jialicheng/unlearn_cifar10_resnet-34_neggrad_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: -1.9602
• Accuracy: 0.7433
• Dt Accuracy: 0.7433
• Df Accuracy: 0.759
• Unlearn Overall Accuracy: 0.4737
• 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: 1.25e-05
• 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	16	-0.1390	0.99	0.1981	0.1981	None
No log	2.0	32	-0.1705	0.983	0.2092	0.2092	None
No log	3.0	48	-0.2362	0.9665	0.2348	0.2348	None
No log	4.0	64	-0.4642	0.9115	0.3132	0.3132	None
No log	5.0	80	-0.9571	0.8415	0.3976	0.3976	None
No log	6.0	96	-1.3475	0.813	0.4265	0.4265	None
No log	7.0	112	-1.6644	0.7915	0.4460	0.4460	None
No log	8.0	128	-1.8791	0.7725	0.4624	0.4624	None
No log	9.0	144	-1.9393	0.763	0.4705	0.4705	None
No log	10.0	160	-1.9602	0.759	0.4737	0.4737	None

Framework versions

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