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: 0.6132
- Accuracy: 0.8323
- Dt Accuracy: 0.8323
- Df Accuracy: 0.8938
- Unlearn Overall Accuracy: 0.2083
- 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 |
|---|---|---|---|---|---|---|---|
| 1.5113 | 1.0 | 391 | 0.6311 | 0.8872 | 0.2184 | 0.2184 | None |
| 1.4198 | 2.0 | 782 | 0.6173 | 0.888 | 0.2174 | 0.2174 | None |
| 1.3504 | 3.0 | 1173 | 0.6219 | 0.8865 | 0.2197 | 0.2197 | None |
| 1.3012 | 4.0 | 1564 | 0.6110 | 0.889 | 0.2158 | 0.2158 | None |
| 1.2406 | 5.0 | 1955 | 0.6126 | 0.8878 | 0.2178 | 0.2178 | None |
| 1.2182 | 6.0 | 2346 | 0.6170 | 0.887 | 0.2190 | 0.2190 | None |
| 1.1771 | 7.0 | 2737 | 0.6090 | 0.8932 | 0.2091 | 0.2091 | None |
| 1.1553 | 8.0 | 3128 | 0.6175 | 0.891 | 0.2127 | 0.2127 | None |
| 1.1567 | 9.0 | 3519 | 0.6139 | 0.8892 | 0.2155 | 0.2155 | None |
| 1.1382 | 10.0 | 3910 | 0.6132 | 0.8938 | 0.2083 | 0.2083 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0