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-800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-855/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": [
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "up_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 sha256:2d1d712b18e5fdde0827be7c13ee38092552ce2760d2294d44c5e6a2370157d8
+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-800/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-800/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": [
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-800/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4bc700df546887d90e034a2cb959c0a11a8ad9f102c61b99ee532a1b0b1a48
+size 528550256

checkpoint-800/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-800/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-800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a177aa350277a25bbfa008e9e361b8f4fb4c20c6f2776f00e73709cc69aa2fd6
+size 1057397963

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ec2d0981ee059a7ea334230ae1bda26cd409cba7b9cc01e3e11f2db632cd2bd
+size 14645

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4515318f59dee3a653c6babe8f18a7bd51e6e56fe8d494fc85584dd4618c69ff
+size 1465

checkpoint-800/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-800/tokenizer.json

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

checkpoint-800/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-800/trainer_state.json

@@ -0,0 +1,802 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.807017543859649,
+  "eval_steps": 30,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 4.878787040710449,
+      "learning_rate": 2.0930232558139536e-05,
+      "loss": 2.4934,
+      "step": 10
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 0.776142418384552,
+      "learning_rate": 4.418604651162791e-05,
+      "loss": 0.9685,
+      "step": 20
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.7527797818183899,
+      "learning_rate": 6.744186046511628e-05,
+      "loss": 0.5823,
+      "step": 30
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "eval_loss": 0.45968249440193176,
+      "eval_runtime": 25.548,
+      "eval_samples_per_second": 4.697,
+      "eval_steps_per_second": 4.697,
+      "step": 30
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 0.5810465812683105,
+      "learning_rate": 9.069767441860465e-05,
+      "loss": 0.4143,
+      "step": 40
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.6364761590957642,
+      "learning_rate": 0.00011395348837209304,
+      "loss": 0.3,
+      "step": 50
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.7183641791343689,
+      "learning_rate": 0.0001372093023255814,
+      "loss": 0.2551,
+      "step": 60
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 0.21707303822040558,
+      "eval_runtime": 24.8756,
+      "eval_samples_per_second": 4.824,
+      "eval_steps_per_second": 4.824,
+      "step": 60
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 0.4606807231903076,
+      "learning_rate": 0.00016046511627906978,
+      "loss": 0.223,
+      "step": 70
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.5203229784965515,
+      "learning_rate": 0.00018372093023255815,
+      "loss": 0.1933,
+      "step": 80
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.44623491168022156,
+      "learning_rate": 0.0001999924897543333,
+      "loss": 0.1902,
+      "step": 90
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 0.1671793907880783,
+      "eval_runtime": 25.9688,
+      "eval_samples_per_second": 4.621,
+      "eval_steps_per_second": 4.621,
+      "step": 90
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.5045297145843506,
+      "learning_rate": 0.000199859005655354,
+      "loss": 0.1724,
+      "step": 100
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.2889767289161682,
+      "learning_rate": 0.00019955888361169273,
+      "loss": 0.1666,
+      "step": 110
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.4197916090488434,
+      "learning_rate": 0.00019909262444668715,
+      "loss": 0.1611,
+      "step": 120
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 0.13614678382873535,
+      "eval_runtime": 25.0008,
+      "eval_samples_per_second": 4.8,
+      "eval_steps_per_second": 4.8,
+      "step": 120
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 0.3050219714641571,
+      "learning_rate": 0.00019846100622204974,
+      "loss": 0.1593,
+      "step": 130
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.24451592564582825,
+      "learning_rate": 0.00019766508293949108,
+      "loss": 0.1594,
+      "step": 140
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.29427045583724976,
+      "learning_rate": 0.00019670618278187318,
+      "loss": 0.1424,
+      "step": 150
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "eval_loss": 0.13314871490001678,
+      "eval_runtime": 25.9586,
+      "eval_samples_per_second": 4.623,
+      "eval_steps_per_second": 4.623,
+      "step": 150
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.36817243695259094,
+      "learning_rate": 0.00019558590589682795,
+      "loss": 0.1383,
+      "step": 160
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.16424335539340973,
+      "learning_rate": 0.00019430612172653908,
+      "loss": 0.1447,
+      "step": 170
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.17733046412467957,
+      "learning_rate": 0.00019286896588814373,
+      "loss": 0.1335,
+      "step": 180
+    },
+    {
+      "epoch": 0.631578947368421,
+      "eval_loss": 0.13173671066761017,
+      "eval_runtime": 25.9972,
+      "eval_samples_per_second": 4.616,
+      "eval_steps_per_second": 4.616,
+      "step": 180
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.22004777193069458,
+      "learning_rate": 0.00019127683660995914,
+      "loss": 0.1457,
+      "step": 190
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.2817850112915039,
+      "learning_rate": 0.00018953239072948182,
+      "loss": 0.1304,
+      "step": 200
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.22587062418460846,
+      "learning_rate": 0.00018763853925983693,
+      "loss": 0.1426,
+      "step": 210
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "eval_loss": 0.12666551768779755,
+      "eval_runtime": 25.8854,
+      "eval_samples_per_second": 4.636,
+      "eval_steps_per_second": 4.636,
+      "step": 210
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.1741916984319687,
+      "learning_rate": 0.0001855984425320769,
+      "loss": 0.1404,
+      "step": 220
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.14528629183769226,
+      "learning_rate": 0.00018341550492143496,
+      "loss": 0.1486,
+      "step": 230
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.26741355657577515,
