42
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: 0.1369
- Accuracy: 0.9625
- Dt Accuracy: 0.9625
- Df Accuracy: 0.852
- Unlearn Overall Accuracy: 0.3970
- 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: 42
- 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 | 0.1736 | 0.877 | 0.3635 | 0.3635 | None |
| 0.417 | 2.0 | 782 | 0.1509 | 0.877 | 0.3639 | 0.3639 | None |
| 0.3925 | 3.0 | 1173 | 0.1625 | 0.864 | 0.3810 | 0.3810 | None |
| 0.3756 | 4.0 | 1564 | 0.1583 | 0.864 | 0.3812 | 0.3812 | None |
| 0.3756 | 5.0 | 1955 | 0.1416 | 0.877 | 0.3643 | 0.3643 | None |
| 0.3527 | 6.0 | 2346 | 0.1461 | 0.869 | 0.3748 | 0.3748 | None |
| 0.3222 | 7.0 | 2737 | 0.1411 | 0.881 | 0.3590 | 0.3590 | None |
| 0.3072 | 8.0 | 3128 | 0.1384 | 0.863 | 0.3829 | 0.3829 | None |
| 0.2954 | 9.0 | 3519 | 0.1382 | 0.845 | 0.4059 | 0.4059 | None |
| 0.2954 | 10.0 | 3910 | 0.1369 | 0.852 | 0.3970 | 0.3970 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2