21
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: -0.9644
- Accuracy: 0.7326
- Dt Accuracy: 0.7326
- Df Accuracy: 0.707
- Unlearn Overall Accuracy: 0.4533
- 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: 21
- 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 | 8 | -0.5829 | 0.895 | 0.2061 | 0.2061 | None |
| No log | 2.0 | 16 | -0.6126 | 0.872 | 0.2421 | 0.2421 | None |
| No log | 3.0 | 24 | -0.6487 | 0.841 | 0.2881 | 0.2881 | None |
| No log | 4.0 | 32 | -0.7003 | 0.816 | 0.3227 | 0.3227 | None |
| No log | 5.0 | 40 | -0.7561 | 0.79 | 0.3571 | 0.3571 | None |
| No log | 6.0 | 48 | -0.8249 | 0.761 | 0.3930 | 0.3930 | None |
| No log | 7.0 | 56 | -0.8783 | 0.752 | 0.4029 | 0.4029 | None |
| No log | 8.0 | 64 | -0.9286 | 0.728 | 0.4301 | 0.4301 | None |
| No log | 9.0 | 72 | -0.9573 | 0.717 | 0.4425 | 0.4425 | None |
| No log | 10.0 | 80 | -0.9644 | 0.707 | 0.4533 | 0.4533 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2