+      "learning_rate": 0.00018109336916633426,
+      "loss": 0.1281,
+      "step": 240
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.12144554406404495,
+      "eval_runtime": 24.7052,
+      "eval_samples_per_second": 4.857,
+      "eval_steps_per_second": 4.857,
+      "step": 240
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.12268830090761185,
+      "learning_rate": 0.000178635910289633,
+      "loss": 0.1281,
+      "step": 250
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.2916463613510132,
+      "learning_rate": 0.00017604722913224842,
+      "loss": 0.1348,
+      "step": 260
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.13800819218158722,
+      "learning_rate": 0.00017333164550995152,
+      "loss": 0.1258,
+      "step": 270
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "eval_loss": 0.11921060085296631,
+      "eval_runtime": 24.7901,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 270
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.11254072189331055,
+      "learning_rate": 0.000170493691004751,
+      "loss": 0.1304,
+      "step": 280
+    },
+    {
+      "epoch": 1.0175438596491229,
+      "grad_norm": 0.14597080647945404,
+      "learning_rate": 0.00016753810140289607,
+      "loss": 0.1288,
+      "step": 290
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.12981514632701874,
+      "learning_rate": 0.0001644698087921173,
+      "loss": 0.1307,
+      "step": 300
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "eval_loss": 0.1170278862118721,
+      "eval_runtime": 24.9635,
+      "eval_samples_per_second": 4.807,
+      "eval_steps_per_second": 4.807,
+      "step": 300
+    },
+    {
+      "epoch": 1.087719298245614,
+      "grad_norm": 0.10934378206729889,
+      "learning_rate": 0.0001612939333312926,
+      "loss": 0.1111,
+      "step": 310
+    },
+    {
+      "epoch": 1.1228070175438596,
+      "grad_norm": 0.1015116274356842,
+      "learning_rate": 0.00015801577470627286,
+      "loss": 0.1288,
+      "step": 320
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.1372503787279129,
+      "learning_rate": 0.0001546408032861252,
+      "loss": 0.116,
+      "step": 330
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "eval_loss": 0.11487225443124771,
+      "eval_runtime": 24.9694,
+      "eval_samples_per_second": 4.806,
+      "eval_steps_per_second": 4.806,
+      "step": 330
+    },
+    {
+      "epoch": 1.1929824561403508,
+      "grad_norm": 0.2865680456161499,
+      "learning_rate": 0.00015117465099455174,
+      "loss": 0.1237,
+      "step": 340
+    },
+    {
+      "epoch": 1.2280701754385965,
+      "grad_norm": 0.12083390355110168,
+      "learning_rate": 0.00014762310191171655,
+      "loss": 0.1305,
+      "step": 350
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.09869180619716644,
+      "learning_rate": 0.00014399208262216474,
+      "loss": 0.1167,
+      "step": 360
+    },
+    {
+      "epoch": 1.263157894736842,
+      "eval_loss": 0.11612139642238617,
+      "eval_runtime": 24.9809,
+      "eval_samples_per_second": 4.804,
+      "eval_steps_per_second": 4.804,
+      "step": 360
+    },
+    {
+      "epoch": 1.2982456140350878,
+      "grad_norm": 0.10779603570699692,
+      "learning_rate": 0.0001402876523249394,
+      "loss": 0.1325,
+      "step": 370
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.20813943445682526,
+      "learning_rate": 0.00013651599272240076,
+      "loss": 0.1203,
+      "step": 380
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.10286935418844223,
+      "learning_rate": 0.0001326833977046199,
+      "loss": 0.1198,
+      "step": 390
+    },
+    {
+      "epoch": 1.368421052631579,
+      "eval_loss": 0.1140877828001976,
+      "eval_runtime": 25.1216,
+      "eval_samples_per_second": 4.777,
+      "eval_steps_per_second": 4.777,
+      "step": 390
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 0.10826771706342697,
+      "learning_rate": 0.00012879626284656142,
+      "loss": 0.1215,
+      "step": 400
+    },
+    {
+      "epoch": 1.4385964912280702,
+      "grad_norm": 0.09107205271720886,
+      "learning_rate": 0.00012486107473558118,
+      "loss": 0.1258,
+      "step": 410
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.23670166730880737,
+      "learning_rate": 0.00012088440014704858,
+      "loss": 0.1194,
+      "step": 420
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "eval_loss": 0.11560888588428497,
+      "eval_runtime": 25.1077,
+      "eval_samples_per_second": 4.779,
+      "eval_steps_per_second": 4.779,
+      "step": 420
+    },
+    {
+      "epoch": 1.5087719298245614,
+      "grad_norm": 0.09810595214366913,
+      "learning_rate": 0.0001168728750861567,
+      "loss": 0.1282,
+      "step": 430
+    },
+    {
+      "epoch": 1.543859649122807,
+      "grad_norm": 0.11235892027616501,
+      "learning_rate": 0.0001128331937142062,
+      "loss": 0.1234,
+      "step": 440
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.09267847239971161,
+      "learning_rate": 0.0001087720971778426,
+      "loss": 0.1292,
+      "step": 450
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "eval_loss": 0.11425888538360596,
+      "eval_runtime": 25.0231,
+      "eval_samples_per_second": 4.796,
+      "eval_steps_per_second": 4.796,
+      "step": 450
+    },
+    {
+      "epoch": 1.6140350877192984,
+      "grad_norm": 0.12776316702365875,
+      "learning_rate": 0.0001046963623598871,
+      "loss": 0.12,
+      "step": 460
+    },
+    {
+      "epoch": 1.6491228070175439,
+      "grad_norm": 0.12537536025047302,
+      "learning_rate": 0.00010061279057053386,
+      "loss": 0.1231,
+      "step": 470
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.11115119606256485,
+      "learning_rate": 9.652819619778386e-05,
+      "loss": 0.1262,
+      "step": 480
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "eval_loss": 0.11288858950138092,
+      "eval_runtime": 24.9273,
+      "eval_samples_per_second": 4.814,
+      "eval_steps_per_second": 4.814,
+      "step": 480
+    },
+    {
+      "epoch": 1.719298245614035,
+      "grad_norm": 0.09119213372468948,
+      "learning_rate": 9.244939533605619e-05,
+      "loss": 0.1233,
+      "step": 490
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 0.12485823780298233,
+      "learning_rate": 8.838319441195105e-05,
+      "loss": 0.1212,
+      "step": 500
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.10320759564638138,
+      "learning_rate": 8.433637882614625e-05,
+      "loss": 0.1298,
+      "step": 510
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "eval_loss": 0.11233663558959961,
+      "eval_runtime": 24.9513,
+      "eval_samples_per_second": 4.809,
+      "eval_steps_per_second": 4.809,
+      "step": 510
+    },
+    {
+      "epoch": 1.8245614035087718,
