87
This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1568
- Accuracy: 0.9637
- Dt Accuracy: 0.9637
- Df Accuracy: 0.8775
- Unlearn Overall Accuracy: 0.3637
- 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 | 0.1825 | 0.878 | 0.3623 | 0.3623 | None |
| 0.4919 | 2.0 | 782 | 0.2044 | 0.8745 | 0.3668 | 0.3668 | None |
| 0.4625 | 3.0 | 1173 | 0.1773 | 0.8815 | 0.3579 | 0.3579 | None |
| 0.4354 | 4.0 | 1564 | 0.1697 | 0.8775 | 0.3634 | 0.3634 | None |
| 0.4354 | 5.0 | 1955 | 0.1668 | 0.8765 | 0.3647 | 0.3647 | None |
| 0.4124 | 6.0 | 2346 | 0.1687 | 0.8785 | 0.3622 | 0.3622 | None |
| 0.3879 | 7.0 | 2737 | 0.1612 | 0.866 | 0.3790 | 0.3790 | None |
| 0.3715 | 8.0 | 3128 | 0.1664 | 0.858 | 0.3892 | 0.3892 | None |
| 0.3563 | 9.0 | 3519 | 0.1581 | 0.867 | 0.3776 | 0.3776 | None |
| 0.3563 | 10.0 | 3910 | 0.1568 | 0.8775 | 0.3637 | 0.3637 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2