unlearn_cifar10_swin-base_salun_2_42

jialicheng/unlearn_cifar10_swin-base_salun_2_42

unlearn_cifar10_swin-base_salun_2_42 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. --

Downloads · 30 days

13% of all-time downloads

All-time downloads

Public

Parameters

86.8M

1 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.pt694 MB · 66%

Parameter types

How the weights are stored.

F3286.8M · 100%

Base models

microsoft/swin-base-patch4-window7-224

Model card

From the Hugging Face model README

42

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: 0.0651
Accuracy: 0.9839
Dt Accuracy: 0.9839
Df Accuracy: 0.165
Unlearn Overall Accuracy: 0.9631
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: 42
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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.0	391	0.0816	0.903	0.3286	0.3286	None
0.323	2.0	782	0.0742	0.905	0.3258	0.3258	None
0.3	3.0	1173	0.0824	0.898	0.3356	0.3356	None
0.2882	4.0	1564	0.1027	0.876	0.3652	0.3652	None
0.2882	5.0	1955	0.0728	0.885	0.3534	0.3534	None
0.267	6.0	2346	0.0777	0.828	0.4269	0.4269	None
0.2456	7.0	2737	0.0774	0.779	0.4849	0.4849	None
0.2286	8.0	3128	0.0922	0.675	0.5938	0.5938	None
0.2155	9.0	3519	0.0742	0.623	0.6437	0.6437	None
0.2155	10.0	3910	0.0823	0.534	0.7198	0.7198	None
0.1915	11.0	4301	0.0800	0.46	0.7773	0.7773	None
0.178	12.0	4692	0.0831	0.369	0.8397	0.8397	None
0.1665	13.0	5083	0.0813	0.331	0.8652	0.8652	None
0.1665	14.0	5474	0.0712	0.291	0.8908	0.8908	None
0.1516	15.0	5865	0.0686	0.294	0.8893	0.8893	None
0.1403	16.0	6256	0.0672	0.233	0.9253	0.9253	None
0.1299	17.0	6647	0.0642	0.221	0.9322	0.9322	None
0.1221	18.0	7038	0.0629	0.203	0.9428	0.9428	None
0.1221	19.0	7429	0.0658	0.185	0.9524	0.9524	None
0.1138	20.0	7820	0.0651	0.165	0.9631	0.9631	None

Framework versions

Transformers 4.48.0
Pytorch 2.2.2+cu118
Datasets 3.2.0
Tokenizers 0.21.0

Task: Image Classification
Library: transformers
Type: swin
License: apache-2.0
Created: Oct 22, 2025
Updated: Oct 22, 2025