42

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: 14.9312
Accuracy: 0.2672
Dt Accuracy: 0.2672
Df Accuracy: 0.145
Unlearn Overall Accuracy: 0
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: 0.0002
train_batch_size: 128
eval_batch_size: 256
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Time
No log	1.0	16	1.0955	0.763	None
No log	2.0	32	1.3377	0.736	None
No log	3.0	48	1.5782	0.687	None
No log	4.0	64	2.3996	0.62	None
No log	5.0	80	2.2983	0.626	None
No log	6.0	96	2.4060	0.631	None
No log	7.0	112	3.5954	0.505	None
No log	8.0	128	5.2384	0.396	None
No log	9.0	144	4.3896	0.451	None
No log	10.0	160	5.0817	0.421	None
No log	11.0	176	7.2907	0.307	None
No log	12.0	192	8.6480	0.301	None
No log	13.0	208	9.1179	0.238	None
No log	14.0	224	9.8129	0.242	None
No log	15.0	240	8.8768	0.249	None
No log	16.0	256	10.1024	0.212	None
No log	17.0	272	12.5102	0.18	None
No log	18.0	288	12.5515	0.175	None
No log	19.0	304	12.9056	0.162	None
No log	20.0	320	14.9312	0.145	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.18.0
Tokenizers 0.15.2

jialicheng/unlearn_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

Seed this model