You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_salun_6_21

Name: unlearn-so_cifar10_swin-base_salun_6_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: 0.1250
Accuracy: 0.9794
Dt Accuracy: 0.9794
Df Accuracy: 0.8007
Unlearn Overall Accuracy: 0.4595
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	0.1564	0.8883	0.3480	0.3480	None
0.5566	2.0	782	0.1363	0.894	0.3406	0.3406	None
0.5022	3.0	1173	0.1403	0.912	0.3157	0.3157	None
0.4616	4.0	1564	0.1359	0.9077	0.3220	0.3220	None
0.4616	5.0	1955	0.1376	0.9123	0.3153	0.3153	None
0.4216	6.0	2346	0.1246	0.9017	0.3304	0.3304	None
0.3822	7.0	2737	0.1171	0.8987	0.3347	0.3347	None
0.3525	8.0	3128	0.1324	0.8707	0.3724	0.3724	None
0.3153	9.0	3519	0.1153	0.8387	0.4134	0.4134	None
0.3153	10.0	3910	0.1250	0.8007	0.4595	0.4595	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_6_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_6_21