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-806/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": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_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 sha256:8ad0b7969ec0451f276f34b67b3c1e69629d410b8963f3dd877d4cc23726a7b7
+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": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_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 sha256:12f44d56100b8a3d46731b0146c7cbe7406cc87c120763fd9b51e7ab52185379
+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 sha256:8404a9e5b417536c3beecf042c6b6b1f93db263ee0ed98fde0a7e43429e69707
+size 1057397963

checkpoint-800/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2dc3738cb4b0a71f01d20dd1bb37ae67d81b796bac24651ce577b5c57c6498c
+size 14645

checkpoint-800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:264208c1635c1ff832ee4174664dd536b20c345bd337b7c21651380cb47692f8
+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": 1.9860291834833903,
+  "eval_steps": 30,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024837007140639553,
+      "grad_norm": 5.117508411407471,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 2.4928,
+      "step": 10
+    },
+    {
+      "epoch": 0.04967401428127911,
+      "grad_norm": 0.6627324223518372,
+      "learning_rate": 4.691358024691358e-05,
+      "loss": 0.8895,
+      "step": 20
+    },
+    {
+      "epoch": 0.07451102142191866,
+      "grad_norm": 0.7255606651306152,
+      "learning_rate": 7.160493827160494e-05,
+      "loss": 0.5422,
+      "step": 30
+    },
+    {
+      "epoch": 0.07451102142191866,
+      "eval_loss": 0.47528332471847534,
+      "eval_runtime": 39.0867,
+      "eval_samples_per_second": 4.349,
+      "eval_steps_per_second": 4.349,
+      "step": 30
+    },
+    {
+      "epoch": 0.09934802856255821,
+      "grad_norm": 0.5475447773933411,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.3958,
+      "step": 40
+    },
+    {
+      "epoch": 0.12418503570319776,
+      "grad_norm": 0.6105160713195801,
+      "learning_rate": 0.00012098765432098766,
+      "loss": 0.302,
+      "step": 50
+    },
+    {
+      "epoch": 0.14902204284383733,
+      "grad_norm": 0.4131757915019989,
+      "learning_rate": 0.00014567901234567902,
+      "loss": 0.2557,
+      "step": 60
+    },
+    {
+      "epoch": 0.14902204284383733,
+      "eval_loss": 0.25145411491394043,
+      "eval_runtime": 38.8069,
+      "eval_samples_per_second": 4.381,
+      "eval_steps_per_second": 4.381,
+      "step": 60
+    },
+    {
+      "epoch": 0.17385904998447688,
+      "grad_norm": 0.41176778078079224,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.2326,
+      "step": 70
+    },
+    {
+      "epoch": 0.19869605712511643,
+      "grad_norm": 0.7748426795005798,
+      "learning_rate": 0.00019506172839506175,
+      "loss": 0.2114,
+      "step": 80
+    },
+    {
+      "epoch": 0.22353306426575598,
+      "grad_norm": 0.3699084520339966,
+      "learning_rate": 0.0001999399199592735,
+      "loss": 0.1877,
+      "step": 90
+    },
+    {
+      "epoch": 0.22353306426575598,
+      "eval_loss": 0.18242689967155457,
+      "eval_runtime": 38.7296,
+      "eval_samples_per_second": 4.389,
+      "eval_steps_per_second": 4.389,
+      "step": 90
+    },
+    {
+      "epoch": 0.24837007140639553,
+      "grad_norm": 0.2580717206001282,
+      "learning_rate": 0.00019969596851644327,
+      "loss": 0.1805,
+      "step": 100
+    },
+    {
+      "epoch": 0.2732070785470351,
+      "grad_norm": 0.5501871109008789,
+      "learning_rate": 0.00019926484830975113,
+      "loss": 0.1565,
+      "step": 110
+    },
+    {
+      "epoch": 0.29804408568767465,
+      "grad_norm": 0.7400328516960144,
+      "learning_rate": 0.0001986473687223383,
+      "loss": 0.1597,
+      "step": 120
+    },
+    {
+      "epoch": 0.29804408568767465,
+      "eval_loss": 0.15180540084838867,
+      "eval_runtime": 38.7238,
+      "eval_samples_per_second": 4.39,
+      "eval_steps_per_second": 4.39,
+      "step": 120
+    },
+    {
+      "epoch": 0.3228810928283142,
+      "grad_norm": 0.24620673060417175,
+      "learning_rate": 0.00019784468900761095,
+      "loss": 0.1635,
+      "step": 130
+    },
+    {
+      "epoch": 0.34771809996895375,
+      "grad_norm": 0.3211805522441864,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.1597,
+      "step": 140
+    },
+    {
+      "epoch": 0.3725551071095933,
+      "grad_norm": 0.24230831861495972,
+      "learning_rate": 0.00019569010185014062,
+      "loss": 0.1477,
+      "step": 150
+    },
+    {
+      "epoch": 0.3725551071095933,
+      "eval_loss": 0.14081448316574097,
+      "eval_runtime": 38.5399,
+      "eval_samples_per_second": 4.411,
+      "eval_steps_per_second": 4.411,
+      "step": 150
+    },
+    {
+      "epoch": 0.39739211425023285,
+      "grad_norm": 0.18681883811950684,
+      "learning_rate": 0.00019434223941965738,
+      "loss": 0.1519,
+      "step": 160
+    },
+    {
+      "epoch": 0.4222291213908724,
+      "grad_norm": 0.14613085985183716,
+      "learning_rate": 0.00019281725929229127,
+      "loss": 0.1438,
+      "step": 170
+    },
+    {
+      "epoch": 0.44706612853151195,
+      "grad_norm": 0.20696213841438293,
+      "learning_rate": 0.00019111802445888936,
+      "loss": 0.1531,
+      "step": 180
+    },
+    {
+      "epoch": 0.44706612853151195,
