87
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: 0.1548
- Accuracy: 0.9675
- Dt Accuracy: 0.9675
- Df Accuracy: 0.894
- Unlearn Overall Accuracy: 0.3416
- 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: 87
- 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 | 0.1538 | 0.875 | 0.3670 | 0.3670 | None |
| 0.6098 | 2.0 | 782 | 0.1627 | 0.8797 | 0.3608 | 0.3608 | None |
| 0.5564 | 3.0 | 1173 | 0.1613 | 0.873 | 0.3697 | 0.3697 | None |
| 0.533 | 4.0 | 1564 | 0.1613 | 0.8837 | 0.3556 | 0.3556 | None |
| 0.533 | 5.0 | 1955 | 0.1622 | 0.8963 | 0.3384 | 0.3384 | None |
| 0.52 | 6.0 | 2346 | 0.1646 | 0.886 | 0.3524 | 0.3524 | None |
| 0.5003 | 7.0 | 2737 | 0.1594 | 0.883 | 0.3565 | 0.3565 | None |
| 0.4924 | 8.0 | 3128 | 0.1616 | 0.8913 | 0.3453 | 0.3453 | None |
| 0.4797 | 9.0 | 3519 | 0.1574 | 0.8907 | 0.3462 | 0.3462 | None |
| 0.4797 | 10.0 | 3910 | 0.1548 | 0.894 | 0.3416 | 0.3416 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0