unlearn_cifar100_swin-base_random_label_8_42

jialicheng/unlearn_cifar100_swin-base_random_label_8_42

unlearn_cifar100_swin-base_random_label_8_42 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. --

Downloads · 30 days

9% of all-time downloads

All-time downloads

Public

Parameters

86.9M

372 MB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors348 MB · 93%

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 cifar100 dataset. It achieves the following results on the evaluation set:

Loss: 0.5015
Accuracy: 0.8784
Dt Accuracy: 0.8784
Df Accuracy: 0.0275
Unlearn Overall Accuracy: 0.9651
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: 0.0002
train_batch_size: 128
eval_batch_size: 256
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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	0.5797	0.8605	0.2571	0.2571	None
1.3899	2.0	782	0.4892	0.8938	0.2071	0.2071	None
1.173	3.0	1173	0.5165	0.8705	0.2428	0.2428	None
1.0617	4.0	1564	0.5185	0.818	0.3184	0.3184	None
1.0617	5.0	1955	0.4974	0.796	0.3487	0.3487	None
0.9558	6.0	2346	0.5142	0.7027	0.4626	0.4626	None
0.8519	7.0	2737	0.5024	0.6288	0.5426	0.5426	None
0.7786	8.0	3128	0.5204	0.5085	0.6531	0.6531	None
0.7118	9.0	3519	0.5121	0.4223	0.7208	0.7208	None
0.7118	10.0	3910	0.5544	0.3262	0.7855	0.7855	None
0.6305	11.0	4301	0.5370	0.2557	0.8354	0.8354	None
0.5835	12.0	4692	0.5530	0.2042	0.8630	0.8630	None
0.529	13.0	5083	0.5397	0.1338	0.9040	0.9040	None
0.529	14.0	5474	0.5323	0.1343	0.9059	0.9059	None
0.4736	15.0	5865	0.5359	0.0885	0.9290	0.9290	None
0.4361	16.0	6256	0.5201	0.073	0.9393	0.9393	None
0.3948	17.0	6647	0.5273	0.055	0.9479	0.9479	None
0.3631	18.0	7038	0.5209	0.036	0.9576	0.9576	None
0.3631	19.0	7429	0.5080	0.0305	0.9630	0.9630	None
0.3424	20.0	7820	0.5015	0.0275	0.9651	0.9651	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.18.0
Tokenizers 0.15.2

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