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=16)
+
+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: 2048
+- Epochs: 2
+- Learning rate: 2e-05
+- LoRA: r=16, alpha=32
+
+## 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": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_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 sha256:4eb9831d0196d20a3f92f727b3cdb2371f030c5800005f460fb683783ccc2253
+size 132187888

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": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_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 sha256:6c1671645a8ee62d9867c2421b3a1216bd2c12bf30ded5280ccc738053e7b9d8
+size 132187888

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:bf55083a28e748c3306b9b0a7cfd279907b5867c28f1af3e96a1ef1792c16c14
+size 264673227

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 sha256:0e734d99987bf40913ada775d605f73eaaad01f93070871478ff216deb4693a2
+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": 1.9857231533209188,
+  "eval_steps": 30,
+  "global_step": 800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.024829298572315334,
+      "grad_norm": 7.621621131896973,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 2.9278,
+      "step": 10
+    },
+    {
+      "epoch": 0.04965859714463067,
+      "grad_norm": 6.982970237731934,
+      "learning_rate": 4.691358024691358e-06,
+      "loss": 2.7139,
+      "step": 20
+    },
+    {
+      "epoch": 0.074487895716946,
+      "grad_norm": 6.744388580322266,
+      "learning_rate": 7.160493827160494e-06,
+      "loss": 2.5972,
+      "step": 30
+    },
+    {
+      "epoch": 0.074487895716946,
+      "eval_loss": 2.417867660522461,
+      "eval_runtime": 41.6844,
+      "eval_samples_per_second": 4.078,
+      "eval_steps_per_second": 2.039,
+      "step": 30
+    },
+    {
+      "epoch": 0.09931719428926133,
+      "grad_norm": 5.335218906402588,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 2.0383,
+      "step": 40
+    },
+    {
+      "epoch": 0.12414649286157665,
+      "grad_norm": 2.143411874771118,
+      "learning_rate": 1.2098765432098767e-05,
+      "loss": 1.3351,
+      "step": 50
+    },
+    {
+      "epoch": 0.148975791433892,
+      "grad_norm": 0.8463016748428345,
+      "learning_rate": 1.4567901234567903e-05,
+      "loss": 0.9604,
+      "step": 60
+    },
+    {
+      "epoch": 0.148975791433892,
+      "eval_loss": 0.9155183434486389,
+      "eval_runtime": 41.0238,
+      "eval_samples_per_second": 4.144,
+      "eval_steps_per_second": 2.072,
+      "step": 60
+    },
+    {
+      "epoch": 0.17380509000620734,
+      "grad_norm": 0.595171332359314,
+      "learning_rate": 1.7037037037037038e-05,
+      "loss": 0.7447,
+      "step": 70
+    },
+    {
+      "epoch": 0.19863438857852267,
+      "grad_norm": 0.5561698079109192,
+      "learning_rate": 1.9506172839506175e-05,
+      "loss": 0.6919,
+      "step": 80
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.5283234715461731,
+      "learning_rate": 1.999399199592735e-05,
+      "loss": 0.6338,
+      "step": 90
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "eval_loss": 0.6309370994567871,
+      "eval_runtime": 41.0557,
+      "eval_samples_per_second": 4.141,
+      "eval_steps_per_second": 2.07,
+      "step": 90
+    },
+    {
+      "epoch": 0.2482929857231533,
+      "grad_norm": 0.5148088335990906,
+      "learning_rate": 1.996959685164433e-05,
+      "loss": 0.5407,
+      "step": 100
+    },
+    {
+      "epoch": 0.27312228429546864,
+      "grad_norm": 0.7455502152442932,
+      "learning_rate": 1.9926484830975116e-05,
+      "loss": 0.5309,
+      "step": 110
+    },
+    {
+      "epoch": 0.297951582867784,
+      "grad_norm": 0.5646942853927612,
+      "learning_rate": 1.986473687223383e-05,
+      "loss": 0.474,
+      "step": 120
+    },
+    {
+      "epoch": 0.297951582867784,
+      "eval_loss": 0.4833507835865021,
+      "eval_runtime": 41.0325,
+      "eval_samples_per_second": 4.143,
+      "eval_steps_per_second": 2.072,
+      "step": 120
+    },
+    {
+      "epoch": 0.3227808814400993,
+      "grad_norm": 0.5670679211616516,
+      "learning_rate": 1.9784468900761097e-05,
+      "loss": 0.4259,
+      "step": 130
+    },
+    {
+      "epoch": 0.34761018001241467,
+      "grad_norm": 0.7423049211502075,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.412,
+      "step": 140
+    },
+    {
+      "epoch": 0.37243947858473,
+      "grad_norm": 0.6956289410591125,
+      "learning_rate": 1.9569010185014062e-05,
+      "loss": 0.377,
+      "step": 150
+    },
+    {
+      "epoch": 0.37243947858473,
+      "eval_loss": 0.38657110929489136,
+      "eval_runtime": 40.924,
+      "eval_samples_per_second": 4.154,
+      "eval_steps_per_second": 2.077,
+      "step": 150
+    },
+    {
+      "epoch": 0.39726877715704534,
+      "grad_norm": 0.8065354824066162,
+      "learning_rate": 1.9434223941965738e-05,
+      "loss": 0.3361,
+      "step": 160
+    },
+    {
+      "epoch": 0.42209807572936064,
+      "grad_norm": 0.7633559703826904,
+      "learning_rate": 1.9281725929229127e-05,
+      "loss": 0.3348,
+      "step": 170
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.7941247224807739,
+      "learning_rate": 1.9111802445888936e-05,
