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: 1.5373
Accuracy: 0.7711
Dt Accuracy: 0.7711
Df Accuracy: 0.7622
Unlearn Overall Accuracy: 0.3827
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	63	0.6759	0.8822	0.2241	0.2241	None
0.0	2.0	126	0.8289	0.8652	0.2494	0.2494	None
0.0	3.0	189	0.8482	0.8692	0.2436	0.2436	None
0.0	4.0	252	1.1060	0.8363	0.2901	0.2901	None
0.0	5.0	315	1.0648	0.8413	0.2836	0.2836	None
0.0	6.0	378	1.2247	0.8135	0.3205	0.3205	None
0.0	7.0	441	1.3283	0.7985	0.3398	0.3398	None
0.0	8.0	504	1.3708	0.7843	0.3573	0.3573	None
0.0	9.0	567	1.5034	0.7662	0.3782	0.3782	None
0.0	10.0	630	1.5373	0.7622	0.3827	0.3827	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_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_bad_teaching_8_42