+      "grad_norm": 0.115440234541893,
+      "learning_rate": 8.031570163038005e-05,
+      "loss": 0.1298,
+      "step": 520
+    },
+    {
+      "epoch": 1.8596491228070176,
+      "grad_norm": 0.09397278726100922,
+      "learning_rate": 7.632787225841593e-05,
+      "loss": 0.1258,
+      "step": 530
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.08502210676670074,
+      "learning_rate": 7.237954532979401e-05,
+      "loss": 0.119,
+      "step": 540
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "eval_loss": 0.11294586211442947,
+      "eval_runtime": 25.0566,
+      "eval_samples_per_second": 4.789,
+      "eval_steps_per_second": 4.789,
+      "step": 540
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 0.09859590232372284,
+      "learning_rate": 6.847730954505261e-05,
+      "loss": 0.1222,
+      "step": 550
+    },
+    {
+      "epoch": 1.9649122807017543,
+      "grad_norm": 0.07687846571207047,
+      "learning_rate": 6.462767669095109e-05,
+      "loss": 0.1143,
+      "step": 560
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.09160079807043076,
+      "learning_rate": 6.0837070774041284e-05,
+      "loss": 0.1227,
+      "step": 570
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.11345366388559341,
+      "eval_runtime": 25.1502,
+      "eval_samples_per_second": 4.771,
+      "eval_steps_per_second": 4.771,
+      "step": 570
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.08900679647922516,
+      "learning_rate": 5.711181730072044e-05,
+      "loss": 0.1068,
+      "step": 580
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.11684390157461166,
+      "learning_rate": 5.3458132721654564e-05,
+      "loss": 0.122,
+      "step": 590
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.11595682054758072,
+      "learning_rate": 4.9882114058186616e-05,
+      "loss": 0.1493,
+      "step": 600
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "eval_loss": 0.11257700622081757,
+      "eval_runtime": 24.9265,
+      "eval_samples_per_second": 4.814,
+      "eval_steps_per_second": 4.814,
+      "step": 600
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 0.10183674842119217,
+      "learning_rate": 4.638972872804038e-05,
+      "loss": 0.1168,
+      "step": 610
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.10958362370729446,
+      "learning_rate": 4.298680458729792e-05,
+      "loss": 0.1206,
+      "step": 620
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.09745143353939056,
+      "learning_rate": 3.967902020526797e-05,
+      "loss": 0.1272,
+      "step": 630
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "eval_loss": 0.11299394816160202,
+      "eval_runtime": 25.0837,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 4.784,
+      "step": 630
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.08707338571548462,
+      "learning_rate": 3.647189538847432e-05,
+      "loss": 0.1212,
+      "step": 640
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.09840196371078491,
+      "learning_rate": 3.337078196957647e-05,
+      "loss": 0.1137,
+      "step": 650
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.10066810250282288,
+      "learning_rate": 3.0380854876593723e-05,
+      "loss": 0.1147,
+      "step": 660
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "eval_loss": 0.11169523745775223,
+      "eval_runtime": 24.9457,
+      "eval_samples_per_second": 4.81,
+      "eval_steps_per_second": 4.81,
+      "step": 660
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.11805769056081772,
+      "learning_rate": 2.7507103497336016e-05,
+      "loss": 0.124,
+      "step": 670
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.09834598004817963,
+      "learning_rate": 2.475432335345128e-05,
+      "loss": 0.1269,
+      "step": 680
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.11241532862186432,
+      "learning_rate": 2.212710809798393e-05,
+      "loss": 0.1137,
+      "step": 690
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "eval_loss": 0.11132458597421646,
+      "eval_runtime": 24.998,
+      "eval_samples_per_second": 4.8,
+      "eval_steps_per_second": 4.8,
+      "step": 690
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.10056956857442856,
+      "learning_rate": 1.9629841849797736e-05,
+      "loss": 0.1151,
+      "step": 700
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.09482597559690475,
+      "learning_rate": 1.7266691877655127e-05,
+      "loss": 0.1091,
+      "step": 710
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.11021561920642853,
+      "learning_rate": 1.5041601646161585e-05,
+      "loss": 0.1225,
+      "step": 720
+    },
+    {
+      "epoch": 2.526315789473684,
+      "eval_loss": 0.11140093952417374,
+      "eval_runtime": 25.0288,
+      "eval_samples_per_second": 4.794,
+      "eval_steps_per_second": 4.794,
+      "step": 720
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.09573051333427429,
+      "learning_rate": 1.295828423517874e-05,
+      "loss": 0.1124,
+      "step": 730
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.1159501001238823,
+      "learning_rate": 1.1020216143688444e-05,
+      "loss": 0.1181,
+      "step": 740
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.09099686145782471,
+      "learning_rate": 9.230631488446639e-06,
+      "loss": 0.1185,
+      "step": 750
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "eval_loss": 0.11138518154621124,
+      "eval_runtime": 24.9674,
+      "eval_samples_per_second": 4.806,
+      "eval_steps_per_second": 4.806,
+      "step": 750
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.10761657357215881,
+      "learning_rate": 7.592516607108324e-06,
+      "loss": 0.1131,
+      "step": 760
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 0.11243995279073715,
+      "learning_rate": 6.108605074829709e-06,
+      "loss": 0.1178,
+      "step": 770
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.07883230596780777,
+      "learning_rate": 4.781373142663004e-06,
+      "loss": 0.1095,
+      "step": 780
+    },
+    {
+      "epoch": 2.736842105263158,
+      "eval_loss": 0.11120390146970749,
+      "eval_runtime": 24.9973,
+      "eval_samples_per_second": 4.801,
+      "eval_steps_per_second": 4.801,
+      "step": 780
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.11856161803007126,
+      "learning_rate": 3.613035605356463e-06,
+      "loss": 0.1148,
+      "step": 790
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.08602704107761383,
+      "learning_rate": 2.6055421054549613e-06,
+      "loss": 0.1095,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 855,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.123736288598528e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575c8b2166a905c3c64fc6f7849aaefacfddb90adb2a255f96969649f334dd0d
+size 5777

