unlearn_cifar10_resnet-50_neggrad_4_87 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn_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: -0.1117
Accuracy: 0.9651
Dt Accuracy: 0.9651
Df Accuracy: 0.9835
Unlearn Overall Accuracy: 0.2086
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: 1e-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	-0.1083	0.985	0.2063	0.2063	None
No log	2.0	32	-0.1087	0.9845	0.2071	0.2071	None
No log	3.0	48	-0.1099	0.984	0.2079	0.2079	None
No log	4.0	64	-0.1109	0.985	0.2062	0.2062	None
No log	5.0	80	-0.1110	0.985	0.2062	0.2062	None
No log	6.0	96	-0.1109	0.984	0.2079	0.2079	None
No log	7.0	112	-0.1119	0.983	0.2095	0.2095	None
No log	8.0	128	-0.1123	0.9825	0.2102	0.2102	None
No log	9.0	144	-0.1119	0.9835	0.2086	0.2086	None
No log	10.0	160	-0.1117	0.9835	0.2086	0.2086	None

Framework versions

Transformers 4.37.2
Pytorch 2.3.0+cu121
Datasets 2.19.0
Tokenizers 0.15.2