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: 0.2286
- Accuracy: 0.9589
- Dt Accuracy: 0.9589
- Df Accuracy: 0.8832
- Unlearn Overall Accuracy: 0.3558
- 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 | 0.2741 | 0.885 | 0.3526 | 0.3526 | None |
| 0.6793 | 2.0 | 782 | 0.2483 | 0.8932 | 0.3418 | 0.3418 | None |
| 0.6153 | 3.0 | 1173 | 0.2483 | 0.893 | 0.3424 | 0.3424 | None |
| 0.5874 | 4.0 | 1564 | 0.2337 | 0.895 | 0.3394 | 0.3394 | None |
| 0.5874 | 5.0 | 1955 | 0.2403 | 0.8956 | 0.3388 | 0.3388 | None |
| 0.5647 | 6.0 | 2346 | 0.2336 | 0.894 | 0.3411 | 0.3411 | None |
| 0.536 | 7.0 | 2737 | 0.2306 | 0.8984 | 0.3351 | 0.3351 | None |
| 0.5166 | 8.0 | 3128 | 0.2344 | 0.8878 | 0.3496 | 0.3496 | None |
| 0.4983 | 9.0 | 3519 | 0.2262 | 0.8756 | 0.3661 | 0.3661 | None |
| 0.4983 | 10.0 | 3910 | 0.2286 | 0.8832 | 0.3558 | 0.3558 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2