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: 13.8330
- Accuracy: 0.0107
- Dt Accuracy: 0.0107
- Df Accuracy: 0.0114
- 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: 0.0001
- 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 | 79 | 2.1952 | 0.5692 | 0 | 0 | None |
| 0.0 | 2.0 | 158 | 5.1075 | 0.207 | 0 | 0 | None |
| 0.0 | 3.0 | 237 | 11.4550 | 0.0446 | 0 | 0 | None |
| 0.0 | 4.0 | 316 | 11.6656 | 0.0198 | 0 | 0 | None |
| 0.0 | 5.0 | 395 | 10.1453 | 0.0134 | 0 | 0 | None |
| 0.0 | 6.0 | 474 | 11.6249 | 0.0114 | 0 | 0 | None |
| 0.0 | 7.0 | 553 | 11.7392 | 0.012 | 0 | 0 | None |
| 0.0 | 8.0 | 632 | 13.3269 | 0.0118 | 0 | 0 | None |
| 0.0 | 9.0 | 711 | 12.9624 | 0.0122 | 0 | 0 | None |
| 0.0 | 10.0 | 790 | 13.8330 | 0.0114 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2