swin-tiny-patch4-window7-224-finetuned-eurosat
This model is a fine-tuned version of microsoft/swin-tiny-patch4-window7-224 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1332
- Accuracy: 0.9572
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: 128
- eval_batch_size: 128
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 512
- 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 |
|---|---|---|---|---|
| 0.6031 | 1.0 | 88 | 0.2208 | 0.9282 |
| 0.4569 | 2.0 | 176 | 0.1426 | 0.953 |
| 0.3886 | 3.0 | 264 | 0.1332 | 0.9572 |
Framework versions
- Transformers 4.28.0
- Pytorch 1.13.1+cu116
- Datasets 2.12.0
- Tokenizers 0.13.3