You can deploy this model and start earning money today!

jialicheng/
unlearn-cl_cifar10_swin-base_random_label_2_87

generated_from_trainer

microsoft/swin-base-patch4-window7-224

finetune

apache-2.0

endpoints_compatible

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: 0.0504
Accuracy: 0.9856
Dt Accuracy: 0.9856
Df Accuracy: 0.052
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-05
train_batch_size: 128
eval_batch_size: 256
seed: 87
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	391	0.0604	0.993	0.1932	0.1932	None
0.2371	2.0	782	0.0634	0.989	0.1997	0.1997	None
0.2278	3.0	1173	0.0538	0.98	0.2142	0.2142	None
0.2158	4.0	1564	0.0563	0.961	0.2440	0.2440	None
0.2158	5.0	1955	0.0586	0.916	0.3106	0.3106	None
0.206	6.0	2346	0.0671	0.828	0.4273	0.4273	None
0.1909	7.0	2737	0.0622	0.748	0.5199	0.5199	None
0.183	8.0	3128	0.0716	0.568	0.6928	0.6928	None
0.1737	9.0	3519	0.0661	0.483	0.7609	0.7609	None
0.1737	10.0	3910	0.0599	0.411	0.8139	0.8139	None
0.1579	11.0	4301	0.0592	0.327	0.8699	0.8699	None
0.1482	12.0	4692	0.0591	0.277	0.9003	0.9003	None
0.1408	13.0	5083	0.0591	0.203	0.9427	0.9427	None
0.1408	14.0	5474	0.0575	0.148	0.9722	0.9722	None
0.1298	15.0	5865	0.0504	0.121	0.9870	0.9870	None
0.1228	16.0	6256	0.0512	0.069	0	0	None
0.1176	17.0	6647	0.0513	0.077	0	0	None
0.1121	18.0	7038	0.0516	0.054	0	0	None
0.1121	19.0	7429	0.0505	0.057	0	0	None
0.1059	20.0	7820	0.0504	0.052	0	0	None

Framework versions

Transformers 4.48.0
Pytorch 2.2.2+cu118
Datasets 3.2.0
Tokenizers 0.21.0

jialicheng/unlearn-cl_cifar10_swin-base_random_label_2_87

87

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jialicheng/
unlearn-cl_cifar10_swin-base_random_label_2_87