+      "loss": 0.2987,
+      "step": 180
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "eval_loss": 0.3138997256755829,
+      "eval_runtime": 41.0146,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 2.072,
+      "step": 180
+    },
+    {
+      "epoch": 0.4717566728739913,
+      "grad_norm": 1.1606348752975464,
+      "learning_rate": 1.8924772505530177e-05,
+      "loss": 0.2776,
+      "step": 190
+    },
+    {
+      "epoch": 0.4965859714463066,
+      "grad_norm": 1.1247198581695557,
+      "learning_rate": 1.8720987237323497e-05,
+      "loss": 0.2788,
+      "step": 200
+    },
+    {
+      "epoch": 0.521415270018622,
+      "grad_norm": 0.8864783644676208,
+      "learning_rate": 1.8500829226816853e-05,
+      "loss": 0.2588,
+      "step": 210
+    },
+    {
+      "epoch": 0.521415270018622,
+      "eval_loss": 0.26379144191741943,
+      "eval_runtime": 41.1029,
+      "eval_samples_per_second": 4.136,
+      "eval_steps_per_second": 2.068,
+      "step": 210
+    },
+    {
+      "epoch": 0.5462445685909373,
+      "grad_norm": 0.9481696486473083,
+      "learning_rate": 1.826471179767111e-05,
+      "loss": 0.2359,
+      "step": 220
+    },
+    {
+      "epoch": 0.5710738671632526,
+      "grad_norm": 1.218240737915039,
+      "learning_rate": 1.801307823568806e-05,
+      "loss": 0.2406,
+      "step": 230
+    },
+    {
+      "epoch": 0.595903165735568,
+      "grad_norm": 0.9764422178268433,
+      "learning_rate": 1.7746400956587653e-05,
+      "loss": 0.2241,
+      "step": 240
+    },
+    {
+      "epoch": 0.595903165735568,
+      "eval_loss": 0.2281169593334198,
+      "eval_runtime": 41.0529,
+      "eval_samples_per_second": 4.141,
+      "eval_steps_per_second": 2.071,
+      "step": 240
+    },
+    {
+      "epoch": 0.6207324643078833,
+      "grad_norm": 1.1048036813735962,
+      "learning_rate": 1.7465180619096834e-05,
+      "loss": 0.2199,
+      "step": 250
+    },
+    {
+      "epoch": 0.6455617628801986,
+      "grad_norm": 0.973822832107544,
+      "learning_rate": 1.7169945185015106e-05,
+      "loss": 0.2025,
+      "step": 260
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "grad_norm": 0.758234977722168,
+      "learning_rate": 1.686124892802141e-05,
+      "loss": 0.1932,
+      "step": 270
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "eval_loss": 0.20496493577957153,
+      "eval_runtime": 41.1068,
+      "eval_samples_per_second": 4.136,
+      "eval_steps_per_second": 2.068,
+      "step": 270
+    },
+    {
+      "epoch": 0.6952203600248293,
+      "grad_norm": 1.2279834747314453,
+      "learning_rate": 1.6539671393083218e-05,
+      "loss": 0.1943,
+      "step": 280
+    },
+    {
+      "epoch": 0.7200496585971446,
+      "grad_norm": 0.7134841084480286,
+      "learning_rate": 1.6205816308421386e-05,
+      "loss": 0.1796,
+      "step": 290
+    },
+    {
+      "epoch": 0.74487895716946,
+      "grad_norm": 0.9929455518722534,
+      "learning_rate": 1.586031045207354e-05,
+      "loss": 0.1874,
+      "step": 300
+    },
+    {
+      "epoch": 0.74487895716946,
+      "eval_loss": 0.19150954484939575,
+      "eval_runtime": 41.0713,
+      "eval_samples_per_second": 4.139,
+      "eval_steps_per_second": 2.07,
+      "step": 300
+    },
+    {
+      "epoch": 0.7697082557417753,
+      "grad_norm": 0.8576317429542542,
+      "learning_rate": 1.5503802475183773e-05,
+      "loss": 0.1852,
+      "step": 310
+    },
+    {
+      "epoch": 0.7945375543140907,
+      "grad_norm": 1.0153837203979492,
+      "learning_rate": 1.5136961684227905e-05,
+      "loss": 0.1814,
+      "step": 320
+    },
+    {
+      "epoch": 0.819366852886406,
+      "grad_norm": 0.8694589734077454,
+      "learning_rate": 1.4760476784460514e-05,
+      "loss": 0.1841,
+      "step": 330
+    },
+    {
+      "epoch": 0.819366852886406,
+      "eval_loss": 0.17898762226104736,
+      "eval_runtime": 41.0055,
+      "eval_samples_per_second": 4.146,
+      "eval_steps_per_second": 2.073,
+      "step": 330
+    },
+    {
+      "epoch": 0.8441961514587213,
+      "grad_norm": 1.1345281600952148,
+      "learning_rate": 1.4375054586942771e-05,
+      "loss": 0.1725,
+      "step": 340
+    },
+    {
+      "epoch": 0.8690254500310366,
+      "grad_norm": 1.0460193157196045,
+      "learning_rate": 1.3981418681578546e-05,
+      "loss": 0.1605,
+      "step": 350
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 1.0834463834762573,
+      "learning_rate": 1.3580308078649948e-05,
+      "loss": 0.1652,
+      "step": 360
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "eval_loss": 0.1723683923482895,
+      "eval_runtime": 41.0124,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 2.073,
+      "step": 360
+    },
+    {
+      "epoch": 0.9186840471756673,
+      "grad_norm": 0.7139394283294678,
+      "learning_rate": 1.3172475821402748e-05,
+      "loss": 0.1742,
+      "step": 370
+    },
+    {
+      "epoch": 0.9435133457479826,
+      "grad_norm": 0.8907492756843567,
+      "learning_rate": 1.2758687572286367e-05,
+      "loss": 0.154,
+      "step": 380
+    },
+    {
+      "epoch": 0.9683426443202979,
+      "grad_norm": 0.7731947302818298,
+      "learning_rate": 1.2339720175502643e-05,
+      "loss": 0.1627,
+      "step": 390
+    },
