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: 0.3986
Accuracy: 0.8997
Dt Accuracy: 0.8997
Df Accuracy: 0.315
Unlearn Overall Accuracy: 0.8097
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
1.131	1.0	391	0.4652	0.8965	0.2027	0.2027	None
0.9996	2.0	782	0.4258	0.9048	0.1899	0.1899	None
0.8928	3.0	1173	0.4365	0.8662	0.2502	0.2502	None
0.8238	4.0	1564	0.4211	0.7923	0.3555	0.3555	None
0.7294	5.0	1955	0.4210	0.7225	0.4429	0.4429	None
0.6705	6.0	2346	0.4255	0.5873	0.5875	0.5875	None
0.588	7.0	2737	0.4221	0.5088	0.6590	0.6590	None
0.5437	8.0	3128	0.4217	0.3912	0.7529	0.7529	None
0.4802	9.0	3519	0.4063	0.3305	0.7983	0.7983	None
0.445	10.0	3910	0.3986	0.315	0.8097	0.8097	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_8_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_8_42