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: 0.1979
- Accuracy: 0.9656
- Dt Accuracy: 0.9656
- Df Accuracy: 0.9708
- Unlearn Overall Accuracy: 0.2288
- 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 | 0.2005 | 0.9766 | 0.2196 | 0.2196 | None |
| 0.7173 | 2.0 | 782 | 0.2098 | 0.9748 | 0.2224 | 0.2224 | None |
| 0.6431 | 3.0 | 1173 | 0.2092 | 0.978 | 0.2174 | 0.2174 | None |
| 0.6241 | 4.0 | 1564 | 0.2140 | 0.9754 | 0.2214 | 0.2214 | None |
| 0.6241 | 5.0 | 1955 | 0.2068 | 0.972 | 0.2268 | 0.2268 | None |
| 0.6009 | 6.0 | 2346 | 0.2006 | 0.9736 | 0.2244 | 0.2244 | None |
| 0.5825 | 7.0 | 2737 | 0.1960 | 0.973 | 0.2253 | 0.2253 | None |
| 0.5699 | 8.0 | 3128 | 0.2028 | 0.9722 | 0.2266 | 0.2266 | None |
| 0.5549 | 9.0 | 3519 | 0.1994 | 0.9698 | 0.2303 | 0.2303 | None |
| 0.5549 | 10.0 | 3910 | 0.1979 | 0.9708 | 0.2288 | 0.2288 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0