Ahmed007/vit-base-patch16-224-in21k-Dr.Smart
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: 0.3448
- Train Accuracy: 0.9475
- Train Top-3-accuracy: 0.9910
- Validation Loss: 0.7867
- Validation Accuracy: 0.7646
- Validation Top-3-accuracy: 0.9395
- Epoch: 4
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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 1350, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000}
- training_precision: mixed_float16
Training results
| Train Loss | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
|---|---|---|---|---|---|---|
| 1.6331 | 0.5028 | 0.7892 | 1.2982 | 0.6197 | 0.8717 | 0 |
| 1.0538 | 0.7156 | 0.9293 | 1.0441 | 0.6975 | 0.9116 | 1 |
| 0.6956 | 0.8427 | 0.9699 | 0.8748 | 0.7493 | 0.9282 | 2 |
| 0.4569 | 0.9177 | 0.9855 | 0.8106 | 0.7613 | 0.9335 | 3 |
| 0.3448 | 0.9475 | 0.9910 | 0.7867 | 0.7646 | 0.9395 | 4 |
Framework versions
- Transformers 4.31.0.dev0
- TensorFlow 2.12.0
- Datasets 2.1.0
- Tokenizers 0.13.3