+      "eval_loss": 0.13454553484916687,
+      "eval_runtime": 38.6056,
+      "eval_samples_per_second": 4.404,
+      "eval_steps_per_second": 4.404,
+      "step": 180
+    },
+    {
+      "epoch": 0.47190313567215153,
+      "grad_norm": 0.5880604982376099,
+      "learning_rate": 0.00018924772505530174,
+      "loss": 0.1438,
+      "step": 190
+    },
+    {
+      "epoch": 0.49674014281279105,
+      "grad_norm": 0.16696172952651978,
+      "learning_rate": 0.000187209872373235,
+      "loss": 0.1447,
+      "step": 200
+    },
+    {
+      "epoch": 0.5215771499534306,
+      "grad_norm": 0.16896992921829224,
+      "learning_rate": 0.00018500829226816853,
+      "loss": 0.1431,
+      "step": 210
+    },
+    {
+      "epoch": 0.5215771499534306,
+      "eval_loss": 0.1339797079563141,
+      "eval_runtime": 38.4777,
+      "eval_samples_per_second": 4.418,
+      "eval_steps_per_second": 4.418,
+      "step": 210
+    },
+    {
+      "epoch": 0.5464141570940702,
+      "grad_norm": 0.18485017120838165,
+      "learning_rate": 0.0001826471179767111,
+      "loss": 0.1422,
+      "step": 220
+    },
+    {
+      "epoch": 0.5712511642347097,
+      "grad_norm": 0.32310935854911804,
+      "learning_rate": 0.0001801307823568806,
+      "loss": 0.1464,
+      "step": 230
+    },
+    {
+      "epoch": 0.5960881713753493,
+      "grad_norm": 0.14644373953342438,
+      "learning_rate": 0.00017746400956587653,
+      "loss": 0.1518,
+      "step": 240
+    },
+    {
+      "epoch": 0.5960881713753493,
+      "eval_loss": 0.13374409079551697,
+      "eval_runtime": 38.5238,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 4.413,
+      "step": 240
+    },
+    {
+      "epoch": 0.6209251785159888,
+      "grad_norm": 0.12835970520973206,
+      "learning_rate": 0.00017465180619096832,
+      "loss": 0.1397,
+      "step": 250
+    },
+    {
+      "epoch": 0.6457621856566284,
+      "grad_norm": 0.12649641931056976,
+      "learning_rate": 0.00017169945185015106,
+      "loss": 0.1391,
+      "step": 260
+    },
+    {
+      "epoch": 0.670599192797268,
+      "grad_norm": 0.11043677479028702,
+      "learning_rate": 0.00016861248928021411,
+      "loss": 0.1435,
+      "step": 270
+    },
+    {
+      "epoch": 0.670599192797268,
+      "eval_loss": 0.1273789405822754,
+      "eval_runtime": 38.542,
+      "eval_samples_per_second": 4.411,
+      "eval_steps_per_second": 4.411,
+      "step": 270
+    },
+    {
+      "epoch": 0.6954361999379075,
+      "grad_norm": 0.1751105934381485,
+      "learning_rate": 0.00016539671393083215,
+      "loss": 0.1305,
+      "step": 280
+    },
+    {
+      "epoch": 0.720273207078547,
+      "grad_norm": 0.143985316157341,
+      "learning_rate": 0.00016205816308421386,
+      "loss": 0.1364,
+      "step": 290
+    },
+    {
+      "epoch": 0.7451102142191866,
+      "grad_norm": 0.15529318153858185,
+      "learning_rate": 0.0001586031045207354,
+      "loss": 0.1477,
+      "step": 300
+    },
+    {
+      "epoch": 0.7451102142191866,
+      "eval_loss": 0.12559334933757782,
+      "eval_runtime": 38.8781,
+      "eval_samples_per_second": 4.373,
+      "eval_steps_per_second": 4.373,
+      "step": 300
+    },
+    {
+      "epoch": 0.7699472213598262,
+      "grad_norm": 0.11237718164920807,
+      "learning_rate": 0.00015503802475183773,
+      "loss": 0.1419,
+      "step": 310
+    },
+    {
+      "epoch": 0.7947842285004657,
+      "grad_norm": 0.10596875846385956,
+      "learning_rate": 0.00015136961684227904,
+      "loss": 0.1403,
+      "step": 320
+    },
+    {
+      "epoch": 0.8196212356411052,
+      "grad_norm": 0.1084856167435646,
+      "learning_rate": 0.00014760476784460514,
+      "loss": 0.1446,
+      "step": 330
+    },
+    {
+      "epoch": 0.8196212356411052,
+      "eval_loss": 0.12481025606393814,
+      "eval_runtime": 38.7198,
+      "eval_samples_per_second": 4.391,
+      "eval_steps_per_second": 4.391,
+      "step": 330
+    },
+    {
+      "epoch": 0.8444582427817448,
+      "grad_norm": 0.11786038428544998,
+      "learning_rate": 0.0001437505458694277,
+      "loss": 0.1389,
+      "step": 340
+    },
+    {
+      "epoch": 0.8692952499223844,
+      "grad_norm": 0.1086837649345398,
+      "learning_rate": 0.00013981418681578546,
+      "loss": 0.1317,
+      "step": 350
+    },
+    {
+      "epoch": 0.8941322570630239,
+      "grad_norm": 0.09851235896348953,
+      "learning_rate": 0.0001358030807864995,
+      "loss": 0.1311,
+      "step": 360
+    },
+    {
+      "epoch": 0.8941322570630239,
+      "eval_loss": 0.12259310483932495,
+      "eval_runtime": 38.9167,
+      "eval_samples_per_second": 4.368,
+      "eval_steps_per_second": 4.368,
+      "step": 360
+    },
+    {
+      "epoch": 0.9189692642036634,
+      "grad_norm": 0.11010836809873581,
+      "learning_rate": 0.00013172475821402748,
+      "loss": 0.1455,
+      "step": 370
+    },
+    {
+      "epoch": 0.9438062713443031,
+      "grad_norm": 0.1031259298324585,
+      "learning_rate": 0.00012758687572286367,
+      "loss": 0.133,
+      "step": 380
+    },
+    {
+      "epoch": 0.9686432784849426,
+      "grad_norm": 0.2367333620786667,
+      "learning_rate": 0.00012339720175502642,
+      "loss": 0.1409,
+      "step": 390
+    },
+    {
+      "epoch": 0.9686432784849426,
+      "eval_loss": 0.1259995847940445,
+      "eval_runtime": 38.8274,
+      "eval_samples_per_second": 4.378,
