unlearn_cifar10_swin-base_random_label_4_87

jialicheng/unlearn_cifar10_swin-base_random_label_4_87

unlearn_cifar10_swin-base_random_label_4_87 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

8% of all-time downloads

All-time downloads

Public

Parameters

86.8M

350 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors348 MB · 99%

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

87

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: 0.0822
Accuracy: 0.9799
Dt Accuracy: 0.9799
Df Accuracy: 0.0395
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: 5e-05
train_batch_size: 128
eval_batch_size: 256
seed: 87
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	0.0964	0.994	0.1916	0.1916	None
0.3373	2.0	782	0.0844	0.989	0.1997	0.1997	None
0.3099	3.0	1173	0.0927	0.9795	0.2150	0.2150	None
0.2959	4.0	1564	0.0956	0.943	0.2712	0.2712	None
0.2959	5.0	1955	0.0818	0.9095	0.3198	0.3198	None
0.2817	6.0	2346	0.1033	0.7435	0.5243	0.5243	None
0.2566	7.0	2737	0.1064	0.6525	0.6162	0.6162	None
0.2464	8.0	3128	0.1062	0.5265	0.7255	0.7255	None
0.2224	9.0	3519	0.0962	0.4465	0.7861	0.7861	None
0.2224	10.0	3910	0.0852	0.375	0.8370	0.8370	None
0.2035	11.0	4301	0.0866	0.2905	0.8902	0.8902	None
0.1889	12.0	4692	0.0933	0.2105	0.9355	0.9355	None
0.1765	13.0	5083	0.0991	0.137	0.9735	0.9735	None
0.1765	14.0	5474	0.0929	0.095	0.9900	0.9900	None
0.1622	15.0	5865	0.0886	0.099	0.9932	0.9932	None
0.1462	16.0	6256	0.0886	0.0725	0	0	None
0.1424	17.0	6647	0.0893	0.0605	0	0	None
0.1338	18.0	7038	0.0866	0.0425	0	0	None
0.1338	19.0	7429	0.0821	0.042	0	0	None
0.1288	20.0	7820	0.0822	0.0395	0	0	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