87
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: 6.9739
- Accuracy: 0.6632
- Dt Accuracy: 0.6632
- Df Accuracy: 0.6715
- Unlearn Overall Accuracy: 0
- 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 | 63 | 0.2245 | 0.9665 | 0.2351 | 0.2351 | None |
| No log | 2.0 | 126 | 0.4880 | 0.9375 | 0.2779 | 0.2779 | None |
| No log | 3.0 | 189 | 1.1445 | 0.895 | 0.3350 | 0.3350 | None |
| No log | 4.0 | 252 | 1.7831 | 0.8522 | 0.3867 | 0.3867 | None |
| No log | 5.0 | 315 | 3.1535 | 0.8103 | 0.4299 | 0.4299 | None |
| No log | 6.0 | 378 | 4.3463 | 0.7635 | 0 | 0 | None |
| No log | 7.0 | 441 | 5.0731 | 0.7308 | 0 | 0 | None |
| 0.0 | 8.0 | 504 | 6.0822 | 0.7095 | 0 | 0 | None |
| 0.0 | 9.0 | 567 | 6.7301 | 0.6795 | 0 | 0 | None |
| 0.0 | 10.0 | 630 | 6.9739 | 0.6715 | 0 | 0 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2