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: 0.1165
- Accuracy: 0.9666
- Dt Accuracy: 0.9666
- Df Accuracy: 0.886
- Unlearn Overall Accuracy: 0.3525
- 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 | 0.1310 | 0.865 | 0.3802 | 0.3802 | None |
| 0.4612 | 2.0 | 782 | 0.1229 | 0.88 | 0.3604 | 0.3604 | None |
| 0.4278 | 3.0 | 1173 | 0.1256 | 0.864 | 0.3816 | 0.3816 | None |
| 0.4101 | 4.0 | 1564 | 0.1224 | 0.881 | 0.3592 | 0.3592 | None |
| 0.4101 | 5.0 | 1955 | 0.1182 | 0.874 | 0.3686 | 0.3686 | None |
| 0.3907 | 6.0 | 2346 | 0.1187 | 0.884 | 0.3553 | 0.3553 | None |
| 0.3811 | 7.0 | 2737 | 0.1145 | 0.866 | 0.3791 | 0.3791 | None |
| 0.3695 | 8.0 | 3128 | 0.1170 | 0.874 | 0.3687 | 0.3687 | None |
| 0.3637 | 9.0 | 3519 | 0.1159 | 0.896 | 0.3389 | 0.3389 | None |
| 0.3637 | 10.0 | 3910 | 0.1165 | 0.886 | 0.3525 | 0.3525 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0