You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_salun_10_21

Name: unlearn-so_cifar10_swin-base_salun_10_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: 0.1711
Accuracy: 0.9681
Dt Accuracy: 0.9681
Df Accuracy: 0.7812
Unlearn Overall Accuracy: 0.4807
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	0.2282	0.8964	0.3365	0.3365	None
0.661	2.0	782	0.1514	0.8992	0.3336	0.3336	None
0.5911	3.0	1173	0.1725	0.903	0.3282	0.3282	None
0.5519	4.0	1564	0.1965	0.9004	0.3315	0.3315	None
0.5519	5.0	1955	0.1627	0.919	0.3060	0.3060	None
0.5098	6.0	2346	0.1532	0.9212	0.3029	0.3029	None
0.4766	7.0	2737	0.1643	0.8996	0.3332	0.3332	None
0.4321	8.0	3128	0.1861	0.8448	0.4048	0.4048	None
0.395	9.0	3519	0.1777	0.8054	0.4527	0.4527	None
0.395	10.0	3910	0.1711	0.7812	0.4807	0.4807	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_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_10_21