+    {
+      "epoch": 0.9683426443202979,
+      "eval_loss": 0.16476133465766907,
+      "eval_runtime": 41.0851,
+      "eval_samples_per_second": 4.138,
+      "eval_steps_per_second": 2.069,
+      "step": 390
+    },
+    {
+      "epoch": 0.9931719428926132,
+      "grad_norm": 0.8102223873138428,
+      "learning_rate": 1.191636019856198e-05,
+      "loss": 0.1546,
+      "step": 400
+    },
+    {
+      "epoch": 1.0173805090006207,
+      "grad_norm": 0.9590178728103638,
+      "learning_rate": 1.1489402455585078e-05,
+      "loss": 0.1635,
+      "step": 410
+    },
+    {
+      "epoch": 1.042209807572936,
+      "grad_norm": 1.270085334777832,
+      "learning_rate": 1.1059648515122426e-05,
+      "loss": 0.1578,
+      "step": 420
+    },
+    {
+      "epoch": 1.042209807572936,
+      "eval_loss": 0.16066311299800873,
+      "eval_runtime": 41.0613,
+      "eval_samples_per_second": 4.14,
+      "eval_steps_per_second": 2.07,
+      "step": 420
+    },
+    {
+      "epoch": 1.0670391061452513,
+      "grad_norm": 0.7239245176315308,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 0.1509,
+      "step": 430
+    },
+    {
+      "epoch": 1.0918684047175666,
+      "grad_norm": 1.2316311597824097,
+      "learning_rate": 1.0194983049068212e-05,
+      "loss": 0.1493,
+      "step": 440
+    },
+    {
+      "epoch": 1.1166977032898822,
+      "grad_norm": 1.034386157989502,
+      "learning_rate": 9.761694842542042e-06,
+      "loss": 0.1427,
+      "step": 450
+    },
+    {
+      "epoch": 1.1166977032898822,
+      "eval_loss": 0.15721318125724792,
+      "eval_runtime": 40.9543,
+      "eval_samples_per_second": 4.151,
+      "eval_steps_per_second": 2.075,
+      "step": 450
+    },
+    {
+      "epoch": 1.1415270018621975,
+      "grad_norm": 1.0646947622299194,
+      "learning_rate": 9.328854029048985e-06,
+      "loss": 0.1528,
+      "step": 460
+    },
+    {
+      "epoch": 1.1663563004345128,
+      "grad_norm": 0.8461800813674927,
+      "learning_rate": 8.897273221989715e-06,
+      "loss": 0.1505,
+      "step": 470
+    },
+    {
+      "epoch": 1.191185599006828,
+      "grad_norm": 0.6844385862350464,
+      "learning_rate": 8.467762669234496e-06,
+      "loss": 0.1472,
+      "step": 480
+    },
+    {
+      "epoch": 1.191185599006828,
+      "eval_loss": 0.15322649478912354,
+      "eval_runtime": 41.0165,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 2.072,
+      "step": 480
+    },
+    {
+      "epoch": 1.2160148975791434,
+      "grad_norm": 0.8525738716125488,
+      "learning_rate": 8.041128731967445e-06,
+      "loss": 0.1519,
+      "step": 490
+    },
+    {
+      "epoch": 1.2408441961514587,
+      "grad_norm": 0.7886703014373779,
+      "learning_rate": 7.61817237082768e-06,
+      "loss": 0.1519,
+      "step": 500
+    },
+    {
+      "epoch": 1.265673494723774,
+      "grad_norm": 0.7268862128257751,
+      "learning_rate": 7.199687642189388e-06,
+      "loss": 0.142,
+      "step": 510
+    },
+    {
+      "epoch": 1.265673494723774,
+      "eval_loss": 0.1511753350496292,
+      "eval_runtime": 41.1138,
+      "eval_samples_per_second": 4.135,
+      "eval_steps_per_second": 2.067,
+      "step": 510
+    },
+    {
+      "epoch": 1.2905027932960893,
+      "grad_norm": 0.7751151323318481,
+      "learning_rate": 6.7864602074039775e-06,
+      "loss": 0.1471,
+      "step": 520
+    },
+    {
+      "epoch": 1.3153320918684046,
+      "grad_norm": 0.8264702558517456,
+      "learning_rate": 6.37926585780297e-06,
+      "loss": 0.1438,
+      "step": 530
+    },
+    {
+      "epoch": 1.34016139044072,
+      "grad_norm": 0.5469579100608826,
+      "learning_rate": 5.978869058230841e-06,
+      "loss": 0.1493,
+      "step": 540
+    },
+    {
+      "epoch": 1.34016139044072,
+      "eval_loss": 0.1491098254919052,
+      "eval_runtime": 41.1584,
+      "eval_samples_per_second": 4.13,
+      "eval_steps_per_second": 2.065,
+      "step": 540
+    },
+    {
+      "epoch": 1.3649906890130354,
+      "grad_norm": 0.9022724032402039,
+      "learning_rate": 5.586021511842136e-06,
+      "loss": 0.1371,
+      "step": 550
+    },
+    {
+      "epoch": 1.3898199875853507,
+      "grad_norm": 0.8355094790458679,
+      "learning_rate": 5.201460748857369e-06,
+      "loss": 0.1409,
+      "step": 560
+    },
+    {
+      "epoch": 1.414649286157666,
+      "grad_norm": 0.7820518016815186,
+      "learning_rate": 4.825908741927076e-06,
+      "loss": 0.1417,
+      "step": 570
+    },
+    {
+      "epoch": 1.414649286157666,
+      "eval_loss": 0.14838995039463043,
+      "eval_runtime": 41.137,
+      "eval_samples_per_second": 4.133,
+      "eval_steps_per_second": 2.066,
+      "step": 570
+    },
+    {
+      "epoch": 1.4394785847299814,
+      "grad_norm": 0.7794449925422668,
+      "learning_rate": 4.4600705507036125e-06,
+      "loss": 0.1433,
+      "step": 580
+    },
+    {
+      "epoch": 1.4643078833022967,
+      "grad_norm": 0.7465994358062744,
+      "learning_rate": 4.104632998165309e-06,
+      "loss": 0.1445,
+      "step": 590
+    },
+    {
+      "epoch": 1.489137181874612,
+      "grad_norm": 0.8334828615188599,
+      "learning_rate": 3.7602633811781165e-06,
+      "loss": 0.1458,
+      "step": 600
+    },
+    {
