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: 0.1809
- Accuracy: 0.965
- Dt Accuracy: 0.965
- Df Accuracy: 0.8938
- Unlearn Overall Accuracy: 0.3418
- 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: 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 | 0.1940 | 0.8825 | 0.3568 | 0.3568 | None |
| 0.6645 | 2.0 | 782 | 0.1779 | 0.877 | 0.3643 | 0.3643 | None |
| 0.6021 | 3.0 | 1173 | 0.1777 | 0.8888 | 0.3487 | 0.3487 | None |
| 0.5809 | 4.0 | 1564 | 0.1821 | 0.891 | 0.3456 | 0.3456 | None |
| 0.5809 | 5.0 | 1955 | 0.1829 | 0.889 | 0.3484 | 0.3484 | None |
| 0.5675 | 6.0 | 2346 | 0.1796 | 0.8865 | 0.3517 | 0.3517 | None |
| 0.5504 | 7.0 | 2737 | 0.1744 | 0.8938 | 0.3419 | 0.3419 | None |
| 0.5388 | 8.0 | 3128 | 0.1845 | 0.8972 | 0.3370 | 0.3370 | None |
| 0.5282 | 9.0 | 3519 | 0.1849 | 0.8908 | 0.3459 | 0.3459 | None |
| 0.5282 | 10.0 | 3910 | 0.1809 | 0.8938 | 0.3418 | 0.3418 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0