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: 0.2145
- Accuracy: 0.9606
- Dt Accuracy: 0.9606
- Df Accuracy: 0.8796
- Unlearn Overall Accuracy: 0.3607
- 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 | 0.2362 | 0.8816 | 0.3576 | 0.3576 | None |
| 0.6704 | 2.0 | 782 | 0.2522 | 0.8866 | 0.3508 | 0.3508 | None |
| 0.6115 | 3.0 | 1173 | 0.2335 | 0.8906 | 0.3457 | 0.3457 | None |
| 0.587 | 4.0 | 1564 | 0.2460 | 0.8842 | 0.3544 | 0.3544 | None |
| 0.587 | 5.0 | 1955 | 0.2295 | 0.8994 | 0.3336 | 0.3336 | None |
| 0.5624 | 6.0 | 2346 | 0.2357 | 0.8912 | 0.3447 | 0.3447 | None |
| 0.5349 | 7.0 | 2737 | 0.2315 | 0.8876 | 0.3498 | 0.3498 | None |
| 0.5199 | 8.0 | 3128 | 0.2137 | 0.8858 | 0.3524 | 0.3524 | None |
| 0.4978 | 9.0 | 3519 | 0.2185 | 0.877 | 0.3641 | 0.3641 | None |
| 0.4978 | 10.0 | 3910 | 0.2145 | 0.8796 | 0.3607 | 0.3607 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2