13
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: 0.2041
- Accuracy: 0.9635
- Dt Accuracy: 0.9635
- Df Accuracy: 0.9674
- Unlearn Overall Accuracy: 0.2340
- 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: 13
- 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 | 0.2045 | 0.9744 | 0.2230 | 0.2230 | None |
| 0.7111 | 2.0 | 782 | 0.2246 | 0.9752 | 0.2218 | 0.2218 | None |
| 0.642 | 3.0 | 1173 | 0.2078 | 0.9776 | 0.2180 | 0.2180 | None |
| 0.6197 | 4.0 | 1564 | 0.2156 | 0.9744 | 0.2231 | 0.2231 | None |
| 0.6197 | 5.0 | 1955 | 0.2034 | 0.976 | 0.2206 | 0.2206 | None |
| 0.5994 | 6.0 | 2346 | 0.1975 | 0.9762 | 0.2203 | 0.2203 | None |
| 0.5833 | 7.0 | 2737 | 0.2082 | 0.9732 | 0.2249 | 0.2249 | None |
| 0.5661 | 8.0 | 3128 | 0.2045 | 0.9718 | 0.2272 | 0.2272 | None |
| 0.558 | 9.0 | 3519 | 0.2016 | 0.9712 | 0.2281 | 0.2281 | None |
| 0.558 | 10.0 | 3910 | 0.2041 | 0.9674 | 0.2340 | 0.2340 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0