+      "eval_steps_per_second": 4.378,
+      "step": 390
+    },
+    {
+      "epoch": 0.9934802856255821,
+      "grad_norm": 0.12191720306873322,
+      "learning_rate": 0.0001191636019856198,
+      "loss": 0.1296,
+      "step": 400
+    },
+    {
+      "epoch": 1.0173859049984477,
+      "grad_norm": 0.17330284416675568,
+      "learning_rate": 0.00011489402455585076,
+      "loss": 0.1363,
+      "step": 410
+    },
+    {
+      "epoch": 1.0422229121390871,
+      "grad_norm": 0.11796925961971283,
+      "learning_rate": 0.00011059648515122424,
+      "loss": 0.1358,
+      "step": 420
+    },
+    {
+      "epoch": 1.0422229121390871,
+      "eval_loss": 0.12484858185052872,
+      "eval_runtime": 39.2153,
+      "eval_samples_per_second": 4.335,
+      "eval_steps_per_second": 4.335,
+      "step": 420
+    },
+    {
+      "epoch": 1.0670599192797268,
+      "grad_norm": 0.09223978221416473,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.1336,
+      "step": 430
+    },
+    {
+      "epoch": 1.0918969264203664,
+      "grad_norm": 0.08990605920553207,
+      "learning_rate": 0.00010194983049068212,
+      "loss": 0.1325,
+      "step": 440
+    },
+    {
+      "epoch": 1.1167339335610058,
+      "grad_norm": 0.1788116693496704,
+      "learning_rate": 9.76169484254204e-05,
+      "loss": 0.1203,
+      "step": 450
+    },
+    {
+      "epoch": 1.1167339335610058,
+      "eval_loss": 0.12273622304201126,
+      "eval_runtime": 38.9668,
+      "eval_samples_per_second": 4.363,
+      "eval_steps_per_second": 4.363,
+      "step": 450
+    },
+    {
+      "epoch": 1.1415709407016454,
+      "grad_norm": 0.09232629090547562,
+      "learning_rate": 9.328854029048984e-05,
+      "loss": 0.1303,
+      "step": 460
+    },
+    {
+      "epoch": 1.166407947842285,
+      "grad_norm": 0.10365134477615356,
+      "learning_rate": 8.897273221989714e-05,
+      "loss": 0.1315,
+      "step": 470
+    },
+    {
+      "epoch": 1.1912449549829245,
+      "grad_norm": 0.08306622505187988,
+      "learning_rate": 8.467762669234495e-05,
+      "loss": 0.1298,
+      "step": 480
+    },
+    {
+      "epoch": 1.1912449549829245,
+      "eval_loss": 0.12196367979049683,
+      "eval_runtime": 39.0957,
+      "eval_samples_per_second": 4.348,
+      "eval_steps_per_second": 4.348,
+      "step": 480
+    },
+    {
+      "epoch": 1.2160819621235641,
+      "grad_norm": 0.11125741899013519,
+      "learning_rate": 8.041128731967444e-05,
+      "loss": 0.1354,
+      "step": 490
+    },
+    {
+      "epoch": 1.2409189692642038,
+      "grad_norm": 0.09507475048303604,
+      "learning_rate": 7.61817237082768e-05,
+      "loss": 0.1325,
+      "step": 500
+    },
+    {
+      "epoch": 1.2657559764048432,
+      "grad_norm": 0.10722286999225616,
+      "learning_rate": 7.199687642189387e-05,
+      "loss": 0.1252,
+      "step": 510
+    },
+    {
+      "epoch": 1.2657559764048432,
+      "eval_loss": 0.12068262696266174,
+      "eval_runtime": 38.82,
+      "eval_samples_per_second": 4.379,
+      "eval_steps_per_second": 4.379,
+      "step": 510
+    },
+    {
+      "epoch": 1.2905929835454828,
+      "grad_norm": 0.10612589865922928,
+      "learning_rate": 6.786460207403978e-05,
+      "loss": 0.1298,
+      "step": 520
+    },
+    {
+      "epoch": 1.3154299906861224,
+      "grad_norm": 0.08328951150178909,
+      "learning_rate": 6.379265857802969e-05,
+      "loss": 0.1321,
+      "step": 530
+    },
+    {
+      "epoch": 1.3402669978267618,
+      "grad_norm": 0.08099208027124405,
+      "learning_rate": 5.9788690582308404e-05,
+      "loss": 0.13,
+      "step": 540
+    },
+    {
+      "epoch": 1.3402669978267618,
+      "eval_loss": 0.120365209877491,
+      "eval_runtime": 39.0465,
+      "eval_samples_per_second": 4.354,
+      "eval_steps_per_second": 4.354,
+      "step": 540
+    },
+    {
+      "epoch": 1.3651040049674015,
+      "grad_norm": 0.11394084990024567,
+      "learning_rate": 5.586021511842136e-05,
+      "loss": 0.1273,
+      "step": 550
+    },
+    {
+      "epoch": 1.389941012108041,
+      "grad_norm": 0.10131323337554932,
+      "learning_rate": 5.201460748857369e-05,
+      "loss": 0.1308,
+      "step": 560
+    },
+    {
+      "epoch": 1.4147780192486805,
+      "grad_norm": 0.09320731461048126,
+      "learning_rate": 4.8259087419270756e-05,
+      "loss": 0.1302,
+      "step": 570
+    },
+    {
+      "epoch": 1.4147780192486805,
+      "eval_loss": 0.12034006416797638,
+      "eval_runtime": 39.1366,
+      "eval_samples_per_second": 4.344,
+      "eval_steps_per_second": 4.344,
+      "step": 570
+    },
+    {
+      "epoch": 1.4396150263893202,
+      "grad_norm": 0.08965238928794861,
+      "learning_rate": 4.460070550703612e-05,
+      "loss": 0.1331,
+      "step": 580
+    },
+    {
+      "epoch": 1.4644520335299596,
+      "grad_norm": 0.08468832820653915,
+      "learning_rate": 4.1046329981653086e-05,
+      "loss": 0.1275,
+      "step": 590
+    },
+    {
+      "epoch": 1.4892890406705992,
+      "grad_norm": 0.0952211394906044,
+      "learning_rate": 3.7602633811781166e-05,
+      "loss": 0.1299,
+      "step": 600
+    },
+    {
+      "epoch": 1.4892890406705992,
+      "eval_loss": 0.11901157349348068,
+      "eval_runtime": 39.4945,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 4.304,
+      "step": 600
+    },
+    {
+      "epoch": 1.5141260478112386,
