13
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.0719
- Accuracy: 0.985
- Dt Accuracy: 0.985
- Df Accuracy: 0.756
- Unlearn Overall Accuracy: 0.5111
- Unlearn Time: None
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: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 13
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 391 | 0.1278 | 0.975 | 0.2216 | 0.2216 | None |
| 0.49 | 2.0 | 782 | 0.1137 | 0.974 | 0.2232 | 0.2232 | None |
| 0.4221 | 3.0 | 1173 | 0.1437 | 0.962 | 0.2416 | 0.2416 | None |
| 0.3739 | 4.0 | 1564 | 0.0942 | 0.972 | 0.2265 | 0.2265 | None |
| 0.3739 | 5.0 | 1955 | 0.0913 | 0.965 | 0.2375 | 0.2375 | None |
| 0.3316 | 6.0 | 2346 | 0.0811 | 0.953 | 0.2559 | 0.2559 | None |
| 0.2914 | 7.0 | 2737 | 0.0794 | 0.926 | 0.2961 | 0.2961 | None |
| 0.2579 | 8.0 | 3128 | 0.0767 | 0.851 | 0.3981 | 0.3981 | None |
| 0.2295 | 9.0 | 3519 | 0.0737 | 0.808 | 0.4514 | 0.4514 | None |
| 0.2295 | 10.0 | 3910 | 0.0719 | 0.756 | 0.5111 | 0.5111 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0