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: 0.4035
Accuracy: 0.9004
Dt Accuracy: 0.9004
Df Accuracy: 0.3395
Unlearn Overall Accuracy: 0.7930
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
1.1468	1.0	391	0.4611	0.9038	0.1912	0.1912	None
1.0099	2.0	782	0.4395	0.8952	0.2050	0.2050	None
0.9226	3.0	1173	0.4355	0.8582	0.2624	0.2624	None
0.8219	4.0	1564	0.4171	0.802	0.3426	0.3426	None
0.7531	5.0	1955	0.4010	0.734	0.4301	0.4301	None
0.6843	6.0	2346	0.4175	0.6162	0.5595	0.5595	None
0.6142	7.0	2737	0.4240	0.5115	0.6581	0.6581	None
0.5381	8.0	3128	0.4189	0.4047	0.7441	0.7441	None
0.5001	9.0	3519	0.4088	0.3675	0.7730	0.7730	None
0.4654	10.0	3910	0.4035	0.3395	0.7930	0.7930	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_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_8_87