87
This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.1969
- Accuracy: 0.9608
- Dt Accuracy: 0.9608
- Df Accuracy: 0.8845
- Unlearn Overall Accuracy: 0.3542
- 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: 87
- 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 | 0.2492 | 0.891 | 0.3445 | 0.3445 | None |
| 0.6224 | 2.0 | 782 | 0.2194 | 0.8882 | 0.3487 | 0.3487 | None |
| 0.5666 | 3.0 | 1173 | 0.2235 | 0.891 | 0.3451 | 0.3451 | None |
| 0.5404 | 4.0 | 1564 | 0.1952 | 0.8965 | 0.3378 | 0.3378 | None |
| 0.5404 | 5.0 | 1955 | 0.1955 | 0.8858 | 0.3525 | 0.3525 | None |
| 0.5158 | 6.0 | 2346 | 0.2044 | 0.9008 | 0.3320 | 0.3320 | None |
| 0.4909 | 7.0 | 2737 | 0.2044 | 0.8872 | 0.3505 | 0.3505 | None |
| 0.4699 | 8.0 | 3128 | 0.2065 | 0.8922 | 0.3436 | 0.3436 | None |
| 0.4527 | 9.0 | 3519 | 0.1956 | 0.8815 | 0.3583 | 0.3583 | None |
| 0.4527 | 10.0 | 3910 | 0.1969 | 0.8845 | 0.3542 | 0.3542 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2