swin-tiny-patch4-window7-224-finetuned-eurosat
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the imagefolder dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0684
- Accuracy: 0.9742
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:
- learning_rate: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
| Training Loss |
Epoch |
Step |
Validation Loss |
Accuracy |
| 0.4378 |
1.0 |
527 |
0.3668 |
0.8507 |
| 0.3133 |
2.0 |
1054 |
0.1586 |
0.9430 |
| 0.2065 |
3.0 |
1581 |
0.1049 |
0.9607 |
| 0.22 |
4.0 |
2108 |
0.0838 |
0.9701 |
| 0.173 |
5.0 |
2635 |
0.0684 |
0.9742 |
Framework versions
- Transformers 4.26.0
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
