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: 0.1826
- Accuracy: 0.966
- Dt Accuracy: 0.966
- Df Accuracy: 0.891
- Unlearn Overall Accuracy: 0.3457
- 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 | 0.1808 | 0.8932 | 0.3423 | 0.3423 | None |
| 0.6979 | 2.0 | 782 | 0.1759 | 0.8965 | 0.3380 | 0.3380 | None |
| 0.6083 | 3.0 | 1173 | 0.1942 | 0.8855 | 0.3530 | 0.3530 | None |
| 0.59 | 4.0 | 1564 | 0.1795 | 0.8915 | 0.3449 | 0.3449 | None |
| 0.59 | 5.0 | 1955 | 0.1821 | 0.8838 | 0.3555 | 0.3555 | None |
| 0.5761 | 6.0 | 2346 | 0.1815 | 0.898 | 0.3360 | 0.3360 | None |
| 0.5671 | 7.0 | 2737 | 0.1873 | 0.9015 | 0.3311 | 0.3311 | None |
| 0.5588 | 8.0 | 3128 | 0.1847 | 0.8925 | 0.3436 | 0.3436 | None |
| 0.5569 | 9.0 | 3519 | 0.1812 | 0.899 | 0.3346 | 0.3346 | None |
| 0.5569 | 10.0 | 3910 | 0.1826 | 0.891 | 0.3457 | 0.3457 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2