You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_swin-base_salun_10_87

Name: unlearn-so_cifar100_swin-base_salun_10_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: 0.4141
Accuracy: 0.9031
Dt Accuracy: 0.9031
Df Accuracy: 0.5804
Unlearn Overall Accuracy: 0.5960
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
1.0999	1.0	391	0.4561	0.7936	0.3529	0.3529	None
1.0031	2.0	782	0.4357	0.8056	0.3377	0.3377	None
0.9052	3.0	1173	0.4162	0.7958	0.3512	0.3512	None
0.8381	4.0	1564	0.4225	0.774	0.3797	0.3797	None
0.788	5.0	1955	0.4108	0.7526	0.4074	0.4074	None
0.7105	6.0	2346	0.4326	0.7068	0.4621	0.4621	None
0.6572	7.0	2737	0.4276	0.6644	0.5094	0.5094	None
0.5997	8.0	3128	0.4241	0.6062	0.5702	0.5702	None
0.5744	9.0	3519	0.4195	0.587	0.5894	0.5894	None
0.5201	10.0	3910	0.4141	0.5804	0.5960	0.5960	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_10_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_10_87