+      "epoch": 1.489137181874612,
+      "eval_loss": 0.1462916135787964,
+      "eval_runtime": 41.086,
+      "eval_samples_per_second": 4.138,
+      "eval_steps_per_second": 2.069,
+      "step": 600
+    },
+    {
+      "epoch": 1.5139664804469275,
+      "grad_norm": 0.8605223894119263,
+      "learning_rate": 3.4276082177154536e-06,
+      "loss": 0.1447,
+      "step": 610
+    },
+    {
+      "epoch": 1.5387957790192428,
+      "grad_norm": 0.5568763017654419,
+      "learning_rate": 3.107292033088265e-06,
+      "loss": 0.1384,
+      "step": 620
+    },
+    {
+      "epoch": 1.563625077591558,
+      "grad_norm": 0.7917467951774597,
+      "learning_rate": 2.7999161874640026e-06,
+      "loss": 0.1481,
+      "step": 630
+    },
+    {
+      "epoch": 1.563625077591558,
+      "eval_loss": 0.14508940279483795,
+      "eval_runtime": 41.1236,
+      "eval_samples_per_second": 4.134,
+      "eval_steps_per_second": 2.067,
+      "step": 630
+    },
+    {
+      "epoch": 1.5884543761638734,
+      "grad_norm": 0.7165929675102234,
+      "learning_rate": 2.506057746875753e-06,
+      "loss": 0.1422,
+      "step": 640
+    },
+    {
+      "epoch": 1.6132836747361887,
+      "grad_norm": 0.8443304896354675,
+      "learning_rate": 2.226268399841055e-06,
+      "loss": 0.1406,
+      "step": 650
+    },
+    {
+      "epoch": 1.638112973308504,
+      "grad_norm": 1.0195279121398926,
+      "learning_rate": 1.961073421624352e-06,
+      "loss": 0.1403,
+      "step": 660
+    },
+    {
+      "epoch": 1.638112973308504,
+      "eval_loss": 0.1443227380514145,
+      "eval_runtime": 41.1177,
+      "eval_samples_per_second": 4.134,
+      "eval_steps_per_second": 2.067,
+      "step": 660
+    },
+    {
+      "epoch": 1.6629422718808193,
+      "grad_norm": 0.7534502148628235,
+      "learning_rate": 1.710970688087561e-06,
+      "loss": 0.1398,
+      "step": 670
+    },
+    {
+      "epoch": 1.6877715704531346,
+      "grad_norm": 0.8134092092514038,
+      "learning_rate": 1.4764297409801764e-06,
+      "loss": 0.1377,
+      "step": 680
+    },
+    {
+      "epoch": 1.71260086902545,
+      "grad_norm": 0.7144195437431335,
+      "learning_rate": 1.2578909064236887e-06,
+      "loss": 0.1457,
+      "step": 690
+    },
+    {
+      "epoch": 1.71260086902545,
+      "eval_loss": 0.1440444439649582,
+      "eval_runtime": 41.1467,
+      "eval_samples_per_second": 4.132,
+      "eval_steps_per_second": 2.066,
+      "step": 690
+    },
+    {
+      "epoch": 1.7374301675977653,
+      "grad_norm": 0.5405588150024414,
+      "learning_rate": 1.055764468245304e-06,
+      "loss": 0.1406,
+      "step": 700
+    },
+    {
+      "epoch": 1.7622594661700806,
+      "grad_norm": 0.6921040415763855,
+      "learning_rate": 8.70429897712921e-07,
+      "loss": 0.1366,
+      "step": 710
+    },
+    {
+      "epoch": 1.7870887647423959,
+      "grad_norm": 0.7384780645370483,
+      "learning_rate": 7.022351411174866e-07,
+      "loss": 0.1473,
+      "step": 720
+    },
+    {
+      "epoch": 1.7870887647423959,
+      "eval_loss": 0.1436140090227127,
+      "eval_runtime": 41.1175,
+      "eval_samples_per_second": 4.134,
+      "eval_steps_per_second": 2.067,
+      "step": 720
+    },
+    {
+      "epoch": 1.8119180633147114,
+      "grad_norm": 0.7989315986633301,
+      "learning_rate": 5.51495966540182e-07,
+      "loss": 0.1368,
+      "step": 730
+    },
+    {
+      "epoch": 1.8367473618870267,
+      "grad_norm": 0.8284072875976562,
+      "learning_rate": 4.1849537103084924e-07,
+      "loss": 0.1445,
+      "step": 740
+    },
+    {
+      "epoch": 1.861576660459342,
+      "grad_norm": 0.8498286604881287,
+      "learning_rate": 3.0348304931059556e-07,
+      "loss": 0.1347,
+      "step": 750
+    },
+    {
+      "epoch": 1.861576660459342,
+      "eval_loss": 0.14337773621082306,
+      "eval_runtime": 41.0893,
+      "eval_samples_per_second": 4.137,
+      "eval_steps_per_second": 2.069,
+      "step": 750
+    },
+    {
+      "epoch": 1.8864059590316573,
+      "grad_norm": 0.7535120844841003,
+      "learning_rate": 2.066749249960498e-07,
+      "loss": 0.1422,
+      "step": 760
+    },
+    {
+      "epoch": 1.9112352576039728,
+      "grad_norm": 0.8711650371551514,
+      "learning_rate": 1.2825274522532795e-07,
+      "loss": 0.129,
+      "step": 770
+    },
+    {
+      "epoch": 1.9360645561762881,
+      "grad_norm": 0.751017689704895,
+      "learning_rate": 6.836373944677954e-08,
+      "loss": 0.1423,
+      "step": 780
+    },
+    {
+      "epoch": 1.9360645561762881,
+      "eval_loss": 0.1432679146528244,
+      "eval_runtime": 41.1344,
+      "eval_samples_per_second": 4.133,
+      "eval_steps_per_second": 2.066,
+      "step": 780
+    },
+    {
+      "epoch": 1.9608938547486034,
+      "grad_norm": 0.7860766053199768,
+      "learning_rate": 2.7120343011071138e-08,
+      "loss": 0.1492,
+      "step": 790
+    },
+    {
+      "epoch": 1.9857231533209188,
+      "grad_norm": 0.7165619134902954,
+      "learning_rate": 4.599986085573882e-09,
+      "loss": 0.138,
+      "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": 1.4861828204940288e+17,
+  "train_batch_size": 2,
+  "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:a3bce0aacf508b2c7728234707ab3cef1308e18e4702dace098ab3344ddcef39
