100
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: 0.1577
- Accuracy: 0.9672
- Dt Accuracy: 0.9672
- Df Accuracy: 0.9697
- Unlearn Overall Accuracy: 0.2306
- 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: 100
- 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 | 0.1743 | 0.971 | 0.2283 | 0.2283 | None |
| 0.6004 | 2.0 | 782 | 0.1841 | 0.9753 | 0.2215 | 0.2215 | None |
| 0.5522 | 3.0 | 1173 | 0.1677 | 0.978 | 0.2174 | 0.2174 | None |
| 0.5274 | 4.0 | 1564 | 0.1603 | 0.9807 | 0.2132 | 0.2132 | None |
| 0.5274 | 5.0 | 1955 | 0.1697 | 0.972 | 0.2269 | 0.2269 | None |
| 0.5087 | 6.0 | 2346 | 0.1571 | 0.9777 | 0.2179 | 0.2179 | None |
| 0.495 | 7.0 | 2737 | 0.1613 | 0.974 | 0.2238 | 0.2238 | None |
| 0.475 | 8.0 | 3128 | 0.1576 | 0.974 | 0.2238 | 0.2238 | None |
| 0.4675 | 9.0 | 3519 | 0.1571 | 0.9697 | 0.2306 | 0.2306 | None |
| 0.4675 | 10.0 | 3910 | 0.1577 | 0.9697 | 0.2306 | 0.2306 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0