_second": 4.545,
+      "eval_steps_per_second": 4.545,
+      "step": 570
+    },
+    {
+      "epoch": 0.9987085665088248,
+      "grad_norm": 0.14954382181167603,
+      "learning_rate": 0.000118088053433211,
+      "loss": 0.1275,
+      "step": 580
+    },
+    {
+      "epoch": 1.0154972018941024,
+      "grad_norm": 0.16672547161579132,
+      "learning_rate": 0.00011512360558844994,
+      "loss": 0.122,
+      "step": 590
+    },
+    {
+      "epoch": 1.0327163151097718,
+      "grad_norm": 0.22516606748104095,
+      "learning_rate": 0.00011214549022117967,
+      "loss": 0.1215,
+      "step": 600
+    },
+    {
+      "epoch": 1.0327163151097718,
+      "eval_loss": 0.11643720418214798,
+      "eval_runtime": 54.0392,
+      "eval_samples_per_second": 4.534,
+      "eval_steps_per_second": 4.534,
+      "step": 600
+    },
+    {
+      "epoch": 1.0499354283254412,
+      "grad_norm": 0.10763582587242126,
+      "learning_rate": 0.00010915639871729874,
+      "loss": 0.1092,
+      "step": 610
+    },
+    {
+      "epoch": 1.0671545415411106,
+      "grad_norm": 0.12457219511270523,
+      "learning_rate": 0.00010615903238207292,
+      "loss": 0.1262,
+      "step": 620
+    },
+    {
+      "epoch": 1.08437365475678,
+      "grad_norm": 0.10427327454090118,
+      "learning_rate": 0.00010315609999890798,
+      "loss": 0.1221,
+      "step": 630
+    },
+    {
+      "epoch": 1.08437365475678,
+      "eval_loss": 0.11431042104959488,
+      "eval_runtime": 53.9648,
+      "eval_samples_per_second": 4.54,
+      "eval_steps_per_second": 4.54,
+      "step": 630
+    },
+    {
+      "epoch": 1.1015927679724493,
+      "grad_norm": 0.10417324304580688,
+      "learning_rate": 0.00010015031538136518,
+      "loss": 0.1243,
+      "step": 640
+    },
+    {
+      "epoch": 1.118811881188119,
+      "grad_norm": 0.10996241122484207,
+      "learning_rate": 9.71443949206304e-05,
+      "loss": 0.123,
+      "step": 650
+    },
+    {
+      "epoch": 1.1360309944037883,
+      "grad_norm": 0.09512694925069809,
+      "learning_rate": 9.41410551306537e-05,
+      "loss": 0.1161,
+      "step": 660
+    },
+    {
+      "epoch": 1.1360309944037883,
+      "eval_loss": 0.11319658905267715,
+      "eval_runtime": 54.1752,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 660
+    },
+    {
+      "epoch": 1.1532501076194577,
+      "grad_norm": 0.08619705587625504,
+      "learning_rate": 9.114301019317854e-05,
+      "loss": 0.1138,
+      "step": 670
+    },
+    {
+      "epoch": 1.170469220835127,
+      "grad_norm": 0.099159836769104,
+      "learning_rate": 8.815296950487804e-05,
+      "loss": 0.116,
+      "step": 680
+    },
+    {
+      "epoch": 1.1876883340507964,
+      "grad_norm": 0.09249532967805862,
+      "learning_rate": 8.517363522881579e-05,
+      "loss": 0.1209,
+      "step": 690
+    },
+    {
+      "epoch": 1.1876883340507964,
+      "eval_loss": 0.11321850121021271,
+      "eval_runtime": 54.1757,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 690
+    },
+    {
+      "epoch": 1.2049074472664658,
+      "grad_norm": 0.10436110198497772,
+      "learning_rate": 8.220769985244425e-05,
+      "loss": 0.1245,
+      "step": 700
+    },
+    {
+      "epoch": 1.2221265604821352,
+      "grad_norm": 0.08504263311624527,
+      "learning_rate": 7.925784375434629e-05,
+      "loss": 0.1116,
+      "step": 710
+    },
+    {
+      "epoch": 1.2393456736978046,
+      "grad_norm": 0.10974706709384918,
+      "learning_rate": 7.63267327819209e-05,
+      "loss": 0.1213,
+      "step": 720
+    },
+    {
+      "epoch": 1.2393456736978046,
+      "eval_loss": 0.11273372918367386,
+      "eval_runtime": 54.1807,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 720
+    },
+    {
+      "epoch": 1.256564786913474,
+      "grad_norm": 0.0872415080666542,
+      "learning_rate": 7.341701584220006e-05,
+      "loss": 0.1164,
+      "step": 730
+    },
+    {
+      "epoch": 1.2737839001291433,
+      "grad_norm": 0.09694085270166397,
+      "learning_rate": 7.05313225079756e-05,
+      "loss": 0.1193,
+      "step": 740
+    },
+    {
+      "epoch": 1.2910030133448127,
+      "grad_norm": 0.09382116794586182,
+      "learning_rate": 6.767226064139841e-05,
+      "loss": 0.1212,
+      "step": 750
+    },
+    {
+      "epoch": 1.2910030133448127,
+      "eval_loss": 0.11223271489143372,
+      "eval_runtime": 53.9413,
+      "eval_samples_per_second": 4.542,
+      "eval_steps_per_second": 4.542,
+      "step": 750
+    },
+    {
+      "epoch": 1.308222126560482,
+      "grad_norm": 0.09150267392396927,
+      "learning_rate": 6.484241403719842e-05,
+      "loss": 0.1204,
+      "step": 760
+    },
+    {
+      "epoch": 1.3254412397761515,
+      "grad_norm": 0.10270262509584427,
+      "learning_rate": 6.204434008765458e-05,
+      "loss": 0.119,
+      "step": 770
+    },
+    {
+      "epoch": 1.3426603529918208,
+      "grad_norm": 0.10682746022939682,
+      "learning_rate": 5.9280567471425077e-05,
+      "loss": 0.1158,
+      "step": 780
+    },
+    {
+      "epoch": 1.3426603529918208,
+      "eval_loss": 0.11181723326444626,
+      "eval_runtime": 53.9263,
+      "eval_samples_per_second": 4.543,
+      "eval_steps_per_second": 4.543,
+      "step": 780
+    },
+    {
+      "epoch": 1.3598794662074902,
+      "grad_norm": 0.0856538936495781,
+      "learning_rate": 5.655359386832728e-05,
+      "loss": 0.1214,
+      "step": 790
+    },
+    {
+      "epoch": 1.3770985794231598,
+      "grad_norm": 0.08333317190408707,
+      "learning_rate": 5.386588370213124e-05,
+      "loss": 0.123,
+      "step": 800
+    },
+    {
+      "epoch": 1.394317692638829,
+      "grad_norm": 0.08669654279947281,
+      "learning_rate": 5.121986591340808e-05,
+      "loss": 0.1177,
+      "step": 810
+    },
+    {
+      "epoch": 1.394317692638829,
+      "eval_loss": 0.11222003400325775,
+      "eval_runtime": 53.9921,
+      "eval_samples_per_second": 4.538,
+      "eval_steps_per_second": 4.538,
+      "step": 810
+    },
+    {
+      "epoch": 1.4115368058544986,
+      "grad_norm": 0.09735915809869766,
+      "learning_rate": 4.861793176444479e-05,
+      "loss": 0.1155,
+      "step": 820
+    },
+    {
+      "epoch": 1.428755919070168,
+      "grad_norm": 0.10614746063947678,
+      "learning_rate": 4.6062432678209986e-05,
+      "loss": 0.1126,
+      "step": 830
+    },
+    {
+      "epoch": 1.4459750322858373,
+      "grad_norm": 0.09488119930028915,
+      "learning_rate": 4.355567811332311e-05,
+      "loss": 0.1153,
+      "step": 840
+    },
+    {
+      "epoch": 1.4459750322858373,
+      "eval_loss": 0.11169660836458206,
