swin-tiny-patch4-window7-224-blank_img
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: 0.0726
- Accuracy: 0.9797
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1329 | 0.99 | 72 | 0.0882 | 0.9767 |
| 0.1247 | 1.99 | 144 | 0.0805 | 0.9767 |
| 0.0742 | 2.99 | 216 | 0.0721 | 0.9767 |
| 0.0745 | 3.99 | 288 | 0.0726 | 0.9797 |
| 0.1289 | 4.99 | 360 | 0.0848 | 0.9729 |
Framework versions
- Transformers 4.26.1
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.13.3