87
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the cifar100 dataset. It achieves the following results on the evaluation set:
- Loss: -111.3971
- Accuracy: 0.01
- Dt Accuracy: 0.01
- Df Accuracy: 0.01
- 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: 87
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 40 | -46.4646 | 0.01 | 0 | 0 | None |
| No log | 2.0 | 80 | -52.5000 | 0.01 | 0 | 0 | None |
| No log | 3.0 | 120 | -58.2513 | 0.01 | 0 | 0 | None |
| No log | 4.0 | 160 | -63.8393 | 0.01 | 0 | 0 | None |
| No log | 5.0 | 200 | -69.2717 | 0.01 | 0 | 0 | None |
| No log | 6.0 | 240 | -74.4759 | 0.01 | 0 | 0 | None |
| No log | 7.0 | 280 | -79.4339 | 0.01 | 0 | 0 | None |
| No log | 8.0 | 320 | -84.0876 | 0.01 | 0 | 0 | None |
| No log | 9.0 | 360 | -88.3994 | 0.01 | 0 | 0 | None |
| No log | 10.0 | 400 | -92.3653 | 0.01 | 0 | 0 | None |
| No log | 11.0 | 440 | -95.9748 | 0.01 | 0 | 0 | None |
| No log | 12.0 | 480 | -99.2090 | 0.01 | 0 | 0 | None |
| -73.1062 | 13.0 | 520 | -102.0727 | 0.01 | 0 | 0 | None |
| -73.1062 | 14.0 | 560 | -104.5372 | 0.01 | 0 | 0 | None |
| -73.1062 | 15.0 | 600 | -106.6421 | 0.01 | 0 | 0 | None |
| -73.1062 | 16.0 | 640 | -108.3537 | 0.01 | 0 | 0 | None |
| -73.1062 | 17.0 | 680 | -109.6809 | 0.01 | 0 | 0 | None |
| -73.1062 | 18.0 | 720 | -110.6335 | 0.01 | 0 | 0 | None |
| -73.1062 | 19.0 | 760 | -111.2057 | 0.01 | 0 | 0 | None |
| -73.1062 | 20.0 | 800 | -111.3971 | 0.01 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2