+      "eval_runtime": 54.1675,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 4.523,
+      "step": 840
+    },
+    {
+      "epoch": 1.4631941455015067,
+      "grad_norm": 0.10649088025093079,
+      "learning_rate": 4.109993347694781e-05,
+      "loss": 0.1289,
+      "step": 850
+    },
+    {
+      "epoch": 1.480413258717176,
+      "grad_norm": 0.08584726601839066,
+      "learning_rate": 3.8697418077495575e-05,
+      "loss": 0.1193,
+      "step": 860
+    },
+    {
+      "epoch": 1.4976323719328455,
+      "grad_norm": 0.08480769395828247,
+      "learning_rate": 3.635030311898975e-05,
+      "loss": 0.1167,
+      "step": 870
+    },
+    {
+      "epoch": 1.4976323719328455,
+      "eval_loss": 0.1113625019788742,
+      "eval_runtime": 54.0863,
+      "eval_samples_per_second": 4.53,
+      "eval_steps_per_second": 4.53,
+      "step": 870
+    },
+    {
+      "epoch": 1.5148514851485149,
+      "grad_norm": 0.09291431307792664,
+      "learning_rate": 3.4060709738902485e-05,
+      "loss": 0.1223,
+      "step": 880
+    },
+    {
+      "epoch": 1.5320705983641842,
+      "grad_norm": 0.06462642550468445,
+      "learning_rate": 3.183070709123781e-05,
+      "loss": 0.1113,
+      "step": 890
+    },
+    {
+      "epoch": 1.5492897115798536,
+      "grad_norm": 0.08776138722896576,
+      "learning_rate": 2.9662310476593492e-05,
+      "loss": 0.1159,
+      "step": 900
+    },
+    {
+      "epoch": 1.5492897115798536,
+      "eval_loss": 0.11135545372962952,
+      "eval_runtime": 54.2115,
+      "eval_samples_per_second": 4.519,
+      "eval_steps_per_second": 4.519,
+      "step": 900
+    },
+    {
+      "epoch": 1.566508824795523,
+      "grad_norm": 0.08839749544858932,
+      "learning_rate": 2.7557479520891104e-05,
+      "loss": 0.1226,
+      "step": 910
+    },
+    {
+      "epoch": 1.5837279380111924,
+      "grad_norm": 0.1001950353384018,
+      "learning_rate": 2.551811640442081e-05,
+      "loss": 0.1156,
+      "step": 920
+    },
+    {
+      "epoch": 1.6009470512268618,
+      "grad_norm": 0.08094879239797592,
+      "learning_rate": 2.354606414280045e-05,
+      "loss": 0.1178,
+      "step": 930
+    },
+    {
+      "epoch": 1.6009470512268618,
+      "eval_loss": 0.11072849482297897,
+      "eval_runtime": 54.2409,
+      "eval_samples_per_second": 4.517,
+      "eval_steps_per_second": 4.517,
+      "step": 930
+    },
+    {
+      "epoch": 1.6181661644425311,
+      "grad_norm": 0.0837637260556221,
+      "learning_rate": 2.1643104921403657e-05,
+      "loss": 0.1163,
+      "step": 940
+    },
+    {
+      "epoch": 1.6353852776582007,
+      "grad_norm": 0.08061401546001434,
+      "learning_rate": 1.98109584847609e-05,
+      "loss": 0.1215,
+      "step": 950
+    },
+    {
+      "epoch": 1.65260439087387,
+      "grad_norm": 0.08909575641155243,
+      "learning_rate": 1.805128058239014e-05,
+      "loss": 0.1214,
+      "step": 960
+    },
+    {
+      "epoch": 1.65260439087387,
+      "eval_loss": 0.11049379408359528,
+      "eval_runtime": 54.0663,
+      "eval_samples_per_second": 4.531,
+      "eval_steps_per_second": 4.531,
+      "step": 960
+    },
+    {
+      "epoch": 1.6698235040895395,
+      "grad_norm": 0.0853874459862709,
+      "learning_rate": 1.6365661472460946e-05,
+      "loss": 0.1223,
+      "step": 970
+    },
+    {
+      "epoch": 1.6870426173052087,
+      "grad_norm": 0.07660456001758575,
+      "learning_rate": 1.475562448464437e-05,
+      "loss": 0.1249,
+      "step": 980
+    },
+    {
+      "epoch": 1.7042617305208783,
+      "grad_norm": 0.08277535438537598,
+      "learning_rate": 1.3222624643447879e-05,
+      "loss": 0.1139,
+      "step": 990
+    },
+    {
+      "epoch": 1.7042617305208783,
+      "eval_loss": 0.11061510443687439,
+      "eval_runtime": 54.1562,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 4.524,
+      "step": 990
+    },
+    {
+      "epoch": 1.7214808437365474,
+      "grad_norm": 0.08193802833557129,
+      "learning_rate": 1.1768047353278721e-05,
+      "loss": 0.1163,
+      "step": 1000
+    },
+    {
+      "epoch": 1.738699956952217,
+      "grad_norm": 0.09207924455404282,
+      "learning_rate": 1.0393207146424766e-05,
+      "loss": 0.1171,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7559190701678864,
+      "grad_norm": 0.07924116402864456,
+      "learning_rate": 9.09934649508375e-06,
+      "loss": 0.1215,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7559190701678864,
+      "eval_loss": 0.1104968935251236,
+      "eval_runtime": 54.2108,
+      "eval_samples_per_second": 4.519,
+      "eval_steps_per_second": 4.519,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7731381833835558,
+      "grad_norm": 0.0777198001742363,
+      "learning_rate": 7.887634688515e-06,
+      "loss": 0.1204,
+      "step": 1030
+    },
+    {
+      "epoch": 1.7903572965992252,
+      "grad_norm": 0.09511927515268326,
+      "learning_rate": 6.759166776327786e-06,
+      "loss": 0.1125,
+      "step": 1040
+    },
+    {
+      "epoch": 1.8075764098148945,
+      "grad_norm": 0.08975937217473984,
+      "learning_rate": 5.71496257886196e-06,
+      "loss": 0.1143,
+      "step": 1050
+    },
+    {
+      "epoch": 1.8075764098148945,
+      "eval_loss": 0.11050143837928772,
+      "eval_runtime": 54.1535,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 4.524,
+      "step": 1050
+    },
+    {
+      "epoch": 1.824795523030564,
+      "grad_norm": 0.08812955766916275,
+      "learning_rate": 4.755965765554637e-06,
+      "loss": 0.112,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8420146362462333,
+      "grad_norm": 0.08198709785938263,
+      "learning_rate": 3.883043002126219e-06,
+      "loss": 0.1149,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8592337494619027,
+      "grad_norm": 0.0873785987496376,
+      "learning_rate": 3.0969831673562042e-06,
+      "loss": 0.1142,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8592337494619027,
+      "eval_loss": 0.11041069775819778,
+      "eval_runtime": 54.1647,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 4.523,
+      "step": 1080
+    },
+    {
+      "epoch": 1.876452862677572,
+      "grad_norm": 0.08640486001968384,
+      "learning_rate": 2.3984966401567e-06,
+      "loss": 0.1154,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8936719758932417,
+      "grad_norm": 0.09290562570095062,
+      "learning_rate": 1.7882146575880166e-06,
+      "loss": 0.1163,
+      "step": 1100
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.570950638239273e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df85a2dc62117d691e5665e76e86e08b05c157a75892a77849b25ff3759ae220
+size 5777

