21
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: 0.1862
- Accuracy: 0.9658
- Dt Accuracy: 0.9658
- Df Accuracy: 0.8902
- Unlearn Overall Accuracy: 0.3467
- 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: 21
- 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 | 0.1952 | 0.891 | 0.3453 | 0.3453 | None |
| 0.6648 | 2.0 | 782 | 0.1874 | 0.8772 | 0.3640 | 0.3640 | None |
| 0.6015 | 3.0 | 1173 | 0.1917 | 0.8935 | 0.3420 | 0.3420 | None |
| 0.5861 | 4.0 | 1564 | 0.1851 | 0.881 | 0.3591 | 0.3591 | None |
| 0.5861 | 5.0 | 1955 | 0.1880 | 0.8945 | 0.3408 | 0.3408 | None |
| 0.5659 | 6.0 | 2346 | 0.1894 | 0.8852 | 0.3534 | 0.3534 | None |
| 0.5488 | 7.0 | 2737 | 0.1849 | 0.8915 | 0.3450 | 0.3450 | None |
| 0.5412 | 8.0 | 3128 | 0.1843 | 0.8945 | 0.3409 | 0.3409 | None |
| 0.5283 | 9.0 | 3519 | 0.1815 | 0.8912 | 0.3453 | 0.3453 | None |
| 0.5283 | 10.0 | 3910 | 0.1862 | 0.8902 | 0.3467 | 0.3467 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0