13
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: -16.6010
- Accuracy: 0.0292
- Dt Accuracy: 0.0292
- Df Accuracy: 0.0266
- 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: 13
- 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 | 40 | -0.9628 | 0.7686 | 0.3801 | 0.3801 | None |
| No log | 2.0 | 80 | -3.0492 | 0.4466 | 0 | 0 | None |
| -2.7899 | 3.0 | 120 | -6.3927 | 0.218 | 0 | 0 | None |
| -2.7899 | 4.0 | 160 | -9.4565 | 0.1128 | 0 | 0 | None |
| -11.3242 | 5.0 | 200 | -11.7758 | 0.0684 | 0 | 0 | None |
| -11.3242 | 6.0 | 240 | -13.5168 | 0.0502 | 0 | 0 | None |
| -11.3242 | 7.0 | 280 | -14.7340 | 0.039 | 0 | 0 | None |
| -19.1818 | 8.0 | 320 | -16.1097 | 0.032 | 0 | 0 | None |
| -19.1818 | 9.0 | 360 | -16.4958 | 0.0284 | 0 | 0 | None |
| -23.4387 | 10.0 | 400 | -16.6010 | 0.0266 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2