87
This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1390
- Accuracy: 0.9668
- Dt Accuracy: 0.9668
- Df Accuracy: 0.959
- Unlearn Overall Accuracy: 0.2471
- 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: 0.0001
- 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 391 | 0.1481 | 0.972 | 0.2268 | 0.2268 | None |
| 0.5364 | 2.0 | 782 | 0.1479 | 0.97 | 0.2299 | 0.2299 | None |
| 0.4949 | 3.0 | 1173 | 0.1431 | 0.97 | 0.2300 | 0.2300 | None |
| 0.4724 | 4.0 | 1564 | 0.1437 | 0.9635 | 0.2401 | 0.2401 | None |
| 0.4724 | 5.0 | 1955 | 0.1428 | 0.9655 | 0.2370 | 0.2370 | None |
| 0.4574 | 6.0 | 2346 | 0.1440 | 0.9635 | 0.2401 | 0.2401 | None |
| 0.436 | 7.0 | 2737 | 0.1398 | 0.964 | 0.2394 | 0.2394 | None |
| 0.4275 | 8.0 | 3128 | 0.1400 | 0.963 | 0.2410 | 0.2410 | None |
| 0.4139 | 9.0 | 3519 | 0.1387 | 0.9605 | 0.2448 | 0.2448 | None |
| 0.4139 | 10.0 | 3910 | 0.1390 | 0.959 | 0.2471 | 0.2471 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0