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: 0.8733
Accuracy: 0.8107
Dt Accuracy: 0.8107
Df Accuracy: 0.793
Unlearn Overall Accuracy: 0.3482
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
No log	1.0	16	0.6189	0.888	0.2149	0.2149	None
No log	2.0	32	0.7125	0.866	0.2477	0.2477	None
No log	3.0	48	0.7007	0.867	0.2465	0.2465	None
No log	4.0	64	0.7612	0.86	0.2568	0.2568	None
No log	5.0	80	0.7720	0.824	0.3074	0.3074	None
No log	6.0	96	0.7258	0.846	0.2774	0.2774	None
0.0	7.0	112	0.8082	0.817	0.3170	0.3170	None
0.0	8.0	128	0.7911	0.826	0.3052	0.3052	None
0.0	9.0	144	0.7982	0.818	0.3161	0.3161	None
0.0	10.0	160	0.8733	0.793	0.3482	0.3482	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_bad_teaching_2_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_bad_teaching_2_87