You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_swin-base_random_label_8_42

Name: unlearn-so_cifar10_swin-base_random_label_8_42
Availability: InStock

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

endpoints_compatible

Views

No views yet

42

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: 0.1376
Accuracy: 0.9759
Dt Accuracy: 0.9759
Df Accuracy: 0.811
Unlearn Overall Accuracy: 0.4469
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: 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	391	0.2151	0.9637	0.2388	0.2388	None
0.6673	2.0	782	0.1886	0.971	0.2278	0.2278	None
0.5921	3.0	1173	0.1814	0.975	0.2216	0.2216	None
0.5471	4.0	1564	0.1472	0.9848	0.2063	0.2063	None
0.5471	5.0	1955	0.1401	0.98	0.2140	0.2140	None
0.5056	6.0	2346	0.1706	0.973	0.2251	0.2251	None
0.4627	7.0	2737	0.1546	0.9495	0.2612	0.2612	None
0.4217	8.0	3128	0.1507	0.9085	0.3208	0.3208	None
0.3854	9.0	3519	0.1359	0.8568	0.3903	0.3903	None
0.3854	10.0	3910	0.1376	0.811	0.4469	0.4469	None

Framework versions

Transformers 4.48.0
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.21.0

jialicheng/unlearn-so_cifar10_swin-base_random_label_8_42

42

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-so_cifar10_swin-base_random_label_8_42