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: 0.1981
- Accuracy: 0.962
- Dt Accuracy: 0.962
- Df Accuracy: 0.875
- Unlearn Overall Accuracy: 0.3670
- 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 | 0.2182 | 0.892 | 0.3435 | 0.3435 | None |
| 0.6222 | 2.0 | 782 | 0.2220 | 0.882 | 0.3572 | 0.3572 | None |
| 0.5658 | 3.0 | 1173 | 0.2168 | 0.8892 | 0.3470 | 0.3470 | None |
| 0.5442 | 4.0 | 1564 | 0.2230 | 0.8882 | 0.3490 | 0.3490 | None |
| 0.5442 | 5.0 | 1955 | 0.2147 | 0.8928 | 0.3427 | 0.3427 | None |
| 0.5176 | 6.0 | 2346 | 0.2110 | 0.8935 | 0.3417 | 0.3417 | None |
| 0.4937 | 7.0 | 2737 | 0.2133 | 0.8802 | 0.3598 | 0.3598 | None |
| 0.4721 | 8.0 | 3128 | 0.1951 | 0.8832 | 0.3558 | 0.3558 | None |
| 0.4564 | 9.0 | 3519 | 0.2036 | 0.8815 | 0.3582 | 0.3582 | None |
| 0.4564 | 10.0 | 3910 | 0.1981 | 0.875 | 0.3670 | 0.3670 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2