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: 0.1587
- Accuracy: 0.9671
- Dt Accuracy: 0.9671
- Df Accuracy: 0.8953
- Unlearn Overall Accuracy: 0.3398
- 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 | 0.1599 | 0.8817 | 0.3581 | 0.3581 | None |
| 0.6066 | 2.0 | 782 | 0.1575 | 0.882 | 0.3577 | 0.3577 | None |
| 0.5495 | 3.0 | 1173 | 0.1600 | 0.8793 | 0.3613 | 0.3613 | None |
| 0.5352 | 4.0 | 1564 | 0.1589 | 0.886 | 0.3525 | 0.3525 | None |
| 0.5352 | 5.0 | 1955 | 0.1565 | 0.8823 | 0.3573 | 0.3573 | None |
| 0.5177 | 6.0 | 2346 | 0.1556 | 0.8827 | 0.3571 | 0.3571 | None |
| 0.5049 | 7.0 | 2737 | 0.1533 | 0.8953 | 0.3398 | 0.3398 | None |
| 0.4872 | 8.0 | 3128 | 0.1569 | 0.9003 | 0.3328 | 0.3328 | None |
| 0.4814 | 9.0 | 3519 | 0.1558 | 0.889 | 0.3484 | 0.3484 | None |
| 0.4814 | 10.0 | 3910 | 0.1587 | 0.8953 | 0.3398 | 0.3398 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0