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: 0.1385
- Accuracy: 0.9669
- Dt Accuracy: 0.9669
- Df Accuracy: 0.89
- Unlearn Overall Accuracy: 0.3471
- 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 | 0.1486 | 0.8835 | 0.3555 | 0.3555 | None |
| 0.5365 | 2.0 | 782 | 0.1353 | 0.877 | 0.3645 | 0.3645 | None |
| 0.498 | 3.0 | 1173 | 0.1416 | 0.8695 | 0.3746 | 0.3746 | None |
| 0.4713 | 4.0 | 1564 | 0.1437 | 0.8865 | 0.3518 | 0.3518 | None |
| 0.4713 | 5.0 | 1955 | 0.1391 | 0.8825 | 0.3572 | 0.3572 | None |
| 0.4616 | 6.0 | 2346 | 0.1385 | 0.886 | 0.3524 | 0.3524 | None |
| 0.4415 | 7.0 | 2737 | 0.1396 | 0.88 | 0.3605 | 0.3605 | None |
| 0.4305 | 8.0 | 3128 | 0.1405 | 0.8855 | 0.3532 | 0.3532 | None |
| 0.4249 | 9.0 | 3519 | 0.1378 | 0.8805 | 0.3600 | 0.3600 | None |
| 0.4249 | 10.0 | 3910 | 0.1385 | 0.89 | 0.3471 | 0.3471 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0