---
library_name: transformers
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
tags:
- generated_from_trainer
model-index:
- name: Qwen3-0.6B-finetuned-astro-horoscope-fsdp
  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. -->

# Qwen3-0.6B-finetuned-astro-horoscope-fsdp

This model is a fine-tuned version of [Qwen/Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2469
- Perplexity: 1.2800

## 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: 0.0002
- train_batch_size: 64
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 512
- total_eval_batch_size: 64
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5

### Training results

| Training Loss | Epoch | Step | Validation Loss | Perplexity |
|:-------------:|:-----:|:----:|:---------------:|:----------:|
| No log        | 1.0   | 39   | 1.4018          | 4.0626     |
| 2.1578        | 2.0   | 78   | 0.8331          | 2.3004     |
| 0.8726        | 3.0   | 117  | 0.5413          | 1.7182     |
| 0.4763        | 4.0   | 156  | 0.3450          | 1.4121     |
| 0.4763        | 5.0   | 195  | 0.2469          | 1.2800     |


### Framework versions

- Transformers 5.5.4
- Pytorch 2.11.0+cu128
- Datasets 4.8.4
- Tokenizers 0.22.2