42
This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: 1.0513
- Accuracy: 0.7291
- Dt Accuracy: 0.7291
- Df Accuracy: 0.794
- Unlearn Overall Accuracy: 0.3481
- 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: 5e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 | 16 | 0.5976 | 0.914 | 0.1751 | 0.1751 | None |
| No log | 2.0 | 32 | 0.6490 | 0.904 | 0.1913 | 0.1913 | None |
| No log | 3.0 | 48 | 0.7266 | 0.875 | 0.2369 | 0.2369 | None |
| No log | 4.0 | 64 | 0.7897 | 0.855 | 0.2666 | 0.2666 | None |
| No log | 5.0 | 80 | 0.8446 | 0.843 | 0.2836 | 0.2836 | None |
| No log | 6.0 | 96 | 0.9232 | 0.828 | 0.3041 | 0.3041 | None |
| 0.0 | 7.0 | 112 | 0.9839 | 0.807 | 0.3320 | 0.3320 | None |
| 0.0 | 8.0 | 128 | 0.9878 | 0.808 | 0.3306 | 0.3306 | None |
| 0.0 | 9.0 | 144 | 1.0372 | 0.794 | 0.3483 | 0.3483 | None |
| 0.0 | 10.0 | 160 | 1.0513 | 0.794 | 0.3481 | 0.3481 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0