42
This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1193
- Accuracy: 0.9669
- Dt Accuracy: 0.9669
- Df Accuracy: 0.957
- Unlearn Overall Accuracy: 0.2502
- 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: 0.0001
- 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 | 391 | 0.1365 | 0.975 | 0.2220 | 0.2220 | None |
| 0.4572 | 2.0 | 782 | 0.1300 | 0.968 | 0.2331 | 0.2331 | None |
| 0.4234 | 3.0 | 1173 | 0.1214 | 0.97 | 0.2300 | 0.2300 | None |
| 0.4067 | 4.0 | 1564 | 0.1263 | 0.968 | 0.2331 | 0.2331 | None |
| 0.4067 | 5.0 | 1955 | 0.1186 | 0.969 | 0.2316 | 0.2316 | None |
| 0.3913 | 6.0 | 2346 | 0.1228 | 0.967 | 0.2347 | 0.2347 | None |
| 0.3715 | 7.0 | 2737 | 0.1186 | 0.957 | 0.2502 | 0.2502 | None |
| 0.3562 | 8.0 | 3128 | 0.1196 | 0.957 | 0.2502 | 0.2502 | None |
| 0.3534 | 9.0 | 3519 | 0.1184 | 0.955 | 0.2533 | 0.2533 | None |
| 0.3534 | 10.0 | 3910 | 0.1193 | 0.957 | 0.2502 | 0.2502 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0