Downloads · 30 days
2
3% of all-time downloads
unlearn_cifar100_swin-base_bad_teaching_8_42
jialicheng/unlearn_cifar100_swin-base_bad_teaching_8_42
unlearn_cifar100_swin-base_bad_teaching_8_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
67
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: 45.6366
- Accuracy: 0.1544
- Dt Accuracy: 0.1544
- Df Accuracy: 0.1175
- 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 | 63 | 2.0460 | 0.6665 | 0 | 0 | None |
| No log | 2.0 | 126 | 3.5320 | 0.5453 | 0 | 0 | None |
| No log | 3.0 | 189 | 5.4383 | 0.4382 | 0 | 0 | None |
| No log | 4.0 | 252 | 8.0667 | 0.3558 | 0 | 0 | None |
| No log | 5.0 | 315 | 9.4059 | 0.316 | 0 | 0 | None |
| No log | 6.0 | 378 | 13.4480 | 0.2502 | 0 | 0 | None |
| No log | 7.0 | 441 | 12.0032 | 0.2878 | 0 | 0 | None |
| 0.0 | 8.0 | 504 | 15.8713 | 0.2412 | 0 | 0 | None |
| 0.0 | 9.0 | 567 | 18.5691 | 0.2167 | 0 | 0 | None |
| 0.0 | 10.0 | 630 | 19.1335 | 0.2223 | 0 | 0 | None |
| 0.0 | 11.0 | 693 | 21.5844 | 0.2 | 0 | 0 | None |
| 0.0 | 12.0 | 756 | 25.4353 | 0.1898 | 0 | 0 | None |
| 0.0 | 13.0 | 819 | 27.6008 | 0.17 | 0 | 0 | None |
| 0.0 | 14.0 | 882 | 30.2568 | 0.15 | 0 | 0 | None |
| 0.0 | 15.0 | 945 | 31.5030 | 0.1505 | 0 | 0 | None |
| 0.0 | 16.0 | 1008 | 37.0207 | 0.1383 | 0 | 0 | None |
| 0.0 | 17.0 | 1071 | 38.7103 | 0.1318 | 0 | 0 | None |
| 0.0 | 18.0 | 1134 | 43.8554 | 0.1165 | 0 | 0 | None |
| 0.0 | 19.0 | 1197 | 43.3444 | 0.121 | 0 | 0 | None |
| 0.0 | 20.0 | 1260 | 45.6366 | 0.1175 | 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