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: 0.5780
- Accuracy: 0.7503
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.683 | 0.9990 | 245 | 0.6377 | 0.7175 |
| 0.6309 | 1.9980 | 490 | 0.5958 | 0.7406 |
| 0.6332 | 2.9969 | 735 | 0.5780 | 0.7503 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1