adhisetiawan/mnist-test
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: 0.7312
- Validation Loss: 0.9257
- Train Accuracy: 0.8
- 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', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1600, '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 |
|---|---|---|---|
| 2.2668 | 2.2081 | 0.4 | 0 |
| 2.1502 | 2.1140 | 0.6 | 1 |
| 2.0506 | 2.0350 | 0.65 | 2 |
| 1.9473 | 1.9239 | 0.7 | 3 |
| 1.8164 | 1.8355 | 0.7 | 4 |
| 1.7091 | 1.7534 | 0.75 | 5 |
| 1.6152 | 1.6683 | 0.8 | 6 |
| 1.5122 | 1.5825 | 0.8 | 7 |
| 1.4108 | 1.4897 | 0.8 | 8 |
| 1.3225 | 1.4149 | 0.8 | 9 |
| 1.2426 | 1.3135 | 0.8 | 10 |
| 1.1740 | 1.2704 | 0.8 | 11 |
| 1.0894 | 1.2213 | 0.85 | 12 |
| 1.0230 | 1.1424 | 0.8 | 13 |
| 0.9646 | 1.1171 | 0.85 | 14 |
| 0.9109 | 1.0744 | 0.8 | 15 |
| 0.8547 | 1.0376 | 0.85 | 16 |
| 0.8082 | 0.9892 | 0.8 | 17 |
| 0.7632 | 0.9604 | 0.85 | 18 |
| 0.7312 | 0.9257 | 0.8 | 19 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.15.0
- Datasets 2.16.1
- Tokenizers 0.15.0