You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_bad_teaching_4_100

Name: unlearn-so_cifar10_swin-base_bad_teaching_4_100
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

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: 0.6804
Accuracy: 0.9711
Dt Accuracy: 0.9711
Df Accuracy: 0.9725
Unlearn Overall Accuracy: 0.2256
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: 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	1.1847	0.9495	0.2598	0.2598	None
No log	2.0	64	0.8822	0.957	0.2491	0.2491	None
No log	3.0	96	0.9935	0.9575	0.2482	0.2482	None
No log	4.0	128	1.0200	0.9555	0.2513	0.2513	None
No log	5.0	160	0.9658	0.9705	0.2285	0.2285	None
No log	6.0	192	0.9240	0.968	0.2324	0.2324	None
No log	7.0	224	0.7974	0.9665	0.2348	0.2348	None
No log	8.0	256	0.7365	0.976	0.2201	0.2201	None
No log	9.0	288	0.6704	0.9755	0.2210	0.2210	None
No log	10.0	320	0.6804	0.9725	0.2256	0.2256	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_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_bad_teaching_4_100