swin-tiny-patch4-window7-224-BottomSportsCasual
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: 0.0189
- Accuracy: 0.9955
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: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 7
- total_train_batch_size: 56
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.01
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.1765 | 1.0 | 141 | 0.0538 | 0.9796 |
| 0.1572 | 2.0 | 283 | 0.0309 | 0.9886 |
| 0.1412 | 2.99 | 424 | 0.0167 | 0.9943 |
| 0.0825 | 4.0 | 566 | 0.0217 | 0.9898 |
| 0.0881 | 4.99 | 707 | 0.0278 | 0.9921 |
| 0.102 | 6.0 | 849 | 0.0189 | 0.9955 |
| 0.0784 | 7.0 | 991 | 0.0167 | 0.9932 |
| 0.0902 | 8.0 | 1132 | 0.0255 | 0.9921 |
| 0.0686 | 9.0 | 1274 | 0.0182 | 0.9932 |
| 0.0529 | 9.96 | 1410 | 0.0157 | 0.9943 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.0
- Datasets 2.12.0
- Tokenizers 0.13.3