This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the cifar100 dataset. It achieves the following results on the evaluation set:

Loss: 0.4353
Accuracy: 0.8899
Dt Accuracy: 0.8899
Df Accuracy: 0.3222
Unlearn Overall Accuracy: 0.8013
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: 5e-05
train_batch_size: 128
eval_batch_size: 256
seed: 87
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
1.1928	1.0	391	0.4658	0.9104	0.1804	0.1804	None
1.0549	2.0	782	0.4449	0.908	0.1845	0.1845	None
0.9505	3.0	1173	0.4475	0.8586	0.2616	0.2616	None
0.8641	4.0	1564	0.4648	0.792	0.3552	0.3552	None
0.7833	5.0	1955	0.4347	0.7208	0.4453	0.4453	None
0.7071	6.0	2346	0.4487	0.6196	0.5552	0.5552	None
0.6472	7.0	2737	0.4526	0.5156	0.6528	0.6528	None
0.5702	8.0	3128	0.4461	0.4006	0.7434	0.7434	None
0.5179	9.0	3519	0.4364	0.3578	0.7763	0.7763	None
0.4841	10.0	3910	0.4353	0.3222	0.8013	0.8013	None

Framework versions

Transformers 4.48.0
Pytorch 2.2.2+cu118
Datasets 3.2.0
Tokenizers 0.21.0

jialicheng/unlearn-so_cifar100_swin-base_random_label_10_87

87

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar100_swin-base_random_label_10_87