42
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: 0.6094
- Accuracy: 0.8328
- Dt Accuracy: 0.8328
- Df Accuracy: 0.7352
- Unlearn Overall Accuracy: 0.4311
- 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: 42
- 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 |
|---|---|---|---|---|---|---|---|
| 1.515 | 1.0 | 391 | 0.6284 | 0.7408 | 0.4236 | 0.4236 | None |
| 1.4683 | 2.0 | 782 | 0.6079 | 0.7388 | 0.4265 | 0.4265 | None |
| 1.3606 | 3.0 | 1173 | 0.6192 | 0.7305 | 0.4364 | 0.4364 | None |
| 1.3548 | 4.0 | 1564 | 0.6053 | 0.7468 | 0.4162 | 0.4162 | None |
| 1.2966 | 5.0 | 1955 | 0.6105 | 0.7372 | 0.4284 | 0.4284 | None |
| 1.2605 | 6.0 | 2346 | 0.6047 | 0.7352 | 0.4308 | 0.4308 | None |
| 1.2283 | 7.0 | 2737 | 0.6079 | 0.728 | 0.4397 | 0.4397 | None |
| 1.2116 | 8.0 | 3128 | 0.6091 | 0.735 | 0.4313 | 0.4313 | None |
| 1.2091 | 9.0 | 3519 | 0.6104 | 0.7298 | 0.4378 | 0.4378 | None |
| 1.2131 | 10.0 | 3910 | 0.6094 | 0.7352 | 0.4311 | 0.4311 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.2.2+cu118
- Datasets 3.2.0
- Tokenizers 0.21.0