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: 0.8049
- Accuracy: 0.7246
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 |
|---|---|---|---|---|
| 1.5124 | 1.0 | 13 | 1.0907 | 0.6184 |
| 1.1298 | 2.0 | 26 | 0.8774 | 0.7005 |
| 0.8668 | 3.0 | 39 | 0.8510 | 0.7150 |
| 0.6712 | 4.0 | 52 | 0.7277 | 0.7246 |
| 0.6934 | 5.0 | 65 | 0.8049 | 0.7246 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1