42
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: 0.2028
- Accuracy: 0.9655
- Dt Accuracy: 0.9655
- Df Accuracy: 0.8876
- Unlearn Overall Accuracy: 0.3503
- 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: 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 391 | 0.2124 | 0.8762 | 0.3654 | 0.3654 | None |
| 0.723 | 2.0 | 782 | 0.1992 | 0.884 | 0.3550 | 0.3550 | None |
| 0.6484 | 3.0 | 1173 | 0.2070 | 0.8768 | 0.3646 | 0.3646 | None |
| 0.6252 | 4.0 | 1564 | 0.2013 | 0.8922 | 0.3439 | 0.3439 | None |
| 0.6252 | 5.0 | 1955 | 0.2011 | 0.8876 | 0.3502 | 0.3502 | None |
| 0.6071 | 6.0 | 2346 | 0.1985 | 0.8924 | 0.3436 | 0.3436 | None |
| 0.594 | 7.0 | 2737 | 0.2003 | 0.8938 | 0.3418 | 0.3418 | None |
| 0.5796 | 8.0 | 3128 | 0.2015 | 0.8926 | 0.3434 | 0.3434 | None |
| 0.5762 | 9.0 | 3519 | 0.2043 | 0.8914 | 0.3451 | 0.3451 | None |
| 0.5762 | 10.0 | 3910 | 0.2028 | 0.8876 | 0.3503 | 0.3503 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0