87
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: 0.1585
- Accuracy: 0.9663
- Dt Accuracy: 0.9663
- Df Accuracy: 0.8923
- Unlearn Overall Accuracy: 0.3438
- 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: 87
- 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 | 0.1512 | 0.8807 | 0.3595 | 0.3595 | None |
| 0.6275 | 2.0 | 782 | 0.1592 | 0.8857 | 0.3528 | 0.3528 | None |
| 0.5623 | 3.0 | 1173 | 0.1614 | 0.8893 | 0.3479 | 0.3479 | None |
| 0.5389 | 4.0 | 1564 | 0.1611 | 0.8943 | 0.3409 | 0.3409 | None |
| 0.5389 | 5.0 | 1955 | 0.1601 | 0.8963 | 0.3383 | 0.3383 | None |
| 0.5329 | 6.0 | 2346 | 0.1562 | 0.8963 | 0.3383 | 0.3383 | None |
| 0.5108 | 7.0 | 2737 | 0.1543 | 0.8923 | 0.3439 | 0.3439 | None |
| 0.5143 | 8.0 | 3128 | 0.1649 | 0.897 | 0.3374 | 0.3374 | None |
| 0.5112 | 9.0 | 3519 | 0.1591 | 0.897 | 0.3374 | 0.3374 | None |
| 0.5112 | 10.0 | 3910 | 0.1585 | 0.8923 | 0.3438 | 0.3438 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2