jialicheng/unlearn_cifar10_swin-base_random_label_6_87

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: 0.0970
• Accuracy: 0.9734
• Dt Accuracy: 0.9734
• Df Accuracy: 0.0543
• 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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• 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	0.1163	0.993	0.1932	0.1932	None
0.4108	2.0	782	0.1171	0.9947	0.1905	0.1905	None
0.3837	3.0	1173	0.1140	0.99	0.1981	0.1981	None
0.3653	4.0	1564	0.1035	0.977	0.2190	0.2190	None
0.3653	5.0	1955	0.1122	0.9267	0.2952	0.2952	None
0.3472	6.0	2346	0.1287	0.8363	0.4166	0.4166	None
0.318	7.0	2737	0.1191	0.7663	0.4992	0.4992	None
0.3056	8.0	3128	0.1308	0.6023	0.6608	0.6608	None
0.2842	9.0	3519	0.1313	0.5027	0.7424	0.7424	None
0.2842	10.0	3910	0.1182	0.42	0.8037	0.8037	None
0.257	11.0	4301	0.1197	0.3367	0.8579	0.8579	None
0.2351	12.0	4692	0.1033	0.2577	0.9077	0.9077	None
0.2193	13.0	5083	0.1151	0.1957	0.9403	0.9403	None
0.2193	14.0	5474	0.1152	0.1643	0.9564	0.9564	None
0.2077	15.0	5865	0.1076	0.1183	0.9807	0.9807	None
0.1906	16.0	6256	0.1027	0.093	0.9871	0.9871	None
0.1816	17.0	6647	0.1055	0.072	0	0	None
0.1736	18.0	7038	0.0968	0.0667	0	0	None
0.1736	19.0	7429	0.1003	0.0517	0	0	None
0.161	20.0	7820	0.0970	0.0543	0	0	None

Framework versions

• Transformers 4.37.2
• Pytorch 2.3.0+cu121
• Datasets 2.19.0
• Tokenizers 0.15.2