unlearn-so_cifar100_resnet-50_neggrad_10_87 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_resnet-50_neggrad_10_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 cifar100 dataset. It achieves the following results on the evaluation set:

Loss: -21.0658
Accuracy: 0.027
Dt Accuracy: 0.027
Df Accuracy: 0.0288
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: 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	40	-1.2421	0.744	0.4074	0.4074	None
No log	2.0	80	-4.2104	0.4494	0	0	None
-3.0776	3.0	120	-7.8109	0.2374	0	0	None
-3.0776	4.0	160	-10.7112	0.1116	0	0	None
-12.3046	5.0	200	-13.5279	0.0668	0	0	None
-12.3046	6.0	240	-16.0423	0.0472	0	0	None
-12.3046	7.0	280	-17.3981	0.039	0	0	None
-20.2207	8.0	320	-20.0833	0.0344	0	0	None
-20.2207	9.0	360	-20.2581	0.0292	0	0	None
-24.2884	10.0	400	-21.0658	0.0288	0	0	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.19.0
Tokenizers 0.15.2