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: 0.1194
- Accuracy: 0.9675
- Dt Accuracy: 0.9675
- Df Accuracy: 0.877
- Unlearn Overall Accuracy: 0.3647
- 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 | 0.1334 | 0.869 | 0.3748 | 0.3748 | None |
| 0.4571 | 2.0 | 782 | 0.1221 | 0.89 | 0.3470 | 0.3470 | None |
| 0.4238 | 3.0 | 1173 | 0.1230 | 0.882 | 0.3577 | 0.3577 | None |
| 0.4093 | 4.0 | 1564 | 0.1232 | 0.885 | 0.3537 | 0.3537 | None |
| 0.4093 | 5.0 | 1955 | 0.1193 | 0.876 | 0.3659 | 0.3659 | None |
| 0.3894 | 6.0 | 2346 | 0.1253 | 0.884 | 0.3551 | 0.3551 | None |
| 0.3833 | 7.0 | 2737 | 0.1201 | 0.865 | 0.3806 | 0.3806 | None |
| 0.3753 | 8.0 | 3128 | 0.1170 | 0.884 | 0.3553 | 0.3553 | None |
| 0.3648 | 9.0 | 3519 | 0.1168 | 0.877 | 0.3646 | 0.3646 | None |
| 0.3648 | 10.0 | 3910 | 0.1194 | 0.877 | 0.3647 | 0.3647 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0