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: 0.8609
- Accuracy: 0.9619
- Dt Accuracy: 0.9619
- Df Accuracy: 0.959
- Unlearn Overall Accuracy: 0.2462
- 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 | 16 | 0.5547 | 0.962 | 0.2416 | 0.2416 | None |
| No log | 2.0 | 32 | 1.2324 | 0.941 | 0.2723 | 0.2723 | None |
| No log | 3.0 | 48 | 0.9226 | 0.963 | 0.2400 | 0.2400 | None |
| No log | 4.0 | 64 | 0.8922 | 0.965 | 0.2370 | 0.2370 | None |
| No log | 5.0 | 80 | 0.8288 | 0.969 | 0.2309 | 0.2309 | None |
| No log | 6.0 | 96 | 0.9246 | 0.972 | 0.2262 | 0.2262 | None |
| No log | 7.0 | 112 | 0.8645 | 0.964 | 0.2386 | 0.2386 | None |
| No log | 8.0 | 128 | 0.9277 | 0.961 | 0.2431 | 0.2431 | None |
| No log | 9.0 | 144 | 0.8539 | 0.958 | 0.2477 | 0.2477 | None |
| No log | 10.0 | 160 | 0.8609 | 0.959 | 0.2462 | 0.2462 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2