metadata
license: apache-2.0
base_model: microsoft/swin-tiny-patch4-window7-224
tags:
- generated_from_keras_callback
model-index:
- name: Deexit/swin-tiny-patch4-window7-224-finetuned-eurosat
results: []
Deexit/swin-tiny-patch4-window7-224-finetuned-eurosat
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 1.9176
- Validation Loss: 3.2903
- Validation Accuracy: 0.0
- Epoch: 13
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': 5e-05, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|
| 2.7734 | 2.7408 | 0.0 | 0 |
| 2.4056 | 2.7463 | 0.0 | 1 |
| 2.1880 | 2.7762 | 0.0 | 2 |
| 2.0477 | 2.8285 | 0.0 | 3 |
| 2.1556 | 2.8884 | 0.0 | 4 |
| 2.0269 | 2.9569 | 0.0 | 5 |
| 1.7258 | 3.0337 | 0.0 | 6 |
| 2.3555 | 3.1071 | 0.0 | 7 |
| 1.8657 | 3.1494 | 0.0 | 8 |
| 1.8121 | 3.1848 | 0.0 | 9 |
| 1.9192 | 3.2109 | 0.0 | 10 |
| 1.9925 | 3.2335 | 0.0 | 11 |
| 2.0157 | 3.2654 | 0.0 | 12 |
| 1.9176 | 3.2903 | 0.0 | 13 |
Framework versions
- Transformers 4.31.0
- TensorFlow 2.13.0
- Datasets 2.14.3
- Tokenizers 0.13.3