87
This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1834
- Accuracy: 0.9599
- Dt Accuracy: 0.9599
- Df Accuracy: 0.875
- Unlearn Overall Accuracy: 0.3668
- 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 | 0.2040 | 0.8753 | 0.3657 | 0.3657 | None |
| 0.5673 | 2.0 | 782 | 0.2029 | 0.8937 | 0.3413 | 0.3413 | None |
| 0.5223 | 3.0 | 1173 | 0.1987 | 0.8827 | 0.3564 | 0.3564 | None |
| 0.4908 | 4.0 | 1564 | 0.1939 | 0.901 | 0.3313 | 0.3313 | None |
| 0.4908 | 5.0 | 1955 | 0.1943 | 0.8843 | 0.3543 | 0.3543 | None |
| 0.47 | 6.0 | 2346 | 0.1863 | 0.885 | 0.3534 | 0.3534 | None |
| 0.4371 | 7.0 | 2737 | 0.1895 | 0.886 | 0.3521 | 0.3521 | None |
| 0.4282 | 8.0 | 3128 | 0.1851 | 0.882 | 0.3575 | 0.3575 | None |
| 0.4099 | 9.0 | 3519 | 0.1853 | 0.8817 | 0.3579 | 0.3579 | None |
| 0.4099 | 10.0 | 3910 | 0.1834 | 0.875 | 0.3668 | 0.3668 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2