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: 0.1985
- Accuracy: 0.967
- Dt Accuracy: 0.967
- Df Accuracy: 0.8982
- Unlearn Overall Accuracy: 0.3358
- 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 | 0.2052 | 0.877 | 0.3640 | 0.3640 | None |
| 0.7222 | 2.0 | 782 | 0.2120 | 0.8782 | 0.3627 | 0.3627 | None |
| 0.6514 | 3.0 | 1173 | 0.2059 | 0.8866 | 0.3514 | 0.3514 | None |
| 0.6284 | 4.0 | 1564 | 0.2111 | 0.8848 | 0.3539 | 0.3539 | None |
| 0.6284 | 5.0 | 1955 | 0.2037 | 0.8922 | 0.3439 | 0.3439 | None |
| 0.6123 | 6.0 | 2346 | 0.2005 | 0.8904 | 0.3465 | 0.3465 | None |
| 0.594 | 7.0 | 2737 | 0.2010 | 0.8834 | 0.3560 | 0.3560 | None |
| 0.583 | 8.0 | 3128 | 0.2032 | 0.8946 | 0.3408 | 0.3408 | None |
| 0.5745 | 9.0 | 3519 | 0.2000 | 0.8886 | 0.3489 | 0.3489 | None |
| 0.5745 | 10.0 | 3910 | 0.1985 | 0.8982 | 0.3358 | 0.3358 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0