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: 8.6402
- Accuracy: 0.0506
- Dt Accuracy: 0.0506
- Df Accuracy: 0.0546
- 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: 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 79 | 1.0512 | 0.7906 | 0.3528 | 0.3528 | None |
| 0.0 | 2.0 | 158 | 2.2199 | 0.5842 | 0 | 0 | None |
| 0.0 | 3.0 | 237 | 3.0130 | 0.4326 | 0 | 0 | None |
| 0.0 | 4.0 | 316 | 4.3290 | 0.2866 | 0 | 0 | None |
| 0.0 | 5.0 | 395 | 6.3021 | 0.1736 | 0 | 0 | None |
| 0.0 | 6.0 | 474 | 7.0323 | 0.1244 | 0 | 0 | None |
| 0.0 | 7.0 | 553 | 7.8451 | 0.0874 | 0 | 0 | None |
| 0.0 | 8.0 | 632 | 8.5330 | 0.0672 | 0 | 0 | None |
| 0.0 | 9.0 | 711 | 9.5011 | 0.0486 | 0 | 0 | None |
| 0.0 | 10.0 | 790 | 8.6402 | 0.0546 | 0 | 0 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0