Downloads · 30 days
4
6% of all-time downloads
unlearn-so_cifar10_swin-base_random_label_10_100
jialicheng/unlearn-so_cifar10_swin-base_random_label_10_100
unlearn-so_cifar10_swin-base_random_label_10_100 is a image classification model from jialicheng. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.
should probably proofread and complete it, then remove this comment. --
All-time downloads
68
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: 0.1786
- Accuracy: 0.9687
- Dt Accuracy: 0.9687
- Df Accuracy: 0.7986
- Unlearn Overall Accuracy: 0.4608
- 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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 | 391 | 0.2841 | 0.9606 | 0.2434 | 0.2434 | None |
| 0.716 | 2.0 | 782 | 0.2095 | 0.9772 | 0.2182 | 0.2182 | None |
| 0.6379 | 3.0 | 1173 | 0.1997 | 0.9802 | 0.2135 | 0.2135 | None |
| 0.5962 | 4.0 | 1564 | 0.1838 | 0.9798 | 0.2141 | 0.2141 | None |
| 0.5962 | 5.0 | 1955 | 0.1816 | 0.9854 | 0.2053 | 0.2053 | None |
| 0.5418 | 6.0 | 2346 | 0.1739 | 0.9722 | 0.2263 | 0.2263 | None |
| 0.5056 | 7.0 | 2737 | 0.1823 | 0.9528 | 0.2562 | 0.2562 | None |
| 0.4641 | 8.0 | 3128 | 0.1784 | 0.9094 | 0.3194 | 0.3194 | None |
| 0.4239 | 9.0 | 3519 | 0.1528 | 0.8828 | 0.3560 | 0.3560 | None |
| 0.4239 | 10.0 | 3910 | 0.1786 | 0.7986 | 0.4608 | 0.4608 | None |
Framework versions
- Transformers 4.48.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.21.0
- Task
- Image Classification
- Library
- transformers
- Type
- swin
- License
- apache-2.0
- Created
- Oct 29, 2025
- Updated
- Oct 29, 2025