You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_bad_teaching_6_87

Name: unlearn-so_cifar10_swin-base_bad_teaching_6_87
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

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: 0.8724
Accuracy: 0.9717
Dt Accuracy: 0.9717
Df Accuracy: 0.975
Unlearn Overall Accuracy: 0.2217
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: Adam with betas=(0.9,0.999) and epsilon=1e-08
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	47	1.3787	0.9463	0.2646	0.2646	None
No log	2.0	94	0.9567	0.968	0.2323	0.2323	None
No log	3.0	141	1.2643	0.9657	0.2357	0.2357	None
No log	4.0	188	1.4671	0.964	0.2383	0.2383	None
No log	5.0	235	1.3527	0.9687	0.2311	0.2311	None
No log	6.0	282	1.2884	0.9683	0.2317	0.2317	None
No log	7.0	329	0.9426	0.9737	0.2237	0.2237	None
No log	8.0	376	0.9854	0.9717	0.2269	0.2269	None
No log	9.0	423	0.8801	0.9783	0.2164	0.2164	None
No log	10.0	470	0.8724	0.975	0.2217	0.2217	None

Framework versions

Transformers 4.37.2
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.15.2

jialicheng/unlearn-so_cifar10_swin-base_bad_teaching_6_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_bad_teaching_6_87