You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_salun_6_100

Name: unlearn-so_cifar10_swin-base_salun_6_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: 0.1179
Accuracy: 0.9806
Dt Accuracy: 0.9806
Df Accuracy: 0.792
Unlearn Overall Accuracy: 0.4698
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	0.1778	0.8867	0.3503	0.3503	None
0.5562	2.0	782	0.1518	0.897	0.3362	0.3362	None
0.5002	3.0	1173	0.1389	0.8993	0.3334	0.3334	None
0.4581	4.0	1564	0.1247	0.9107	0.3179	0.3179	None
0.4581	5.0	1955	0.1218	0.91	0.3188	0.3188	None
0.4215	6.0	2346	0.1181	0.91	0.3189	0.3189	None
0.387	7.0	2737	0.1171	0.8953	0.3393	0.3393	None
0.3472	8.0	3128	0.1076	0.878	0.3628	0.3628	None
0.3164	9.0	3519	0.1101	0.847	0.4031	0.4031	None
0.3164	10.0	3910	0.1179	0.792	0.4698	0.4698	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_6_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_salun_6_100