---
library_name: peft
license: other
base_model: Qwen/Qwen3-VL-8B-Instruct
tags:
- base_model:adapter:Qwen/Qwen3-VL-8B-Instruct
- llama-factory
- lora
- transformers
pipeline_tag: text-generation
model-index:
- name: 4dreasoner_v2_cot
  results: []
---

<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->

# 4dreasoner_v2_cot

This model is a fine-tuned version of [Qwen/Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) on the 4dreasoner_v2_cot_train dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3077

## Model description

More information needed

## Intended uses & limitations

More information needed

## Training and evaluation data

More information needed

## Training procedure

### Training hyperparameters

The following hyperparameters were used during training:
- learning_rate: 0.0001
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 8
- total_train_batch_size: 32
- total_eval_batch_size: 4
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3.0

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.3258        | 0.9112 | 100  | 0.3247          |
| 0.2463        | 1.8200 | 200  | 0.3013          |
| 0.1706        | 2.7289 | 300  | 0.3079          |


### Framework versions

- PEFT 0.17.1
- Transformers 4.57.1
- Pytorch 2.11.0+cu130
- Datasets 4.0.0
- Tokenizers 0.22.2