42
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: 2.5810
- Accuracy: 0.789
- Dt Accuracy: 0.789
- Df Accuracy: 0.782
- Unlearn Overall Accuracy: 0.4585
- 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 | 16 | 1.1472 | 0.888 | 0.3431 | 0.3431 | None |
| No log | 2.0 | 32 | 1.4901 | 0.853 | 0.3857 | 0.3857 | None |
| No log | 3.0 | 48 | 1.8968 | 0.82 | 0.4216 | 0.4216 | None |
| No log | 4.0 | 64 | 2.1157 | 0.807 | 0.4351 | 0.4351 | None |
| No log | 5.0 | 80 | 2.2832 | 0.784 | 0.4573 | 0.4573 | None |
| No log | 6.0 | 96 | 2.1860 | 0.792 | 0.4497 | 0.4497 | None |
| No log | 7.0 | 112 | 2.6150 | 0.78 | 0.4595 | 0.4595 | None |
| No log | 8.0 | 128 | 2.4719 | 0.782 | 0.4589 | 0.4589 | None |
| No log | 9.0 | 144 | 2.7684 | 0.777 | 0.4620 | 0.4620 | None |
| No log | 10.0 | 160 | 2.5810 | 0.782 | 0.4585 | 0.4585 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2