You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_bad_teaching_4_13

Name: unlearn-so_cifar10_swin-base_bad_teaching_4_13
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

Views

No views yet

13

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: 1.1821
Accuracy: 0.9581
Dt Accuracy: 0.9581
Df Accuracy: 0.937
Unlearn Overall Accuracy: 0.2790
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: 13
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	0.8722	0.9565	0.2498	0.2498	None
No log	2.0	64	1.1867	0.9505	0.2586	0.2586	None
No log	3.0	96	1.6671	0.939	0.2752	0.2752	None
No log	4.0	128	0.9955	0.9695	0.2301	0.2301	None
No log	5.0	160	1.2303	0.9535	0.2543	0.2543	None
No log	6.0	192	0.8710	0.9735	0.2240	0.2240	None
No log	7.0	224	0.9577	0.959	0.2464	0.2464	None
No log	8.0	256	1.0630	0.9515	0.2576	0.2576	None
No log	9.0	288	1.0827	0.9455	0.2665	0.2665	None
No log	10.0	320	1.1821	0.937	0.2790	0.2790	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_13

13

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_13