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: 0.6399
- Accuracy: 0.8318
- Dt Accuracy: 0.8318
- Df Accuracy: 0.89
- Unlearn Overall Accuracy: 0.2143
- 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 |
|---|---|---|---|---|---|---|---|
| 1.6195 | 1.0 | 391 | 0.6542 | 0.8846 | 0.2226 | 0.2226 | None |
| 1.4807 | 2.0 | 782 | 0.6457 | 0.883 | 0.2251 | 0.2251 | None |
| 1.3938 | 3.0 | 1173 | 0.6351 | 0.8864 | 0.2198 | 0.2198 | None |
| 1.3415 | 4.0 | 1564 | 0.6399 | 0.8846 | 0.2227 | 0.2227 | None |
| 1.2761 | 5.0 | 1955 | 0.6469 | 0.885 | 0.2220 | 0.2220 | None |
| 1.2686 | 6.0 | 2346 | 0.6436 | 0.8872 | 0.2186 | 0.2186 | None |
| 1.2223 | 7.0 | 2737 | 0.6435 | 0.8888 | 0.2161 | 0.2161 | None |
| 1.2285 | 8.0 | 3128 | 0.6438 | 0.8884 | 0.2168 | 0.2168 | None |
| 1.2026 | 9.0 | 3519 | 0.6395 | 0.8878 | 0.2178 | 0.2178 | None |
| 1.1643 | 10.0 | 3910 | 0.6399 | 0.89 | 0.2143 | 0.2143 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0