metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: Entrnal_eyes_data_4class_resize_224_model
results: []
Entrnal_eyes_data_4class_resize_224_model
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: 0.0823
- Train Accuracy: 0.9261
- Train Top-3-accuracy: 0.9972
- Validation Loss: 0.2588
- Validation Accuracy: 0.9299
- Validation Top-3-accuracy: 0.9974
- 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': 651, '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 |
|---|---|---|---|---|---|---|
| 0.7993 | 0.6130 | 0.9518 | 0.5184 | 0.7611 | 0.9833 | 0 |
| 0.3482 | 0.8052 | 0.9881 | 0.3126 | 0.8382 | 0.9913 | 1 |
| 0.2260 | 0.8597 | 0.9929 | 0.2990 | 0.8739 | 0.9942 | 2 |
| 0.1576 | 0.8861 | 0.9949 | 0.2597 | 0.8954 | 0.9956 | 3 |
| 0.1191 | 0.9041 | 0.9960 | 0.2642 | 0.9106 | 0.9964 | 4 |
| 0.0933 | 0.9167 | 0.9967 | 0.2598 | 0.9216 | 0.9970 | 5 |
| 0.0823 | 0.9261 | 0.9972 | 0.2588 | 0.9299 | 0.9974 | 6 |
Framework versions
- Transformers 4.44.2
- TensorFlow 2.15.1
- Datasets 3.0.0
- Tokenizers 0.19.1