HarshaSingamshetty1/roof_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: 1.6380
- Validation Loss: 2.1987
- Train Accuracy: 0.4375
- Epoch: 14
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': 1770, '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 |
---|---|---|---|
2.9764 | 2.9730 | 0.05 | 0 |
2.8746 | 2.9232 | 0.125 | 1 |
2.7792 | 2.8802 | 0.1375 | 2 |
2.6648 | 2.8491 | 0.225 | 3 |
2.5573 | 2.7563 | 0.1625 | 4 |
2.4614 | 2.7155 | 0.2875 | 5 |
2.3453 | 2.7005 | 0.2 | 6 |
2.2737 | 2.6443 | 0.2875 | 7 |
2.1555 | 2.5396 | 0.3625 | 8 |
2.0694 | 2.4244 | 0.425 | 9 |
2.0112 | 2.3738 | 0.4875 | 10 |
1.8867 | 2.3843 | 0.4125 | 11 |
1.8217 | 2.2878 | 0.45 | 12 |
1.7253 | 2.2642 | 0.475 | 13 |
1.6380 | 2.1987 | 0.4375 | 14 |
Framework versions
- Transformers 4.35.2
- TensorFlow 2.14.0
- Datasets 2.15.0
- Tokenizers 0.15.0
- Downloads last month
- 12