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: 0.1835
- Accuracy: 0.9676
- Dt Accuracy: 0.9676
- Df Accuracy: 0.9698
- Unlearn Overall Accuracy: 0.2305
- 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 | 0.2066 | 0.9762 | 0.2201 | 0.2201 | None |
| 0.6587 | 2.0 | 782 | 0.1926 | 0.9758 | 0.2209 | 0.2209 | None |
| 0.606 | 3.0 | 1173 | 0.1787 | 0.977 | 0.2190 | 0.2190 | None |
| 0.5789 | 4.0 | 1564 | 0.1761 | 0.9785 | 0.2166 | 0.2166 | None |
| 0.5789 | 5.0 | 1955 | 0.1890 | 0.976 | 0.2205 | 0.2205 | None |
| 0.5535 | 6.0 | 2346 | 0.1781 | 0.975 | 0.2222 | 0.2222 | None |
| 0.5384 | 7.0 | 2737 | 0.1817 | 0.9715 | 0.2277 | 0.2277 | None |
| 0.5243 | 8.0 | 3128 | 0.1858 | 0.974 | 0.2238 | 0.2238 | None |
| 0.5103 | 9.0 | 3519 | 0.1811 | 0.9708 | 0.2289 | 0.2289 | None |
| 0.5103 | 10.0 | 3910 | 0.1835 | 0.9698 | 0.2305 | 0.2305 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0