+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": 32,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "gate_proj",
+    "down_proj",
+    "q_proj",
+    "up_proj",
+    "k_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 sha256:4eb9831d0196d20a3f92f727b3cdb2371f030c5800005f460fb683783ccc2253
+size 132187888

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:e29deb820028b1d70a0cf9e60ccb1657a95d455c31689200a8c54fae47465d23
+size 264673227

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:d916f80f0e8069fc76004cbbbcd39b2005ae234f3db519f9dd5d6a8545d89e9b
+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": 0.024829298572315334,
+      "grad_norm": 7.621621131896973,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 2.9278,
+      "step": 10
+    },
+    {
+      "epoch": 0.04965859714463067,
+      "grad_norm": 6.982970237731934,
+      "learning_rate": 4.691358024691358e-06,
+      "loss": 2.7139,
+      "step": 20
+    },
+    {
+      "epoch": 0.074487895716946,
+      "grad_norm": 6.744388580322266,
+      "learning_rate": 7.160493827160494e-06,
+      "loss": 2.5972,
+      "step": 30
+    },
+    {
+      "epoch": 0.074487895716946,
+      "eval_loss": 2.417867660522461,
+      "eval_runtime": 41.6844,
+      "eval_samples_per_second": 4.078,
+      "eval_steps_per_second": 2.039,
+      "step": 30
+    },
+    {
+      "epoch": 0.09931719428926133,
+      "grad_norm": 5.335218906402588,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 2.0383,
+      "step": 40
+    },
+    {
+      "epoch": 0.12414649286157665,
+      "grad_norm": 2.143411874771118,
+      "learning_rate": 1.2098765432098767e-05,
+      "loss": 1.3351,
+      "step": 50
+    },
+    {
+      "epoch": 0.148975791433892,
+      "grad_norm": 0.8463016748428345,
+      "learning_rate": 1.4567901234567903e-05,
+      "loss": 0.9604,
+      "step": 60
+    },
+    {
+      "epoch": 0.148975791433892,
+      "eval_loss": 0.9155183434486389,
+      "eval_runtime": 41.0238,
+      "eval_samples_per_second": 4.144,
+      "eval_steps_per_second": 2.072,
+      "step": 60
+    },
+    {
+      "epoch": 0.17380509000620734,
+      "grad_norm": 0.595171332359314,
+      "learning_rate": 1.7037037037037038e-05,
+      "loss": 0.7447,
+      "step": 70
+    },
+    {
+      "epoch": 0.19863438857852267,
+      "grad_norm": 0.5561698079109192,
+      "learning_rate": 1.9506172839506175e-05,
+      "loss": 0.6919,
+      "step": 80
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "grad_norm": 0.5283234715461731,
+      "learning_rate": 1.999399199592735e-05,
+      "loss": 0.6338,
+      "step": 90
+    },
+    {
+      "epoch": 0.22346368715083798,
+      "eval_loss": 0.6309370994567871,
+      "eval_runtime": 41.0557,
+      "eval_samples_per_second": 4.141,
+      "eval_steps_per_second": 2.07,
+      "step": 90
+    },
+    {
+      "epoch": 0.2482929857231533,
+      "grad_norm": 0.5148088335990906,
+      "learning_rate": 1.996959685164433e-05,
+      "loss": 0.5407,
+      "step": 100
+    },
+    {
+      "epoch": 0.27312228429546864,
+      "grad_norm": 0.7455502152442932,
+      "learning_rate": 1.9926484830975116e-05,
+      "loss": 0.5309,
+      "step": 110
+    },
+    {
+      "epoch": 0.297951582867784,
+      "grad_norm": 0.5646942853927612,
+      "learning_rate": 1.986473687223383e-05,
+      "loss": 0.474,
+      "step": 120
+    },
+    {
+      "epoch": 0.297951582867784,
+      "eval_loss": 0.4833507835865021,
+      "eval_runtime": 41.0325,
+      "eval_samples_per_second": 4.143,
+      "eval_steps_per_second": 2.072,
+      "step": 120
+    },
+    {
+      "epoch": 0.3227808814400993,
+      "grad_norm": 0.5670679211616516,
+      "learning_rate": 1.9784468900761097e-05,
+      "loss": 0.4259,
+      "step": 130
+    },
+    {
+      "epoch": 0.34761018001241467,
+      "grad_norm": 0.7423049211502075,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.412,
+      "step": 140
+    },
+    {
+      "epoch": 0.37243947858473,
+      "grad_norm": 0.6956289410591125,
+      "learning_rate": 1.9569010185014062e-05,
+      "loss": 0.377,
+      "step": 150
+    },
+    {
+      "epoch": 0.37243947858473,
+      "eval_loss": 0.38657110929489136,
+      "eval_runtime": 40.924,
+      "eval_samples_per_second": 4.154,
+      "eval_steps_per_second": 2.077,
+      "step": 150
+    },
+    {
+      "epoch": 0.39726877715704534,
+      "grad_norm": 0.8065354824066162,
+      "learning_rate": 1.9434223941965738e-05,
+      "loss": 0.3361,
+      "step": 160
+    },
+    {
+      "epoch": 0.42209807572936064,
+      "grad_norm": 0.7633559703826904,
+      "learning_rate": 1.9281725929229127e-05,
+      "loss": 0.3348,
+      "step": 170
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "grad_norm": 0.7941247224807739,
+      "learning_rate": 1.9111802445888936e-05,
+      "loss": 0.2987,
+      "step": 180
+    },
+    {
+      "epoch": 0.44692737430167595,
+      "eval_loss": 0.3138997256755829,
+      "eval_runtime": 41.0146,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 2.072,
+      "step": 180
+    },
+    {
+      "epoch": 0.4717566728739913,
+      "grad_norm": 1.1606348752975464,
+      "learning_rate": 1.8924772505530177e-05,
+      "loss": 0.2776,
+      "step": 190