checkpoint-1162/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-4B-Instruct-2507
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.13.2

checkpoint-1162/adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": {
+    "base_model_class": "Qwen3ForCausalLM",
+    "parent_library": "transformers.models.qwen3.modeling_qwen3",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Qwen3-4B-Instruct-2507",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 128,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-1162/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84a1d31d17384133f04ead482a00de00fc0e6eee7662ec25fbefb1a97ec78ac6
+size 528550256

checkpoint-1162/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-1162/chat_template.jinja

@@ -0,0 +1,86 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

checkpoint-1162/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d141e6e2e529e3754c491a5b2bc08295c3a4d087e6bd88be9cff246b3b55cac6
+size 1057397963

checkpoint-1162/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59d572acfd8f6356d9c1a1d26513b13f04e3ead37ff464ed6d5d33c0736d4fb6
+size 14645

checkpoint-1162/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d437e74ad88ff1a6f151c02382ae83434c5decbea0435683fac7a6fdec77accc
+size 1465

checkpoint-1162/special_tokens_map.json

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

checkpoint-1162/tokenizer.json

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

checkpoint-1162/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-1162/trainer_state.json

@@ -0,0 +1,1150 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 30,
+  "global_step": 1162,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.017219113215669393,
+      "grad_norm": 8.32422161102295,
+      "learning_rate": 1.5384615384615387e-05,
+      "loss": 2.589,
+      "step": 10
+    },
+    {
+      "epoch": 0.034438226431338786,
+      "grad_norm": 0.8107045292854309,
+      "learning_rate": 3.247863247863248e-05,
+      "loss": 0.9674,
+      "step": 20
+    },
+    {
+      "epoch": 0.05165733964700818,
+      "grad_norm": 0.7474735379219055,
+      "learning_rate": 4.9572649572649575e-05,
+      "loss": 0.5896,
+      "step": 30
+    },
+    {
+      "epoch": 0.05165733964700818,
+      "eval_loss": 0.5013840198516846,
+      "eval_runtime": 53.9761,
+      "eval_samples_per_second": 4.539,
+      "eval_steps_per_second": 4.539,
+      "step": 30
+    },
+    {
+      "epoch": 0.06887645286267757,
+      "grad_norm": 0.5421889424324036,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 0.439,
+      "step": 40
+    },
+    {
+      "epoch": 0.08609556607834697,
+      "grad_norm": 0.5523178577423096,
+      "learning_rate": 8.376068376068377e-05,
+      "loss": 0.334,
+      "step": 50
+    },
+    {
+      "epoch": 0.10331467929401636,
+      "grad_norm": 0.5268102884292603,
+      "learning_rate": 0.00010085470085470086,
+      "loss": 0.2835,
+      "step": 60
+    },
+    {
+      "epoch": 0.10331467929401636,
+      "eval_loss": 0.2452857494354248,
+      "eval_runtime": 53.6208,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 4.569,
+      "step": 60
+    },
+    {
+      "epoch": 0.12053379250968575,
+      "grad_norm": 0.4393221437931061,
+      "learning_rate": 0.00011794871794871796,
+      "loss": 0.2366,
+      "step": 70
+    },
+    {
+      "epoch": 0.13775290572535515,
+      "grad_norm": 0.5775641202926636,
+      "learning_rate": 0.00013504273504273505,
+      "loss": 0.2218,
+      "step": 80
+    },
+    {
+      "epoch": 0.15497201894102453,
+      "grad_norm": 0.4302266240119934,
+      "learning_rate": 0.00015213675213675214,
+      "loss": 0.1986,
+      "step": 90
+    },
+    {
+      "epoch": 0.15497201894102453,
+      "eval_loss": 0.1793452501296997,
+      "eval_runtime": 53.5304,
+      "eval_samples_per_second": 4.577,
+      "eval_steps_per_second": 4.577,
+      "step": 90
+    },
+    {
+      "epoch": 0.17219113215669393,
+      "grad_norm": 0.39770159125328064,
+      "learning_rate": 0.00016923076923076923,
+      "loss": 0.186,
+      "step": 100
+    },
+    {
+      "epoch": 0.1894102453723633,
+      "grad_norm": 0.4006386399269104,
+      "learning_rate": 0.00018632478632478634,
+      "loss": 0.1708,
+      "step": 110
+    },
+    {
+      "epoch": 0.20662935858803272,
+      "grad_norm": 0.4491441547870636,
+      "learning_rate": 0.00019999819242697418,
+      "loss": 0.1712,
+      "step": 120
+    },
+    {
+      "epoch": 0.20662935858803272,
+      "eval_loss": 0.15836507081985474,
+      "eval_runtime": 53.6179,
+      "eval_samples_per_second": 4.569,
+      "eval_steps_per_second": 4.569,
+      "step": 120
+    },
+    {
+      "epoch": 0.2238484718037021,
+      "grad_norm": 0.33016568422317505,
+      "learning_rate": 0.00019993493423217814,
+      "loss": 0.1638,
+      "step": 130
+    },
+    {
+      "epoch": 0.2410675850193715,
+      "grad_norm": 0.22399674355983734,
+      "learning_rate": 0.00019978136272187747,
+      "loss": 0.1533,
+      "step": 140
+    },
+    {
+      "epoch": 0.2582866982350409,
+      "grad_norm": 0.2746177911758423,
+      "learning_rate": 0.0001995376166818969,
+      "loss": 0.158,
+      "step": 150
+    },
+    {
+      "epoch": 0.2582866982350409,
+      "eval_loss": 0.14334778487682343,
+      "eval_runtime": 53.578,
