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: 0.1962
- Accuracy: 0.9669
- Dt Accuracy: 0.9669
- Df Accuracy: 0.9716
- Unlearn Overall Accuracy: 0.2276
- 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: 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 | 0.2151 | 0.973 | 0.2252 | 0.2252 | None |
| 0.7082 | 2.0 | 782 | 0.2081 | 0.9724 | 0.2261 | 0.2261 | None |
| 0.6429 | 3.0 | 1173 | 0.2057 | 0.9784 | 0.2167 | 0.2167 | None |
| 0.6254 | 4.0 | 1564 | 0.2019 | 0.9788 | 0.2161 | 0.2161 | None |
| 0.6254 | 5.0 | 1955 | 0.1954 | 0.9762 | 0.2203 | 0.2203 | None |
| 0.6017 | 6.0 | 2346 | 0.1981 | 0.9776 | 0.2180 | 0.2180 | None |
| 0.5814 | 7.0 | 2737 | 0.1958 | 0.9744 | 0.2232 | 0.2232 | None |
| 0.5656 | 8.0 | 3128 | 0.2003 | 0.9722 | 0.2266 | 0.2266 | None |
| 0.5541 | 9.0 | 3519 | 0.1950 | 0.9722 | 0.2266 | 0.2266 | None |
| 0.5541 | 10.0 | 3910 | 0.1962 | 0.9716 | 0.2276 | 0.2276 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0