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: 0.1596
- Accuracy: 0.9663
- Dt Accuracy: 0.9663
- Df Accuracy: 0.969
- Unlearn Overall Accuracy: 0.2316
- 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 | 0.1682 | 0.975 | 0.2221 | 0.2221 | None |
| 0.5997 | 2.0 | 782 | 0.1727 | 0.9737 | 0.2242 | 0.2242 | None |
| 0.5567 | 3.0 | 1173 | 0.1678 | 0.975 | 0.2222 | 0.2222 | None |
| 0.525 | 4.0 | 1564 | 0.1565 | 0.9757 | 0.2212 | 0.2212 | None |
| 0.525 | 5.0 | 1955 | 0.1618 | 0.9717 | 0.2275 | 0.2275 | None |
| 0.5118 | 6.0 | 2346 | 0.1584 | 0.974 | 0.2238 | 0.2238 | None |
| 0.4882 | 7.0 | 2737 | 0.1598 | 0.9723 | 0.2264 | 0.2264 | None |
| 0.4771 | 8.0 | 3128 | 0.1617 | 0.9677 | 0.2337 | 0.2337 | None |
| 0.4661 | 9.0 | 3519 | 0.1568 | 0.9693 | 0.2311 | 0.2311 | None |
| 0.4661 | 10.0 | 3910 | 0.1596 | 0.969 | 0.2316 | 0.2316 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0