+      "eval_samples_per_second": 4.573,
+      "eval_steps_per_second": 4.573,
+      "step": 150
+    },
+    {
+      "epoch": 0.2755058114507103,
+      "grad_norm": 0.2805308699607849,
+      "learning_rate": 0.00019920391639069242,
+      "loss": 0.1509,
+      "step": 160
+    },
+    {
+      "epoch": 0.29272492466637967,
+      "grad_norm": 0.4730603098869324,
+      "learning_rate": 0.00019878056342028102,
+      "loss": 0.1496,
+      "step": 170
+    },
+    {
+      "epoch": 0.30994403788204905,
+      "grad_norm": 0.23217393457889557,
+      "learning_rate": 0.00019826794036370362,
+      "loss": 0.1472,
+      "step": 180
+    },
+    {
+      "epoch": 0.30994403788204905,
+      "eval_loss": 0.13477234542369843,
+      "eval_runtime": 53.4805,
+      "eval_samples_per_second": 4.581,
+      "eval_steps_per_second": 4.581,
+      "step": 180
+    },
+    {
+      "epoch": 0.3271631510977185,
+      "grad_norm": 0.28313347697257996,
+      "learning_rate": 0.0001976665104892678,
+      "loss": 0.147,
+      "step": 190
+    },
+    {
+      "epoch": 0.34438226431338786,
+      "grad_norm": 0.15724846720695496,
+      "learning_rate": 0.00019697681732188218,
+      "loss": 0.1426,
+      "step": 200
+    },
+    {
+      "epoch": 0.36160137752905724,
+      "grad_norm": 0.24457155168056488,
+      "learning_rate": 0.00019619948415186173,
+      "loss": 0.1397,
+      "step": 210
+    },
+    {
+      "epoch": 0.36160137752905724,
+      "eval_loss": 0.13591289520263672,
+      "eval_runtime": 53.3683,
+      "eval_samples_per_second": 4.591,
+      "eval_steps_per_second": 4.591,
+      "step": 210
+    },
+    {
+      "epoch": 0.3788204907447266,
+      "grad_norm": 0.25315046310424805,
+      "learning_rate": 0.00019533521347164687,
+      "loss": 0.1454,
+      "step": 220
+    },
+    {
+      "epoch": 0.39603960396039606,
+      "grad_norm": 0.20438989996910095,
+      "learning_rate": 0.00019438478634094638,
+      "loss": 0.1404,
+      "step": 230
+    },
+    {
+      "epoch": 0.41325871717606544,
+      "grad_norm": 0.3646264672279358,
+      "learning_rate": 0.00019334906168087698,
+      "loss": 0.1371,
+      "step": 240
+    },
+    {
+      "epoch": 0.41325871717606544,
+      "eval_loss": 0.12897279858589172,
+      "eval_runtime": 53.3855,
+      "eval_samples_per_second": 4.589,
+      "eval_steps_per_second": 4.589,
+      "step": 240
+    },
+    {
+      "epoch": 0.4304778303917348,
+      "grad_norm": 0.24957729876041412,
+      "learning_rate": 0.00019222897549773848,
+      "loss": 0.1489,
+      "step": 250
+    },
+    {
+      "epoch": 0.4476969436074042,
+      "grad_norm": 0.17658768594264984,
+      "learning_rate": 0.00019102554003712466,
+      "loss": 0.1221,
+      "step": 260
+    },
+    {
+      "epoch": 0.46491605682307363,
+      "grad_norm": 0.26017439365386963,
+      "learning_rate": 0.00018973984286913584,
+      "loss": 0.1364,
+      "step": 270
+    },
+    {
+      "epoch": 0.46491605682307363,
+      "eval_loss": 0.12664556503295898,
+      "eval_runtime": 53.4534,
+      "eval_samples_per_second": 4.583,
+      "eval_steps_per_second": 4.583,
+      "step": 270
+    },
+    {
+      "epoch": 0.482135170038743,
+      "grad_norm": 0.13661746680736542,
+      "learning_rate": 0.0001883730459055186,
+      "loss": 0.128,
+      "step": 280
+    },
+    {
+      "epoch": 0.4993542832544124,
+      "grad_norm": 0.20260806381702423,
+      "learning_rate": 0.00018692638434962143,
+      "loss": 0.1341,
+      "step": 290
+    },
+    {
+      "epoch": 0.5165733964700818,
+      "grad_norm": 0.14534738659858704,
+      "learning_rate": 0.0001854011655801157,
+      "loss": 0.1393,
+      "step": 300
+    },
+    {
+      "epoch": 0.5165733964700818,
+      "eval_loss": 0.12330517172813416,
+      "eval_runtime": 53.8347,
+      "eval_samples_per_second": 4.551,
+      "eval_steps_per_second": 4.551,
+      "step": 300
+    },
+    {
+      "epoch": 0.5337925096857512,
+      "grad_norm": 0.15992437303066254,
+      "learning_rate": 0.0001837987679694894,
+      "loss": 0.1344,
+      "step": 310
+    },
+    {
+      "epoch": 0.5510116229014206,
+      "grad_norm": 0.17435793578624725,
+      "learning_rate": 0.0001821206396383831,
+      "loss": 0.1326,
+      "step": 320
+    },
+    {
+      "epoch": 0.56823073611709,
+      "grad_norm": 0.12753354012966156,
+      "learning_rate": 0.00018036829714689252,
+      "loss": 0.1265,
+      "step": 330
+    },
+    {
+      "epoch": 0.56823073611709,
+      "eval_loss": 0.12111596018075943,
+      "eval_runtime": 53.8413,
+      "eval_samples_per_second": 4.55,
+      "eval_steps_per_second": 4.55,
+      "step": 330
+    },
+    {
+      "epoch": 0.5854498493327593,
+      "grad_norm": 0.17733751237392426,
+      "learning_rate": 0.00017854332412402108,
+      "loss": 0.1321,
+      "step": 340
+    },
+    {
+      "epoch": 0.6026689625484287,
+      "grad_norm": 0.18490831553936005,
+      "learning_rate": 0.00017664736983652088,
+      "loss": 0.1336,
+      "step": 350
+    },
+    {
+      "epoch": 0.6198880757640981,
+      "grad_norm": 0.16691215336322784,
+      "learning_rate": 0.0001746821476984154,
+      "loss": 0.1286,
+      "step": 360
+    },
+    {
+      "epoch": 0.6198880757640981,
+      "eval_loss": 0.1179625391960144,
