42
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: 0.1791
- Accuracy: 0.9642
- Dt Accuracy: 0.9642
- Df Accuracy: 0.8813
- Unlearn Overall Accuracy: 0.3586
- 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: 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 | 0.2032 | 0.8853 | 0.3527 | 0.3527 | None |
| 0.5658 | 2.0 | 782 | 0.2033 | 0.884 | 0.3543 | 0.3543 | None |
| 0.515 | 3.0 | 1173 | 0.1988 | 0.895 | 0.3394 | 0.3394 | None |
| 0.4989 | 4.0 | 1564 | 0.1909 | 0.8873 | 0.3502 | 0.3502 | None |
| 0.4989 | 5.0 | 1955 | 0.1902 | 0.887 | 0.3507 | 0.3507 | None |
| 0.465 | 6.0 | 2346 | 0.1843 | 0.8867 | 0.3513 | 0.3513 | None |
| 0.4441 | 7.0 | 2737 | 0.1857 | 0.8847 | 0.3540 | 0.3540 | None |
| 0.4291 | 8.0 | 3128 | 0.1834 | 0.8747 | 0.3674 | 0.3674 | None |
| 0.4105 | 9.0 | 3519 | 0.1834 | 0.878 | 0.3630 | 0.3630 | None |
| 0.4105 | 10.0 | 3910 | 0.1791 | 0.8813 | 0.3586 | 0.3586 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2