21
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: 0.1561
- Accuracy: 0.9685
- Dt Accuracy: 0.9685
- Df Accuracy: 0.971
- Unlearn Overall Accuracy: 0.2285
- 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: 21
- 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 | 0.1819 | 0.9743 | 0.2231 | 0.2231 | None |
| 0.6005 | 2.0 | 782 | 0.1726 | 0.9767 | 0.2194 | 0.2194 | None |
| 0.5487 | 3.0 | 1173 | 0.1636 | 0.976 | 0.2205 | 0.2205 | None |
| 0.5309 | 4.0 | 1564 | 0.1589 | 0.97 | 0.2301 | 0.2301 | None |
| 0.5309 | 5.0 | 1955 | 0.1551 | 0.9763 | 0.2201 | 0.2201 | None |
| 0.51 | 6.0 | 2346 | 0.1526 | 0.9747 | 0.2227 | 0.2227 | None |
| 0.4924 | 7.0 | 2737 | 0.1563 | 0.9723 | 0.2264 | 0.2264 | None |
| 0.4786 | 8.0 | 3128 | 0.1592 | 0.9683 | 0.2326 | 0.2326 | None |
| 0.4605 | 9.0 | 3519 | 0.1591 | 0.9693 | 0.2311 | 0.2311 | None |
| 0.4605 | 10.0 | 3910 | 0.1561 | 0.971 | 0.2285 | 0.2285 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0