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: 0.5430
- Accuracy: 0.8416
- Dt Accuracy: 0.8416
- Df Accuracy: 0.885
- Unlearn Overall Accuracy: 0.2220
- 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 |
|---|---|---|---|---|---|---|---|
| 1.1546 | 1.0 | 391 | 0.5807 | 0.886 | 0.2205 | 0.2205 | None |
| 1.1169 | 2.0 | 782 | 0.5631 | 0.889 | 0.2159 | 0.2159 | None |
| 1.0826 | 3.0 | 1173 | 0.5601 | 0.888 | 0.2174 | 0.2174 | None |
| 1.0478 | 4.0 | 1564 | 0.5570 | 0.881 | 0.2285 | 0.2285 | None |
| 1.0436 | 5.0 | 1955 | 0.5529 | 0.895 | 0.2061 | 0.2061 | None |
| 1.0279 | 6.0 | 2346 | 0.5499 | 0.89 | 0.2141 | 0.2141 | None |
| 0.9957 | 7.0 | 2737 | 0.5461 | 0.895 | 0.2061 | 0.2061 | None |
| 0.9658 | 8.0 | 3128 | 0.5436 | 0.894 | 0.2077 | 0.2077 | None |
| 0.9725 | 9.0 | 3519 | 0.5445 | 0.889 | 0.2157 | 0.2157 | None |
| 0.9528 | 10.0 | 3910 | 0.5430 | 0.885 | 0.2220 | 0.2220 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0