100
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: -8.9740
- Accuracy: 0.1573
- Dt Accuracy: 0.1573
- Df Accuracy: 0.16
- 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: 100
- 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 | -0.6778 | 0.847 | 0.2791 | 0.2791 | None |
| No log | 2.0 | 48 | -1.1224 | 0.745 | 0.4076 | 0.4076 | None |
| No log | 3.0 | 72 | -2.0986 | 0.622 | 0.5156 | 0.5156 | None |
| No log | 4.0 | 96 | -3.5271 | 0.4853 | 0 | 0 | None |
| -2.31 | 5.0 | 120 | -5.1412 | 0.371 | 0 | 0 | None |
| -2.31 | 6.0 | 144 | -6.5135 | 0.2747 | 0 | 0 | None |
| -2.31 | 7.0 | 168 | -7.8198 | 0.2163 | 0 | 0 | None |
| -2.31 | 8.0 | 192 | -8.5083 | 0.185 | 0 | 0 | None |
| -8.5133 | 9.0 | 216 | -9.1514 | 0.166 | 0 | 0 | None |
| -8.5133 | 10.0 | 240 | -8.9740 | 0.16 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2