---
library_name: transformers
license: other
base_model: Qwen/Qwen3-8B
tags:
- llama-factory
- full
- generated_from_trainer
model-index:
- name: Qwen3-feedback-dropout-even
  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. -->

# Qwen3-feedback-dropout-even

This model is a fine-tuned version of [/mnt/task_runtime/models/Qwen3-8B](https://huggingface.co//mnt/task_runtime/models/Qwen3-8B) on the dropout-even dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0359

## 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: 1e-05
- train_batch_size: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 16
- total_eval_batch_size: 16
- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 0.05
- num_epochs: 1.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.0489        | 0.1245 | 1000 | 0.0507          |
| 0.0413        | 0.2491 | 2000 | 0.0438          |
| 0.0394        | 0.3736 | 3000 | 0.0409          |
| 0.0379        | 0.4982 | 4000 | 0.0388          |
| 0.0366        | 0.6227 | 5000 | 0.0374          |
| 0.0329        | 0.7473 | 6000 | 0.0365          |
| 0.0358        | 0.8718 | 7000 | 0.0360          |
| 0.0319        | 0.9964 | 8000 | 0.0359          |


### Framework versions

- Transformers 4.57.6
- Pytorch 2.9.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2