metadata
license: apache-2.0
base_model: google/vit-base-patch16-224-in21k
tags:
- generated_from_keras_callback
model-index:
- name: jtatman/vit-base-patch16-224-in21k-euroSat
results: []
jtatman/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: 0.0217
- Train Accuracy: 0.9835
- Train Top-3-accuracy: 0.9977
- Validation Loss: 0.0529
- Validation Accuracy: 0.9850
- Validation Top-3-accuracy: 0.9979
- 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': 3590, '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 |
---|---|---|---|---|---|---|
0.4701 | 0.8661 | 0.9502 | 0.1578 | 0.9489 | 0.9895 | 0 |
0.0997 | 0.9615 | 0.9929 | 0.0886 | 0.9689 | 0.9948 | 1 |
0.0519 | 0.9735 | 0.9958 | 0.0642 | 0.9771 | 0.9966 | 2 |
0.0308 | 0.9797 | 0.9971 | 0.0549 | 0.9818 | 0.9974 | 3 |
0.0217 | 0.9835 | 0.9977 | 0.0529 | 0.9850 | 0.9979 | 4 |
Framework versions
- Transformers 4.41.1
- TensorFlow 2.15.0
- Datasets 2.19.1
- Tokenizers 0.19.1