metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_keras_callback
model-index:
- name: vit-base-patch16-224-5class224
results: []
vit-base-patch16-224-5class224
This model is a fine-tuned version of google/vit-base-patch16-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0115
- Train Accuracy: 0.9460
- Train Top-3-accuracy: 0.9911
- Validation Loss: 0.1621
- Validation Accuracy: 0.9490
- Validation Top-3-accuracy: 0.9916
- Epoch: 6
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': 574, '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 | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
|---|---|---|---|---|---|---|
| 0.7725 | 0.6414 | 0.8898 | 0.3755 | 0.7636 | 0.9478 | 0 |
| 0.2160 | 0.8219 | 0.9635 | 0.2372 | 0.8557 | 0.9726 | 1 |
| 0.0696 | 0.8812 | 0.9780 | 0.2035 | 0.8989 | 0.9818 | 2 |
| 0.0344 | 0.9108 | 0.9842 | 0.1715 | 0.9203 | 0.9860 | 3 |
| 0.0194 | 0.9278 | 0.9875 | 0.1911 | 0.9337 | 0.9888 | 4 |
| 0.0147 | 0.9381 | 0.9897 | 0.1651 | 0.9425 | 0.9904 | 5 |
| 0.0115 | 0.9460 | 0.9911 | 0.1621 | 0.9490 | 0.9916 | 6 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.15.0
- Datasets 2.20.0
- Tokenizers 0.19.1