ricardoSLabs/paper_model_1
This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.1300
- Validation Loss: 0.1310
- Train Accuracy: 0.9606
- Epoch: 4
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': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 104120, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 0.4731 | 0.3395 | 0.9153 | 0 |
| 0.2639 | 0.2292 | 0.9362 | 1 |
| 0.1898 | 0.1785 | 0.9455 | 2 |
| 0.1524 | 0.1497 | 0.9547 | 3 |
| 0.1300 | 0.1310 | 0.9606 | 4 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.15.0
- Datasets 2.19.2
- Tokenizers 0.19.1