You can deploy this model and start earning money today!

jialicheng/
unlearn_cifar10_swin-base_bad_teaching_4_42

Name: unlearn_cifar10_swin-base_bad_teaching_4_42
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

Views

No views yet

42

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: 0.3955
Accuracy: 0.9793
Dt Accuracy: 0.9793
Df Accuracy: 0.985
Unlearn Overall Accuracy: 0.2060
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: 42
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	32	0.3152	0.9875	0.2020	0.2020	None
No log	2.0	64	0.3169	0.9875	0.2020	0.2020	None
No log	3.0	96	0.4235	0.9865	0.2036	0.2036	None
No log	4.0	128	0.3859	0.99	0.1980	0.1980	None
No log	5.0	160	0.4243	0.989	0.1995	0.1995	None
No log	6.0	192	0.4087	0.986	0.2044	0.2044	None
No log	7.0	224	0.4073	0.9825	0.2100	0.2100	None
No log	8.0	256	0.3693	0.985	0.2060	0.2060	None
No log	9.0	288	0.4068	0.9855	0.2052	0.2052	None
No log	10.0	320	0.3955	0.985	0.2060	0.2060	None

Framework versions

Transformers 4.37.2
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.15.2

jialicheng/unlearn_cifar10_swin-base_bad_teaching_4_42

42

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn_cifar10_swin-base_bad_teaching_4_42