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: 24.6912
Accuracy: 0.2329
Dt Accuracy: 0.2329
Df Accuracy: 0.1605
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	32	1.3404	0.7325	None
No log	2.0	64	2.6689	0.5735	None
No log	3.0	96	2.7328	0.5935	None
No log	4.0	128	3.4698	0.53	None
No log	5.0	160	4.7622	0.454	None
No log	6.0	192	5.4133	0.43	None
No log	7.0	224	7.2147	0.375	None
No log	8.0	256	8.2061	0.348	None
No log	9.0	288	9.6316	0.329	None
No log	10.0	320	9.2762	0.337	None
No log	11.0	352	13.0724	0.262	None
No log	12.0	384	14.4330	0.252	None
No log	13.0	416	15.7955	0.231	None
No log	14.0	448	15.8354	0.219	None
No log	15.0	480	18.2667	0.19	None
0.0	16.0	512	17.8643	0.1995	None
0.0	17.0	544	23.0099	0.1695	None
0.0	18.0	576	23.5217	0.162	None
0.0	19.0	608	24.8197	0.1575	None
0.0	20.0	640	24.6912	0.1605	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_4_42

42

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

为此模型做种