42
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: 0.2012
- Accuracy: 0.9658
- Dt Accuracy: 0.9658
- Df Accuracy: 0.8946
- Unlearn Overall Accuracy: 0.3407
- 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 | 0.1930 | 0.8818 | 0.3578 | 0.3578 | None |
| 0.753 | 2.0 | 782 | 0.2038 | 0.8844 | 0.3543 | 0.3543 | None |
| 0.6508 | 3.0 | 1173 | 0.2003 | 0.8874 | 0.3505 | 0.3505 | None |
| 0.6353 | 4.0 | 1564 | 0.2144 | 0.8884 | 0.3490 | 0.3490 | None |
| 0.6353 | 5.0 | 1955 | 0.2010 | 0.8992 | 0.3343 | 0.3343 | None |
| 0.6213 | 6.0 | 2346 | 0.2095 | 0.895 | 0.3399 | 0.3399 | None |
| 0.6126 | 7.0 | 2737 | 0.2060 | 0.8974 | 0.3369 | 0.3369 | None |
| 0.6098 | 8.0 | 3128 | 0.1985 | 0.8884 | 0.3491 | 0.3491 | None |
| 0.6029 | 9.0 | 3519 | 0.2074 | 0.8908 | 0.3459 | 0.3459 | None |
| 0.6029 | 10.0 | 3910 | 0.2012 | 0.8946 | 0.3407 | 0.3407 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2