You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_bad_teaching_4_42

Name: unlearn-so_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: 0.8220
Accuracy: 0.9686
Dt Accuracy: 0.9686
Df Accuracy: 0.9715
Unlearn Overall Accuracy: 0.2271
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	0.8327	0.967	0.2337	0.2337	None
No log	2.0	64	1.7005	0.933	0.2834	0.2834	None
No log	3.0	96	1.0749	0.9635	0.2391	0.2391	None
No log	4.0	128	1.0284	0.968	0.2323	0.2323	None
No log	5.0	160	0.9400	0.977	0.2184	0.2184	None
No log	6.0	192	0.9861	0.973	0.2246	0.2246	None
No log	7.0	224	0.7604	0.976	0.2201	0.2201	None
No log	8.0	256	0.9420	0.97	0.2294	0.2294	None
No log	9.0	288	0.8274	0.971	0.2279	0.2279	None
No log	10.0	320	0.8220	0.9715	0.2271	0.2271	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_4_42

42

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_4_42