You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_random_label_4_100

Name: unlearn-so_cifar10_swin-base_random_label_4_100
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

endpoints_compatible

Views

No views yet

100

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: 0.0964
Accuracy: 0.9837
Dt Accuracy: 0.9837
Df Accuracy: 0.827
Unlearn Overall Accuracy: 0.4282
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: 100
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	0.1418	0.977	0.2185	0.2185	None
0.5547	2.0	782	0.1284	0.9735	0.2240	0.2240	None
0.4952	3.0	1173	0.1170	0.9695	0.2304	0.2304	None
0.4381	4.0	1564	0.1344	0.973	0.2248	0.2248	None
0.4381	5.0	1955	0.1115	0.97	0.2297	0.2297	None
0.3965	6.0	2346	0.1071	0.965	0.2375	0.2375	None
0.3542	7.0	2737	0.1061	0.9465	0.2657	0.2657	None
0.3196	8.0	3128	0.0897	0.9365	0.2807	0.2807	None
0.2858	9.0	3519	0.0928	0.893	0.3425	0.3425	None
0.2858	10.0	3910	0.0964	0.827	0.4282	0.4282	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_random_label_4_100

100

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar10_swin-base_random_label_4_100