+      "grad_norm": 0.12877437472343445,
+      "learning_rate": 3.4276082177154535e-05,
+      "loss": 0.1301,
+      "step": 610
+    },
+    {
+      "epoch": 1.5389630549518785,
+      "grad_norm": 0.10761962831020355,
+      "learning_rate": 3.1072920330882647e-05,
+      "loss": 0.1283,
+      "step": 620
+    },
+    {
+      "epoch": 1.5638000620925179,
+      "grad_norm": 0.08870566636323929,
+      "learning_rate": 2.7999161874640022e-05,
+      "loss": 0.1295,
+      "step": 630
+    },
+    {
+      "epoch": 1.5638000620925179,
+      "eval_loss": 0.11877088993787766,
+      "eval_runtime": 38.9653,
+      "eval_samples_per_second": 4.363,
+      "eval_steps_per_second": 4.363,
+      "step": 630
+    },
+    {
+      "epoch": 1.5886370692331573,
+      "grad_norm": 0.09591209143400192,
+      "learning_rate": 2.506057746875753e-05,
+      "loss": 0.1301,
+      "step": 640
+    },
+    {
+      "epoch": 1.613474076373797,
+      "grad_norm": 0.09527405351400375,
+      "learning_rate": 2.226268399841055e-05,
+      "loss": 0.124,
+      "step": 650
+    },
+    {
+      "epoch": 1.6383110835144366,
+      "grad_norm": 0.08632130175828934,
+      "learning_rate": 1.9610734216243522e-05,
+      "loss": 0.1168,
+      "step": 660
+    },
+    {
+      "epoch": 1.6383110835144366,
+      "eval_loss": 0.11833836883306503,
+      "eval_runtime": 39.1165,
+      "eval_samples_per_second": 4.346,
+      "eval_steps_per_second": 4.346,
+      "step": 660
+    },
+    {
+      "epoch": 1.663148090655076,
+      "grad_norm": 0.07494412362575531,
+      "learning_rate": 1.710970688087561e-05,
+      "loss": 0.1291,
+      "step": 670
+    },
+    {
+      "epoch": 1.6879850977957156,
+      "grad_norm": 0.0977696105837822,
+      "learning_rate": 1.4764297409801764e-05,
+      "loss": 0.1296,
+      "step": 680
+    },
+    {
+      "epoch": 1.7128221049363552,
+      "grad_norm": 0.10850168764591217,
+      "learning_rate": 1.2578909064236889e-05,
+      "loss": 0.1284,
+      "step": 690
+    },
+    {
+      "epoch": 1.7128221049363552,
+      "eval_loss": 0.11817550659179688,
+      "eval_runtime": 39.105,
+      "eval_samples_per_second": 4.347,
+      "eval_steps_per_second": 4.347,
+      "step": 690
+    },
+    {
+      "epoch": 1.7376591120769946,
+      "grad_norm": 0.07101628929376602,
+      "learning_rate": 1.0557644682453039e-05,
+      "loss": 0.1293,
+      "step": 700
+    },
+    {
+      "epoch": 1.7624961192176343,
+      "grad_norm": 0.09535755962133408,
+      "learning_rate": 8.70429897712921e-06,
+      "loss": 0.1235,
+      "step": 710
+    },
+    {
+      "epoch": 1.787333126358274,
+      "grad_norm": 0.08710920065641403,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.1355,
+      "step": 720
+    },
+    {
+      "epoch": 1.787333126358274,
+      "eval_loss": 0.11791054159402847,
+      "eval_runtime": 39.5267,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 4.301,
+      "step": 720
+    },
+    {
+      "epoch": 1.8121701334989133,
+      "grad_norm": 0.10632126033306122,
+      "learning_rate": 5.51495966540182e-06,
+      "loss": 0.128,
+      "step": 730
+    },
+    {
+      "epoch": 1.837007140639553,
+      "grad_norm": 0.10600100457668304,
+      "learning_rate": 4.1849537103084925e-06,
+      "loss": 0.1291,
+      "step": 740
+    },
+    {
+      "epoch": 1.8618441477801926,
+      "grad_norm": 0.09718228131532669,
+      "learning_rate": 3.034830493105956e-06,
+      "loss": 0.1295,
+      "step": 750
+    },
+    {
+      "epoch": 1.8618441477801926,
+      "eval_loss": 0.11791868507862091,
+      "eval_runtime": 39.1705,
+      "eval_samples_per_second": 4.34,
+      "eval_steps_per_second": 4.34,
+      "step": 750
+    },
+    {
+      "epoch": 1.886681154920832,
+      "grad_norm": 0.09879771620035172,
+      "learning_rate": 2.066749249960498e-06,
+      "loss": 0.1248,
+      "step": 760
+    },
+    {
+      "epoch": 1.9115181620614716,
+      "grad_norm": 0.08744484931230545,
+      "learning_rate": 1.2825274522532792e-06,
+      "loss": 0.1219,
+      "step": 770
+    },
+    {
+      "epoch": 1.9363551692021113,
+      "grad_norm": 0.09460227936506271,
+      "learning_rate": 6.836373944677954e-07,
+      "loss": 0.1306,
+      "step": 780
+    },
+    {
+      "epoch": 1.9363551692021113,
+      "eval_loss": 0.11797964572906494,
+      "eval_runtime": 39.3267,
+      "eval_samples_per_second": 4.323,
+      "eval_steps_per_second": 4.323,
+      "step": 780
+    },
+    {
+      "epoch": 1.9611921763427507,
+      "grad_norm": 0.0938316285610199,
+      "learning_rate": 2.712034301107114e-07,
+      "loss": 0.1291,
+      "step": 790
+    },
+    {
+      "epoch": 1.9860291834833903,
+      "grad_norm": 0.09565218538045883,
+      "learning_rate": 4.599986085573882e-08,
+      "loss": 0.1279,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 806,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2428317974302515e+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 sha256:08da2af24e8b5fbc61e2e663b49a3d334a9b3e4bcaacf57c704cdc1efcfa8c49
+size 5777

checkpoint-806/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-806/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": [
+    "gate_proj",
+    "k_proj",
+    "o_proj",
+    "q_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

checkpoint-806/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ad0b7969ec0451f276f34b67b3c1e69629d410b8963f3dd877d4cc23726a7b7
