unlearn-so_cifar100_resnet-50_neggrad_10_21 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_resnet-50_neggrad_10_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: -13.3431
Accuracy: 0.0242
Dt Accuracy: 0.0242
Df Accuracy: 0.0244
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	40	-0.8543	0.797	0.3461	0.3461	None
No log	2.0	80	-2.5906	0.4974	0	0	None
-2.384	3.0	120	-5.0647	0.2598	0	0	None
-2.384	4.0	160	-8.0907	0.1174	0	0	None
-11.3405	5.0	200	-10.0492	0.0646	0	0	None
-11.3405	6.0	240	-10.5402	0.0478	0	0	None
-11.3405	7.0	280	-12.4275	0.033	0	0	None
-19.6133	8.0	320	-13.3012	0.0296	0	0	None
-19.6133	9.0	360	-13.9759	0.0248	0	0	None
-23.9642	10.0	400	-13.3431	0.0244	0	0	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.19.0
Tokenizers 0.15.2