100
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: 0.1338
- Accuracy: 0.9679
- Dt Accuracy: 0.9679
- Df Accuracy: 0.8865
- Unlearn Overall Accuracy: 0.3518
- 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: 100
- 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 | 0.1495 | 0.864 | 0.3814 | 0.3814 | None |
| 0.5418 | 2.0 | 782 | 0.1361 | 0.8835 | 0.3558 | 0.3558 | None |
| 0.4966 | 3.0 | 1173 | 0.1456 | 0.876 | 0.3657 | 0.3657 | None |
| 0.4797 | 4.0 | 1564 | 0.1377 | 0.885 | 0.3539 | 0.3539 | None |
| 0.4797 | 5.0 | 1955 | 0.1340 | 0.886 | 0.3525 | 0.3525 | None |
| 0.4608 | 6.0 | 2346 | 0.1345 | 0.886 | 0.3525 | 0.3525 | None |
| 0.452 | 7.0 | 2737 | 0.1374 | 0.8745 | 0.3680 | 0.3680 | None |
| 0.4325 | 8.0 | 3128 | 0.1373 | 0.895 | 0.3402 | 0.3402 | None |
| 0.4307 | 9.0 | 3519 | 0.1357 | 0.896 | 0.3389 | 0.3389 | None |
| 0.4307 | 10.0 | 3910 | 0.1338 | 0.8865 | 0.3518 | 0.3518 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0