87
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: 0.4645
- Accuracy: 0.9816
- Dt Accuracy: 0.9816
- Df Accuracy: 0.9886
- Unlearn Overall Accuracy: 0.2003
- 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: 87
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 | 79 | 0.3935 | 0.9896 | 0.1986 | 0.1986 | None |
| No log | 2.0 | 158 | 0.4452 | 0.9906 | 0.1970 | 0.1970 | None |
| No log | 3.0 | 237 | 0.4545 | 0.9932 | 0.1928 | 0.1928 | None |
| No log | 4.0 | 316 | 0.5256 | 0.992 | 0.1947 | 0.1947 | None |
| No log | 5.0 | 395 | 0.4521 | 0.992 | 0.1948 | 0.1948 | None |
| No log | 6.0 | 474 | 0.5032 | 0.9908 | 0.1967 | 0.1967 | None |
| 0.0 | 7.0 | 553 | 0.4694 | 0.9904 | 0.1974 | 0.1974 | None |
| 0.0 | 8.0 | 632 | 0.4967 | 0.9904 | 0.1973 | 0.1973 | None |
| 0.0 | 9.0 | 711 | 0.4332 | 0.9892 | 0.1993 | 0.1993 | None |
| 0.0 | 10.0 | 790 | 0.4645 | 0.9886 | 0.2003 | 0.2003 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2