metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_keras_callback
model-index:
- name: vit-base-patch16-224-4class224
results: []
vit-base-patch16-224-4class224
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: 0.0136
- Train Accuracy: 0.9421
- Train Top-3-accuracy: 0.9958
- Validation Loss: 0.1390
- Validation Accuracy: 0.9458
- Validation Top-3-accuracy: 0.9961
- 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': 455, '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 |
|---|---|---|---|---|---|---|
| 0.7231 | 0.5836 | 0.9174 | 0.3551 | 0.7352 | 0.9701 | 0 |
| 0.2208 | 0.8012 | 0.9802 | 0.2265 | 0.8400 | 0.9858 | 1 |
| 0.0854 | 0.8664 | 0.9886 | 0.1859 | 0.8862 | 0.9907 | 2 |
| 0.0372 | 0.8996 | 0.9920 | 0.1565 | 0.9111 | 0.9931 | 3 |
| 0.0212 | 0.9199 | 0.9938 | 0.1411 | 0.9272 | 0.9945 | 4 |
| 0.0167 | 0.9328 | 0.9950 | 0.1374 | 0.9379 | 0.9954 | 5 |
| 0.0136 | 0.9421 | 0.9958 | 0.1390 | 0.9458 | 0.9961 | 6 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.15.0
- Datasets 2.20.0
- Tokenizers 0.19.1