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: 0.6340
- Accuracy: 0.8308
- Dt Accuracy: 0.8308
- Df Accuracy: 0.741
- Unlearn Overall Accuracy: 0.4238
- 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 |
|---|---|---|---|---|---|---|---|
| 1.6152 | 1.0 | 391 | 0.6479 | 0.7394 | 0.4255 | 0.4255 | None |
| 1.5368 | 2.0 | 782 | 0.6353 | 0.7344 | 0.4311 | 0.4311 | None |
| 1.454 | 3.0 | 1173 | 0.6326 | 0.7342 | 0.4317 | 0.4317 | None |
| 1.3652 | 4.0 | 1564 | 0.6403 | 0.734 | 0.4318 | 0.4318 | None |
| 1.329 | 5.0 | 1955 | 0.6363 | 0.7376 | 0.4275 | 0.4275 | None |
| 1.2898 | 6.0 | 2346 | 0.6345 | 0.733 | 0.4332 | 0.4332 | None |
| 1.2684 | 7.0 | 2737 | 0.6353 | 0.7308 | 0.4361 | 0.4361 | None |
| 1.258 | 8.0 | 3128 | 0.6362 | 0.737 | 0.4287 | 0.4287 | None |
| 1.2642 | 9.0 | 3519 | 0.6337 | 0.742 | 0.4224 | 0.4224 | None |
| 1.2386 | 10.0 | 3910 | 0.6340 | 0.741 | 0.4238 | 0.4238 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0