21
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: 10.5489
- Accuracy: 0.0184
- Dt Accuracy: 0.0184
- Df Accuracy: 0.0137
- 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: 21
- 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 | 47 | 1.2936 | 0.7423 | 0.4077 | 0.4077 | None |
| No log | 2.0 | 94 | 2.5529 | 0.5097 | 0 | 0 | None |
| 0.0 | 3.0 | 141 | 4.8123 | 0.2963 | 0 | 0 | None |
| 0.0 | 4.0 | 188 | 5.7948 | 0.1667 | 0 | 0 | None |
| 0.0 | 5.0 | 235 | 7.8839 | 0.088 | 0 | 0 | None |
| 0.0 | 6.0 | 282 | 9.8849 | 0.049 | 0 | 0 | None |
| 0.0 | 7.0 | 329 | 11.1072 | 0.0293 | 0 | 0 | None |
| 0.0 | 8.0 | 376 | 11.4332 | 0.0217 | 0 | 0 | None |
| 0.0 | 9.0 | 423 | 10.7722 | 0.0157 | 0 | 0 | None |
| 0.0 | 10.0 | 470 | 10.5489 | 0.0137 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2