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: 0.6356
- Accuracy: 0.8309
- Dt Accuracy: 0.8309
- Df Accuracy: 0.7326
- Unlearn Overall Accuracy: 0.4341
- 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 |
|---|---|---|---|---|---|---|---|
| 1.6219 | 1.0 | 391 | 0.6482 | 0.7448 | 0.4186 | 0.4186 | None |
| 1.5152 | 2.0 | 782 | 0.6377 | 0.736 | 0.4293 | 0.4293 | None |
| 1.4346 | 3.0 | 1173 | 0.6306 | 0.7296 | 0.4373 | 0.4373 | None |
| 1.3893 | 4.0 | 1564 | 0.6264 | 0.7418 | 0.4225 | 0.4225 | None |
| 1.3278 | 5.0 | 1955 | 0.6368 | 0.7274 | 0.4401 | 0.4401 | None |
| 1.2947 | 6.0 | 2346 | 0.6288 | 0.7394 | 0.4259 | 0.4259 | None |
| 1.2745 | 7.0 | 2737 | 0.6356 | 0.7368 | 0.4288 | 0.4288 | None |
| 1.2674 | 8.0 | 3128 | 0.6376 | 0.7364 | 0.4295 | 0.4295 | None |
| 1.2582 | 9.0 | 3519 | 0.6358 | 0.7342 | 0.4320 | 0.4320 | None |
| 1.2343 | 10.0 | 3910 | 0.6356 | 0.7326 | 0.4341 | 0.4341 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0