You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_salun_10_13

Name: unlearn-so_cifar10_swin-base_salun_10_13
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

endpoints_compatible

Views

No views yet

13

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: 0.1652
Accuracy: 0.9715
Dt Accuracy: 0.9715
Df Accuracy: 0.7858
Unlearn Overall Accuracy: 0.4759
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: 13
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	0.2023	0.8906	0.3450	0.3450	None
0.6573	2.0	782	0.2141	0.898	0.3348	0.3348	None
0.5932	3.0	1173	0.1673	0.905	0.3255	0.3255	None
0.549	4.0	1564	0.1821	0.9186	0.3065	0.3065	None
0.549	5.0	1955	0.1782	0.9128	0.3146	0.3146	None
0.5158	6.0	2346	0.1509	0.9184	0.3069	0.3069	None
0.4755	7.0	2737	0.1790	0.8806	0.3590	0.3590	None
0.4378	8.0	3128	0.1596	0.8646	0.3801	0.3801	None
0.4006	9.0	3519	0.1745	0.8082	0.4498	0.4498	None
0.4006	10.0	3910	0.1652	0.7858	0.4759	0.4759	None

Framework versions

Transformers 4.48.0
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.21.0

jialicheng/unlearn-so_cifar10_swin-base_salun_10_13

13

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar10_swin-base_salun_10_13