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: 0.3522
Accuracy: 0.9145
Dt Accuracy: 0.9145
Df Accuracy: 0.339
Unlearn Overall Accuracy: 0.7980
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
1.0178	1.0	391	0.4107	0.9155	0.1721	0.1721	None
0.886	2.0	782	0.3818	0.9115	0.1788	0.1788	None
0.8047	3.0	1173	0.3769	0.8945	0.2065	0.2065	None
0.7014	4.0	1564	0.3824	0.8325	0.3004	0.3004	None
0.6655	5.0	1955	0.3502	0.775	0.3793	0.3793	None
0.5831	6.0	2346	0.3781	0.614	0.5631	0.5631	None
0.5243	7.0	2737	0.3679	0.5525	0.6241	0.6241	None
0.4545	8.0	3128	0.3711	0.427	0.7316	0.7316	None
0.4436	9.0	3519	0.3516	0.369	0.7759	0.7759	None
0.4032	10.0	3910	0.3522	0.339	0.7980	0.7980	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_4_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_4_87