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: 0.5500
- Accuracy: 0.8378
- Dt Accuracy: 0.8378
- Df Accuracy: 0.741
- Unlearn Overall Accuracy: 0.4235
- 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 |
|---|---|---|---|---|---|---|---|
| 1.1391 | 1.0 | 391 | 0.5814 | 0.738 | 0.4272 | 0.4272 | None |
| 1.1233 | 2.0 | 782 | 0.5688 | 0.757 | 0.4036 | 0.4036 | None |
| 1.1066 | 3.0 | 1173 | 0.5667 | 0.728 | 0.4399 | 0.4399 | None |
| 1.0864 | 4.0 | 1564 | 0.5610 | 0.733 | 0.4337 | 0.4337 | None |
| 1.0723 | 5.0 | 1955 | 0.5570 | 0.739 | 0.4264 | 0.4264 | None |
| 1.0138 | 6.0 | 2346 | 0.5556 | 0.738 | 0.4274 | 0.4274 | None |
| 1.0294 | 7.0 | 2737 | 0.5531 | 0.732 | 0.4347 | 0.4347 | None |
| 1.0328 | 8.0 | 3128 | 0.5508 | 0.735 | 0.4310 | 0.4310 | None |
| 1.0072 | 9.0 | 3519 | 0.5487 | 0.733 | 0.4332 | 0.4332 | None |
| 1.0152 | 10.0 | 3910 | 0.5500 | 0.741 | 0.4235 | 0.4235 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0