unlearn-so_cifar100_resnet-50_neggrad_4_42 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_resnet-50_neggrad_4_42

like

0

image-classification

generated_from_trainer

microsoft/resnet-50

Views

No views yet

42

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: -4.4300
Accuracy: 0.3471
Dt Accuracy: 0.3471
Df Accuracy: 0.348
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: 42
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	-0.5995	0.881	0.2282	0.2282	None
No log	2.0	32	-0.7574	0.814	0.3247	0.3247	None
No log	3.0	48	-1.0902	0.7205	0.4349	0.4349	None
No log	4.0	64	-1.6381	0.637	0.5060	0.5060	None
No log	5.0	80	-2.3115	0.5525	0.5532	0.5532	None
No log	6.0	96	-2.9602	0.479	0	0	None
-2.1949	7.0	112	-3.6324	0.4075	0	0	None
-2.1949	8.0	128	-4.0724	0.3765	0	0	None
-2.1949	9.0	144	-4.3513	0.3535	0	0	None
-2.1949	10.0	160	-4.4300	0.348	0	0	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.19.0
Tokenizers 0.15.2