<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
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: 2.3442
- Accuracy: 0.2599
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Accuracy |
---|---|---|---|---|
2.7217 | 0.99 | 88 | 2.6958 | 0.1870 |
2.6696 | 1.99 | 177 | 2.5968 | 0.1878 |
2.6458 | 3.0 | 266 | 2.5386 | 0.2092 |
2.5793 | 4.0 | 355 | 2.5269 | 0.1981 |
2.4252 | 4.99 | 443 | 2.5245 | 0.2266 |
2.4689 | 5.99 | 532 | 2.4482 | 0.2314 |
2.3655 | 7.0 | 621 | 2.4109 | 0.2369 |
2.3365 | 8.0 | 710 | 2.3577 | 0.2385 |
2.3095 | 8.99 | 798 | 2.3580 | 0.2544 |
2.3446 | 9.92 | 880 | 2.3442 | 0.2599 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.1.0+cu118
- Datasets 2.14.5
- Tokenizers 0.14.1