42
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: -24.1857
- Accuracy: 0.0269
- Dt Accuracy: 0.0269
- Df Accuracy: 0.0266
- 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: 42
- 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 | 40 | -0.8322 | 0.806 | 0.3345 | 0.3345 | None |
| No log | 2.0 | 80 | -3.0243 | 0.4546 | 0 | 0 | None |
| -2.3062 | 3.0 | 120 | -7.3760 | 0.1888 | 0 | 0 | None |
| -2.3062 | 4.0 | 160 | -12.1726 | 0.0948 | 0 | 0 | None |
| -10.9549 | 5.0 | 200 | -16.6740 | 0.0562 | 0 | 0 | None |
| -10.9549 | 6.0 | 240 | -19.7816 | 0.0404 | 0 | 0 | None |
| -10.9549 | 7.0 | 280 | -22.6879 | 0.034 | 0 | 0 | None |
| -19.6359 | 8.0 | 320 | -23.4787 | 0.0312 | 0 | 0 | None |
| -19.6359 | 9.0 | 360 | -25.9837 | 0.0272 | 0 | 0 | None |
| -24.0534 | 10.0 | 400 | -24.1857 | 0.0266 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.19.0
- Tokenizers 0.15.2