+    },
+    {
+      "epoch": 0.4965859714463066,
+      "grad_norm": 1.1247198581695557,
+      "learning_rate": 1.8720987237323497e-05,
+      "loss": 0.2788,
+      "step": 200
+    },
+    {
+      "epoch": 0.521415270018622,
+      "grad_norm": 0.8864783644676208,
+      "learning_rate": 1.8500829226816853e-05,
+      "loss": 0.2588,
+      "step": 210
+    },
+    {
+      "epoch": 0.521415270018622,
+      "eval_loss": 0.26379144191741943,
+      "eval_runtime": 41.1029,
+      "eval_samples_per_second": 4.136,
+      "eval_steps_per_second": 2.068,
+      "step": 210
+    },
+    {
+      "epoch": 0.5462445685909373,
+      "grad_norm": 0.9481696486473083,
+      "learning_rate": 1.826471179767111e-05,
+      "loss": 0.2359,
+      "step": 220
+    },
+    {
+      "epoch": 0.5710738671632526,
+      "grad_norm": 1.218240737915039,
+      "learning_rate": 1.801307823568806e-05,
+      "loss": 0.2406,
+      "step": 230
+    },
+    {
+      "epoch": 0.595903165735568,
+      "grad_norm": 0.9764422178268433,
+      "learning_rate": 1.7746400956587653e-05,
+      "loss": 0.2241,
+      "step": 240
+    },
+    {
+      "epoch": 0.595903165735568,
+      "eval_loss": 0.2281169593334198,
+      "eval_runtime": 41.0529,
+      "eval_samples_per_second": 4.141,
+      "eval_steps_per_second": 2.071,
+      "step": 240
+    },
+    {
+      "epoch": 0.6207324643078833,
+      "grad_norm": 1.1048036813735962,
+      "learning_rate": 1.7465180619096834e-05,
+      "loss": 0.2199,
+      "step": 250
+    },
+    {
+      "epoch": 0.6455617628801986,
+      "grad_norm": 0.973822832107544,
+      "learning_rate": 1.7169945185015106e-05,
+      "loss": 0.2025,
+      "step": 260
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "grad_norm": 0.758234977722168,
+      "learning_rate": 1.686124892802141e-05,
+      "loss": 0.1932,
+      "step": 270
+    },
+    {
+      "epoch": 0.6703910614525139,
+      "eval_loss": 0.20496493577957153,
+      "eval_runtime": 41.1068,
+      "eval_samples_per_second": 4.136,
+      "eval_steps_per_second": 2.068,
+      "step": 270
+    },
+    {
+      "epoch": 0.6952203600248293,
+      "grad_norm": 1.2279834747314453,
+      "learning_rate": 1.6539671393083218e-05,
+      "loss": 0.1943,
+      "step": 280
+    },
+    {
+      "epoch": 0.7200496585971446,
+      "grad_norm": 0.7134841084480286,
+      "learning_rate": 1.6205816308421386e-05,
+      "loss": 0.1796,
+      "step": 290
+    },
+    {
+      "epoch": 0.74487895716946,
+      "grad_norm": 0.9929455518722534,
+      "learning_rate": 1.586031045207354e-05,
+      "loss": 0.1874,
+      "step": 300
+    },
+    {
+      "epoch": 0.74487895716946,
+      "eval_loss": 0.19150954484939575,
+      "eval_runtime": 41.0713,
+      "eval_samples_per_second": 4.139,
+      "eval_steps_per_second": 2.07,
+      "step": 300
+    },
+    {
+      "epoch": 0.7697082557417753,
+      "grad_norm": 0.8576317429542542,
+      "learning_rate": 1.5503802475183773e-05,
+      "loss": 0.1852,
+      "step": 310
+    },
+    {
+      "epoch": 0.7945375543140907,
+      "grad_norm": 1.0153837203979492,
+      "learning_rate": 1.5136961684227905e-05,
+      "loss": 0.1814,
+      "step": 320
+    },
+    {
+      "epoch": 0.819366852886406,
+      "grad_norm": 0.8694589734077454,
+      "learning_rate": 1.4760476784460514e-05,
+      "loss": 0.1841,
+      "step": 330
+    },
+    {
+      "epoch": 0.819366852886406,
+      "eval_loss": 0.17898762226104736,
+      "eval_runtime": 41.0055,
+      "eval_samples_per_second": 4.146,
+      "eval_steps_per_second": 2.073,
+      "step": 330
+    },
+    {
+      "epoch": 0.8441961514587213,
+      "grad_norm": 1.1345281600952148,
+      "learning_rate": 1.4375054586942771e-05,
+      "loss": 0.1725,
+      "step": 340
+    },
+    {
+      "epoch": 0.8690254500310366,
+      "grad_norm": 1.0460193157196045,
+      "learning_rate": 1.3981418681578546e-05,
+      "loss": 0.1605,
+      "step": 350
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "grad_norm": 1.0834463834762573,
+      "learning_rate": 1.3580308078649948e-05,
+      "loss": 0.1652,
+      "step": 360
+    },
+    {
+      "epoch": 0.8938547486033519,
+      "eval_loss": 0.1723683923482895,
+      "eval_runtime": 41.0124,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 2.073,
+      "step": 360
+    },
+    {
+      "epoch": 0.9186840471756673,
+      "grad_norm": 0.7139394283294678,
+      "learning_rate": 1.3172475821402748e-05,
+      "loss": 0.1742,
+      "step": 370
+    },
+    {
+      "epoch": 0.9435133457479826,
+      "grad_norm": 0.8907492756843567,
+      "learning_rate": 1.2758687572286367e-05,
+      "loss": 0.154,
+      "step": 380
+    },
+    {
+      "epoch": 0.9683426443202979,
+      "grad_norm": 0.7731947302818298,
+      "learning_rate": 1.2339720175502643e-05,
+      "loss": 0.1627,
+      "step": 390
+    },
+    {
+      "epoch": 0.9683426443202979,
+      "eval_loss": 0.16476133465766907,
+      "eval_runtime": 41.0851,
+      "eval_samples_per_second": 4.138,
+      "eval_steps_per_second": 2.069,
+      "step": 390
+    },
+    {
+      "epoch": 0.9931719428926132,
+      "grad_norm": 0.8102223873138428,
+      "learning_rate": 1.191636019856198e-05,
+      "loss": 0.1546,
+      "step": 400