checkpoint-855/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-855/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": [
+    "down_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-855/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d1d712b18e5fdde0827be7c13ee38092552ce2760d2294d44c5e6a2370157d8
+size 528550256

checkpoint-855/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-855/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-855/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be98ba83ee452847668c65598ac36a82ff30b3193a14f44aad771dbb42dbcf02
+size 1057397963

checkpoint-855/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ee0d5b3e0b9b79604384d22a12f1dd320a69412786a5879ebad57284143483
+size 14645

checkpoint-855/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4515ad42ab2c71abeeca44b63868e4ed4631d57cda8be03cc9c6dd378816b343
+size 1465

checkpoint-855/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-855/tokenizer.json

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

checkpoint-855/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-855/trainer_state.json

@@ -0,0 +1,853 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 30,
+  "global_step": 855,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03508771929824561,
+      "grad_norm": 4.878787040710449,
+      "learning_rate": 2.0930232558139536e-05,
+      "loss": 2.4934,
+      "step": 10
+    },
+    {
+      "epoch": 0.07017543859649122,
+      "grad_norm": 0.776142418384552,
+      "learning_rate": 4.418604651162791e-05,
+      "loss": 0.9685,
+      "step": 20
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 0.7527797818183899,
+      "learning_rate": 6.744186046511628e-05,
+      "loss": 0.5823,
+      "step": 30
+    },
+    {
+      "epoch": 0.10526315789473684,
+      "eval_loss": 0.45968249440193176,
+      "eval_runtime": 25.548,
+      "eval_samples_per_second": 4.697,
+      "eval_steps_per_second": 4.697,
+      "step": 30
+    },
+    {
+      "epoch": 0.14035087719298245,
+      "grad_norm": 0.5810465812683105,
+      "learning_rate": 9.069767441860465e-05,
+      "loss": 0.4143,
+      "step": 40
+    },
+    {
+      "epoch": 0.17543859649122806,
+      "grad_norm": 0.6364761590957642,
+      "learning_rate": 0.00011395348837209304,
+      "loss": 0.3,
+      "step": 50
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "grad_norm": 0.7183641791343689,
+      "learning_rate": 0.0001372093023255814,
+      "loss": 0.2551,
+      "step": 60
+    },
+    {
+      "epoch": 0.21052631578947367,
+      "eval_loss": 0.21707303822040558,
+      "eval_runtime": 24.8756,
+      "eval_samples_per_second": 4.824,
+      "eval_steps_per_second": 4.824,
+      "step": 60
+    },
+    {
+      "epoch": 0.24561403508771928,
+      "grad_norm": 0.4606807231903076,
+      "learning_rate": 0.00016046511627906978,
+      "loss": 0.223,
+      "step": 70
+    },
+    {
+      "epoch": 0.2807017543859649,
+      "grad_norm": 0.5203229784965515,
+      "learning_rate": 0.00018372093023255815,
+      "loss": 0.1933,
+      "step": 80
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "grad_norm": 0.44623491168022156,
+      "learning_rate": 0.0001999924897543333,
+      "loss": 0.1902,
+      "step": 90
+    },
+    {
+      "epoch": 0.3157894736842105,
+      "eval_loss": 0.1671793907880783,
+      "eval_runtime": 25.9688,
+      "eval_samples_per_second": 4.621,
+      "eval_steps_per_second": 4.621,
+      "step": 90
+    },
+    {
+      "epoch": 0.3508771929824561,
+      "grad_norm": 0.5045297145843506,
+      "learning_rate": 0.000199859005655354,
+      "loss": 0.1724,
+      "step": 100
+    },
+    {
+      "epoch": 0.38596491228070173,
+      "grad_norm": 0.2889767289161682,
+      "learning_rate": 0.00019955888361169273,
+      "loss": 0.1666,
+      "step": 110
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "grad_norm": 0.4197916090488434,
+      "learning_rate": 0.00019909262444668715,
+      "loss": 0.1611,
+      "step": 120
+    },
+    {
+      "epoch": 0.42105263157894735,
+      "eval_loss": 0.13614678382873535,
+      "eval_runtime": 25.0008,
+      "eval_samples_per_second": 4.8,
+      "eval_steps_per_second": 4.8,
+      "step": 120
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 0.3050219714641571,
+      "learning_rate": 0.00019846100622204974,
+      "loss": 0.1593,
+      "step": 130
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.24451592564582825,
+      "learning_rate": 0.00019766508293949108,
+      "loss": 0.1594,
+      "step": 140
