jialicheng/unlearn_cifar10_resnet-34_bad_teaching_6_42

42

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: 6.5430
• Accuracy: 0.6724
• Dt Accuracy: 0.6724
• Df Accuracy: 0.6773
• 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: 0.0001
• train_batch_size: 128
• eval_batch_size: 256
• seed: 42
• 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	47	2.3051	0.7993	0.4409	0.4409	None
No log	2.0	94	3.8510	0.756	0	0	None
No log	3.0	141	5.0493	0.719	0	0	None
No log	4.0	188	6.0963	0.704	0	0	None
No log	5.0	235	5.9587	0.6717	0	0	None
No log	6.0	282	6.0757	0.6817	0	0	None
No log	7.0	329	7.3287	0.66	0	0	None
No log	8.0	376	7.0539	0.6643	0	0	None
No log	9.0	423	6.9706	0.6703	0	0	None
No log	10.0	470	6.5430	0.6773	0	0	None

Framework versions

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