21
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: 0.9412
- Accuracy: 0.955
- Dt Accuracy: 0.955
- Df Accuracy: 0.936
- Unlearn Overall Accuracy: 0.2803
- 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: 21
- 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 | 16 | 0.6313 | 0.963 | 0.2399 | 0.2399 | None |
| No log | 2.0 | 32 | 0.8377 | 0.951 | 0.2580 | 0.2580 | None |
| No log | 3.0 | 48 | 0.8592 | 0.962 | 0.2414 | 0.2414 | None |
| No log | 4.0 | 64 | 1.2518 | 0.943 | 0.2697 | 0.2697 | None |
| No log | 5.0 | 80 | 1.0190 | 0.954 | 0.2535 | 0.2535 | None |
| No log | 6.0 | 96 | 1.0689 | 0.944 | 0.2685 | 0.2685 | None |
| No log | 7.0 | 112 | 0.9776 | 0.951 | 0.2582 | 0.2582 | None |
| No log | 8.0 | 128 | 0.9352 | 0.941 | 0.2731 | 0.2731 | None |
| No log | 9.0 | 144 | 0.9614 | 0.938 | 0.2774 | 0.2774 | None |
| No log | 10.0 | 160 | 0.9412 | 0.936 | 0.2803 | 0.2803 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2