jialicheng/unlearn_cifar10_resnet-34_random_label_4_87

87

This model is a fine-tuned version of microsoft/resnet-34 on the cifar10 dataset. It achieves the following results on the evaluation set:

• Loss: 0.1611
• Accuracy: 0.958
• Dt Accuracy: 0.958
• Df Accuracy: 0.9455
• Unlearn Overall Accuracy: 0.2673
• 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: 0.0005
• 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	391	0.4014	0.881	0.3530	0.3530	None
0.8855	2.0	782	0.3984	0.8775	0.3575	0.3575	None
0.7295	3.0	1173	0.2906	0.9215	0.3006	0.3006	None
0.6386	4.0	1564	0.2438	0.928	0.2918	0.2918	None
0.6386	5.0	1955	0.2251	0.943	0.2701	0.2701	None
0.5855	6.0	2346	0.2036	0.946	0.2660	0.2660	None
0.5229	7.0	2737	0.1949	0.943	0.2706	0.2706	None
0.4837	8.0	3128	0.1817	0.944	0.2694	0.2694	None
0.4406	9.0	3519	0.1658	0.9485	0.2627	0.2627	None
0.4406	10.0	3910	0.1611	0.9455	0.2673	0.2673	None

Framework versions

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