swin-large-patch4-window7-224-finetuned-eurosat
This model is a fine-tuned version of microsoft/swin-large-patch4-window7-224 on the imagefolder dataset. It achieves the following results on the evaluation set:
- Loss: 1.4098
- Accuracy: 0.4539
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: 1e-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: 12
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.5265 | 1.0 | 20 | 1.6373 | 0.2214 |
| 1.455 | 2.0 | 40 | 1.5808 | 0.2546 |
| 1.41 | 3.0 | 60 | 1.5281 | 0.2620 |
| 1.3791 | 4.0 | 80 | 1.4928 | 0.3026 |
| 1.3496 | 5.0 | 100 | 1.4662 | 0.3395 |
| 1.3218 | 6.0 | 120 | 1.4461 | 0.3985 |
| 1.3146 | 7.0 | 140 | 1.4331 | 0.4207 |
| 1.298 | 8.0 | 160 | 1.4245 | 0.4391 |
| 1.2922 | 9.0 | 180 | 1.4168 | 0.4502 |
| 1.3002 | 10.0 | 200 | 1.4121 | 0.4502 |
| 1.279 | 11.0 | 220 | 1.4101 | 0.4502 |
| 1.279 | 11.4156 | 228 | 1.4098 | 0.4539 |
Framework versions
- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1