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.29427045583724976,
+      "learning_rate": 0.00019670618278187318,
+      "loss": 0.1424,
+      "step": 150
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "eval_loss": 0.13314871490001678,
+      "eval_runtime": 25.9586,
+      "eval_samples_per_second": 4.623,
+      "eval_steps_per_second": 4.623,
+      "step": 150
+    },
+    {
+      "epoch": 0.5614035087719298,
+      "grad_norm": 0.36817243695259094,
+      "learning_rate": 0.00019558590589682795,
+      "loss": 0.1383,
+      "step": 160
+    },
+    {
+      "epoch": 0.5964912280701754,
+      "grad_norm": 0.16424335539340973,
+      "learning_rate": 0.00019430612172653908,
+      "loss": 0.1447,
+      "step": 170
+    },
+    {
+      "epoch": 0.631578947368421,
+      "grad_norm": 0.17733046412467957,
+      "learning_rate": 0.00019286896588814373,
+      "loss": 0.1335,
+      "step": 180
+    },
+    {
+      "epoch": 0.631578947368421,
+      "eval_loss": 0.13173671066761017,
+      "eval_runtime": 25.9972,
+      "eval_samples_per_second": 4.616,
+      "eval_steps_per_second": 4.616,
+      "step": 180
+    },
+    {
+      "epoch": 0.6666666666666666,
+      "grad_norm": 0.22004777193069458,
+      "learning_rate": 0.00019127683660995914,
+      "loss": 0.1457,
+      "step": 190
+    },
+    {
+      "epoch": 0.7017543859649122,
+      "grad_norm": 0.2817850112915039,
+      "learning_rate": 0.00018953239072948182,
+      "loss": 0.1304,
+      "step": 200
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "grad_norm": 0.22587062418460846,
+      "learning_rate": 0.00018763853925983693,
+      "loss": 0.1426,
+      "step": 210
+    },
+    {
+      "epoch": 0.7368421052631579,
+      "eval_loss": 0.12666551768779755,
+      "eval_runtime": 25.8854,
+      "eval_samples_per_second": 4.636,
+      "eval_steps_per_second": 4.636,
+      "step": 210
+    },
+    {
+      "epoch": 0.7719298245614035,
+      "grad_norm": 0.1741916984319687,
+      "learning_rate": 0.0001855984425320769,
+      "loss": 0.1404,
+      "step": 220
+    },
+    {
+      "epoch": 0.8070175438596491,
+      "grad_norm": 0.14528629183769226,
+      "learning_rate": 0.00018341550492143496,
+      "loss": 0.1486,
+      "step": 230
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.26741355657577515,
+      "learning_rate": 0.00018109336916633426,
+      "loss": 0.1281,
+      "step": 240
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "eval_loss": 0.12144554406404495,
+      "eval_runtime": 24.7052,
+      "eval_samples_per_second": 4.857,
+      "eval_steps_per_second": 4.857,
+      "step": 240
+    },
+    {
+      "epoch": 0.8771929824561403,
+      "grad_norm": 0.12268830090761185,
+      "learning_rate": 0.000178635910289633,
+      "loss": 0.1281,
+      "step": 250
+    },
+    {
+      "epoch": 0.9122807017543859,
+      "grad_norm": 0.2916463613510132,
+      "learning_rate": 0.00017604722913224842,
+      "loss": 0.1348,
+      "step": 260
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "grad_norm": 0.13800819218158722,
+      "learning_rate": 0.00017333164550995152,
+      "loss": 0.1258,
+      "step": 270
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "eval_loss": 0.11921060085296631,
+      "eval_runtime": 24.7901,
+      "eval_samples_per_second": 4.841,
+      "eval_steps_per_second": 4.841,
+      "step": 270
+    },
+    {
+      "epoch": 0.9824561403508771,
+      "grad_norm": 0.11254072189331055,
+      "learning_rate": 0.000170493691004751,
+      "loss": 0.1304,
+      "step": 280
+    },
+    {
+      "epoch": 1.0175438596491229,
+      "grad_norm": 0.14597080647945404,
+      "learning_rate": 0.00016753810140289607,
+      "loss": 0.1288,
+      "step": 290
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.12981514632701874,
+      "learning_rate": 0.0001644698087921173,
+      "loss": 0.1307,
+      "step": 300
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "eval_loss": 0.1170278862118721,
+      "eval_runtime": 24.9635,
+      "eval_samples_per_second": 4.807,
+      "eval_steps_per_second": 4.807,
+      "step": 300
+    },
+    {
+      "epoch": 1.087719298245614,
+      "grad_norm": 0.10934378206729889,
+      "learning_rate": 0.0001612939333312926,
+      "loss": 0.1111,
+      "step": 310
+    },
+    {
+      "epoch": 1.1228070175438596,
+      "grad_norm": 0.1015116274356842,
+      "learning_rate": 0.00015801577470627286,
+      "loss": 0.1288,
+      "step": 320
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "grad_norm": 0.1372503787279129,
+      "learning_rate": 0.0001546408032861252,
