87
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: 0.6410
- Accuracy: 0.8303
- Dt Accuracy: 0.8303
- Df Accuracy: 0.8914
- Unlearn Overall Accuracy: 0.2120
- 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: 87
- 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 |
|---|---|---|---|---|---|---|---|
| 1.6061 | 1.0 | 391 | 0.6508 | 0.8856 | 0.2210 | 0.2210 | None |
| 1.4828 | 2.0 | 782 | 0.6368 | 0.882 | 0.2267 | 0.2267 | None |
| 1.3844 | 3.0 | 1173 | 0.6397 | 0.8842 | 0.2233 | 0.2233 | None |
| 1.3256 | 4.0 | 1564 | 0.6451 | 0.8848 | 0.2224 | 0.2224 | None |
| 1.2784 | 5.0 | 1955 | 0.6458 | 0.885 | 0.2222 | 0.2222 | None |
| 1.2635 | 6.0 | 2346 | 0.6426 | 0.8862 | 0.2202 | 0.2202 | None |
| 1.2477 | 7.0 | 2737 | 0.6388 | 0.8886 | 0.2165 | 0.2165 | None |
| 1.2011 | 8.0 | 3128 | 0.6438 | 0.8898 | 0.2145 | 0.2145 | None |
| 1.1985 | 9.0 | 3519 | 0.6404 | 0.8878 | 0.2177 | 0.2177 | None |
| 1.1905 | 10.0 | 3910 | 0.6410 | 0.8914 | 0.2120 | 0.2120 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0