13
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: 0.1385
- Accuracy: 0.968
- Dt Accuracy: 0.968
- Df Accuracy: 0.9625
- Unlearn Overall Accuracy: 0.2417
- 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: 13
- 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 | 0.1477 | 0.9745 | 0.2229 | 0.2229 | None |
| 0.5326 | 2.0 | 782 | 0.1522 | 0.971 | 0.2284 | 0.2284 | None |
| 0.4956 | 3.0 | 1173 | 0.1444 | 0.976 | 0.2205 | 0.2205 | None |
| 0.4763 | 4.0 | 1564 | 0.1363 | 0.9715 | 0.2277 | 0.2277 | None |
| 0.4763 | 5.0 | 1955 | 0.1409 | 0.975 | 0.2222 | 0.2222 | None |
| 0.4483 | 6.0 | 2346 | 0.1351 | 0.971 | 0.2285 | 0.2285 | None |
| 0.4313 | 7.0 | 2737 | 0.1421 | 0.9655 | 0.2371 | 0.2371 | None |
| 0.4239 | 8.0 | 3128 | 0.1350 | 0.9665 | 0.2355 | 0.2355 | None |
| 0.4164 | 9.0 | 3519 | 0.1368 | 0.965 | 0.2379 | 0.2379 | None |
| 0.4164 | 10.0 | 3910 | 0.1385 | 0.9625 | 0.2417 | 0.2417 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0