+size 528550256

checkpoint-806/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-806/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-806/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:495f8eee1781156ab0691c518b13726ed7c79c5243d22ca75d398677a1b0d0dd
+size 1057397963

checkpoint-806/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c2dc3738cb4b0a71f01d20dd1bb37ae67d81b796bac24651ce577b5c57c6498c
+size 14645

checkpoint-806/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee26ce7ae23e4db5f1025510dad8673183f41739f48fdf10762710b10f38fea6
+size 1465

checkpoint-806/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-806/tokenizer.json

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

checkpoint-806/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-806/trainer_state.json

@@ -0,0 +1,802 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 30,
+  "global_step": 806,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024837007140639553,
+      "grad_norm": 5.117508411407471,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 2.4928,
+      "step": 10
+    },
+    {
+      "epoch": 0.04967401428127911,
+      "grad_norm": 0.6627324223518372,
+      "learning_rate": 4.691358024691358e-05,
+      "loss": 0.8895,
+      "step": 20
+    },
+    {
+      "epoch": 0.07451102142191866,
+      "grad_norm": 0.7255606651306152,
+      "learning_rate": 7.160493827160494e-05,
+      "loss": 0.5422,
+      "step": 30
+    },
+    {
+      "epoch": 0.07451102142191866,
+      "eval_loss": 0.47528332471847534,
+      "eval_runtime": 39.0867,
+      "eval_samples_per_second": 4.349,
+      "eval_steps_per_second": 4.349,
+      "step": 30
+    },
+    {
+      "epoch": 0.09934802856255821,
+      "grad_norm": 0.5475447773933411,
+      "learning_rate": 9.62962962962963e-05,
+      "loss": 0.3958,
+      "step": 40
+    },
+    {
+      "epoch": 0.12418503570319776,
+      "grad_norm": 0.6105160713195801,
+      "learning_rate": 0.00012098765432098766,
+      "loss": 0.302,
+      "step": 50
+    },
+    {
+      "epoch": 0.14902204284383733,
+      "grad_norm": 0.4131757915019989,
+      "learning_rate": 0.00014567901234567902,
+      "loss": 0.2557,
+      "step": 60
+    },
+    {
+      "epoch": 0.14902204284383733,
+      "eval_loss": 0.25145411491394043,
+      "eval_runtime": 38.8069,
+      "eval_samples_per_second": 4.381,
+      "eval_steps_per_second": 4.381,
+      "step": 60
+    },
+    {
+      "epoch": 0.17385904998447688,
+      "grad_norm": 0.41176778078079224,
+      "learning_rate": 0.00017037037037037037,
+      "loss": 0.2326,
+      "step": 70
+    },
+    {
+      "epoch": 0.19869605712511643,
+      "grad_norm": 0.7748426795005798,
+      "learning_rate": 0.00019506172839506175,
+      "loss": 0.2114,
+      "step": 80
+    },
+    {
+      "epoch": 0.22353306426575598,
+      "grad_norm": 0.3699084520339966,
+      "learning_rate": 0.0001999399199592735,
+      "loss": 0.1877,
+      "step": 90
+    },
+    {
+      "epoch": 0.22353306426575598,
+      "eval_loss": 0.18242689967155457,
+      "eval_runtime": 38.7296,
+      "eval_samples_per_second": 4.389,
+      "eval_steps_per_second": 4.389,
+      "step": 90
+    },
+    {
+      "epoch": 0.24837007140639553,
+      "grad_norm": 0.2580717206001282,
+      "learning_rate": 0.00019969596851644327,
+      "loss": 0.1805,
+      "step": 100
+    },
+    {
+      "epoch": 0.2732070785470351,
+      "grad_norm": 0.5501871109008789,
+      "learning_rate": 0.00019926484830975113,
+      "loss": 0.1565,
+      "step": 110
+    },
+    {
+      "epoch": 0.29804408568767465,
+      "grad_norm": 0.7400328516960144,
+      "learning_rate": 0.0001986473687223383,
+      "loss": 0.1597,
+      "step": 120
+    },
+    {
+      "epoch": 0.29804408568767465,
+      "eval_loss": 0.15180540084838867,
+      "eval_runtime": 38.7238,
+      "eval_samples_per_second": 4.39,
+      "eval_steps_per_second": 4.39,
+      "step": 120
+    },
+    {
+      "epoch": 0.3228810928283142,
+      "grad_norm": 0.24620673060417175,
+      "learning_rate": 0.00019784468900761095,
+      "loss": 0.1635,
+      "step": 130
+    },
+    {
+      "epoch": 0.34771809996895375,
+      "grad_norm": 0.3211805522441864,
+      "learning_rate": 0.0001968583161128631,
+      "loss": 0.1597,
+      "step": 140
+    },
+    {
+      "epoch": 0.3725551071095933,
+      "grad_norm": 0.24230831861495972,
+      "learning_rate": 0.00019569010185014062,
+      "loss": 0.1477,
+      "step": 150
+    },
+    {
+      "epoch": 0.3725551071095933,
+      "eval_loss": 0.14081448316574097,
+      "eval_runtime": 38.5399,
+      "eval_samples_per_second": 4.411,
+      "eval_steps_per_second": 4.411,
+      "step": 150
+    },
+    {
+      "epoch": 0.39739211425023285,
+      "grad_norm": 0.18681883811950684,
+      "learning_rate": 0.00019434223941965738,
+      "loss": 0.1519,
+      "step": 160
+    },
+    {
+      "epoch": 0.4222291213908724,
+      "grad_norm": 0.14613085985183716,
+      "learning_rate": 0.00019281725929229127,
+      "loss": 0.1438,
+      "step": 170
+    },
+    {
+      "epoch": 0.44706612853151195,
+      "grad_norm": 0.20696213841438293,
+      "learning_rate": 0.00019111802445888936,
+      "loss": 0.1531,
+      "step": 180
+    },
+    {
+      "epoch": 0.44706612853151195,
+      "eval_loss": 0.13454553484916687,
+      "eval_runtime": 38.6056,
