jialicheng/unlearn_cifar10_resnet-34_bad_teaching_6_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: 5.5316
• Accuracy: 0.6966
• Dt Accuracy: 0.6966
• Df Accuracy: 0.703
• 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: 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	47	2.1024	0.8077	0.4324	0.4324	None
No log	2.0	94	3.6595	0.7637	0	0	None
No log	3.0	141	4.1023	0.745	0	0	None
No log	4.0	188	4.6068	0.7287	0	0	None
No log	5.0	235	4.5776	0.7303	0	0	None
No log	6.0	282	5.1808	0.717	0	0	None
No log	7.0	329	5.3526	0.6953	0	0	None
No log	8.0	376	5.7350	0.7077	0	0	None
No log	9.0	423	5.3134	0.7147	0	0	None
No log	10.0	470	5.5316	0.703	0	0	None

Framework versions

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