42
This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1551
- Accuracy: 0.9644
- Dt Accuracy: 0.9644
- Df Accuracy: 0.865
- Unlearn Overall Accuracy: 0.3803
- 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 | 0.1794 | 0.8925 | 0.3428 | 0.3428 | None |
| 0.4919 | 2.0 | 782 | 0.1873 | 0.8835 | 0.3549 | 0.3549 | None |
| 0.457 | 3.0 | 1173 | 0.1765 | 0.8835 | 0.3552 | 0.3552 | None |
| 0.4362 | 4.0 | 1564 | 0.1683 | 0.865 | 0.3801 | 0.3801 | None |
| 0.4362 | 5.0 | 1955 | 0.1591 | 0.865 | 0.3801 | 0.3801 | None |
| 0.4092 | 6.0 | 2346 | 0.1677 | 0.879 | 0.3614 | 0.3614 | None |
| 0.3858 | 7.0 | 2737 | 0.1663 | 0.871 | 0.3723 | 0.3723 | None |
| 0.3683 | 8.0 | 3128 | 0.1570 | 0.8665 | 0.3783 | 0.3783 | None |
| 0.3512 | 9.0 | 3519 | 0.1550 | 0.8675 | 0.3770 | 0.3770 | None |
| 0.3512 | 10.0 | 3910 | 0.1551 | 0.865 | 0.3803 | 0.3803 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2