+      "eval_runtime": 53.9361,
+      "eval_samples_per_second": 4.542,
+      "eval_steps_per_second": 4.542,
+      "step": 360
+    },
+    {
+      "epoch": 0.6371071889797676,
+      "grad_norm": 0.1389610469341278,
+      "learning_rate": 0.000172649433722551,
+      "loss": 0.123,
+      "step": 370
+    },
+    {
+      "epoch": 0.654326302195437,
+      "grad_norm": 0.12287218123674393,
+      "learning_rate": 0.00017055106491557645,
+      "loss": 0.1264,
+      "step": 380
+    },
+    {
+      "epoch": 0.6715454154111064,
+      "grad_norm": 0.13567915558815002,
+      "learning_rate": 0.00016838893761780127,
+      "loss": 0.1258,
+      "step": 390
+    },
+    {
+      "epoch": 0.6715454154111064,
+      "eval_loss": 0.11948917806148529,
+      "eval_runtime": 53.9271,
+      "eval_samples_per_second": 4.543,
+      "eval_steps_per_second": 4.543,
+      "step": 390
+    },
+    {
+      "epoch": 0.6887645286267757,
+      "grad_norm": 0.1640617996454239,
+      "learning_rate": 0.00016616500578943273,
+      "loss": 0.1233,
+      "step": 400
+    },
+    {
+      "epoch": 0.7059836418424451,
+      "grad_norm": 0.10329368710517883,
+      "learning_rate": 0.0001638812792447406,
+      "loss": 0.1275,
+      "step": 410
+    },
+    {
+      "epoch": 0.7232027550581145,
+      "grad_norm": 0.11142633855342865,
+      "learning_rate": 0.0001615398218357457,
+      "loss": 0.132,
+      "step": 420
+    },
+    {
+      "epoch": 0.7232027550581145,
+      "eval_loss": 0.11622682213783264,
+      "eval_runtime": 53.961,
+      "eval_samples_per_second": 4.54,
+      "eval_steps_per_second": 4.54,
+      "step": 420
+    },
+    {
+      "epoch": 0.7404218682737839,
+      "grad_norm": 0.12253064662218094,
+      "learning_rate": 0.0001591427495870729,
+      "loss": 0.1272,
+      "step": 430
+    },
+    {
+      "epoch": 0.7576409814894532,
+      "grad_norm": 0.14540846645832062,
+      "learning_rate": 0.00015669222878365486,
+      "loss": 0.1317,
+      "step": 440
+    },
+    {
+      "epoch": 0.7748600947051227,
+      "grad_norm": 0.10412976145744324,
+      "learning_rate": 0.00015419047401301472,
+      "loss": 0.1317,
+      "step": 450
+    },
+    {
+      "epoch": 0.7748600947051227,
+      "eval_loss": 0.11769552528858185,
+      "eval_runtime": 53.9569,
+      "eval_samples_per_second": 4.541,
+      "eval_steps_per_second": 4.541,
+      "step": 450
+    },
+    {
+      "epoch": 0.7920792079207921,
+      "grad_norm": 0.12871715426445007,
+      "learning_rate": 0.0001516397461638962,
+      "loss": 0.129,
+      "step": 460
+    },
+    {
+      "epoch": 0.8092983211364615,
+      "grad_norm": 0.21784746646881104,
+      "learning_rate": 0.00014904235038305083,
+      "loss": 0.1233,
+      "step": 470
+    },
+    {
+      "epoch": 0.8265174343521309,
+      "grad_norm": 0.4632514417171478,
+      "learning_rate": 0.0001464006339920278,
+      "loss": 0.1363,
+      "step": 480
+    },
+    {
+      "epoch": 0.8265174343521309,
+      "eval_loss": 0.11895836144685745,
+      "eval_runtime": 54.1763,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 480
+    },
+    {
+      "epoch": 0.8437365475678003,
+      "grad_norm": 0.15127432346343994,
+      "learning_rate": 0.00014371698436585004,
+      "loss": 0.1265,
+      "step": 490
+    },
+    {
+      "epoch": 0.8609556607834696,
+      "grad_norm": 0.17194333672523499,
+      "learning_rate": 0.0001409938267754926,
+      "loss": 0.13,
+      "step": 500
+    },
+    {
+      "epoch": 0.878174773999139,
+      "grad_norm": 0.15506021678447723,
+      "learning_rate": 0.0001382336221961141,
+      "loss": 0.1274,
+      "step": 510
+    },
+    {
+      "epoch": 0.878174773999139,
+      "eval_loss": 0.11823900789022446,
+      "eval_runtime": 53.9107,
+      "eval_samples_per_second": 4.545,
+      "eval_steps_per_second": 4.545,
+      "step": 510
+    },
+    {
+      "epoch": 0.8953938872148084,
+      "grad_norm": 0.13229945302009583,
+      "learning_rate": 0.00013543886508302148,
+      "loss": 0.1295,
+      "step": 520
+    },
+    {
+      "epoch": 0.9126130004304779,
+      "grad_norm": 0.19207294285297394,
+      "learning_rate": 0.00013261208111737765,
+      "loss": 0.1156,
+      "step": 530
+    },
+    {
+      "epoch": 0.9298321136461473,
+      "grad_norm": 0.20044037699699402,
+      "learning_rate": 0.00012975582492369016,
+      "loss": 0.1198,
+      "step": 540
+    },
+    {
+      "epoch": 0.9298321136461473,
+      "eval_loss": 0.11498646438121796,
+      "eval_runtime": 53.9988,
+      "eval_samples_per_second": 4.537,
+      "eval_steps_per_second": 4.537,
+      "step": 540
+    },
+    {
+      "epoch": 0.9470512268618166,
+      "grad_norm": 0.2503241002559662,
+      "learning_rate": 0.00012687267776114304,
+      "loss": 0.1325,
+      "step": 550
+    },
+    {
+      "epoch": 0.964270340077486,
+      "grad_norm": 0.1304081231355667,
+      "learning_rate": 0.0001239652451908579,
+      "loss": 0.1305,
+      "step": 560
+    },
+    {
+      "epoch": 0.9814894532931554,
+      "grad_norm": 0.17837955057621002,
+      "learning_rate": 0.0001210361547211936,
+      "loss": 0.1105,
+      "step": 570
+    },
+    {
+      "epoch": 0.9814894532931554,
+      "eval_loss": 0.1158880740404129,
+      "eval_runtime": 53.9013,
