qwen3-finetuned
This model is a fine-tuned version of Qwen/Qwen3-0.6B on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.5165
Model description
Created as part of a base tutorial by Hugging Face found at https://huggingface.co/docs/transformers/en/training and the published model at https://huggingface.co/datasets/karthiksagarn/astro_horoscope.
This was also used as part of my own attempt on an initial basic fine tuning and full code can be found at https://github.com/ar-to/devML/blob/master/hugging_face/fine-tuning_horoscope.ipynb
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: 2e-05
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- 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: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.3943 | 1.0 | 1236 | 2.5165 |
Framework versions
- Transformers 5.18.0
- Pytorch 2.11.0+cu130
- Datasets 4.8.5
- Tokenizers 0.23.2