21
This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: -16.4031
- Accuracy: 0.0393
- Dt Accuracy: 0.0393
- Df Accuracy: 0.041
- 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: 5e-05
- train_batch_size: 128
- eval_batch_size: 256
- seed: 21
- 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 | 32 | -0.7869 | 0.8215 | 0.3142 | 0.3142 | None |
| No log | 2.0 | 64 | -2.0294 | 0.583 | 0.5392 | 0.5392 | None |
| No log | 3.0 | 96 | -4.8550 | 0.336 | 0 | 0 | None |
| -2.6992 | 4.0 | 128 | -7.7407 | 0.1895 | 0 | 0 | None |
| -2.6992 | 5.0 | 160 | -10.3405 | 0.1098 | 0 | 0 | None |
| -2.6992 | 6.0 | 192 | -12.7739 | 0.076 | 0 | 0 | None |
| -10.6479 | 7.0 | 224 | -14.3615 | 0.053 | 0 | 0 | None |
| -10.6479 | 8.0 | 256 | -15.8731 | 0.0435 | 0 | 0 | None |
| -10.6479 | 9.0 | 288 | -16.0683 | 0.0408 | 0 | 0 | None |
| -16.3793 | 10.0 | 320 | -16.4031 | 0.041 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2