You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_bad_teaching_8_21

Name: unlearn-so_cifar10_swin-base_bad_teaching_8_21
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

Views

No views yet

21

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: 0.9804
Accuracy: 0.9714
Dt Accuracy: 0.9714
Df Accuracy: 0.9732
Unlearn Overall Accuracy: 0.2245
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: 21
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	63	1.0259	0.9615	0.2420	0.2420	None
No log	2.0	126	1.4510	0.9627	0.2401	0.2401	None
No log	3.0	189	1.0904	0.9712	0.2273	0.2273	None
No log	4.0	252	1.7512	0.9593	0.2455	0.2455	None
No log	5.0	315	1.2856	0.9683	0.2320	0.2320	None
No log	6.0	378	1.2228	0.9752	0.2212	0.2212	None
No log	7.0	441	1.1988	0.9685	0.2318	0.2318	None
0.0	8.0	504	1.1435	0.9695	0.2302	0.2302	None
0.0	9.0	567	0.9733	0.9765	0.2194	0.2194	None
0.0	10.0	630	0.9804	0.9732	0.2245	0.2245	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_8_21

21

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_8_21