+      "eval_samples_per_second": 4.545,
+      "eval_steps_per_second": 4.545,
+      "step": 570
+    },
+    {
+      "epoch": 0.9987085665088248,
+      "grad_norm": 0.14954382181167603,
+      "learning_rate": 0.000118088053433211,
+      "loss": 0.1275,
+      "step": 580
+    },
+    {
+      "epoch": 1.0154972018941024,
+      "grad_norm": 0.16672547161579132,
+      "learning_rate": 0.00011512360558844994,
+      "loss": 0.122,
+      "step": 590
+    },
+    {
+      "epoch": 1.0327163151097718,
+      "grad_norm": 0.22516606748104095,
+      "learning_rate": 0.00011214549022117967,
+      "loss": 0.1215,
+      "step": 600
+    },
+    {
+      "epoch": 1.0327163151097718,
+      "eval_loss": 0.11643720418214798,
+      "eval_runtime": 54.0392,
+      "eval_samples_per_second": 4.534,
+      "eval_steps_per_second": 4.534,
+      "step": 600
+    },
+    {
+      "epoch": 1.0499354283254412,
+      "grad_norm": 0.10763582587242126,
+      "learning_rate": 0.00010915639871729874,
+      "loss": 0.1092,
+      "step": 610
+    },
+    {
+      "epoch": 1.0671545415411106,
+      "grad_norm": 0.12457219511270523,
+      "learning_rate": 0.00010615903238207292,
+      "loss": 0.1262,
+      "step": 620
+    },
+    {
+      "epoch": 1.08437365475678,
+      "grad_norm": 0.10427327454090118,
+      "learning_rate": 0.00010315609999890798,
+      "loss": 0.1221,
+      "step": 630
+    },
+    {
+      "epoch": 1.08437365475678,
+      "eval_loss": 0.11431042104959488,
+      "eval_runtime": 53.9648,
+      "eval_samples_per_second": 4.54,
+      "eval_steps_per_second": 4.54,
+      "step": 630
+    },
+    {
+      "epoch": 1.1015927679724493,
+      "grad_norm": 0.10417324304580688,
+      "learning_rate": 0.00010015031538136518,
+      "loss": 0.1243,
+      "step": 640
+    },
+    {
+      "epoch": 1.118811881188119,
+      "grad_norm": 0.10996241122484207,
+      "learning_rate": 9.71443949206304e-05,
+      "loss": 0.123,
+      "step": 650
+    },
+    {
+      "epoch": 1.1360309944037883,
+      "grad_norm": 0.09512694925069809,
+      "learning_rate": 9.41410551306537e-05,
+      "loss": 0.1161,
+      "step": 660
+    },
+    {
+      "epoch": 1.1360309944037883,
+      "eval_loss": 0.11319658905267715,
+      "eval_runtime": 54.1752,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 660
+    },
+    {
+      "epoch": 1.1532501076194577,
+      "grad_norm": 0.08619705587625504,
+      "learning_rate": 9.114301019317854e-05,
+      "loss": 0.1138,
+      "step": 670
+    },
+    {
+      "epoch": 1.170469220835127,
+      "grad_norm": 0.099159836769104,
+      "learning_rate": 8.815296950487804e-05,
+      "loss": 0.116,
+      "step": 680
+    },
+    {
+      "epoch": 1.1876883340507964,
+      "grad_norm": 0.09249532967805862,
+      "learning_rate": 8.517363522881579e-05,
+      "loss": 0.1209,
+      "step": 690
+    },
+    {
+      "epoch": 1.1876883340507964,
+      "eval_loss": 0.11321850121021271,
+      "eval_runtime": 54.1757,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 690
+    },
+    {
+      "epoch": 1.2049074472664658,
+      "grad_norm": 0.10436110198497772,
+      "learning_rate": 8.220769985244425e-05,
+      "loss": 0.1245,
+      "step": 700
+    },
+    {
+      "epoch": 1.2221265604821352,
+      "grad_norm": 0.08504263311624527,
+      "learning_rate": 7.925784375434629e-05,
+      "loss": 0.1116,
+      "step": 710
+    },
+    {
+      "epoch": 1.2393456736978046,
+      "grad_norm": 0.10974706709384918,
+      "learning_rate": 7.63267327819209e-05,
+      "loss": 0.1213,
+      "step": 720
+    },
+    {
+      "epoch": 1.2393456736978046,
+      "eval_loss": 0.11273372918367386,
+      "eval_runtime": 54.1807,
+      "eval_samples_per_second": 4.522,
+      "eval_steps_per_second": 4.522,
+      "step": 720
+    },
+    {
+      "epoch": 1.256564786913474,
+      "grad_norm": 0.0872415080666542,
+      "learning_rate": 7.341701584220006e-05,
+      "loss": 0.1164,
+      "step": 730
+    },
+    {
+      "epoch": 1.2737839001291433,
+      "grad_norm": 0.09694085270166397,
+      "learning_rate": 7.05313225079756e-05,
+      "loss": 0.1193,
+      "step": 740
+    },
+    {
+      "epoch": 1.2910030133448127,
+      "grad_norm": 0.09382116794586182,
+      "learning_rate": 6.767226064139841e-05,
+      "loss": 0.1212,
+      "step": 750
+    },
+    {
+      "epoch": 1.2910030133448127,
+      "eval_loss": 0.11223271489143372,
+      "eval_runtime": 53.9413,
+      "eval_samples_per_second": 4.542,
+      "eval_steps_per_second": 4.542,
+      "step": 750
+    },
+    {
+      "epoch": 1.308222126560482,
+      "grad_norm": 0.09150267392396927,
+      "learning_rate": 6.484241403719842e-05,
+      "loss": 0.1204,
+      "step": 760
+    },
+    {
+      "epoch": 1.3254412397761515,
+      "grad_norm": 0.10270262509584427,
+      "learning_rate": 6.204434008765458e-05,
+      "loss": 0.119,
+      "step": 770
+    },
+    {
+      "epoch": 1.3426603529918208,
+      "grad_norm": 0.10682746022939682,
+      "learning_rate": 5.9280567471425077e-05,
+      "loss": 0.1158,
+      "step": 780
+    },
+    {
+      "epoch": 1.3426603529918208,
+      "eval_loss": 0.11181723326444626,
+      "eval_runtime": 53.9263,
+      "eval_samples_per_second": 4.543,
+      "eval_steps_per_second": 4.543,
+      "step": 780
