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: 0.5471
- Accuracy: 0.84
- Dt Accuracy: 0.84
- Df Accuracy: 0.743
- Unlearn Overall Accuracy: 0.4208
- 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 |
|---|---|---|---|---|---|---|---|
| 1.1572 | 1.0 | 391 | 0.5812 | 0.73 | 0.4369 | 0.4369 | None |
| 1.1266 | 2.0 | 782 | 0.5679 | 0.75 | 0.4125 | 0.4125 | None |
| 1.099 | 3.0 | 1173 | 0.5662 | 0.738 | 0.4276 | 0.4276 | None |
| 1.0558 | 4.0 | 1564 | 0.5590 | 0.724 | 0.4445 | 0.4445 | None |
| 1.0478 | 5.0 | 1955 | 0.5574 | 0.734 | 0.4323 | 0.4323 | None |
| 1.0413 | 6.0 | 2346 | 0.5539 | 0.728 | 0.4396 | 0.4396 | None |
| 1.0416 | 7.0 | 2737 | 0.5510 | 0.708 | 0.4631 | 0.4631 | None |
| 0.9933 | 8.0 | 3128 | 0.5451 | 0.756 | 0.4046 | 0.4046 | None |
| 1.0101 | 9.0 | 3519 | 0.5483 | 0.74 | 0.4247 | 0.4247 | None |
| 0.9998 | 10.0 | 3910 | 0.5471 | 0.743 | 0.4208 | 0.4208 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0