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: 0.1397
- Accuracy: 0.9667
- Dt Accuracy: 0.9667
- Df Accuracy: 0.888
- Unlearn Overall Accuracy: 0.3498
- 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
- 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 | 0.1367 | 0.891 | 0.3455 | 0.3455 | None |
| 0.5463 | 2.0 | 782 | 0.1407 | 0.892 | 0.3441 | 0.3441 | None |
| 0.4958 | 3.0 | 1173 | 0.1392 | 0.8895 | 0.3477 | 0.3477 | None |
| 0.4823 | 4.0 | 1564 | 0.1418 | 0.8795 | 0.3612 | 0.3612 | None |
| 0.4823 | 5.0 | 1955 | 0.1414 | 0.875 | 0.3672 | 0.3672 | None |
| 0.4698 | 6.0 | 2346 | 0.1421 | 0.893 | 0.3429 | 0.3429 | None |
| 0.4569 | 7.0 | 2737 | 0.1382 | 0.8875 | 0.3504 | 0.3504 | None |
| 0.4542 | 8.0 | 3128 | 0.1393 | 0.889 | 0.3485 | 0.3485 | None |
| 0.4478 | 9.0 | 3519 | 0.1385 | 0.9035 | 0.3284 | 0.3284 | None |
| 0.4478 | 10.0 | 3910 | 0.1397 | 0.888 | 0.3498 | 0.3498 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2