+    },
+    {
+      "epoch": 1.3598794662074902,
+      "grad_norm": 0.0856538936495781,
+      "learning_rate": 5.655359386832728e-05,
+      "loss": 0.1214,
+      "step": 790
+    },
+    {
+      "epoch": 1.3770985794231598,
+      "grad_norm": 0.08333317190408707,
+      "learning_rate": 5.386588370213124e-05,
+      "loss": 0.123,
+      "step": 800
+    },
+    {
+      "epoch": 1.394317692638829,
+      "grad_norm": 0.08669654279947281,
+      "learning_rate": 5.121986591340808e-05,
+      "loss": 0.1177,
+      "step": 810
+    },
+    {
+      "epoch": 1.394317692638829,
+      "eval_loss": 0.11222003400325775,
+      "eval_runtime": 53.9921,
+      "eval_samples_per_second": 4.538,
+      "eval_steps_per_second": 4.538,
+      "step": 810
+    },
+    {
+      "epoch": 1.4115368058544986,
+      "grad_norm": 0.09735915809869766,
+      "learning_rate": 4.861793176444479e-05,
+      "loss": 0.1155,
+      "step": 820
+    },
+    {
+      "epoch": 1.428755919070168,
+      "grad_norm": 0.10614746063947678,
+      "learning_rate": 4.6062432678209986e-05,
+      "loss": 0.1126,
+      "step": 830
+    },
+    {
+      "epoch": 1.4459750322858373,
+      "grad_norm": 0.09488119930028915,
+      "learning_rate": 4.355567811332311e-05,
+      "loss": 0.1153,
+      "step": 840
+    },
+    {
+      "epoch": 1.4459750322858373,
+      "eval_loss": 0.11169660836458206,
+      "eval_runtime": 54.1675,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 4.523,
+      "step": 840
+    },
+    {
+      "epoch": 1.4631941455015067,
+      "grad_norm": 0.10649088025093079,
+      "learning_rate": 4.109993347694781e-05,
+      "loss": 0.1289,
+      "step": 850
+    },
+    {
+      "epoch": 1.480413258717176,
+      "grad_norm": 0.08584726601839066,
+      "learning_rate": 3.8697418077495575e-05,
+      "loss": 0.1193,
+      "step": 860
+    },
+    {
+      "epoch": 1.4976323719328455,
+      "grad_norm": 0.08480769395828247,
+      "learning_rate": 3.635030311898975e-05,
+      "loss": 0.1167,
+      "step": 870
+    },
+    {
+      "epoch": 1.4976323719328455,
+      "eval_loss": 0.1113625019788742,
+      "eval_runtime": 54.0863,
+      "eval_samples_per_second": 4.53,
+      "eval_steps_per_second": 4.53,
+      "step": 870
+    },
+    {
+      "epoch": 1.5148514851485149,
+      "grad_norm": 0.09291431307792664,
+      "learning_rate": 3.4060709738902485e-05,
+      "loss": 0.1223,
+      "step": 880
+    },
+    {
+      "epoch": 1.5320705983641842,
+      "grad_norm": 0.06462642550468445,
+      "learning_rate": 3.183070709123781e-05,
+      "loss": 0.1113,
+      "step": 890
+    },
+    {
+      "epoch": 1.5492897115798536,
+      "grad_norm": 0.08776138722896576,
+      "learning_rate": 2.9662310476593492e-05,
+      "loss": 0.1159,
+      "step": 900
+    },
+    {
+      "epoch": 1.5492897115798536,
+      "eval_loss": 0.11135545372962952,
+      "eval_runtime": 54.2115,
+      "eval_samples_per_second": 4.519,
+      "eval_steps_per_second": 4.519,
+      "step": 900
+    },
+    {
+      "epoch": 1.566508824795523,
+      "grad_norm": 0.08839749544858932,
+      "learning_rate": 2.7557479520891104e-05,
+      "loss": 0.1226,
+      "step": 910
+    },
+    {
+      "epoch": 1.5837279380111924,
+      "grad_norm": 0.1001950353384018,
+      "learning_rate": 2.551811640442081e-05,
+      "loss": 0.1156,
+      "step": 920
+    },
+    {
+      "epoch": 1.6009470512268618,
+      "grad_norm": 0.08094879239797592,
+      "learning_rate": 2.354606414280045e-05,
+      "loss": 0.1178,
+      "step": 930
+    },
+    {
+      "epoch": 1.6009470512268618,
+      "eval_loss": 0.11072849482297897,
+      "eval_runtime": 54.2409,
+      "eval_samples_per_second": 4.517,
+      "eval_steps_per_second": 4.517,
+      "step": 930
+    },
+    {
+      "epoch": 1.6181661644425311,
+      "grad_norm": 0.0837637260556221,
+      "learning_rate": 2.1643104921403657e-05,
+      "loss": 0.1163,
+      "step": 940
+    },
+    {
+      "epoch": 1.6353852776582007,
+      "grad_norm": 0.08061401546001434,
+      "learning_rate": 1.98109584847609e-05,
+      "loss": 0.1215,
+      "step": 950
+    },
+    {
+      "epoch": 1.65260439087387,
+      "grad_norm": 0.08909575641155243,
+      "learning_rate": 1.805128058239014e-05,
+      "loss": 0.1214,
+      "step": 960
+    },
+    {
+      "epoch": 1.65260439087387,
+      "eval_loss": 0.11049379408359528,
+      "eval_runtime": 54.0663,
+      "eval_samples_per_second": 4.531,
+      "eval_steps_per_second": 4.531,
+      "step": 960
+    },
+    {
+      "epoch": 1.6698235040895395,
+      "grad_norm": 0.0853874459862709,
+      "learning_rate": 1.6365661472460946e-05,
+      "loss": 0.1223,
+      "step": 970
+    },
+    {
+      "epoch": 1.6870426173052087,
+      "grad_norm": 0.07660456001758575,
+      "learning_rate": 1.475562448464437e-05,
+      "loss": 0.1249,
+      "step": 980
+    },
+    {
+      "epoch": 1.7042617305208783,
+      "grad_norm": 0.08277535438537598,
+      "learning_rate": 1.3222624643447879e-05,
+      "loss": 0.1139,
+      "step": 990
+    },
+    {
+      "epoch": 1.7042617305208783,
+      "eval_loss": 0.11061510443687439,
+      "eval_runtime": 54.1562,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 4.524,
+      "step": 990
+    },
+    {
+      "epoch": 1.7214808437365474,
