Downloads · 30 days
2
3% of all-time downloads
unlearn-so_cifar10_swin-base_bad_teaching_4_100
jialicheng/unlearn-so_cifar10_swin-base_bad_teaching_4_100
unlearn-so_cifar10_swin-base_bad_teaching_4_100 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
60
Public
Parameters
86.8M
350 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors348 MB · 99%
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. -->
100
This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the cifar10 dataset. It achieves the following results on the evaluation set:
- Loss: 0.6804
- Accuracy: 0.9711
- Dt Accuracy: 0.9711
- Df Accuracy: 0.9725
- Unlearn Overall Accuracy: 0.2256
- 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: 0.0001
- train_batch_size: 128
- eval_batch_size: 256
- seed: 100
- 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 | 32 | 1.1847 | 0.9495 | 0.2598 | 0.2598 | None |
| No log | 2.0 | 64 | 0.8822 | 0.957 | 0.2491 | 0.2491 | None |
| No log | 3.0 | 96 | 0.9935 | 0.9575 | 0.2482 | 0.2482 | None |
| No log | 4.0 | 128 | 1.0200 | 0.9555 | 0.2513 | 0.2513 | None |
| No log | 5.0 | 160 | 0.9658 | 0.9705 | 0.2285 | 0.2285 | None |
| No log | 6.0 | 192 | 0.9240 | 0.968 | 0.2324 | 0.2324 | None |
| No log | 7.0 | 224 | 0.7974 | 0.9665 | 0.2348 | 0.2348 | None |
| No log | 8.0 | 256 | 0.7365 | 0.976 | 0.2201 | 0.2201 | None |
| No log | 9.0 | 288 | 0.6704 | 0.9755 | 0.2210 | 0.2210 | None |
| No log | 10.0 | 320 | 0.6804 | 0.9725 | 0.2256 | 0.2256 | None |
Framework versions
- Transformers 4.37.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.15.2
- Task
- Image Classification
- Type
- swin
- License
- apache-2.0
- Created
- Oct 29, 2025
- Updated
- Oct 29, 2025