+      "loss": 0.116,
+      "step": 330
+    },
+    {
+      "epoch": 1.1578947368421053,
+      "eval_loss": 0.11487225443124771,
+      "eval_runtime": 24.9694,
+      "eval_samples_per_second": 4.806,
+      "eval_steps_per_second": 4.806,
+      "step": 330
+    },
+    {
+      "epoch": 1.1929824561403508,
+      "grad_norm": 0.2865680456161499,
+      "learning_rate": 0.00015117465099455174,
+      "loss": 0.1237,
+      "step": 340
+    },
+    {
+      "epoch": 1.2280701754385965,
+      "grad_norm": 0.12083390355110168,
+      "learning_rate": 0.00014762310191171655,
+      "loss": 0.1305,
+      "step": 350
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 0.09869180619716644,
+      "learning_rate": 0.00014399208262216474,
+      "loss": 0.1167,
+      "step": 360
+    },
+    {
+      "epoch": 1.263157894736842,
+      "eval_loss": 0.11612139642238617,
+      "eval_runtime": 24.9809,
+      "eval_samples_per_second": 4.804,
+      "eval_steps_per_second": 4.804,
+      "step": 360
+    },
+    {
+      "epoch": 1.2982456140350878,
+      "grad_norm": 0.10779603570699692,
+      "learning_rate": 0.0001402876523249394,
+      "loss": 0.1325,
+      "step": 370
+    },
+    {
+      "epoch": 1.3333333333333333,
+      "grad_norm": 0.20813943445682526,
+      "learning_rate": 0.00013651599272240076,
+      "loss": 0.1203,
+      "step": 380
+    },
+    {
+      "epoch": 1.368421052631579,
+      "grad_norm": 0.10286935418844223,
+      "learning_rate": 0.0001326833977046199,
+      "loss": 0.1198,
+      "step": 390
+    },
+    {
+      "epoch": 1.368421052631579,
+      "eval_loss": 0.1140877828001976,
+      "eval_runtime": 25.1216,
+      "eval_samples_per_second": 4.777,
+      "eval_steps_per_second": 4.777,
+      "step": 390
+    },
+    {
+      "epoch": 1.4035087719298245,
+      "grad_norm": 0.10826771706342697,
+      "learning_rate": 0.00012879626284656142,
+      "loss": 0.1215,
+      "step": 400
+    },
+    {
+      "epoch": 1.4385964912280702,
+      "grad_norm": 0.09107205271720886,
+      "learning_rate": 0.00012486107473558118,
+      "loss": 0.1258,
+      "step": 410
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.23670166730880737,
+      "learning_rate": 0.00012088440014704858,
+      "loss": 0.1194,
+      "step": 420
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "eval_loss": 0.11560888588428497,
+      "eval_runtime": 25.1077,
+      "eval_samples_per_second": 4.779,
+      "eval_steps_per_second": 4.779,
+      "step": 420
+    },
+    {
+      "epoch": 1.5087719298245614,
+      "grad_norm": 0.09810595214366913,
+      "learning_rate": 0.0001168728750861567,
+      "loss": 0.1282,
+      "step": 430
+    },
+    {
+      "epoch": 1.543859649122807,
+      "grad_norm": 0.11235892027616501,
+      "learning_rate": 0.0001128331937142062,
+      "loss": 0.1234,
+      "step": 440
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.09267847239971161,
+      "learning_rate": 0.0001087720971778426,
+      "loss": 0.1292,
+      "step": 450
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "eval_loss": 0.11425888538360596,
+      "eval_runtime": 25.0231,
+      "eval_samples_per_second": 4.796,
+      "eval_steps_per_second": 4.796,
+      "step": 450
+    },
+    {
+      "epoch": 1.6140350877192984,
+      "grad_norm": 0.12776316702365875,
+      "learning_rate": 0.0001046963623598871,
+      "loss": 0.12,
+      "step": 460
+    },
+    {
+      "epoch": 1.6491228070175439,
+      "grad_norm": 0.12537536025047302,
+      "learning_rate": 0.00010061279057053386,
+      "loss": 0.1231,
+      "step": 470
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 0.11115119606256485,
+      "learning_rate": 9.652819619778386e-05,
+      "loss": 0.1262,
+      "step": 480
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "eval_loss": 0.11288858950138092,
+      "eval_runtime": 24.9273,
+      "eval_samples_per_second": 4.814,
+      "eval_steps_per_second": 4.814,
+      "step": 480
+    },
+    {
+      "epoch": 1.719298245614035,
+      "grad_norm": 0.09119213372468948,
+      "learning_rate": 9.244939533605619e-05,
+      "loss": 0.1233,
+      "step": 490
+    },
+    {
+      "epoch": 1.7543859649122808,
+      "grad_norm": 0.12485823780298233,
+      "learning_rate": 8.838319441195105e-05,
+      "loss": 0.1212,
+      "step": 500
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "grad_norm": 0.10320759564638138,
+      "learning_rate": 8.433637882614625e-05,
+      "loss": 0.1298,
+      "step": 510
+    },
+    {
+      "epoch": 1.7894736842105263,
