21
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: 0.1585
- Accuracy: 0.9682
- Dt Accuracy: 0.9682
- Df Accuracy: 0.882
- Unlearn Overall Accuracy: 0.3579
- 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: 21
- 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 | 0.1695 | 0.8753 | 0.3663 | 0.3663 | None |
| 0.6112 | 2.0 | 782 | 0.1658 | 0.8793 | 0.3613 | 0.3613 | None |
| 0.5496 | 3.0 | 1173 | 0.1588 | 0.8917 | 0.3447 | 0.3447 | None |
| 0.5357 | 4.0 | 1564 | 0.1650 | 0.8823 | 0.3574 | 0.3574 | None |
| 0.5357 | 5.0 | 1955 | 0.1647 | 0.8797 | 0.3610 | 0.3610 | None |
| 0.52 | 6.0 | 2346 | 0.1657 | 0.8893 | 0.3479 | 0.3479 | None |
| 0.5003 | 7.0 | 2737 | 0.1561 | 0.8873 | 0.3507 | 0.3507 | None |
| 0.4885 | 8.0 | 3128 | 0.1578 | 0.8917 | 0.3448 | 0.3448 | None |
| 0.4839 | 9.0 | 3519 | 0.1595 | 0.9 | 0.3333 | 0.3333 | None |
| 0.4839 | 10.0 | 3910 | 0.1585 | 0.882 | 0.3579 | 0.3579 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0