42
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: 0.1491
- Accuracy: 0.955
- Dt Accuracy: 0.955
- Df Accuracy: 0.0716
- Unlearn Overall Accuracy: 0
- 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: 5e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 391 | 0.1616 | 0.9936 | 0.1922 | 0.1922 | None |
| 0.5151 | 2.0 | 782 | 0.1771 | 0.993 | 0.1933 | 0.1933 | None |
| 0.4701 | 3.0 | 1173 | 0.1557 | 0.992 | 0.1949 | 0.1949 | None |
| 0.4571 | 4.0 | 1564 | 0.1684 | 0.9694 | 0.2309 | 0.2309 | None |
| 0.4571 | 5.0 | 1955 | 0.1563 | 0.9234 | 0.2998 | 0.2998 | None |
| 0.4361 | 6.0 | 2346 | 0.1517 | 0.8706 | 0.3725 | 0.3725 | None |
| 0.412 | 7.0 | 2737 | 0.1628 | 0.7526 | 0.5134 | 0.5134 | None |
| 0.3885 | 8.0 | 3128 | 0.1574 | 0.6636 | 0.6035 | 0.6035 | None |
| 0.358 | 9.0 | 3519 | 0.1777 | 0.525 | 0.7223 | 0.7223 | None |
| 0.358 | 10.0 | 3910 | 0.1571 | 0.4664 | 0.7672 | 0.7672 | None |
| 0.3292 | 11.0 | 4301 | 0.1713 | 0.3358 | 0.8520 | 0.8520 | None |
| 0.3045 | 12.0 | 4692 | 0.1495 | 0.3064 | 0.8730 | 0.8730 | None |
| 0.2834 | 13.0 | 5083 | 0.1658 | 0.218 | 0.9199 | 0.9199 | None |
| 0.2834 | 14.0 | 5474 | 0.1727 | 0.1562 | 0.9487 | 0.9487 | None |
| 0.2633 | 15.0 | 5865 | 0.1536 | 0.1438 | 0.9598 | 0.9598 | None |
| 0.2416 | 16.0 | 6256 | 0.1573 | 0.112 | 0.9738 | 0.9738 | None |
| 0.2271 | 17.0 | 6647 | 0.1546 | 0.086 | 0.9746 | 0.9746 | None |
| 0.215 | 18.0 | 7038 | 0.1630 | 0.068 | 0 | 0 | None |
| 0.215 | 19.0 | 7429 | 0.1506 | 0.073 | 0 | 0 | None |
| 0.2063 | 20.0 | 7820 | 0.1491 | 0.0716 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2