unlearn_cifar10_swin-base_salun_2_87

jialicheng/unlearn_cifar10_swin-base_salun_2_87

unlearn_cifar10_swin-base_salun_2_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

3% 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

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: 0.0658
Accuracy: 0.9857
Dt Accuracy: 0.9857
Df Accuracy: 0.207
Unlearn Overall Accuracy: 0.9411
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: 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	0.0837	0.924	0.2989	0.2989	None
0.3235	2.0	782	0.0746	0.925	0.2975	0.2975	None
0.3069	3.0	1173	0.0729	0.903	0.3288	0.3288	None
0.2875	4.0	1564	0.0700	0.911	0.3176	0.3176	None
0.2875	5.0	1955	0.0831	0.888	0.3492	0.3492	None
0.2693	6.0	2346	0.0839	0.819	0.4379	0.4379	None
0.2492	7.0	2737	0.0888	0.782	0.4812	0.4812	None
0.2321	8.0	3128	0.0991	0.671	0.5986	0.5986	None
0.2143	9.0	3519	0.0789	0.601	0.6637	0.6637	None
0.2143	10.0	3910	0.0773	0.561	0.6982	0.6982	None
0.1967	11.0	4301	0.0783	0.474	0.7667	0.7667	None
0.1749	12.0	4692	0.0807	0.458	0.7786	0.7786	None
0.1654	13.0	5083	0.0769	0.377	0.8362	0.8362	None
0.1654	14.0	5474	0.0715	0.278	0.8990	0.8990	None
0.1518	15.0	5865	0.0740	0.266	0.9062	0.9062	None
0.1406	16.0	6256	0.0719	0.236	0.9235	0.9235	None
0.1319	17.0	6647	0.0701	0.219	0.9341	0.9341	None
0.1238	18.0	7038	0.0696	0.196	0.9464	0.9464	None
0.1238	19.0	7429	0.0674	0.189	0.9506	0.9506	None
0.1153	20.0	7820	0.0658	0.207	0.9411	0.9411	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