jialicheng/unlearn_cifar10_resnet-34_bad_teaching_4_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: 4.6750
• Accuracy: 0.7248
• Dt Accuracy: 0.7248
• Df Accuracy: 0.734
• 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	32	1.9091	0.828	0.4119	0.4119	None
No log	2.0	64	2.9815	0.7885	0.4501	0.4501	None
No log	3.0	96	3.7770	0.7515	0	0	None
No log	4.0	128	3.7162	0.754	0	0	None
No log	5.0	160	4.3877	0.7395	0	0	None
No log	6.0	192	4.8596	0.738	0	0	None
No log	7.0	224	4.0900	0.727	0	0	None
No log	8.0	256	4.9009	0.729	0	0	None
No log	9.0	288	4.8932	0.724	0	0	None
No log	10.0	320	4.6750	0.734	0	0	None

Framework versions

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