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: 0.1366
- Accuracy: 0.9682
- Dt Accuracy: 0.9682
- Df Accuracy: 0.8815
- Unlearn Overall Accuracy: 0.3586
- 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 | 0.1499 | 0.88 | 0.3603 | 0.3603 | None |
| 0.5358 | 2.0 | 782 | 0.1431 | 0.877 | 0.3644 | 0.3644 | None |
| 0.5002 | 3.0 | 1173 | 0.1447 | 0.881 | 0.3591 | 0.3591 | None |
| 0.4784 | 4.0 | 1564 | 0.1430 | 0.8815 | 0.3585 | 0.3585 | None |
| 0.4784 | 5.0 | 1955 | 0.1335 | 0.8895 | 0.3477 | 0.3477 | None |
| 0.4587 | 6.0 | 2346 | 0.1360 | 0.89 | 0.3471 | 0.3471 | None |
| 0.4447 | 7.0 | 2737 | 0.1388 | 0.8805 | 0.3600 | 0.3600 | None |
| 0.4386 | 8.0 | 3128 | 0.1392 | 0.882 | 0.3579 | 0.3579 | None |
| 0.4314 | 9.0 | 3519 | 0.1367 | 0.884 | 0.3552 | 0.3552 | None |
| 0.4314 | 10.0 | 3910 | 0.1366 | 0.8815 | 0.3586 | 0.3586 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0