13
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: 0.1546
- Accuracy: 0.968
- Dt Accuracy: 0.968
- Df Accuracy: 0.887
- Unlearn Overall Accuracy: 0.3512
- 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: 13
- 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 | 0.1642 | 0.8773 | 0.3639 | 0.3639 | None |
| 0.6054 | 2.0 | 782 | 0.1645 | 0.8857 | 0.3528 | 0.3528 | None |
| 0.5557 | 3.0 | 1173 | 0.1595 | 0.8793 | 0.3615 | 0.3615 | None |
| 0.5341 | 4.0 | 1564 | 0.1606 | 0.888 | 0.3497 | 0.3497 | None |
| 0.5341 | 5.0 | 1955 | 0.1629 | 0.8957 | 0.3392 | 0.3392 | None |
| 0.5165 | 6.0 | 2346 | 0.1595 | 0.8873 | 0.3507 | 0.3507 | None |
| 0.501 | 7.0 | 2737 | 0.1602 | 0.8917 | 0.3446 | 0.3446 | None |
| 0.494 | 8.0 | 3128 | 0.1588 | 0.895 | 0.3402 | 0.3402 | None |
| 0.4868 | 9.0 | 3519 | 0.1537 | 0.886 | 0.3525 | 0.3525 | None |
| 0.4868 | 10.0 | 3910 | 0.1546 | 0.887 | 0.3512 | 0.3512 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0