patacoswin_v2
This model is a fine-tuned version of microsoft/swinv2-tiny-patch4-window16-256 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0328
- Accuracy: 0.9910
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: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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 |
|---|---|---|---|---|
| 0.6055 | 0.95 | 13 | 0.2709 | 0.9615 |
| 0.2812 | 1.96 | 27 | 0.0866 | 0.9683 |
| 0.1426 | 2.98 | 41 | 0.0584 | 0.9796 |
| 0.07 | 4.0 | 55 | 0.0268 | 0.9932 |
| 0.0579 | 4.95 | 68 | 0.0451 | 0.9864 |
| 0.091 | 5.96 | 82 | 0.0300 | 0.9887 |
| 0.0247 | 6.98 | 96 | 0.0387 | 0.9864 |
| 0.0323 | 8.0 | 110 | 0.0456 | 0.9887 |
| 0.032 | 8.95 | 123 | 0.0475 | 0.9864 |
| 0.0187 | 9.45 | 130 | 0.0328 | 0.9910 |
Framework versions
- Transformers 4.31.0
- Pytorch 2.0.1+cu118
- Datasets 2.14.3
- Tokenizers 0.13.3