+      "eval_samples_per_second": 4.404,
+      "eval_steps_per_second": 4.404,
+      "step": 180
+    },
+    {
+      "epoch": 0.47190313567215153,
+      "grad_norm": 0.5880604982376099,
+      "learning_rate": 0.00018924772505530174,
+      "loss": 0.1438,
+      "step": 190
+    },
+    {
+      "epoch": 0.49674014281279105,
+      "grad_norm": 0.16696172952651978,
+      "learning_rate": 0.000187209872373235,
+      "loss": 0.1447,
+      "step": 200
+    },
+    {
+      "epoch": 0.5215771499534306,
+      "grad_norm": 0.16896992921829224,
+      "learning_rate": 0.00018500829226816853,
+      "loss": 0.1431,
+      "step": 210
+    },
+    {
+      "epoch": 0.5215771499534306,
+      "eval_loss": 0.1339797079563141,
+      "eval_runtime": 38.4777,
+      "eval_samples_per_second": 4.418,
+      "eval_steps_per_second": 4.418,
+      "step": 210
+    },
+    {
+      "epoch": 0.5464141570940702,
+      "grad_norm": 0.18485017120838165,
+      "learning_rate": 0.0001826471179767111,
+      "loss": 0.1422,
+      "step": 220
+    },
+    {
+      "epoch": 0.5712511642347097,
+      "grad_norm": 0.32310935854911804,
+      "learning_rate": 0.0001801307823568806,
+      "loss": 0.1464,
+      "step": 230
+    },
+    {
+      "epoch": 0.5960881713753493,
+      "grad_norm": 0.14644373953342438,
+      "learning_rate": 0.00017746400956587653,
+      "loss": 0.1518,
+      "step": 240
+    },
+    {
+      "epoch": 0.5960881713753493,
+      "eval_loss": 0.13374409079551697,
+      "eval_runtime": 38.5238,
+      "eval_samples_per_second": 4.413,
+      "eval_steps_per_second": 4.413,
+      "step": 240
+    },
+    {
+      "epoch": 0.6209251785159888,
+      "grad_norm": 0.12835970520973206,
+      "learning_rate": 0.00017465180619096832,
+      "loss": 0.1397,
+      "step": 250
+    },
+    {
+      "epoch": 0.6457621856566284,
+      "grad_norm": 0.12649641931056976,
+      "learning_rate": 0.00017169945185015106,
+      "loss": 0.1391,
+      "step": 260
+    },
+    {
+      "epoch": 0.670599192797268,
+      "grad_norm": 0.11043677479028702,
+      "learning_rate": 0.00016861248928021411,
+      "loss": 0.1435,
+      "step": 270
+    },
+    {
+      "epoch": 0.670599192797268,
+      "eval_loss": 0.1273789405822754,
+      "eval_runtime": 38.542,
+      "eval_samples_per_second": 4.411,
+      "eval_steps_per_second": 4.411,
+      "step": 270
+    },
+    {
+      "epoch": 0.6954361999379075,
+      "grad_norm": 0.1751105934381485,
+      "learning_rate": 0.00016539671393083215,
+      "loss": 0.1305,
+      "step": 280
+    },
+    {
+      "epoch": 0.720273207078547,
+      "grad_norm": 0.143985316157341,
+      "learning_rate": 0.00016205816308421386,
+      "loss": 0.1364,
+      "step": 290
+    },
+    {
+      "epoch": 0.7451102142191866,
+      "grad_norm": 0.15529318153858185,
+      "learning_rate": 0.0001586031045207354,
+      "loss": 0.1477,
+      "step": 300
+    },
+    {
+      "epoch": 0.7451102142191866,
+      "eval_loss": 0.12559334933757782,
+      "eval_runtime": 38.8781,
+      "eval_samples_per_second": 4.373,
+      "eval_steps_per_second": 4.373,
+      "step": 300
+    },
+    {
+      "epoch": 0.7699472213598262,
+      "grad_norm": 0.11237718164920807,
+      "learning_rate": 0.00015503802475183773,
+      "loss": 0.1419,
+      "step": 310
+    },
+    {
+      "epoch": 0.7947842285004657,
+      "grad_norm": 0.10596875846385956,
+      "learning_rate": 0.00015136961684227904,
+      "loss": 0.1403,
+      "step": 320
+    },
+    {
+      "epoch": 0.8196212356411052,
+      "grad_norm": 0.1084856167435646,
+      "learning_rate": 0.00014760476784460514,
+      "loss": 0.1446,
+      "step": 330
+    },
+    {
+      "epoch": 0.8196212356411052,
+      "eval_loss": 0.12481025606393814,
+      "eval_runtime": 38.7198,
+      "eval_samples_per_second": 4.391,
+      "eval_steps_per_second": 4.391,
+      "step": 330
+    },
+    {
+      "epoch": 0.8444582427817448,
+      "grad_norm": 0.11786038428544998,
+      "learning_rate": 0.0001437505458694277,
+      "loss": 0.1389,
+      "step": 340
+    },
+    {
+      "epoch": 0.8692952499223844,
+      "grad_norm": 0.1086837649345398,
+      "learning_rate": 0.00013981418681578546,
+      "loss": 0.1317,
+      "step": 350
+    },
+    {
+      "epoch": 0.8941322570630239,
+      "grad_norm": 0.09851235896348953,
+      "learning_rate": 0.0001358030807864995,
+      "loss": 0.1311,
+      "step": 360
+    },
+    {
+      "epoch": 0.8941322570630239,
+      "eval_loss": 0.12259310483932495,
+      "eval_runtime": 38.9167,
+      "eval_samples_per_second": 4.368,
+      "eval_steps_per_second": 4.368,
+      "step": 360
+    },
+    {
+      "epoch": 0.9189692642036634,
+      "grad_norm": 0.11010836809873581,
+      "learning_rate": 0.00013172475821402748,
+      "loss": 0.1455,
+      "step": 370
+    },
+    {
+      "epoch": 0.9438062713443031,
+      "grad_norm": 0.1031259298324585,
+      "learning_rate": 0.00012758687572286367,
+      "loss": 0.133,
+      "step": 380
+    },
+    {
+      "epoch": 0.9686432784849426,
+      "grad_norm": 0.2367333620786667,
+      "learning_rate": 0.00012339720175502642,
+      "loss": 0.1409,
+      "step": 390
+    },
+    {
+      "epoch": 0.9686432784849426,
+      "eval_loss": 0.1259995847940445,
+      "eval_runtime": 38.8274,
+      "eval_samples_per_second": 4.378,
+      "eval_steps_per_second": 4.378,
+      "step": 390
