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: 0.7291
Accuracy: 0.8354
Dt Accuracy: 0.8354
Df Accuracy: 0.847
Unlearn Overall Accuracy: 0.2763
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: 42
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	0.5882	0.904	0.1898	0.1898	None
No log	2.0	32	0.6398	0.892	0.2088	0.2088	None
No log	3.0	48	0.5640	0.903	0.1917	0.1917	None
No log	4.0	64	0.6199	0.899	0.1980	0.1980	None
No log	5.0	80	0.6407	0.897	0.2011	0.2011	None
No log	6.0	96	0.6457	0.884	0.2216	0.2216	None
0.0	7.0	112	0.6889	0.863	0.2529	0.2529	None
0.0	8.0	128	0.7214	0.848	0.2748	0.2748	None
0.0	9.0	144	0.7227	0.857	0.2618	0.2618	None
0.0	10.0	160	0.7291	0.847	0.2763	0.2763	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_42

42

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_42