100
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: 0.9658
- Dt Accuracy: 0.9658
- Df Accuracy: 0.8848
- Unlearn Overall Accuracy: 0.3541
- 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: 100
- 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 | 0.1917 | 0.8698 | 0.3739 | 0.3739 | None |
| 0.6674 | 2.0 | 782 | 0.1988 | 0.8818 | 0.3580 | 0.3580 | None |
| 0.604 | 3.0 | 1173 | 0.1902 | 0.8902 | 0.3465 | 0.3465 | None |
| 0.5804 | 4.0 | 1564 | 0.1877 | 0.8952 | 0.3397 | 0.3397 | None |
| 0.5804 | 5.0 | 1955 | 0.1859 | 0.8828 | 0.3567 | 0.3567 | None |
| 0.5651 | 6.0 | 2346 | 0.1842 | 0.8915 | 0.3449 | 0.3449 | None |
| 0.5567 | 7.0 | 2737 | 0.1905 | 0.8915 | 0.3448 | 0.3448 | None |
| 0.5377 | 8.0 | 3128 | 0.1856 | 0.891 | 0.3457 | 0.3457 | None |
| 0.5365 | 9.0 | 3519 | 0.1835 | 0.8892 | 0.3480 | 0.3480 | None |
| 0.5365 | 10.0 | 3910 | 0.1823 | 0.8848 | 0.3541 | 0.3541 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0