87
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: 0.1815
- Accuracy: 0.9655
- Dt Accuracy: 0.9655
- Df Accuracy: 0.8992
- Unlearn Overall Accuracy: 0.3343
- 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: 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 | 0.1826 | 0.8835 | 0.3557 | 0.3557 | None |
| 0.6691 | 2.0 | 782 | 0.1920 | 0.8842 | 0.3546 | 0.3546 | None |
| 0.5999 | 3.0 | 1173 | 0.1860 | 0.8912 | 0.3452 | 0.3452 | None |
| 0.587 | 4.0 | 1564 | 0.1910 | 0.8852 | 0.3532 | 0.3532 | None |
| 0.587 | 5.0 | 1955 | 0.1850 | 0.8888 | 0.3487 | 0.3487 | None |
| 0.5699 | 6.0 | 2346 | 0.1905 | 0.8912 | 0.3453 | 0.3453 | None |
| 0.5527 | 7.0 | 2737 | 0.1851 | 0.8862 | 0.3520 | 0.3520 | None |
| 0.5402 | 8.0 | 3128 | 0.1859 | 0.889 | 0.3483 | 0.3483 | None |
| 0.5338 | 9.0 | 3519 | 0.1797 | 0.8995 | 0.3340 | 0.3340 | None |
| 0.5338 | 10.0 | 3910 | 0.1815 | 0.8992 | 0.3343 | 0.3343 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0