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: 7.3286
- Accuracy: 0.1273
- Dt Accuracy: 0.1273
- Df Accuracy: 0.1358
- 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: 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 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 63 | 0.9128 | 0.8237 | 0.3103 | 0.3103 | None |
| 0.0 | 2.0 | 126 | 1.3976 | 0.6995 | 0 | 0 | None |
| 0.0 | 3.0 | 189 | 2.4695 | 0.5285 | 0 | 0 | None |
| 0.0 | 4.0 | 252 | 3.2086 | 0.4193 | 0 | 0 | None |
| 0.0 | 5.0 | 315 | 4.5113 | 0.3018 | 0 | 0 | None |
| 0.0 | 6.0 | 378 | 5.2439 | 0.232 | 0 | 0 | None |
| 0.0 | 7.0 | 441 | 6.3598 | 0.1787 | 0 | 0 | None |
| 0.0 | 8.0 | 504 | 6.2819 | 0.1557 | 0 | 0 | None |
| 0.0 | 9.0 | 567 | 7.6156 | 0.1368 | 0 | 0 | None |
| 0.0 | 10.0 | 630 | 7.3286 | 0.1358 | 0 | 0 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0