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: 0.1586
- Accuracy: 0.9676
- Dt Accuracy: 0.9676
- Df Accuracy: 0.892
- Unlearn Overall Accuracy: 0.3444
- 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 | 0.1534 | 0.888 | 0.3495 | 0.3495 | None |
| 0.6247 | 2.0 | 782 | 0.1545 | 0.8907 | 0.3460 | 0.3460 | None |
| 0.5543 | 3.0 | 1173 | 0.1605 | 0.8977 | 0.3364 | 0.3364 | None |
| 0.5457 | 4.0 | 1564 | 0.1619 | 0.8883 | 0.3493 | 0.3493 | None |
| 0.5457 | 5.0 | 1955 | 0.1603 | 0.885 | 0.3539 | 0.3539 | None |
| 0.5254 | 6.0 | 2346 | 0.1592 | 0.8797 | 0.3611 | 0.3611 | None |
| 0.5156 | 7.0 | 2737 | 0.1636 | 0.889 | 0.3484 | 0.3484 | None |
| 0.5184 | 8.0 | 3128 | 0.1605 | 0.8883 | 0.3493 | 0.3493 | None |
| 0.5076 | 9.0 | 3519 | 0.1608 | 0.8887 | 0.3489 | 0.3489 | None |
| 0.5076 | 10.0 | 3910 | 0.1586 | 0.892 | 0.3444 | 0.3444 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2