You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_salun_10_87

Name: unlearn-so_cifar10_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 cifar10 dataset. It achieves the following results on the evaluation set:

Loss: 0.1607
Accuracy: 0.9678
Dt Accuracy: 0.9678
Df Accuracy: 0.7886
Unlearn Overall Accuracy: 0.4722
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: 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
No log	1.0	391	0.1813	0.8802	0.3588	0.3588	None
0.6527	2.0	782	0.2032	0.9046	0.3259	0.3259	None
0.5914	3.0	1173	0.1589	0.9008	0.3313	0.3313	None
0.5485	4.0	1564	0.1671	0.9168	0.3090	0.3090	None
0.5485	5.0	1955	0.1556	0.9112	0.3169	0.3169	None
0.5146	6.0	2346	0.1516	0.9172	0.3086	0.3086	None
0.4732	7.0	2737	0.1549	0.8978	0.3357	0.3357	None
0.439	8.0	3128	0.1737	0.8582	0.3881	0.3881	None
0.3986	9.0	3519	0.1622	0.8116	0.4456	0.4456	None
0.3986	10.0	3910	0.1607	0.7886	0.4722	0.4722	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_10_87

87

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar10_swin-base_salun_10_87