You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_swin-base_salun_6_42

Name: unlearn-so_cifar100_swin-base_salun_6_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: 0.3558
Accuracy: 0.9163
Dt Accuracy: 0.9163
Df Accuracy: 0.5637
Unlearn Overall Accuracy: 0.6145
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
1.0126	1.0	391	0.4008	0.7853	0.3647	0.3647	None
0.9006	2.0	782	0.3518	0.815	0.3254	0.3254	None
0.7939	3.0	1173	0.3766	0.7967	0.3504	0.3504	None
0.754	4.0	1564	0.3737	0.779	0.3738	0.3738	None
0.671	5.0	1955	0.3756	0.7467	0.4150	0.4150	None
0.6289	6.0	2346	0.3682	0.728	0.4381	0.4381	None
0.5677	7.0	2737	0.3527	0.6917	0.4814	0.4814	None
0.5369	8.0	3128	0.3790	0.6067	0.5715	0.5715	None
0.4808	9.0	3519	0.3641	0.5737	0.6049	0.6049	None
0.4715	10.0	3910	0.3558	0.5637	0.6145	0.6145	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_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_6_42