+      "eval_loss": 0.11233663558959961,
+      "eval_runtime": 24.9513,
+      "eval_samples_per_second": 4.809,
+      "eval_steps_per_second": 4.809,
+      "step": 510
+    },
+    {
+      "epoch": 1.8245614035087718,
+      "grad_norm": 0.115440234541893,
+      "learning_rate": 8.031570163038005e-05,
+      "loss": 0.1298,
+      "step": 520
+    },
+    {
+      "epoch": 1.8596491228070176,
+      "grad_norm": 0.09397278726100922,
+      "learning_rate": 7.632787225841593e-05,
+      "loss": 0.1258,
+      "step": 530
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.08502210676670074,
+      "learning_rate": 7.237954532979401e-05,
+      "loss": 0.119,
+      "step": 540
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "eval_loss": 0.11294586211442947,
+      "eval_runtime": 25.0566,
+      "eval_samples_per_second": 4.789,
+      "eval_steps_per_second": 4.789,
+      "step": 540
+    },
+    {
+      "epoch": 1.9298245614035088,
+      "grad_norm": 0.09859590232372284,
+      "learning_rate": 6.847730954505261e-05,
+      "loss": 0.1222,
+      "step": 550
+    },
+    {
+      "epoch": 1.9649122807017543,
+      "grad_norm": 0.07687846571207047,
+      "learning_rate": 6.462767669095109e-05,
+      "loss": 0.1143,
+      "step": 560
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.09160079807043076,
+      "learning_rate": 6.0837070774041284e-05,
+      "loss": 0.1227,
+      "step": 570
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.11345366388559341,
+      "eval_runtime": 25.1502,
+      "eval_samples_per_second": 4.771,
+      "eval_steps_per_second": 4.771,
+      "step": 570
+    },
+    {
+      "epoch": 2.0350877192982457,
+      "grad_norm": 0.08900679647922516,
+      "learning_rate": 5.711181730072044e-05,
+      "loss": 0.1068,
+      "step": 580
+    },
+    {
+      "epoch": 2.0701754385964914,
+      "grad_norm": 0.11684390157461166,
+      "learning_rate": 5.3458132721654564e-05,
+      "loss": 0.122,
+      "step": 590
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.11595682054758072,
+      "learning_rate": 4.9882114058186616e-05,
+      "loss": 0.1493,
+      "step": 600
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "eval_loss": 0.11257700622081757,
+      "eval_runtime": 24.9265,
+      "eval_samples_per_second": 4.814,
+      "eval_steps_per_second": 4.814,
+      "step": 600
+    },
+    {
+      "epoch": 2.1403508771929824,
+      "grad_norm": 0.10183674842119217,
+      "learning_rate": 4.638972872804038e-05,
+      "loss": 0.1168,
+      "step": 610
+    },
+    {
+      "epoch": 2.175438596491228,
+      "grad_norm": 0.10958362370729446,
+      "learning_rate": 4.298680458729792e-05,
+      "loss": 0.1206,
+      "step": 620
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "grad_norm": 0.09745143353939056,
+      "learning_rate": 3.967902020526797e-05,
+      "loss": 0.1272,
+      "step": 630
+    },
+    {
+      "epoch": 2.2105263157894735,
+      "eval_loss": 0.11299394816160202,
+      "eval_runtime": 25.0837,
+      "eval_samples_per_second": 4.784,
+      "eval_steps_per_second": 4.784,
+      "step": 630
+    },
+    {
+      "epoch": 2.245614035087719,
+      "grad_norm": 0.08707338571548462,
+      "learning_rate": 3.647189538847432e-05,
+      "loss": 0.1212,
+      "step": 640
+    },
+    {
+      "epoch": 2.280701754385965,
+      "grad_norm": 0.09840196371078491,
+      "learning_rate": 3.337078196957647e-05,
+      "loss": 0.1137,
+      "step": 650
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "grad_norm": 0.10066810250282288,
+      "learning_rate": 3.0380854876593723e-05,
+      "loss": 0.1147,
+      "step": 660
+    },
+    {
+      "epoch": 2.3157894736842106,
+      "eval_loss": 0.11169523745775223,
+      "eval_runtime": 24.9457,
+      "eval_samples_per_second": 4.81,
+      "eval_steps_per_second": 4.81,
+      "step": 660
+    },
+    {
+      "epoch": 2.3508771929824563,
+      "grad_norm": 0.11805769056081772,
+      "learning_rate": 2.7507103497336016e-05,
+      "loss": 0.124,
+      "step": 670
+    },
+    {
+      "epoch": 2.3859649122807016,
+      "grad_norm": 0.09834598004817963,
+      "learning_rate": 2.475432335345128e-05,
+      "loss": 0.1269,
+      "step": 680
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "grad_norm": 0.11241532862186432,
+      "learning_rate": 2.212710809798393e-05,
+      "loss": 0.1137,
+      "step": 690
+    },
+    {
+      "epoch": 2.4210526315789473,
+      "eval_loss": 0.11132458597421646,
+      "eval_runtime": 24.998,
+      "eval_samples_per_second": 4.8,
