21
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: 0.1977
- Accuracy: 0.9678
- Dt Accuracy: 0.9678
- Df Accuracy: 0.9728
- Unlearn Overall Accuracy: 0.2257
- 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: 21
- 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 | 0.2321 | 0.9754 | 0.2214 | 0.2214 | None |
| 0.7122 | 2.0 | 782 | 0.2157 | 0.9776 | 0.2179 | 0.2179 | None |
| 0.6454 | 3.0 | 1173 | 0.2009 | 0.9748 | 0.2224 | 0.2224 | None |
| 0.6188 | 4.0 | 1564 | 0.1953 | 0.9786 | 0.2165 | 0.2165 | None |
| 0.6188 | 5.0 | 1955 | 0.2149 | 0.9708 | 0.2287 | 0.2287 | None |
| 0.6006 | 6.0 | 2346 | 0.1995 | 0.9764 | 0.2200 | 0.2200 | None |
| 0.5816 | 7.0 | 2737 | 0.2021 | 0.973 | 0.2254 | 0.2254 | None |
| 0.569 | 8.0 | 3128 | 0.1988 | 0.9742 | 0.2234 | 0.2234 | None |
| 0.5517 | 9.0 | 3519 | 0.2016 | 0.9708 | 0.2288 | 0.2288 | None |
| 0.5517 | 10.0 | 3910 | 0.1977 | 0.9728 | 0.2257 | 0.2257 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0