42
This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5456
- Accuracy: 0.8396
- Dt Accuracy: 0.8396
- Df Accuracy: 0.907
- Unlearn Overall Accuracy: 0.1616
- 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 |
|---|---|---|---|---|---|---|---|
| 1.146 | 1.0 | 391 | 0.5865 | 0.898 | 0.1678 | 0.1678 | None |
| 1.1193 | 2.0 | 782 | 0.5712 | 0.9 | 0.1666 | 0.1666 | None |
| 1.1058 | 3.0 | 1173 | 0.5706 | 0.896 | 0.1694 | 0.1694 | None |
| 1.0641 | 4.0 | 1564 | 0.5514 | 0.905 | 0.1631 | 0.1631 | None |
| 1.0401 | 5.0 | 1955 | 0.5528 | 0.9 | 0.1665 | 0.1665 | None |
| 1.0003 | 6.0 | 2346 | 0.5608 | 0.893 | 0.1714 | 0.1714 | None |
| 1.0065 | 7.0 | 2737 | 0.5465 | 0.905 | 0.1630 | 0.1630 | None |
| 0.9978 | 8.0 | 3128 | 0.5472 | 0.902 | 0.1651 | 0.1651 | None |
| 0.975 | 9.0 | 3519 | 0.5446 | 0.905 | 0.1630 | 0.1630 | None |
| 0.9475 | 10.0 | 3910 | 0.5456 | 0.907 | 0.1616 | 0.1616 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2