metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: arieg/4_100_s_200
results: []
arieg/4_100_s_200
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: 0.0155
- Validation Loss: 0.0151
- Train Accuracy: 1.0
- Epoch: 19
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', 'clipnorm': 1.0, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 14400, '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 | Validation Loss | Train Accuracy | Epoch |
|---|---|---|---|
| 0.6483 | 0.2667 | 1.0 | 0 |
| 0.1768 | 0.1322 | 1.0 | 1 |
| 0.1096 | 0.0960 | 1.0 | 2 |
| 0.0850 | 0.0781 | 1.0 | 3 |
| 0.0710 | 0.0663 | 1.0 | 4 |
| 0.0612 | 0.0576 | 1.0 | 5 |
| 0.0534 | 0.0506 | 1.0 | 6 |
| 0.0472 | 0.0448 | 1.0 | 7 |
| 0.0420 | 0.0400 | 1.0 | 8 |
| 0.0376 | 0.0359 | 1.0 | 9 |
| 0.0339 | 0.0324 | 1.0 | 10 |
| 0.0306 | 0.0294 | 1.0 | 11 |
| 0.0278 | 0.0267 | 1.0 | 12 |
| 0.0253 | 0.0244 | 1.0 | 13 |
| 0.0232 | 0.0223 | 1.0 | 14 |
| 0.0212 | 0.0205 | 1.0 | 15 |
| 0.0196 | 0.0189 | 1.0 | 16 |
| 0.0180 | 0.0175 | 1.0 | 17 |
| 0.0167 | 0.0162 | 1.0 | 18 |
| 0.0155 | 0.0151 | 1.0 | 19 |
Framework versions
- Transformers 4.35.0
- TensorFlow 2.14.0
- Datasets 2.14.6
- Tokenizers 0.14.1