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: 1.1290
- Accuracy: 0.5523
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: Use OptimizerNames.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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.2513 | 1.0 | 35 | 1.2502 | 0.4862 |
| 1.1966 | 2.0 | 70 | 1.2707 | 0.4936 |
| 1.2163 | 3.0 | 105 | 1.1919 | 0.5468 |
| 1.098 | 4.0 | 140 | 1.1604 | 0.5284 |
| 1.1705 | 5.0 | 175 | 1.1649 | 0.5193 |
| 1.0887 | 6.0 | 210 | 1.1538 | 0.5450 |
| 1.1253 | 7.0 | 245 | 1.1397 | 0.5486 |
| 1.0148 | 8.0 | 280 | 1.1312 | 0.5505 |
| 1.1047 | 9.0 | 315 | 1.1376 | 0.5486 |
| 1.1108 | 9.7299 | 340 | 1.1290 | 0.5523 |
Framework versions
- Transformers 4.50.0
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1