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: 0.9478
Accuracy: 0.819
Dt Accuracy: 0.819
Df Accuracy: 0.816
Unlearn Overall Accuracy: 0.3185
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
No log	1.0	32	0.6885	0.8735	0.2367	0.2367	None
No log	2.0	64	0.6974	0.8855	0.2189	0.2189	None
No log	3.0	96	0.6705	0.897	0.2014	0.2014	None
0.0	4.0	128	0.7270	0.8765	0.2329	0.2329	None
0.0	5.0	160	0.7085	0.8845	0.2208	0.2208	None
0.0	6.0	192	0.7668	0.8615	0.2553	0.2553	None
0.0	7.0	224	0.9034	0.8355	0.2919	0.2919	None
0.0	8.0	256	0.8866	0.838	0.2886	0.2886	None
0.0	9.0	288	0.9619	0.8185	0.3150	0.3150	None
0.0	10.0	320	0.9478	0.816	0.3185	0.3185	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_bad_teaching_4_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_bad_teaching_4_42