metadata
library_name: transformers
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: glacoma_andOther_model1
results: []
glacoma_andOther_model1
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: 0.0575
- Train Accuracy: 0.9403
- Train Top-3-accuracy: 0.9984
- Validation Loss: 0.2329
- Validation Accuracy: 0.9442
- Validation Top-3-accuracy: 0.9985
- 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': 1266, '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 |
|---|---|---|---|---|---|---|
| 0.5871 | 0.7237 | 0.9808 | 0.3574 | 0.8358 | 0.9916 | 0 |
| 0.2606 | 0.8643 | 0.9942 | 0.2785 | 0.8821 | 0.9958 | 1 |
| 0.1643 | 0.8966 | 0.9966 | 0.2490 | 0.9077 | 0.9971 | 2 |
| 0.1114 | 0.9168 | 0.9975 | 0.2644 | 0.9239 | 0.9978 | 3 |
| 0.0797 | 0.9301 | 0.9980 | 0.2345 | 0.9353 | 0.9982 | 4 |
| 0.0575 | 0.9403 | 0.9984 | 0.2329 | 0.9442 | 0.9985 | 5 |
Framework versions
- Transformers 4.44.2
- TensorFlow 2.15.0
- Datasets 2.21.0
- Tokenizers 0.19.1