Downloads · 30 days
1
2% of all-time downloads
unlearn_cifar100_swin-base_bad_teaching_6_42
jialicheng/unlearn_cifar100_swin-base_bad_teaching_6_42
unlearn_cifar100_swin-base_bad_teaching_6_42 is a image classification model from jialicheng. Use it when you need a label for an image. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
57
Public
Parameters
86.9M
376 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors348 MB · 93%
Parameter types
How the weights are stored.
F3286.8M · 100%
Base models
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
42
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: 37.3071
- Accuracy: 0.1768
- Dt Accuracy: 0.1768
- Df Accuracy: 0.1223
- 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: 0.0002
- 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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Overall Accuracy | Unlearn Overall Accuracy | Time |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 47 | 1.5751 | 0.71 | 0 | 0 | None |
| No log | 2.0 | 94 | 3.0157 | 0.5943 | 0 | 0 | None |
| No log | 3.0 | 141 | 4.5211 | 0.475 | 0 | 0 | None |
| No log | 4.0 | 188 | 5.4633 | 0.4523 | 0 | 0 | None |
| No log | 5.0 | 235 | 7.3936 | 0.39 | 0 | 0 | None |
| No log | 6.0 | 282 | 9.1390 | 0.3477 | 0 | 0 | None |
| No log | 7.0 | 329 | 11.9795 | 0.2747 | 0 | 0 | None |
| No log | 8.0 | 376 | 11.1489 | 0.2913 | 0 | 0 | None |
| No log | 9.0 | 423 | 12.7584 | 0.273 | 0 | 0 | None |
| No log | 10.0 | 470 | 15.1925 | 0.246 | 0 | 0 | None |
| 0.0 | 11.0 | 517 | 17.5846 | 0.2153 | 0 | 0 | None |
| 0.0 | 12.0 | 564 | 21.0736 | 0.1893 | 0 | 0 | None |
| 0.0 | 13.0 | 611 | 21.0434 | 0.188 | 0 | 0 | None |
| 0.0 | 14.0 | 658 | 26.1360 | 0.171 | 0 | 0 | None |
| 0.0 | 15.0 | 705 | 24.8298 | 0.1597 | 0 | 0 | None |
| 0.0 | 16.0 | 752 | 28.5803 | 0.1507 | 0 | 0 | None |
| 0.0 | 17.0 | 799 | 37.3501 | 0.1237 | 0 | 0 | None |
| 0.0 | 18.0 | 846 | 38.3154 | 0.1207 | 0 | 0 | None |
| 0.0 | 19.0 | 893 | 35.8127 | 0.126 | 0 | 0 | None |
| 0.0 | 20.0 | 940 | 37.3071 | 0.1223 | 0 | 0 | None |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.2+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2
- Task
- Image Classification
- Type
- swin
- License
- apache-2.0
- Created
- Oct 22, 2025
- Updated
- Oct 22, 2025