13
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: 0.1783
- Accuracy: 0.9668
- Dt Accuracy: 0.9668
- Df Accuracy: 0.8858
- Unlearn Overall Accuracy: 0.3529
- 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: 13
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 | 0.1955 | 0.8828 | 0.3565 | 0.3565 | None |
| 0.6694 | 2.0 | 782 | 0.1931 | 0.8808 | 0.3593 | 0.3593 | None |
| 0.6037 | 3.0 | 1173 | 0.1852 | 0.8848 | 0.3539 | 0.3539 | None |
| 0.5843 | 4.0 | 1564 | 0.1874 | 0.8825 | 0.3572 | 0.3572 | None |
| 0.5843 | 5.0 | 1955 | 0.1823 | 0.8948 | 0.3405 | 0.3405 | None |
| 0.5619 | 6.0 | 2346 | 0.1812 | 0.8868 | 0.3515 | 0.3515 | None |
| 0.5482 | 7.0 | 2737 | 0.1840 | 0.8848 | 0.3542 | 0.3542 | None |
| 0.5404 | 8.0 | 3128 | 0.1818 | 0.8972 | 0.3371 | 0.3371 | None |
| 0.535 | 9.0 | 3519 | 0.1800 | 0.9005 | 0.3326 | 0.3326 | None |
| 0.535 | 10.0 | 3910 | 0.1783 | 0.8858 | 0.3529 | 0.3529 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0