unlearn-so_cifar100_resnet-50_neggrad_2_13 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_resnet-50_neggrad_2_13

like

0

image-classification

generated_from_trainer

microsoft/resnet-50

Views

No views yet

13

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: -1.1204
Accuracy: 0.7187
Dt Accuracy: 0.7187
Df Accuracy: 0.717
Unlearn Overall Accuracy: 0.4404
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: 13
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	8	-0.5752	0.899	0.1998	0.1998	None
No log	2.0	16	-0.6269	0.873	0.2405	0.2405	None
No log	3.0	24	-0.6891	0.845	0.2819	0.2819	None
No log	4.0	32	-0.7563	0.812	0.3277	0.3277	None
No log	5.0	40	-0.8430	0.793	0.3523	0.3523	None
No log	6.0	48	-0.9340	0.767	0.3845	0.3845	None
No log	7.0	56	-1.0134	0.751	0.4026	0.4026	None
No log	8.0	64	-1.0743	0.732	0.4241	0.4241	None
No log	9.0	72	-1.1091	0.719	0.4385	0.4385	None
No log	10.0	80	-1.1204	0.717	0.4404	0.4404	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.19.0
Tokenizers 0.15.2