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: -1.2121
- Accuracy: 0.7022
- Dt Accuracy: 0.7022
- Df Accuracy: 0.706
- Unlearn Overall Accuracy: 0.4505
- 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 | 8 | -0.5851 | 0.895 | 0.2061 | 0.2061 | None |
| No log | 2.0 | 16 | -0.6238 | 0.862 | 0.2572 | 0.2572 | None |
| No log | 3.0 | 24 | -0.6921 | 0.836 | 0.2948 | 0.2948 | None |
| No log | 4.0 | 32 | -0.7749 | 0.806 | 0.3356 | 0.3356 | None |
| No log | 5.0 | 40 | -0.8673 | 0.772 | 0.3787 | 0.3787 | None |
| No log | 6.0 | 48 | -0.9877 | 0.747 | 0.4076 | 0.4076 | None |
| No log | 7.0 | 56 | -1.0791 | 0.734 | 0.4213 | 0.4213 | None |
| No log | 8.0 | 64 | -1.1637 | 0.716 | 0.4402 | 0.4402 | None |
| No log | 9.0 | 72 | -1.2034 | 0.709 | 0.4473 | 0.4473 | None |
| No log | 10.0 | 80 | -1.2121 | 0.706 | 0.4505 | 0.4505 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2