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: 0.4348
Accuracy: 0.8895
Dt Accuracy: 0.8895
Df Accuracy: 0.3294
Unlearn Overall Accuracy: 0.7963
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
1.2009	1.0	391	0.4539	0.9014	0.1951	0.1951	None
1.0569	2.0	782	0.4382	0.8952	0.2052	0.2052	None
0.9502	3.0	1173	0.4480	0.854	0.2686	0.2686	None
0.8956	4.0	1564	0.4360	0.8144	0.3255	0.3255	None
0.7797	5.0	1955	0.4442	0.7264	0.4384	0.4384	None
0.7027	6.0	2346	0.4372	0.6188	0.5563	0.5563	None
0.6271	7.0	2737	0.4364	0.547	0.6254	0.6254	None
0.5825	8.0	3128	0.4420	0.4202	0.7293	0.7293	None
0.5236	9.0	3519	0.4465	0.3536	0.7784	0.7784	None
0.4726	10.0	3910	0.4348	0.3294	0.7963	0.7963	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_10_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_random_label_10_42