+      "grad_norm": 0.08193802833557129,
+      "learning_rate": 1.1768047353278721e-05,
+      "loss": 0.1163,
+      "step": 1000
+    },
+    {
+      "epoch": 1.738699956952217,
+      "grad_norm": 0.09207924455404282,
+      "learning_rate": 1.0393207146424766e-05,
+      "loss": 0.1171,
+      "step": 1010
+    },
+    {
+      "epoch": 1.7559190701678864,
+      "grad_norm": 0.07924116402864456,
+      "learning_rate": 9.09934649508375e-06,
+      "loss": 0.1215,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7559190701678864,
+      "eval_loss": 0.1104968935251236,
+      "eval_runtime": 54.2108,
+      "eval_samples_per_second": 4.519,
+      "eval_steps_per_second": 4.519,
+      "step": 1020
+    },
+    {
+      "epoch": 1.7731381833835558,
+      "grad_norm": 0.0777198001742363,
+      "learning_rate": 7.887634688515e-06,
+      "loss": 0.1204,
+      "step": 1030
+    },
+    {
+      "epoch": 1.7903572965992252,
+      "grad_norm": 0.09511927515268326,
+      "learning_rate": 6.759166776327786e-06,
+      "loss": 0.1125,
+      "step": 1040
+    },
+    {
+      "epoch": 1.8075764098148945,
+      "grad_norm": 0.08975937217473984,
+      "learning_rate": 5.71496257886196e-06,
+      "loss": 0.1143,
+      "step": 1050
+    },
+    {
+      "epoch": 1.8075764098148945,
+      "eval_loss": 0.11050143837928772,
+      "eval_runtime": 54.1535,
+      "eval_samples_per_second": 4.524,
+      "eval_steps_per_second": 4.524,
+      "step": 1050
+    },
+    {
+      "epoch": 1.824795523030564,
+      "grad_norm": 0.08812955766916275,
+      "learning_rate": 4.755965765554637e-06,
+      "loss": 0.112,
+      "step": 1060
+    },
+    {
+      "epoch": 1.8420146362462333,
+      "grad_norm": 0.08198709785938263,
+      "learning_rate": 3.883043002126219e-06,
+      "loss": 0.1149,
+      "step": 1070
+    },
+    {
+      "epoch": 1.8592337494619027,
+      "grad_norm": 0.0873785987496376,
+      "learning_rate": 3.0969831673562042e-06,
+      "loss": 0.1142,
+      "step": 1080
+    },
+    {
+      "epoch": 1.8592337494619027,
+      "eval_loss": 0.11041069775819778,
+      "eval_runtime": 54.1647,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 4.523,
+      "step": 1080
+    },
+    {
+      "epoch": 1.876452862677572,
+      "grad_norm": 0.08640486001968384,
+      "learning_rate": 2.3984966401567e-06,
+      "loss": 0.1154,
+      "step": 1090
+    },
+    {
+      "epoch": 1.8936719758932417,
+      "grad_norm": 0.09290562570095062,
+      "learning_rate": 1.7882146575880166e-06,
+      "loss": 0.1163,
+      "step": 1100
+    },
+    {
+      "epoch": 1.9108910891089108,
+      "grad_norm": 0.0945608988404274,
+      "learning_rate": 1.266688744396327e-06,
+      "loss": 0.1162,
+      "step": 1110
+    },
+    {
+      "epoch": 1.9108910891089108,
+      "eval_loss": 0.11023778468370438,
+      "eval_runtime": 54.2854,
+      "eval_samples_per_second": 4.513,
+      "eval_steps_per_second": 4.513,
+      "step": 1110
+    },
+    {
+      "epoch": 1.9281102023245804,
+      "grad_norm": 0.09848543256521225,
+      "learning_rate": 8.343902145891646e-07,
+      "loss": 0.1112,
+      "step": 1120
+    },
+    {
+      "epoch": 1.9453293155402496,
+      "grad_norm": 0.09019118547439575,
+      "learning_rate": 4.917097454988584e-07,
+      "loss": 0.1156,
+      "step": 1130
+    },
+    {
+      "epoch": 1.9625484287559192,
+      "grad_norm": 0.09469816088676453,
+      "learning_rate": 2.389570247192552e-07,
+      "loss": 0.1218,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9625484287559192,
+      "eval_loss": 0.11023097485303879,
+      "eval_runtime": 54.1686,
+      "eval_samples_per_second": 4.523,
+      "eval_steps_per_second": 4.523,
+      "step": 1140
+    },
+    {
+      "epoch": 1.9797675419715883,
+      "grad_norm": 0.08748683333396912,
+      "learning_rate": 7.636047023441561e-08,
+      "loss": 0.1202,
+      "step": 1150
+    },
+    {
+      "epoch": 1.996986655187258,
+      "grad_norm": 0.09518461674451828,
+      "learning_rate": 4.0670239925155725e-09,
+      "loss": 0.1136,
+      "step": 1160
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1162,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6568373351982694e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1162/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df85a2dc62117d691e5665e76e86e08b05c157a75892a77849b25ff3759ae220
+size 5777

config.json

@@ -0,0 +1,70 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 262144,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151654,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 5000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.56.2",
+  "unsloth_fixed": true,
+  "unsloth_version": "2025.12.7",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 262144,
+  "pad_token_id": 151654,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.56.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7f78cac4b16709153d5a102918eefd8f4b3639fb6f27559d68d80041f2f0f84
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:505e186513b7f6540666f2ebe2946b74304c70b4e43c7beb2120f5842e131561
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_parameters": 4022468096,
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 262144,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}