87
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: 0.5601
- Accuracy: 0.8383
- Dt Accuracy: 0.8383
- Df Accuracy: 0.8915
- Unlearn Overall Accuracy: 0.2118
- 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: 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 |
|---|---|---|---|---|---|---|---|
| 1.2988 | 1.0 | 391 | 0.5881 | 0.8885 | 0.2165 | 0.2165 | None |
| 1.2487 | 2.0 | 782 | 0.5867 | 0.888 | 0.2174 | 0.2174 | None |
| 1.221 | 3.0 | 1173 | 0.5796 | 0.881 | 0.2285 | 0.2285 | None |
| 1.1502 | 4.0 | 1564 | 0.5766 | 0.8875 | 0.2183 | 0.2183 | None |
| 1.1508 | 5.0 | 1955 | 0.5679 | 0.886 | 0.2205 | 0.2205 | None |
| 1.1095 | 6.0 | 2346 | 0.5664 | 0.884 | 0.2237 | 0.2237 | None |
| 1.0777 | 7.0 | 2737 | 0.5661 | 0.8885 | 0.2166 | 0.2166 | None |
| 1.0245 | 8.0 | 3128 | 0.5582 | 0.888 | 0.2173 | 0.2173 | None |
| 1.0522 | 9.0 | 3519 | 0.5636 | 0.8885 | 0.2165 | 0.2165 | None |
| 1.0587 | 10.0 | 3910 | 0.5601 | 0.8915 | 0.2118 | 0.2118 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0