recipe_book_final_lr
This model is a fine-tuned version of t5-small on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3280
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: 8
- eval_batch_size: 8
- seed: 42
- 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: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.0766 | 1.0 | 109 | 3.0647 |
| 3.1375 | 2.0 | 218 | 2.7541 |
| 2.7927 | 3.0 | 327 | 2.5822 |
| 2.5792 | 4.0 | 436 | 2.4856 |
| 2.3973 | 5.0 | 545 | 2.4246 |
| 2.2256 | 6.0 | 654 | 2.3843 |
| 2.1493 | 7.0 | 763 | 2.3816 |
| 2.0695 | 8.0 | 872 | 2.3374 |
| 1.9696 | 9.0 | 981 | 2.3204 |
| 1.9476 | 10.0 | 1090 | 2.3280 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1