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: 0.1203
- Accuracy: 0.9679
- Dt Accuracy: 0.9679
- Df Accuracy: 0.971
- Unlearn Overall Accuracy: 0.2285
- 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 | 0.1265 | 0.975 | 0.2221 | 0.2221 | None |
| 0.4542 | 2.0 | 782 | 0.1274 | 0.972 | 0.2269 | 0.2269 | None |
| 0.429 | 3.0 | 1173 | 0.1281 | 0.969 | 0.2315 | 0.2315 | None |
| 0.4076 | 4.0 | 1564 | 0.1197 | 0.97 | 0.2300 | 0.2300 | None |
| 0.4076 | 5.0 | 1955 | 0.1182 | 0.97 | 0.2301 | 0.2301 | None |
| 0.386 | 6.0 | 2346 | 0.1160 | 0.973 | 0.2254 | 0.2254 | None |
| 0.3731 | 7.0 | 2737 | 0.1175 | 0.962 | 0.2425 | 0.2425 | None |
| 0.3594 | 8.0 | 3128 | 0.1187 | 0.965 | 0.2379 | 0.2379 | None |
| 0.3527 | 9.0 | 3519 | 0.1189 | 0.967 | 0.2348 | 0.2348 | None |
| 0.3527 | 10.0 | 3910 | 0.1203 | 0.971 | 0.2285 | 0.2285 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0