You can deploy this model and start earning money today!

jialicheng/
unlearn_cifar10_swin-base_neggrad_10_42

Name: unlearn_cifar10_swin-base_neggrad_10_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: -49.1295
Accuracy: 0.1
Dt Accuracy: 0.1
Df Accuracy: 0.1
Unlearn Overall Accuracy: 0
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-06
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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Overall Accuracy	Unlearn Overall Accuracy	Time
No log	1.0	40	-0.0608	0.998	0.1851	0.1851	None
No log	2.0	80	-10.4346	0.313	0	0	None
No log	3.0	120	-35.6375	0.1	0	0	None
No log	4.0	160	-41.0251	0.1	0	0	None
No log	5.0	200	-43.0922	0.1	0	0	None
No log	6.0	240	-44.1355	0.1	0	0	None
No log	7.0	280	-44.8496	0.1	0	0	None
No log	8.0	320	-45.4907	0.1	0	0	None
No log	9.0	360	-46.0966	0.1	0	0	None
No log	10.0	400	-46.6587	0.1	0	0	None
No log	11.0	440	-47.1468	0.1	0	0	None
No log	12.0	480	-47.5392	0.1	0	0	None
-36.0286	13.0	520	-47.9485	0.1	0	0	None
-36.0286	14.0	560	-48.2224	0.1	0	0	None
-36.0286	15.0	600	-48.4875	0.1	0	0	None
-36.0286	16.0	640	-48.7011	0.1	0	0	None
-36.0286	17.0	680	-48.9115	0.1	0	0	None
-36.0286	18.0	720	-49.0247	0.1	0	0	None
-36.0286	19.0	760	-49.0929	0.1	0	0	None
-36.0286	20.0	800	-49.1295	0.1	0	0	None

Framework versions

Transformers 4.48.0
Pytorch 2.2.2+cu118
Datasets 3.2.0
Tokenizers 0.21.0

jialicheng/unlearn_cifar10_swin-base_neggrad_10_42

42

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn_cifar10_swin-base_neggrad_10_42