+    },
+    {
+      "epoch": 1.0173805090006207,
+      "grad_norm": 0.9590178728103638,
+      "learning_rate": 1.1489402455585078e-05,
+      "loss": 0.1635,
+      "step": 410
+    },
+    {
+      "epoch": 1.042209807572936,
+      "grad_norm": 1.270085334777832,
+      "learning_rate": 1.1059648515122426e-05,
+      "loss": 0.1578,
+      "step": 420
+    },
+    {
+      "epoch": 1.042209807572936,
+      "eval_loss": 0.16066311299800873,
+      "eval_runtime": 41.0613,
+      "eval_samples_per_second": 4.14,
+      "eval_steps_per_second": 2.07,
+      "step": 420
+    },
+    {
+      "epoch": 1.0670391061452513,
+      "grad_norm": 0.7239245176315308,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 0.1509,
+      "step": 430
+    },
+    {
+      "epoch": 1.0918684047175666,
+      "grad_norm": 1.2316311597824097,
+      "learning_rate": 1.0194983049068212e-05,
+      "loss": 0.1493,
+      "step": 440
+    },
+    {
+      "epoch": 1.1166977032898822,
+      "grad_norm": 1.034386157989502,
+      "learning_rate": 9.761694842542042e-06,
+      "loss": 0.1427,
+      "step": 450
+    },
+    {
+      "epoch": 1.1166977032898822,
+      "eval_loss": 0.15721318125724792,
+      "eval_runtime": 40.9543,
+      "eval_samples_per_second": 4.151,
+      "eval_steps_per_second": 2.075,
+      "step": 450
+    },
+    {
+      "epoch": 1.1415270018621975,
+      "grad_norm": 1.0646947622299194,
+      "learning_rate": 9.328854029048985e-06,
+      "loss": 0.1528,
+      "step": 460
+    },
+    {
+      "epoch": 1.1663563004345128,
+      "grad_norm": 0.8461800813674927,
+      "learning_rate": 8.897273221989715e-06,
+      "loss": 0.1505,
+      "step": 470
+    },
+    {
+      "epoch": 1.191185599006828,
+      "grad_norm": 0.6844385862350464,
+      "learning_rate": 8.467762669234496e-06,
+      "loss": 0.1472,
+      "step": 480
+    },
+    {
+      "epoch": 1.191185599006828,
+      "eval_loss": 0.15322649478912354,
+      "eval_runtime": 41.0165,
+      "eval_samples_per_second": 4.145,
+      "eval_steps_per_second": 2.072,
+      "step": 480
+    },
+    {
+      "epoch": 1.2160148975791434,
+      "grad_norm": 0.8525738716125488,
+      "learning_rate": 8.041128731967445e-06,
+      "loss": 0.1519,
+      "step": 490
+    },
+    {
+      "epoch": 1.2408441961514587,
+      "grad_norm": 0.7886703014373779,
+      "learning_rate": 7.61817237082768e-06,
+      "loss": 0.1519,
+      "step": 500
+    },
+    {
+      "epoch": 1.265673494723774,
+      "grad_norm": 0.7268862128257751,
+      "learning_rate": 7.199687642189388e-06,
+      "loss": 0.142,
+      "step": 510
+    },
+    {
+      "epoch": 1.265673494723774,
+      "eval_loss": 0.1511753350496292,
+      "eval_runtime": 41.1138,
+      "eval_samples_per_second": 4.135,
+      "eval_steps_per_second": 2.067,
+      "step": 510
+    },
+    {
+      "epoch": 1.2905027932960893,
+      "grad_norm": 0.7751151323318481,
+      "learning_rate": 6.7864602074039775e-06,
+      "loss": 0.1471,
+      "step": 520
+    },
+    {
+      "epoch": 1.3153320918684046,
+      "grad_norm": 0.8264702558517456,
+      "learning_rate": 6.37926585780297e-06,
+      "loss": 0.1438,
+      "step": 530
+    },
+    {
+      "epoch": 1.34016139044072,
+      "grad_norm": 0.5469579100608826,
+      "learning_rate": 5.978869058230841e-06,
+      "loss": 0.1493,
+      "step": 540
+    },
+    {
+      "epoch": 1.34016139044072,
+      "eval_loss": 0.1491098254919052,
+      "eval_runtime": 41.1584,
+      "eval_samples_per_second": 4.13,
+      "eval_steps_per_second": 2.065,
+      "step": 540
+    },
+    {
+      "epoch": 1.3649906890130354,
+      "grad_norm": 0.9022724032402039,
+      "learning_rate": 5.586021511842136e-06,
+      "loss": 0.1371,
+      "step": 550
+    },
+    {
+      "epoch": 1.3898199875853507,
+      "grad_norm": 0.8355094790458679,
+      "learning_rate": 5.201460748857369e-06,
+      "loss": 0.1409,
+      "step": 560
+    },
+    {
+      "epoch": 1.414649286157666,
+      "grad_norm": 0.7820518016815186,
+      "learning_rate": 4.825908741927076e-06,
+      "loss": 0.1417,
+      "step": 570
+    },
+    {
+      "epoch": 1.414649286157666,
+      "eval_loss": 0.14838995039463043,
+      "eval_runtime": 41.137,
+      "eval_samples_per_second": 4.133,
+      "eval_steps_per_second": 2.066,
+      "step": 570
+    },
+    {
+      "epoch": 1.4394785847299814,
+      "grad_norm": 0.7794449925422668,
+      "learning_rate": 4.4600705507036125e-06,
+      "loss": 0.1433,
+      "step": 580
+    },
+    {
+      "epoch": 1.4643078833022967,
+      "grad_norm": 0.7465994358062744,
+      "learning_rate": 4.104632998165309e-06,
+      "loss": 0.1445,
+      "step": 590
+    },
+    {
+      "epoch": 1.489137181874612,
+      "grad_norm": 0.8334828615188599,
+      "learning_rate": 3.7602633811781165e-06,
+      "loss": 0.1458,
+      "step": 600
+    },
+    {
+      "epoch": 1.489137181874612,
+      "eval_loss": 0.1462916135787964,
+      "eval_runtime": 41.086,
+      "eval_samples_per_second": 4.138,
+      "eval_steps_per_second": 2.069,
+      "step": 600
+    },
+    {
+      "epoch": 1.5139664804469275,
+      "grad_norm": 0.8605223894119263,
+      "learning_rate": 3.4276082177154536e-06,
+      "loss": 0.1447,
+      "step": 610
+    },
