aalonso-developer/vit-base-patch16-224-in21k-clothing-classifier
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: 0.1749
- Train Accuracy: 0.9686
- Train Top-3-accuracy: 0.9922
- Validation Loss: 0.7294
- Validation Accuracy: 0.7906
- Validation Top-3-accuracy: 0.9437
- 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': 3665, '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 |
|---|---|---|---|---|---|---|
| 1.3672 | 0.6720 | 0.8895 | 0.8886 | 0.7613 | 0.9415 | 0 |
| 0.6745 | 0.8197 | 0.9615 | 0.7492 | 0.7790 | 0.9427 | 1 |
| 0.4135 | 0.8942 | 0.9814 | 0.7119 | 0.7848 | 0.9475 | 2 |
| 0.2566 | 0.9449 | 0.9892 | 0.7212 | 0.7860 | 0.9451 | 3 |
| 0.1749 | 0.9686 | 0.9922 | 0.7294 | 0.7906 | 0.9437 | 4 |
Framework versions
- Transformers 4.29.1
- TensorFlow 2.11.0
- Datasets 2.12.0
- Tokenizers 0.13.3