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: 0.1343
- Accuracy: 0.9677
- Dt Accuracy: 0.9677
- Df Accuracy: 0.8935
- Unlearn Overall Accuracy: 0.3423
- 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 | 0.1432 | 0.872 | 0.3709 | 0.3709 | None |
| 0.5383 | 2.0 | 782 | 0.1479 | 0.8765 | 0.3650 | 0.3650 | None |
| 0.5029 | 3.0 | 1173 | 0.1489 | 0.885 | 0.3536 | 0.3536 | None |
| 0.4782 | 4.0 | 1564 | 0.1396 | 0.884 | 0.3552 | 0.3552 | None |
| 0.4782 | 5.0 | 1955 | 0.1358 | 0.8815 | 0.3585 | 0.3585 | None |
| 0.4591 | 6.0 | 2346 | 0.1391 | 0.883 | 0.3566 | 0.3566 | None |
| 0.4473 | 7.0 | 2737 | 0.1377 | 0.8795 | 0.3613 | 0.3613 | None |
| 0.4419 | 8.0 | 3128 | 0.1341 | 0.9 | 0.3333 | 0.3333 | None |
| 0.426 | 9.0 | 3519 | 0.1338 | 0.88 | 0.3606 | 0.3606 | None |
| 0.426 | 10.0 | 3910 | 0.1343 | 0.8935 | 0.3423 | 0.3423 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0