87
This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1323
- Accuracy: 0.9641
- Dt Accuracy: 0.9641
- Df Accuracy: 0.859
- Unlearn Overall Accuracy: 0.3881
- 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 | 0.1765 | 0.869 | 0.3739 | 0.3739 | None |
| 0.4192 | 2.0 | 782 | 0.1503 | 0.892 | 0.3437 | 0.3437 | None |
| 0.3954 | 3.0 | 1173 | 0.1434 | 0.887 | 0.3506 | 0.3506 | None |
| 0.3685 | 4.0 | 1564 | 0.1434 | 0.873 | 0.3695 | 0.3695 | None |
| 0.3685 | 5.0 | 1955 | 0.1514 | 0.874 | 0.3680 | 0.3680 | None |
| 0.3482 | 6.0 | 2346 | 0.1455 | 0.863 | 0.3827 | 0.3827 | None |
| 0.3226 | 7.0 | 2737 | 0.1410 | 0.828 | 0.4272 | 0.4272 | None |
| 0.3044 | 8.0 | 3128 | 0.1409 | 0.85 | 0.3996 | 0.3996 | None |
| 0.2927 | 9.0 | 3519 | 0.1344 | 0.848 | 0.4022 | 0.4022 | None |
| 0.2927 | 10.0 | 3910 | 0.1323 | 0.859 | 0.3881 | 0.3881 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2