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: 0.1578
- Accuracy: 0.9679
- Dt Accuracy: 0.9679
- Df Accuracy: 0.966
- Unlearn Overall Accuracy: 0.2363
- 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 | 0.1660 | 0.974 | 0.2236 | 0.2236 | None |
| 0.6014 | 2.0 | 782 | 0.1685 | 0.975 | 0.2221 | 0.2221 | None |
| 0.5454 | 3.0 | 1173 | 0.1702 | 0.975 | 0.2222 | 0.2222 | None |
| 0.5282 | 4.0 | 1564 | 0.1562 | 0.9773 | 0.2185 | 0.2185 | None |
| 0.5282 | 5.0 | 1955 | 0.1543 | 0.9753 | 0.2217 | 0.2217 | None |
| 0.514 | 6.0 | 2346 | 0.1626 | 0.9703 | 0.2295 | 0.2295 | None |
| 0.4906 | 7.0 | 2737 | 0.1591 | 0.9683 | 0.2327 | 0.2327 | None |
| 0.4795 | 8.0 | 3128 | 0.1642 | 0.9657 | 0.2368 | 0.2368 | None |
| 0.4658 | 9.0 | 3519 | 0.1578 | 0.9637 | 0.2399 | 0.2399 | None |
| 0.4658 | 10.0 | 3910 | 0.1578 | 0.966 | 0.2363 | 0.2363 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0