+      "eval_steps_per_second": 4.8,
+      "step": 690
+    },
+    {
+      "epoch": 2.456140350877193,
+      "grad_norm": 0.10056956857442856,
+      "learning_rate": 1.9629841849797736e-05,
+      "loss": 0.1151,
+      "step": 700
+    },
+    {
+      "epoch": 2.4912280701754383,
+      "grad_norm": 0.09482597559690475,
+      "learning_rate": 1.7266691877655127e-05,
+      "loss": 0.1091,
+      "step": 710
+    },
+    {
+      "epoch": 2.526315789473684,
+      "grad_norm": 0.11021561920642853,
+      "learning_rate": 1.5041601646161585e-05,
+      "loss": 0.1225,
+      "step": 720
+    },
+    {
+      "epoch": 2.526315789473684,
+      "eval_loss": 0.11140093952417374,
+      "eval_runtime": 25.0288,
+      "eval_samples_per_second": 4.794,
+      "eval_steps_per_second": 4.794,
+      "step": 720
+    },
+    {
+      "epoch": 2.56140350877193,
+      "grad_norm": 0.09573051333427429,
+      "learning_rate": 1.295828423517874e-05,
+      "loss": 0.1124,
+      "step": 730
+    },
+    {
+      "epoch": 2.5964912280701755,
+      "grad_norm": 0.1159501001238823,
+      "learning_rate": 1.1020216143688444e-05,
+      "loss": 0.1181,
+      "step": 740
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.09099686145782471,
+      "learning_rate": 9.230631488446639e-06,
+      "loss": 0.1185,
+      "step": 750
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "eval_loss": 0.11138518154621124,
+      "eval_runtime": 24.9674,
+      "eval_samples_per_second": 4.806,
+      "eval_steps_per_second": 4.806,
+      "step": 750
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.10761657357215881,
+      "learning_rate": 7.592516607108324e-06,
+      "loss": 0.1131,
+      "step": 760
+    },
+    {
+      "epoch": 2.7017543859649122,
+      "grad_norm": 0.11243995279073715,
+      "learning_rate": 6.108605074829709e-06,
+      "loss": 0.1178,
+      "step": 770
+    },
+    {
+      "epoch": 2.736842105263158,
+      "grad_norm": 0.07883230596780777,
+      "learning_rate": 4.781373142663004e-06,
+      "loss": 0.1095,
+      "step": 780
+    },
+    {
+      "epoch": 2.736842105263158,
+      "eval_loss": 0.11120390146970749,
+      "eval_runtime": 24.9973,
+      "eval_samples_per_second": 4.801,
+      "eval_steps_per_second": 4.801,
+      "step": 780
+    },
+    {
+      "epoch": 2.7719298245614032,
+      "grad_norm": 0.11856161803007126,
+      "learning_rate": 3.613035605356463e-06,
+      "loss": 0.1148,
+      "step": 790
+    },
+    {
+      "epoch": 2.807017543859649,
+      "grad_norm": 0.08602704107761383,
+      "learning_rate": 2.6055421054549613e-06,
+      "loss": 0.1095,
+      "step": 800
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "grad_norm": 0.0988084003329277,
+      "learning_rate": 1.7605738798684768e-06,
+      "loss": 0.1132,
+      "step": 810
+    },
+    {
+      "epoch": 2.8421052631578947,
+      "eval_loss": 0.11113225668668747,
+      "eval_runtime": 24.9096,
+      "eval_samples_per_second": 4.817,
+      "eval_steps_per_second": 4.817,
+      "step": 810
+    },
+    {
+      "epoch": 2.8771929824561404,
+      "grad_norm": 0.10732480138540268,
+      "learning_rate": 1.0795409543379097e-06,
+      "loss": 0.1219,
+      "step": 820
+    },
+    {
+      "epoch": 2.912280701754386,
+      "grad_norm": 0.11461273580789566,
+      "learning_rate": 5.635797904795847e-07,
+      "loss": 0.1167,
+      "step": 830
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "grad_norm": 0.1043296605348587,
+      "learning_rate": 2.13551389335076e-07,
+      "loss": 0.115,
+      "step": 840
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "eval_loss": 0.11119555681943893,
+      "eval_runtime": 25.0035,
+      "eval_samples_per_second": 4.799,
+      "eval_steps_per_second": 4.799,
+      "step": 840
+    },
+    {
+      "epoch": 2.982456140350877,
+      "grad_norm": 0.11734732985496521,
+      "learning_rate": 3.003985459101299e-08,
+      "loss": 0.1228,
+      "step": 850
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 855,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 1.1985551891035546e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-855/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:575c8b2166a905c3c64fc6f7849aaefacfddb90adb2a255f96969649f334dd0d
+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:a5722c06d9edcc506bc885144d04f57268f00bc1c8a06a29cfa4d63155c93f3f
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ffe0a3d86e4a1fd38abbac9f1eb219f647cf89821f07aab20c1832d221219b
+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
+}