Downloads · 30 days
1
2% of all-time downloads
unlearn_cifar100_swin-base_bad_teaching_4_87
jialicheng/unlearn_cifar100_swin-base_bad_teaching_4_87
unlearn_cifar100_swin-base_bad_teaching_4_87 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
59
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. -->
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: 18.9074
- Accuracy: 0.221
- Dt Accuracy: 0.221
- Df Accuracy: 0.168
- 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: 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 | 32 | 1.2256 | 0.7415 | 0 | 0 | None |
| No log | 2.0 | 64 | 2.2360 | 0.622 | 0 | 0 | None |
| No log | 3.0 | 96 | 2.8432 | 0.5705 | 0 | 0 | None |
| No log | 4.0 | 128 | 4.1840 | 0.51 | 0 | 0 | None |
| No log | 5.0 | 160 | 5.1642 | 0.4115 | 0 | 0 | None |
| No log | 6.0 | 192 | 5.1769 | 0.4435 | 0 | 0 | None |
| No log | 7.0 | 224 | 6.5196 | 0.3635 | 0 | 0 | None |
| No log | 8.0 | 256 | 9.7232 | 0.287 | 0 | 0 | None |
| No log | 9.0 | 288 | 8.2489 | 0.2935 | 0 | 0 | None |
| No log | 10.0 | 320 | 8.8725 | 0.297 | 0 | 0 | None |
| No log | 11.0 | 352 | 10.6613 | 0.244 | 0 | 0 | None |
| No log | 12.0 | 384 | 11.3227 | 0.2415 | 0 | 0 | None |
| No log | 13.0 | 416 | 11.6732 | 0.2435 | 0 | 0 | None |
| No log | 14.0 | 448 | 12.9163 | 0.229 | 0 | 0 | None |
| No log | 15.0 | 480 | 14.3269 | 0.202 | 0 | 0 | None |
| 0.0 | 16.0 | 512 | 14.1039 | 0.193 | 0 | 0 | None |
| 0.0 | 17.0 | 544 | 15.3147 | 0.193 | 0 | 0 | None |
| 0.0 | 18.0 | 576 | 18.4849 | 0.1755 | 0 | 0 | None |
| 0.0 | 19.0 | 608 | 17.9957 | 0.1745 | 0 | 0 | None |
| 0.0 | 20.0 | 640 | 18.9074 | 0.168 | 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