21
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: 0.1176
- Accuracy: 0.9677
- Dt Accuracy: 0.9677
- Df Accuracy: 0.884
- Unlearn Overall Accuracy: 0.3552
- 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: 21
- 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 | 0.1268 | 0.868 | 0.3762 | 0.3762 | None |
| 0.4607 | 2.0 | 782 | 0.1255 | 0.875 | 0.3672 | 0.3672 | None |
| 0.4243 | 3.0 | 1173 | 0.1228 | 0.877 | 0.3645 | 0.3645 | None |
| 0.413 | 4.0 | 1564 | 0.1208 | 0.895 | 0.3401 | 0.3401 | None |
| 0.413 | 5.0 | 1955 | 0.1193 | 0.885 | 0.3538 | 0.3538 | None |
| 0.3937 | 6.0 | 2346 | 0.1193 | 0.881 | 0.3592 | 0.3592 | None |
| 0.382 | 7.0 | 2737 | 0.1212 | 0.859 | 0.3883 | 0.3883 | None |
| 0.3711 | 8.0 | 3128 | 0.1153 | 0.88 | 0.3606 | 0.3606 | None |
| 0.3644 | 9.0 | 3519 | 0.1178 | 0.874 | 0.3686 | 0.3686 | None |
| 0.3644 | 10.0 | 3910 | 0.1176 | 0.884 | 0.3552 | 0.3552 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0