+    },
+    {
+      "epoch": 0.9934802856255821,
+      "grad_norm": 0.12191720306873322,
+      "learning_rate": 0.0001191636019856198,
+      "loss": 0.1296,
+      "step": 400
+    },
+    {
+      "epoch": 1.0173859049984477,
+      "grad_norm": 0.17330284416675568,
+      "learning_rate": 0.00011489402455585076,
+      "loss": 0.1363,
+      "step": 410
+    },
+    {
+      "epoch": 1.0422229121390871,
+      "grad_norm": 0.11796925961971283,
+      "learning_rate": 0.00011059648515122424,
+      "loss": 0.1358,
+      "step": 420
+    },
+    {
+      "epoch": 1.0422229121390871,
+      "eval_loss": 0.12484858185052872,
+      "eval_runtime": 39.2153,
+      "eval_samples_per_second": 4.335,
+      "eval_steps_per_second": 4.335,
+      "step": 420
+    },
+    {
+      "epoch": 1.0670599192797268,
+      "grad_norm": 0.09223978221416473,
+      "learning_rate": 0.00010627905195293135,
+      "loss": 0.1336,
+      "step": 430
+    },
+    {
+      "epoch": 1.0918969264203664,
+      "grad_norm": 0.08990605920553207,
+      "learning_rate": 0.00010194983049068212,
+      "loss": 0.1325,
+      "step": 440
+    },
+    {
+      "epoch": 1.1167339335610058,
+      "grad_norm": 0.1788116693496704,
+      "learning_rate": 9.76169484254204e-05,
+      "loss": 0.1203,
+      "step": 450
+    },
+    {
+      "epoch": 1.1167339335610058,
+      "eval_loss": 0.12273622304201126,
+      "eval_runtime": 38.9668,
+      "eval_samples_per_second": 4.363,
+      "eval_steps_per_second": 4.363,
+      "step": 450
+    },
+    {
+      "epoch": 1.1415709407016454,
+      "grad_norm": 0.09232629090547562,
+      "learning_rate": 9.328854029048984e-05,
+      "loss": 0.1303,
+      "step": 460
+    },
+    {
+      "epoch": 1.166407947842285,
+      "grad_norm": 0.10365134477615356,
+      "learning_rate": 8.897273221989714e-05,
+      "loss": 0.1315,
+      "step": 470
+    },
+    {
+      "epoch": 1.1912449549829245,
+      "grad_norm": 0.08306622505187988,
+      "learning_rate": 8.467762669234495e-05,
+      "loss": 0.1298,
+      "step": 480
+    },
+    {
+      "epoch": 1.1912449549829245,
+      "eval_loss": 0.12196367979049683,
+      "eval_runtime": 39.0957,
+      "eval_samples_per_second": 4.348,
+      "eval_steps_per_second": 4.348,
+      "step": 480
+    },
+    {
+      "epoch": 1.2160819621235641,
+      "grad_norm": 0.11125741899013519,
+      "learning_rate": 8.041128731967444e-05,
+      "loss": 0.1354,
+      "step": 490
+    },
+    {
+      "epoch": 1.2409189692642038,
+      "grad_norm": 0.09507475048303604,
+      "learning_rate": 7.61817237082768e-05,
+      "loss": 0.1325,
+      "step": 500
+    },
+    {
+      "epoch": 1.2657559764048432,
+      "grad_norm": 0.10722286999225616,
+      "learning_rate": 7.199687642189387e-05,
+      "loss": 0.1252,
+      "step": 510
+    },
+    {
+      "epoch": 1.2657559764048432,
+      "eval_loss": 0.12068262696266174,
+      "eval_runtime": 38.82,
+      "eval_samples_per_second": 4.379,
+      "eval_steps_per_second": 4.379,
+      "step": 510
+    },
+    {
+      "epoch": 1.2905929835454828,
+      "grad_norm": 0.10612589865922928,
+      "learning_rate": 6.786460207403978e-05,
+      "loss": 0.1298,
+      "step": 520
+    },
+    {
+      "epoch": 1.3154299906861224,
+      "grad_norm": 0.08328951150178909,
+      "learning_rate": 6.379265857802969e-05,
+      "loss": 0.1321,
+      "step": 530
+    },
+    {
+      "epoch": 1.3402669978267618,
+      "grad_norm": 0.08099208027124405,
+      "learning_rate": 5.9788690582308404e-05,
+      "loss": 0.13,
+      "step": 540
+    },
+    {
+      "epoch": 1.3402669978267618,
+      "eval_loss": 0.120365209877491,
+      "eval_runtime": 39.0465,
+      "eval_samples_per_second": 4.354,
+      "eval_steps_per_second": 4.354,
+      "step": 540
+    },
+    {
+      "epoch": 1.3651040049674015,
+      "grad_norm": 0.11394084990024567,
+      "learning_rate": 5.586021511842136e-05,
+      "loss": 0.1273,
+      "step": 550
+    },
+    {
+      "epoch": 1.389941012108041,
+      "grad_norm": 0.10131323337554932,
+      "learning_rate": 5.201460748857369e-05,
+      "loss": 0.1308,
+      "step": 560
+    },
+    {
+      "epoch": 1.4147780192486805,
+      "grad_norm": 0.09320731461048126,
+      "learning_rate": 4.8259087419270756e-05,
+      "loss": 0.1302,
+      "step": 570
+    },
+    {
+      "epoch": 1.4147780192486805,
+      "eval_loss": 0.12034006416797638,
+      "eval_runtime": 39.1366,
+      "eval_samples_per_second": 4.344,
+      "eval_steps_per_second": 4.344,
+      "step": 570
+    },
+    {
+      "epoch": 1.4396150263893202,
+      "grad_norm": 0.08965238928794861,
+      "learning_rate": 4.460070550703612e-05,
+      "loss": 0.1331,
+      "step": 580
+    },
+    {
+      "epoch": 1.4644520335299596,
+      "grad_norm": 0.08468832820653915,
+      "learning_rate": 4.1046329981653086e-05,
+      "loss": 0.1275,
+      "step": 590
+    },
+    {
+      "epoch": 1.4892890406705992,
+      "grad_norm": 0.0952211394906044,
+      "learning_rate": 3.7602633811781166e-05,
+      "loss": 0.1299,
+      "step": 600
+    },
+    {
+      "epoch": 1.4892890406705992,
+      "eval_loss": 0.11901157349348068,
+      "eval_runtime": 39.4945,
+      "eval_samples_per_second": 4.304,
+      "eval_steps_per_second": 4.304,
+      "step": 600
+    },
+    {
+      "epoch": 1.5141260478112386,
+      "grad_norm": 0.12877437472343445,
