87
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: 4.0988
- Accuracy: 0.3115
- Dt Accuracy: 0.3115
- Df Accuracy: 0.3267
- 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: 87
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 | 0.7589 | 0.8633 | 0.2544 | 0.2544 | None |
| No log | 2.0 | 94 | 1.2148 | 0.755 | 0.3942 | 0.3942 | None |
| 0.0 | 3.0 | 141 | 1.6508 | 0.6707 | 0 | 0 | None |
| 0.0 | 4.0 | 188 | 2.0958 | 0.579 | 0 | 0 | None |
| 0.0 | 5.0 | 235 | 2.7345 | 0.4943 | 0 | 0 | None |
| 0.0 | 6.0 | 282 | 3.2994 | 0.4303 | 0 | 0 | None |
| 0.0 | 7.0 | 329 | 3.5724 | 0.3877 | 0 | 0 | None |
| 0.0 | 8.0 | 376 | 3.8935 | 0.3583 | 0 | 0 | None |
| 0.0 | 9.0 | 423 | 4.5284 | 0.3203 | 0 | 0 | None |
| 0.0 | 10.0 | 470 | 4.0988 | 0.3267 | 0 | 0 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0