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: 0.1790
- Accuracy: 0.9665
- Dt Accuracy: 0.9665
- Df Accuracy: 0.9702
- Unlearn Overall Accuracy: 0.2297
- 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 | 0.1931 | 0.9785 | 0.2166 | 0.2166 | None |
| 0.6606 | 2.0 | 782 | 0.1927 | 0.9755 | 0.2212 | 0.2212 | None |
| 0.5976 | 3.0 | 1173 | 0.1907 | 0.9738 | 0.2241 | 0.2241 | None |
| 0.5781 | 4.0 | 1564 | 0.1843 | 0.977 | 0.2190 | 0.2190 | None |
| 0.5781 | 5.0 | 1955 | 0.1812 | 0.9765 | 0.2198 | 0.2198 | None |
| 0.5594 | 6.0 | 2346 | 0.1886 | 0.9765 | 0.2198 | 0.2198 | None |
| 0.5423 | 7.0 | 2737 | 0.1824 | 0.972 | 0.2269 | 0.2269 | None |
| 0.5271 | 8.0 | 3128 | 0.1821 | 0.9712 | 0.2281 | 0.2281 | None |
| 0.513 | 9.0 | 3519 | 0.1756 | 0.9712 | 0.2281 | 0.2281 | None |
| 0.513 | 10.0 | 3910 | 0.1790 | 0.9702 | 0.2297 | 0.2297 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0