100
This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1154
- Accuracy: 0.9683
- Dt Accuracy: 0.9683
- Df Accuracy: 0.889
- Unlearn Overall Accuracy: 0.3484
- 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: 100
- 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 | 391 | 0.1284 | 0.887 | 0.3507 | 0.3507 | None |
| 0.4536 | 2.0 | 782 | 0.1234 | 0.886 | 0.3524 | 0.3524 | None |
| 0.4287 | 3.0 | 1173 | 0.1219 | 0.893 | 0.3429 | 0.3429 | None |
| 0.4091 | 4.0 | 1564 | 0.1186 | 0.876 | 0.3659 | 0.3659 | None |
| 0.4091 | 5.0 | 1955 | 0.1149 | 0.865 | 0.3805 | 0.3805 | None |
| 0.3945 | 6.0 | 2346 | 0.1128 | 0.885 | 0.3539 | 0.3539 | None |
| 0.3817 | 7.0 | 2737 | 0.1142 | 0.891 | 0.3457 | 0.3457 | None |
| 0.3706 | 8.0 | 3128 | 0.1159 | 0.87 | 0.3740 | 0.3740 | None |
| 0.3615 | 9.0 | 3519 | 0.1164 | 0.886 | 0.3525 | 0.3525 | None |
| 0.3615 | 10.0 | 3910 | 0.1154 | 0.889 | 0.3484 | 0.3484 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0