sayakpaul/mit-b0-finetuned-pets
This model is a fine-tuned version of nvidia/mit-b0 on the Oxford Pets dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1481
- Validation Loss: 0.1962
- Epoch: 9
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:
- optimizer: {'name': 'Adam', 'learning_rate': 6e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.2821 | 0.2146 | 0 |
| 0.2090 | 0.1983 | 1 |
| 0.1920 | 0.2002 | 2 |
| 0.1805 | 0.1868 | 3 |
| 0.1716 | 0.1920 | 4 |
| 0.1651 | 0.1850 | 5 |
| 0.1537 | 0.1943 | 6 |
| 0.1570 | 0.1842 | 7 |
| 0.1462 | 0.1833 | 8 |
| 0.1481 | 0.1962 | 9 |
Framework versions
- Transformers 4.25.1
- TensorFlow 2.10.1
- Tokenizers 0.13.2
