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: 0.5656
- Accuracy: 0.8396
- Dt Accuracy: 0.8396
- Df Accuracy: 0.8875
- Unlearn Overall Accuracy: 0.2181
- 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 |
|---|---|---|---|---|---|---|---|
| 1.2677 | 1.0 | 391 | 0.5909 | 0.889 | 0.2157 | 0.2157 | None |
| 1.2377 | 2.0 | 782 | 0.5800 | 0.891 | 0.2126 | 0.2126 | None |
| 1.1979 | 3.0 | 1173 | 0.5847 | 0.878 | 0.2331 | 0.2331 | None |
| 1.1634 | 4.0 | 1564 | 0.5772 | 0.881 | 0.2285 | 0.2285 | None |
| 1.1283 | 5.0 | 1955 | 0.5722 | 0.887 | 0.2190 | 0.2190 | None |
| 1.0939 | 6.0 | 2346 | 0.5721 | 0.8875 | 0.2182 | 0.2182 | None |
| 1.0777 | 7.0 | 2737 | 0.5656 | 0.8835 | 0.2245 | 0.2245 | None |
| 1.0638 | 8.0 | 3128 | 0.5759 | 0.884 | 0.2237 | 0.2237 | None |
| 1.0449 | 9.0 | 3519 | 0.5640 | 0.8865 | 0.2197 | 0.2197 | None |
| 1.0251 | 10.0 | 3910 | 0.5656 | 0.8875 | 0.2181 | 0.2181 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0