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: 0.2945
- Accuracy: 0.9341
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 2.0989 | 1.0 | 298 | 1.4063 | 0.7473 |
| 1.1113 | 2.0 | 596 | 0.5557 | 0.8881 |
| 0.8402 | 3.0 | 894 | 0.3966 | 0.9154 |
| 0.6992 | 4.0 | 1192 | 0.3321 | 0.9254 |
| 0.6345 | 5.0 | 1490 | 0.3044 | 0.9318 |
| 0.6295 | 5.9807 | 1782 | 0.2945 | 0.9341 |
Framework versions
- Transformers 4.47.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0