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: 0.5844
- Accuracy: 0.8346
- Dt Accuracy: 0.8346
- Df Accuracy: 0.7523
- Unlearn Overall Accuracy: 0.4096
- 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 |
|---|---|---|---|---|---|---|---|
| 1.3911 | 1.0 | 391 | 0.6165 | 0.7417 | 0.4228 | 0.4228 | None |
| 1.3646 | 2.0 | 782 | 0.5977 | 0.7457 | 0.4176 | 0.4176 | None |
| 1.2918 | 3.0 | 1173 | 0.6006 | 0.736 | 0.4294 | 0.4294 | None |
| 1.2837 | 4.0 | 1564 | 0.5913 | 0.7333 | 0.4332 | 0.4332 | None |
| 1.2384 | 5.0 | 1955 | 0.5880 | 0.7313 | 0.4355 | 0.4355 | None |
| 1.2064 | 6.0 | 2346 | 0.5855 | 0.738 | 0.4276 | 0.4276 | None |
| 1.1867 | 7.0 | 2737 | 0.5843 | 0.7397 | 0.4255 | 0.4255 | None |
| 1.1868 | 8.0 | 3128 | 0.5844 | 0.7443 | 0.4197 | 0.4197 | None |
| 1.1475 | 9.0 | 3519 | 0.5792 | 0.7307 | 0.4366 | 0.4366 | None |
| 1.1402 | 10.0 | 3910 | 0.5844 | 0.7523 | 0.4096 | 0.4096 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0