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: 0.5507
- Accuracy: 0.8388
- Dt Accuracy: 0.8388
- Df Accuracy: 0.902
- Unlearn Overall Accuracy: 0.1948
- 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: 5e-05
- 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 |
|---|---|---|---|---|---|---|---|
| 1.1453 | 1.0 | 391 | 0.5857 | 0.896 | 0.2045 | 0.2045 | None |
| 1.1187 | 2.0 | 782 | 0.5686 | 0.89 | 0.2143 | 0.2143 | None |
| 1.1014 | 3.0 | 1173 | 0.5703 | 0.899 | 0.1998 | 0.1998 | None |
| 1.0586 | 4.0 | 1564 | 0.5550 | 0.898 | 0.2014 | 0.2014 | None |
| 1.034 | 5.0 | 1955 | 0.5553 | 0.899 | 0.1997 | 0.1997 | None |
| 0.9955 | 6.0 | 2346 | 0.5596 | 0.897 | 0.2030 | 0.2030 | None |
| 0.998 | 7.0 | 2737 | 0.5510 | 0.904 | 0.1916 | 0.1916 | None |
| 0.9918 | 8.0 | 3128 | 0.5524 | 0.898 | 0.2013 | 0.2013 | None |
| 0.9623 | 9.0 | 3519 | 0.5494 | 0.899 | 0.1997 | 0.1997 | None |
| 0.9391 | 10.0 | 3910 | 0.5507 | 0.902 | 0.1948 | 0.1948 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0