Ahmed007/Dr.Smart_v3
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: 0.3548
- Train Accuracy: 0.9304
- Train Top-3-accuracy: 0.9905
- Validation Loss: 0.6948
- Validation Accuracy: 0.7893
- Validation Top-3-accuracy: 0.9455
- Epoch: 3
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': 2198, '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 |
|---|---|---|---|---|---|---|
| 1.5583 | 0.5509 | 0.8160 | 1.1523 | 0.6705 | 0.9045 | 0 |
| 0.9379 | 0.7513 | 0.9445 | 0.8892 | 0.75 | 0.9304 | 1 |
| 0.5855 | 0.8658 | 0.9746 | 0.7279 | 0.7964 | 0.9491 | 2 |
| 0.3548 | 0.9304 | 0.9905 | 0.6948 | 0.7893 | 0.9455 | 3 |
Framework versions
- Transformers 4.31.0.dev0
- TensorFlow 2.12.0
- Datasets 2.1.0
- Tokenizers 0.13.3