42
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: 0.1153
- Accuracy: 0.9672
- Dt Accuracy: 0.9672
- Df Accuracy: 0.876
- Unlearn Overall Accuracy: 0.3660
- 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: 42
- 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 | 391 | 0.1189 | 0.881 | 0.3591 | 0.3591 | None |
| 0.4471 | 2.0 | 782 | 0.1170 | 0.887 | 0.3511 | 0.3511 | None |
| 0.4243 | 3.0 | 1173 | 0.1221 | 0.87 | 0.3737 | 0.3737 | None |
| 0.4179 | 4.0 | 1564 | 0.1180 | 0.876 | 0.3658 | 0.3658 | None |
| 0.4179 | 5.0 | 1955 | 0.1176 | 0.886 | 0.3524 | 0.3524 | None |
| 0.4045 | 6.0 | 2346 | 0.1195 | 0.895 | 0.3402 | 0.3402 | None |
| 0.3923 | 7.0 | 2737 | 0.1171 | 0.909 | 0.3207 | 0.3207 | None |
| 0.384 | 8.0 | 3128 | 0.1187 | 0.882 | 0.3579 | 0.3579 | None |
| 0.3848 | 9.0 | 3519 | 0.1147 | 0.893 | 0.3430 | 0.3430 | None |
| 0.3848 | 10.0 | 3910 | 0.1153 | 0.876 | 0.3660 | 0.3660 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2