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: 36.0268
- Accuracy: 0.0168
- Dt Accuracy: 0.0168
- Df Accuracy: 0.0153
- Unlearn Overall Accuracy: 0
- 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: 0.0002
- train_batch_size: 128
- eval_batch_size: 256
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 47 | 2.0602 | 0.6227 | 0 | 0 | None |
| No log | 2.0 | 94 | 4.8078 | 0.3137 | 0 | 0 | None |
| No log | 3.0 | 141 | 9.6638 | 0.1017 | 0 | 0 | None |
| No log | 4.0 | 188 | 16.2774 | 0.0287 | 0 | 0 | None |
| No log | 5.0 | 235 | 16.5814 | 0.019 | 0 | 0 | None |
| No log | 6.0 | 282 | 21.0942 | 0.0193 | 0 | 0 | None |
| No log | 7.0 | 329 | 20.9663 | 0.018 | 0 | 0 | None |
| No log | 8.0 | 376 | 23.0531 | 0.0173 | 0 | 0 | None |
| No log | 9.0 | 423 | 37.7848 | 0.0173 | 0 | 0 | None |
| No log | 10.0 | 470 | 29.0187 | 0.0147 | 0 | 0 | None |
| 0.0 | 11.0 | 517 | 29.1290 | 0.0153 | 0 | 0 | None |
| 0.0 | 12.0 | 564 | 36.2223 | 0.014 | 0 | 0 | None |
| 0.0 | 13.0 | 611 | 34.2616 | 0.0147 | 0 | 0 | None |
| 0.0 | 14.0 | 658 | 37.3977 | 0.0153 | 0 | 0 | None |
| 0.0 | 15.0 | 705 | 29.6960 | 0.0163 | 0 | 0 | None |
| 0.0 | 16.0 | 752 | 35.8729 | 0.0153 | 0 | 0 | None |
| 0.0 | 17.0 | 799 | 30.7437 | 0.0163 | 0 | 0 | None |
| 0.0 | 18.0 | 846 | 33.8901 | 0.016 | 0 | 0 | None |
| 0.0 | 19.0 | 893 | 36.7432 | 0.0153 | 0 | 0 | None |
| 0.0 | 20.0 | 940 | 36.0268 | 0.0153 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2