13
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: 0.2029
- Accuracy: 0.966
- Dt Accuracy: 0.966
- Df Accuracy: 0.8904
- Unlearn Overall Accuracy: 0.3465
- 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: 13
- 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 | 0.2076 | 0.8724 | 0.3703 | 0.3703 | None |
| 0.7285 | 2.0 | 782 | 0.2198 | 0.882 | 0.3575 | 0.3575 | None |
| 0.6447 | 3.0 | 1173 | 0.2040 | 0.8838 | 0.3554 | 0.3554 | None |
| 0.626 | 4.0 | 1564 | 0.2139 | 0.89 | 0.3470 | 0.3470 | None |
| 0.626 | 5.0 | 1955 | 0.1998 | 0.889 | 0.3483 | 0.3483 | None |
| 0.6077 | 6.0 | 2346 | 0.2006 | 0.8876 | 0.3503 | 0.3503 | None |
| 0.5942 | 7.0 | 2737 | 0.2028 | 0.8848 | 0.3542 | 0.3542 | None |
| 0.5862 | 8.0 | 3128 | 0.2051 | 0.886 | 0.3525 | 0.3525 | None |
| 0.5739 | 9.0 | 3519 | 0.2026 | 0.8912 | 0.3454 | 0.3454 | None |
| 0.5739 | 10.0 | 3910 | 0.2029 | 0.8904 | 0.3465 | 0.3465 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0