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: 0.3238
Accuracy: 0.9183
Dt Accuracy: 0.9183
Df Accuracy: 0.383
Unlearn Overall Accuracy: 0.7672
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
0.9369	1.0	391	0.3791	0.922	0.1613	0.1613	None
0.8305	2.0	782	0.3766	0.905	0.1893	0.1893	None
0.7314	3.0	1173	0.3439	0.879	0.2311	0.2311	None
0.6435	4.0	1564	0.3490	0.851	0.2735	0.2735	None
0.5961	5.0	1955	0.3544	0.783	0.3684	0.3684	None
0.5525	6.0	2346	0.3398	0.665	0.5113	0.5113	None
0.4662	7.0	2737	0.3553	0.542	0.6342	0.6342	None
0.4275	8.0	3128	0.3339	0.47	0.6977	0.6977	None
0.38	9.0	3519	0.3361	0.4	0.7542	0.7542	None
0.3588	10.0	3910	0.3238	0.383	0.7672	0.7672	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_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_random_label_2_87