metadata
license: apache-2.0
base_model: google/vit-base-patch16-224
tags:
- generated_from_keras_callback
model-index:
- name: vit-base-patch16-224-2class_pterygium
results: []
vit-base-patch16-224-2class_pterygium
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: 0.0044
- Train Accuracy: 0.9515
- Train Top-3-accuracy: 1.0
- Validation Loss: 0.1337
- Validation Accuracy: 0.9550
- Validation Top-3-accuracy: 1.0
- Epoch: 5
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': 366, '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 |
---|---|---|---|---|---|---|
0.4319 | 0.6998 | 1.0 | 0.2552 | 0.8013 | 1.0 | 0 |
0.1258 | 0.8484 | 1.0 | 0.1345 | 0.8810 | 1.0 | 1 |
0.0223 | 0.9030 | 1.0 | 0.1283 | 0.9190 | 1.0 | 2 |
0.0079 | 0.9287 | 1.0 | 0.1303 | 0.9367 | 1.0 | 3 |
0.0054 | 0.9429 | 1.0 | 0.1333 | 0.9479 | 1.0 | 4 |
0.0044 | 0.9515 | 1.0 | 0.1337 | 0.9550 | 1.0 | 5 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.15.0
- Datasets 2.20.0
- Tokenizers 0.19.1