You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_swin-base_salun_8_42

Name: unlearn-so_cifar100_swin-base_salun_8_42
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

endpoints_compatible

Views

No views yet

42

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the cifar100 dataset. It achieves the following results on the evaluation set:

Loss: 0.3833
Accuracy: 0.9078
Dt Accuracy: 0.9078
Df Accuracy: 0.59
Unlearn Overall Accuracy: 0.5876
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: 5e-05
train_batch_size: 128
eval_batch_size: 256
seed: 42
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
1.0531	1.0	391	0.4269	0.8007	0.3443	0.3443	None
0.97	2.0	782	0.4155	0.795	0.3518	0.3518	None
0.8429	3.0	1173	0.3987	0.799	0.3468	0.3468	None
0.8161	4.0	1564	0.4135	0.789	0.3603	0.3603	None
0.7303	5.0	1955	0.4030	0.7678	0.3880	0.3880	None
0.6823	6.0	2346	0.3960	0.726	0.4399	0.4399	None
0.606	7.0	2737	0.3981	0.6837	0.4889	0.4889	None
0.5758	8.0	3128	0.3930	0.634	0.5430	0.5430	None
0.5349	9.0	3519	0.3902	0.6132	0.5643	0.5643	None
0.5078	10.0	3910	0.3833	0.59	0.5876	0.5876	None

Framework versions

Transformers 4.48.0
Pytorch 2.2.2+cu118
Datasets 3.2.0
Tokenizers 0.21.0

jialicheng/unlearn-so_cifar100_swin-base_salun_8_42

42

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar100_swin-base_salun_8_42