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: -1.1130
- Accuracy: 0.7225
- Dt Accuracy: 0.7225
- Df Accuracy: 0.702
- Unlearn Overall Accuracy: 0.4576
- 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 | 8 | -0.5790 | 0.9 | 0.1981 | 0.1981 | None |
| No log | 2.0 | 16 | -0.6284 | 0.869 | 0.2464 | 0.2464 | None |
| No log | 3.0 | 24 | -0.6941 | 0.834 | 0.2975 | 0.2975 | None |
| No log | 4.0 | 32 | -0.7636 | 0.808 | 0.3330 | 0.3330 | None |
| No log | 5.0 | 40 | -0.8454 | 0.775 | 0.3755 | 0.3755 | None |
| No log | 6.0 | 48 | -0.9352 | 0.75 | 0.4054 | 0.4054 | None |
| No log | 7.0 | 56 | -1.0095 | 0.73 | 0.4279 | 0.4279 | None |
| No log | 8.0 | 64 | -1.0687 | 0.715 | 0.4439 | 0.4439 | None |
| No log | 9.0 | 72 | -1.1105 | 0.705 | 0.4543 | 0.4543 | None |
| No log | 10.0 | 80 | -1.1130 | 0.702 | 0.4576 | 0.4576 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2