42
This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: -8.4064
- Accuracy: 0.17
- Dt Accuracy: 0.17
- Df Accuracy: 0.1703
- Unlearn Overall Accuracy: 0
- 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: 5e-05
- 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 | 24 | -0.6359 | 0.862 | 0.2571 | 0.2571 | None |
| No log | 2.0 | 48 | -1.0349 | 0.7573 | 0.3943 | 0.3943 | None |
| No log | 3.0 | 72 | -1.9081 | 0.6333 | 0.5098 | 0.5098 | None |
| No log | 4.0 | 96 | -3.2715 | 0.5063 | 0 | 0 | None |
| -2.1518 | 5.0 | 120 | -4.7650 | 0.387 | 0 | 0 | None |
| -2.1518 | 6.0 | 144 | -6.0502 | 0.292 | 0 | 0 | None |
| -2.1518 | 7.0 | 168 | -7.3744 | 0.235 | 0 | 0 | None |
| -2.1518 | 8.0 | 192 | -8.1236 | 0.1903 | 0 | 0 | None |
| -7.8362 | 9.0 | 216 | -8.3795 | 0.1743 | 0 | 0 | None |
| -7.8362 | 10.0 | 240 | -8.4064 | 0.1703 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2