unlearn-so_cifar100_resnet-50_neggrad_6_21 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_resnet-50_neggrad_6_21

like

0

image-classification

generated_from_trainer

microsoft/resnet-50

Views

No views yet

21

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: -9.3150
Accuracy: 0.1346
Dt Accuracy: 0.1346
Df Accuracy: 0.1337
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: 5e-05
train_batch_size: 128
eval_batch_size: 256
seed: 21
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	24	-0.6560	0.859	0.2613	0.2613	None
No log	2.0	48	-1.1345	0.741	0.4113	0.4113	None
No log	3.0	72	-2.3057	0.574	0.5473	0.5473	None
No log	4.0	96	-4.0565	0.426	0	0	None
-2.3782	5.0	120	-5.7368	0.318	0	0	None
-2.3782	6.0	144	-7.3533	0.2363	0	0	None
-2.3782	7.0	168	-8.4022	0.1873	0	0	None
-2.3782	8.0	192	-9.1579	0.1557	0	0	None
-8.784	9.0	216	-9.3536	0.138	0	0	None
-8.784	10.0	240	-9.3150	0.1337	0	0	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.19.0
Tokenizers 0.15.2