+    {
+      "epoch": 1.5387957790192428,
+      "grad_norm": 0.5568763017654419,
+      "learning_rate": 3.107292033088265e-06,
+      "loss": 0.1384,
+      "step": 620
+    },
+    {
+      "epoch": 1.563625077591558,
+      "grad_norm": 0.7917467951774597,
+      "learning_rate": 2.7999161874640026e-06,
+      "loss": 0.1481,
+      "step": 630
+    },
+    {
+      "epoch": 1.563625077591558,
+      "eval_loss": 0.14508940279483795,
+      "eval_runtime": 41.1236,
+      "eval_samples_per_second": 4.134,
+      "eval_steps_per_second": 2.067,
+      "step": 630
+    },
+    {
+      "epoch": 1.5884543761638734,
+      "grad_norm": 0.7165929675102234,
+      "learning_rate": 2.506057746875753e-06,
+      "loss": 0.1422,
+      "step": 640
+    },
+    {
+      "epoch": 1.6132836747361887,
+      "grad_norm": 0.8443304896354675,
+      "learning_rate": 2.226268399841055e-06,
+      "loss": 0.1406,
+      "step": 650
+    },
+    {
+      "epoch": 1.638112973308504,
+      "grad_norm": 1.0195279121398926,
+      "learning_rate": 1.961073421624352e-06,
+      "loss": 0.1403,
+      "step": 660
+    },
+    {
+      "epoch": 1.638112973308504,
+      "eval_loss": 0.1443227380514145,
+      "eval_runtime": 41.1177,
+      "eval_samples_per_second": 4.134,
+      "eval_steps_per_second": 2.067,
+      "step": 660
+    },
+    {
+      "epoch": 1.6629422718808193,
+      "grad_norm": 0.7534502148628235,
+      "learning_rate": 1.710970688087561e-06,
+      "loss": 0.1398,
+      "step": 670
+    },
+    {
+      "epoch": 1.6877715704531346,
+      "grad_norm": 0.8134092092514038,
+      "learning_rate": 1.4764297409801764e-06,
+      "loss": 0.1377,
+      "step": 680
+    },
+    {
+      "epoch": 1.71260086902545,
+      "grad_norm": 0.7144195437431335,
+      "learning_rate": 1.2578909064236887e-06,
+      "loss": 0.1457,
+      "step": 690
+    },
+    {
+      "epoch": 1.71260086902545,
+      "eval_loss": 0.1440444439649582,
+      "eval_runtime": 41.1467,
+      "eval_samples_per_second": 4.132,
+      "eval_steps_per_second": 2.066,
+      "step": 690
+    },
+    {
+      "epoch": 1.7374301675977653,
+      "grad_norm": 0.5405588150024414,
+      "learning_rate": 1.055764468245304e-06,
+      "loss": 0.1406,
+      "step": 700
+    },
+    {
+      "epoch": 1.7622594661700806,
+      "grad_norm": 0.6921040415763855,
+      "learning_rate": 8.70429897712921e-07,
+      "loss": 0.1366,
+      "step": 710
+    },
+    {
+      "epoch": 1.7870887647423959,
+      "grad_norm": 0.7384780645370483,
+      "learning_rate": 7.022351411174866e-07,
+      "loss": 0.1473,
+      "step": 720
+    },
+    {
+      "epoch": 1.7870887647423959,
+      "eval_loss": 0.1436140090227127,
+      "eval_runtime": 41.1175,
+      "eval_samples_per_second": 4.134,
+      "eval_steps_per_second": 2.067,
+      "step": 720
+    },
+    {
+      "epoch": 1.8119180633147114,
+      "grad_norm": 0.7989315986633301,
+      "learning_rate": 5.51495966540182e-07,
+      "loss": 0.1368,
+      "step": 730
+    },
+    {
+      "epoch": 1.8367473618870267,
+      "grad_norm": 0.8284072875976562,
+      "learning_rate": 4.1849537103084924e-07,
+      "loss": 0.1445,
+      "step": 740
+    },
+    {
+      "epoch": 1.861576660459342,
+      "grad_norm": 0.8498286604881287,
+      "learning_rate": 3.0348304931059556e-07,
+      "loss": 0.1347,
+      "step": 750
+    },
+    {
+      "epoch": 1.861576660459342,
+      "eval_loss": 0.14337773621082306,
+      "eval_runtime": 41.0893,
+      "eval_samples_per_second": 4.137,
+      "eval_steps_per_second": 2.069,
+      "step": 750
+    },
+    {
+      "epoch": 1.8864059590316573,
+      "grad_norm": 0.7535120844841003,
+      "learning_rate": 2.066749249960498e-07,
+      "loss": 0.1422,
+      "step": 760
+    },
+    {
+      "epoch": 1.9112352576039728,
+      "grad_norm": 0.8711650371551514,
+      "learning_rate": 1.2825274522532795e-07,
+      "loss": 0.129,
+      "step": 770
+    },
+    {
+      "epoch": 1.9360645561762881,
+      "grad_norm": 0.751017689704895,
+      "learning_rate": 6.836373944677954e-08,
+      "loss": 0.1423,
+      "step": 780
+    },
+    {
+      "epoch": 1.9360645561762881,
+      "eval_loss": 0.1432679146528244,
+      "eval_runtime": 41.1344,
+      "eval_samples_per_second": 4.133,
+      "eval_steps_per_second": 2.066,
+      "step": 780
+    },
+    {
+      "epoch": 1.9608938547486034,
+      "grad_norm": 0.7860766053199768,
+      "learning_rate": 2.7120343011071138e-08,
+      "loss": 0.1492,
+      "step": 790
+    },
+    {
+      "epoch": 1.9857231533209188,
+      "grad_norm": 0.7165619134902954,
+      "learning_rate": 4.599986085573882e-09,
+      "loss": 0.138,
+      "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": 1.4958063934914048e+17,
+  "train_batch_size": 2,
+  "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:a3bce0aacf508b2c7728234707ab3cef1308e18e4702dace098ab3344ddcef39
+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 sha256:8b249ab3dda8e82df4dc804c8245bb994e5072041ea8bd3b6ad0ccf2ba712462
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d100a3ced16b57559fb676f63553984fdce3ef6cd51e5498b4277ec57d9b7fd4
+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": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}