unlearn-so_cifar10_resnet-50_neggrad_4_87 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar10_resnet-50_neggrad_4_87

like

0

image-classification

generated_from_trainer

microsoft/resnet-50

Views

No views yet

87

This model is a fine-tuned version of microsoft/resnet-50 on the cifar10 dataset. It achieves the following results on the evaluation set:

Loss: -1.4792
Accuracy: 0.7372
Dt Accuracy: 0.7372
Df Accuracy: 0.738
Unlearn Overall Accuracy: 0.4924
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: 5e-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	-0.1164	0.979	0.2158	0.2158	None
No log	2.0	32	-0.1349	0.9695	0.2307	0.2307	None
No log	3.0	48	-0.1829	0.955	0.2526	0.2526	None
No log	4.0	64	-0.2870	0.9285	0.2907	0.2907	None
No log	5.0	80	-0.4755	0.8885	0.3433	0.3433	None
No log	6.0	96	-0.7418	0.8335	0.4075	0.4075	None
No log	7.0	112	-1.0503	0.7905	0.4501	0.4501	None
No log	8.0	128	-1.3046	0.764	0.4722	0.4722	None
No log	9.0	144	-1.4559	0.7445	0.4874	0.4874	None
No log	10.0	160	-1.4792	0.738	0.4924	0.4924	None

Framework versions

Transformers 4.37.2
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.15.2