You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_salun_2_100

Name: unlearn-so_cifar10_swin-base_salun_2_100
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

endpoints_compatible

Views

No views yet

100

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: 0.0685
Accuracy: 0.9855
Dt Accuracy: 0.9855
Df Accuracy: 0.8
Unlearn Overall Accuracy: 0.4610
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: 100
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	0.0931	0.89	0.3461	0.3461	None
0.421	2.0	782	0.0873	0.911	0.3173	0.3173	None
0.3783	3.0	1173	0.0936	0.885	0.3530	0.3530	None
0.3356	4.0	1564	0.0807	0.898	0.3356	0.3356	None
0.3356	5.0	1955	0.0809	0.885	0.3534	0.3534	None
0.3002	6.0	2346	0.0673	0.9	0.3330	0.3330	None
0.2653	7.0	2737	0.0714	0.874	0.3682	0.3682	None
0.2353	8.0	3128	0.0733	0.844	0.4071	0.4071	None
0.2082	9.0	3519	0.0669	0.819	0.4384	0.4384	None
0.2082	10.0	3910	0.0685	0.8	0.4610	0.4610	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_2_100

100

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar10_swin-base_salun_2_100