You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_bad_teaching_8_87

Name: unlearn-so_cifar10_swin-base_bad_teaching_8_87
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

Views

No views yet

87

This model is a fine-tuned version of microsoft/swin-base-patch4-window7-224 on the cifar10 dataset. It achieves the following results on the evaluation set:

Loss: 0.8365
Accuracy: 0.9736
Dt Accuracy: 0.9736
Df Accuracy: 0.9765
Unlearn Overall Accuracy: 0.2194
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: 0.0001
train_batch_size: 128
eval_batch_size: 256
seed: 87
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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	1.4675	0.9437	0.2680	0.2680	None
No log	2.0	126	1.4375	0.9603	0.2438	0.2438	None
No log	3.0	189	1.1945	0.968	0.2323	0.2323	None
No log	4.0	252	1.9980	0.9513	0.2573	0.2573	None
No log	5.0	315	1.9949	0.9615	0.2421	0.2421	None
No log	6.0	378	1.1425	0.9738	0.2235	0.2235	None
No log	7.0	441	0.8408	0.9815	0.2115	0.2115	None
0.0	8.0	504	0.9150	0.974	0.2233	0.2233	None
0.0	9.0	567	0.8936	0.9778	0.2174	0.2174	None
0.0	10.0	630	0.8365	0.9765	0.2194	0.2194	None

Framework versions

Transformers 4.37.2
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.15.2

jialicheng/unlearn-so_cifar10_swin-base_bad_teaching_8_87

87

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar10_swin-base_bad_teaching_8_87