jialicheng/unlearn-so_cifar100_resnet-50_bad_teaching_8_100

100

This model is a fine-tuned version of microsoft/resnet-50 on the cifar100 dataset. It achieves the following results on the evaluation set:

• Loss: 12.0802
• Accuracy: 0.0094
• Dt Accuracy: 0.0094
• Df Accuracy: 0.0112
• 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: 100
• 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	63	1.6527	0.6637	0	0	None
0.0	2.0	126	3.9261	0.3523	0	0	None
0.0	3.0	189	7.2149	0.1325	0	0	None
0.0	4.0	252	9.9746	0.0473	0	0	None
0.0	5.0	315	10.5151	0.0192	0	0	None
0.0	6.0	378	11.5446	0.015	0	0	None
0.0	7.0	441	13.8045	0.013	0	0	None
0.0	8.0	504	13.4218	0.0107	0	0	None
0.0	9.0	567	12.2747	0.0103	0	0	None
0.0	10.0	630	12.0802	0.0112	0	0	None

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.2+cu118
• Datasets 2.19.0
• Tokenizers 0.15.2