swin-tiny-patch4-window7-224-finetuned-skin-cancer
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: 0.3821
- Accuracy: 0.8613
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: 64
- eval_batch_size: 64
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- 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 |
|---|---|---|---|---|
| 0.9232 | 0.9929 | 35 | 0.8263 | 0.7116 |
| 0.6427 | 1.9858 | 70 | 0.6465 | 0.7645 |
| 0.5475 | 2.9787 | 105 | 0.5370 | 0.8054 |
| 0.4539 | 4.0 | 141 | 0.4634 | 0.8234 |
| 0.4547 | 4.9929 | 176 | 0.4462 | 0.8353 |
| 0.4009 | 5.9858 | 211 | 0.4218 | 0.8483 |
| 0.3722 | 6.9787 | 246 | 0.3942 | 0.8533 |
| 0.3042 | 8.0 | 282 | 0.4198 | 0.8453 |
| 0.3071 | 8.9929 | 317 | 0.4136 | 0.8493 |
| 0.3103 | 9.9291 | 350 | 0.3821 | 0.8613 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1