You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_salun_4_21

Name: unlearn-so_cifar10_swin-base_salun_4_21
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

endpoints_compatible

Views

No views yet

21

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: 0.0987
Accuracy: 0.9811
Dt Accuracy: 0.9811
Df Accuracy: 0.765
Unlearn Overall Accuracy: 0.5006
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: 21
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	0.1241	0.8835	0.3549	0.3549	None
0.4979	2.0	782	0.1276	0.883	0.3552	0.3552	None
0.4471	3.0	1173	0.1033	0.9055	0.3251	0.3251	None
0.4019	4.0	1564	0.1112	0.9045	0.3264	0.3264	None
0.4019	5.0	1955	0.0998	0.9015	0.3306	0.3306	None
0.3642	6.0	2346	0.0966	0.8915	0.3445	0.3445	None
0.3313	7.0	2737	0.1019	0.871	0.3721	0.3721	None
0.2978	8.0	3128	0.0937	0.8475	0.4025	0.4025	None
0.2626	9.0	3519	0.1033	0.784	0.4791	0.4791	None
0.2626	10.0	3910	0.0987	0.765	0.5006	0.5006	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_4_21

21

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar10_swin-base_salun_4_21