42
This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1823
- Accuracy: 0.9648
- Dt Accuracy: 0.9648
- Df Accuracy: 0.887
- Unlearn Overall Accuracy: 0.3510
- 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: 42
- 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 | 391 | 0.1770 | 0.8912 | 0.3451 | 0.3451 | None |
| 0.6926 | 2.0 | 782 | 0.1856 | 0.8892 | 0.3479 | 0.3479 | None |
| 0.6055 | 3.0 | 1173 | 0.1789 | 0.887 | 0.3510 | 0.3510 | None |
| 0.5939 | 4.0 | 1564 | 0.1893 | 0.8918 | 0.3445 | 0.3445 | None |
| 0.5939 | 5.0 | 1955 | 0.1926 | 0.8885 | 0.3489 | 0.3489 | None |
| 0.5712 | 6.0 | 2346 | 0.1883 | 0.895 | 0.3402 | 0.3402 | None |
| 0.5655 | 7.0 | 2737 | 0.1900 | 0.891 | 0.3456 | 0.3456 | None |
| 0.5622 | 8.0 | 3128 | 0.1780 | 0.8908 | 0.3459 | 0.3459 | None |
| 0.5572 | 9.0 | 3519 | 0.1866 | 0.9067 | 0.3238 | 0.3238 | None |
| 0.5572 | 10.0 | 3910 | 0.1823 | 0.887 | 0.3510 | 0.3510 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2