100
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: 0.1772
- Accuracy: 0.9684
- Dt Accuracy: 0.9684
- Df Accuracy: 0.9705
- Unlearn Overall Accuracy: 0.2293
- 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: 100
- 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 | 0.1845 | 0.9765 | 0.2197 | 0.2197 | None |
| 0.6664 | 2.0 | 782 | 0.2002 | 0.9788 | 0.2162 | 0.2162 | None |
| 0.6065 | 3.0 | 1173 | 0.1891 | 0.975 | 0.2221 | 0.2221 | None |
| 0.5775 | 4.0 | 1564 | 0.1849 | 0.9795 | 0.2150 | 0.2150 | None |
| 0.5775 | 5.0 | 1955 | 0.1836 | 0.9772 | 0.2186 | 0.2186 | None |
| 0.5566 | 6.0 | 2346 | 0.1783 | 0.9762 | 0.2202 | 0.2202 | None |
| 0.5395 | 7.0 | 2737 | 0.1820 | 0.973 | 0.2254 | 0.2254 | None |
| 0.529 | 8.0 | 3128 | 0.1864 | 0.9725 | 0.2261 | 0.2261 | None |
| 0.5148 | 9.0 | 3519 | 0.1798 | 0.9722 | 0.2265 | 0.2265 | None |
| 0.5148 | 10.0 | 3910 | 0.1772 | 0.9705 | 0.2293 | 0.2293 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0