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: 0.3292
Accuracy: 0.9196
Dt Accuracy: 0.9196
Df Accuracy: 0.387
Unlearn Overall Accuracy: 0.7646
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
0.9302	1.0	391	0.3926	0.909	0.1827	0.1827	None
0.814	2.0	782	0.3763	0.907	0.1861	0.1861	None
0.73	3.0	1173	0.3444	0.893	0.2090	0.2090	None
0.6518	4.0	1564	0.3412	0.837	0.2939	0.2939	None
0.5839	5.0	1955	0.3479	0.762	0.3959	0.3959	None
0.5043	6.0	2346	0.3484	0.672	0.5029	0.5029	None
0.4653	7.0	2737	0.3384	0.571	0.6072	0.6072	None
0.4234	8.0	3128	0.3314	0.447	0.7176	0.7176	None
0.3826	9.0	3519	0.3304	0.418	0.7403	0.7403	None
0.3454	10.0	3910	0.3292	0.387	0.7646	0.7646	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_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_2_42