You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_swin-base_salun_6_87

Name: unlearn-so_cifar100_swin-base_salun_6_87
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

endpoints_compatible

Views

No views yet

87

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: 0.3651
Accuracy: 0.9156
Dt Accuracy: 0.9156
Df Accuracy: 0.587
Unlearn Overall Accuracy: 0.5919
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: 87
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
1.0034	1.0	391	0.3839	0.8113	0.3299	0.3299	None
0.9089	2.0	782	0.3723	0.814	0.3265	0.3265	None
0.8172	3.0	1173	0.3809	0.809	0.3335	0.3335	None
0.7381	4.0	1564	0.3836	0.7887	0.3611	0.3611	None
0.6712	5.0	1955	0.3939	0.758	0.4004	0.4004	None
0.6224	6.0	2346	0.3948	0.7013	0.4686	0.4686	None
0.5809	7.0	2737	0.3711	0.6663	0.5095	0.5095	None
0.5196	8.0	3128	0.3783	0.6307	0.5466	0.5466	None
0.4904	9.0	3519	0.3735	0.5947	0.5837	0.5837	None
0.4745	10.0	3910	0.3651	0.587	0.5919	0.5919	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_6_87

87

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar100_swin-base_salun_6_87