+      "learning_rate": 3.4276082177154535e-05,
+      "loss": 0.1301,
+      "step": 610
+    },
+    {
+      "epoch": 1.5389630549518785,
+      "grad_norm": 0.10761962831020355,
+      "learning_rate": 3.1072920330882647e-05,
+      "loss": 0.1283,
+      "step": 620
+    },
+    {
+      "epoch": 1.5638000620925179,
+      "grad_norm": 0.08870566636323929,
+      "learning_rate": 2.7999161874640022e-05,
+      "loss": 0.1295,
+      "step": 630
+    },
+    {
+      "epoch": 1.5638000620925179,
+      "eval_loss": 0.11877088993787766,
+      "eval_runtime": 38.9653,
+      "eval_samples_per_second": 4.363,
+      "eval_steps_per_second": 4.363,
+      "step": 630
+    },
+    {
+      "epoch": 1.5886370692331573,
+      "grad_norm": 0.09591209143400192,
+      "learning_rate": 2.506057746875753e-05,
+      "loss": 0.1301,
+      "step": 640
+    },
+    {
+      "epoch": 1.613474076373797,
+      "grad_norm": 0.09527405351400375,
+      "learning_rate": 2.226268399841055e-05,
+      "loss": 0.124,
+      "step": 650
+    },
+    {
+      "epoch": 1.6383110835144366,
+      "grad_norm": 0.08632130175828934,
+      "learning_rate": 1.9610734216243522e-05,
+      "loss": 0.1168,
+      "step": 660
+    },
+    {
+      "epoch": 1.6383110835144366,
+      "eval_loss": 0.11833836883306503,
+      "eval_runtime": 39.1165,
+      "eval_samples_per_second": 4.346,
+      "eval_steps_per_second": 4.346,
+      "step": 660
+    },
+    {
+      "epoch": 1.663148090655076,
+      "grad_norm": 0.07494412362575531,
+      "learning_rate": 1.710970688087561e-05,
+      "loss": 0.1291,
+      "step": 670
+    },
+    {
+      "epoch": 1.6879850977957156,
+      "grad_norm": 0.0977696105837822,
+      "learning_rate": 1.4764297409801764e-05,
+      "loss": 0.1296,
+      "step": 680
+    },
+    {
+      "epoch": 1.7128221049363552,
+      "grad_norm": 0.10850168764591217,
+      "learning_rate": 1.2578909064236889e-05,
+      "loss": 0.1284,
+      "step": 690
+    },
+    {
+      "epoch": 1.7128221049363552,
+      "eval_loss": 0.11817550659179688,
+      "eval_runtime": 39.105,
+      "eval_samples_per_second": 4.347,
+      "eval_steps_per_second": 4.347,
+      "step": 690
+    },
+    {
+      "epoch": 1.7376591120769946,
+      "grad_norm": 0.07101628929376602,
+      "learning_rate": 1.0557644682453039e-05,
+      "loss": 0.1293,
+      "step": 700
+    },
+    {
+      "epoch": 1.7624961192176343,
+      "grad_norm": 0.09535755962133408,
+      "learning_rate": 8.70429897712921e-06,
+      "loss": 0.1235,
+      "step": 710
+    },
+    {
+      "epoch": 1.787333126358274,
+      "grad_norm": 0.08710920065641403,
+      "learning_rate": 7.022351411174866e-06,
+      "loss": 0.1355,
+      "step": 720
+    },
+    {
+      "epoch": 1.787333126358274,
+      "eval_loss": 0.11791054159402847,
+      "eval_runtime": 39.5267,
+      "eval_samples_per_second": 4.301,
+      "eval_steps_per_second": 4.301,
+      "step": 720
+    },
+    {
+      "epoch": 1.8121701334989133,
+      "grad_norm": 0.10632126033306122,
+      "learning_rate": 5.51495966540182e-06,
+      "loss": 0.128,
+      "step": 730
+    },
+    {
+      "epoch": 1.837007140639553,
+      "grad_norm": 0.10600100457668304,
+      "learning_rate": 4.1849537103084925e-06,
+      "loss": 0.1291,
+      "step": 740
+    },
+    {
+      "epoch": 1.8618441477801926,
+      "grad_norm": 0.09718228131532669,
+      "learning_rate": 3.034830493105956e-06,
+      "loss": 0.1295,
+      "step": 750
+    },
+    {
+      "epoch": 1.8618441477801926,
+      "eval_loss": 0.11791868507862091,
+      "eval_runtime": 39.1705,
+      "eval_samples_per_second": 4.34,
+      "eval_steps_per_second": 4.34,
+      "step": 750
+    },
+    {
+      "epoch": 1.886681154920832,
+      "grad_norm": 0.09879771620035172,
+      "learning_rate": 2.066749249960498e-06,
+      "loss": 0.1248,
+      "step": 760
+    },
+    {
+      "epoch": 1.9115181620614716,
+      "grad_norm": 0.08744484931230545,
+      "learning_rate": 1.2825274522532792e-06,
+      "loss": 0.1219,
+      "step": 770
+    },
+    {
+      "epoch": 1.9363551692021113,
+      "grad_norm": 0.09460227936506271,
+      "learning_rate": 6.836373944677954e-07,
+      "loss": 0.1306,
+      "step": 780
+    },
+    {
+      "epoch": 1.9363551692021113,
+      "eval_loss": 0.11797964572906494,
+      "eval_runtime": 39.3267,
+      "eval_samples_per_second": 4.323,
+      "eval_steps_per_second": 4.323,
+      "step": 780
+    },
+    {
+      "epoch": 1.9611921763427507,
+      "grad_norm": 0.0938316285610199,
+      "learning_rate": 2.712034301107114e-07,
+      "loss": 0.1291,
+      "step": 790
+    },
+    {
+      "epoch": 1.9860291834833903,
+      "grad_norm": 0.09565218538045883,
+      "learning_rate": 4.599986085573882e-08,
+      "loss": 0.1279,
+      "step": 800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 806,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.2510107512463155e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-806/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08da2af24e8b5fbc61e2e663b49a3d334a9b3e4bcaacf57c704cdc1efcfa8c49
+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:ba0fd986945d1805aa5cb832894e9d7c6c8269a4f333fab7264a24001950ce10
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0537a979bb5a90b5f382f48c974b5c75372be24d5dd6062c843b59a840feeb3b
+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
+}