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: -0.3463
- Accuracy: 0.9065
- Dt Accuracy: 0.9065
- Df Accuracy: 0.873
- Unlearn Overall Accuracy: 0.3656
- 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: 5e-05
- 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 | 8 | -0.1198 | 0.986 | 0.2046 | 0.2046 | None |
| No log | 2.0 | 16 | -0.1263 | 0.973 | 0.2252 | 0.2252 | None |
| No log | 3.0 | 24 | -0.1390 | 0.957 | 0.2499 | 0.2499 | None |
| No log | 4.0 | 32 | -0.1629 | 0.946 | 0.2663 | 0.2663 | None |
| No log | 5.0 | 40 | -0.1959 | 0.932 | 0.2867 | 0.2867 | None |
| No log | 6.0 | 48 | -0.2337 | 0.915 | 0.3106 | 0.3106 | None |
| No log | 7.0 | 56 | -0.2716 | 0.905 | 0.3239 | 0.3239 | None |
| No log | 8.0 | 64 | -0.3043 | 0.881 | 0.3558 | 0.3558 | None |
| No log | 9.0 | 72 | -0.3313 | 0.874 | 0.3645 | 0.3645 | None |
| No log | 10.0 | 80 | -0.3463 | 0.873 | 0.3656 | 0.3656 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2