vit-base-patch16-224-in21k-euroSat
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: 0.1778
- Train Accuracy: 0.9381
- Train Top-3-accuracy: 1.0
- Validation Loss: 0.1819
- Validation Accuracy: 0.9443
- Validation Top-3-accuracy: 1.0
- 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: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 3e-05, 'decay_steps': 120, '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 | Train Accuracy | Train Top-3-accuracy | Validation Loss | Validation Accuracy | Validation Top-3-accuracy | Epoch |
---|---|---|---|---|---|---|
0.8583 | 0.6111 | 1.0 | 0.5968 | 0.7762 | 1.0 | 0 |
0.4764 | 0.8341 | 1.0 | 0.3488 | 0.8683 | 1.0 | 1 |
0.2909 | 0.8920 | 1.0 | 0.2400 | 0.9089 | 1.0 | 2 |
0.2079 | 0.9211 | 1.0 | 0.1928 | 0.9307 | 1.0 | 3 |
0.1778 | 0.9381 | 1.0 | 0.1819 | 0.9443 | 1.0 | 4 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.15.0
- Datasets 2.20.0
- Tokenizers 0.19.1
- Downloads last month
- 1