42
This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: 0.5861
- Accuracy: 0.8338
- Dt Accuracy: 0.8338
- Df Accuracy: 0.8913
- Unlearn Overall Accuracy: 0.2121
- 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: 5e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- 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 |
|---|---|---|---|---|---|---|---|
| 1.4001 | 1.0 | 391 | 0.6190 | 0.8843 | 0.2229 | 0.2229 | None |
| 1.3438 | 2.0 | 782 | 0.6104 | 0.8883 | 0.2167 | 0.2167 | None |
| 1.2855 | 3.0 | 1173 | 0.6013 | 0.8833 | 0.2248 | 0.2248 | None |
| 1.2479 | 4.0 | 1564 | 0.5943 | 0.889 | 0.2158 | 0.2158 | None |
| 1.1909 | 5.0 | 1955 | 0.5923 | 0.8963 | 0.2041 | 0.2041 | None |
| 1.1391 | 6.0 | 2346 | 0.5888 | 0.8917 | 0.2116 | 0.2116 | None |
| 1.1254 | 7.0 | 2737 | 0.5866 | 0.8917 | 0.2116 | 0.2116 | None |
| 1.1123 | 8.0 | 3128 | 0.5885 | 0.892 | 0.2110 | 0.2110 | None |
| 1.0918 | 9.0 | 3519 | 0.5805 | 0.8943 | 0.2073 | 0.2073 | None |
| 1.0779 | 10.0 | 3910 | 0.5861 | 0.8913 | 0.2121 | 0.2121 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0