unlearn-so_cifar100_resnet-50_neggrad_10_42 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_resnet-50_neggrad_10_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: -24.1857
Accuracy: 0.0269
Dt Accuracy: 0.0269
Df Accuracy: 0.0266
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	40	-0.8322	0.806	0.3345	0.3345	None
No log	2.0	80	-3.0243	0.4546	0	0	None
-2.3062	3.0	120	-7.3760	0.1888	0	0	None
-2.3062	4.0	160	-12.1726	0.0948	0	0	None
-10.9549	5.0	200	-16.6740	0.0562	0	0	None
-10.9549	6.0	240	-19.7816	0.0404	0	0	None
-10.9549	7.0	280	-22.6879	0.034	0	0	None
-19.6359	8.0	320	-23.4787	0.0312	0	0	None
-19.6359	9.0	360	-25.9837	0.0272	0	0	None
-24.0534	10.0	400	-24.1857	0.0266	0	0	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.19.0
Tokenizers 0.15.2