unlearn-so_cifar100_resnet-50_bad_teaching_10_21 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_resnet-50_bad_teaching_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: 12.5414
Accuracy: 0.0175
Dt Accuracy: 0.0175
Df Accuracy: 0.0166
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: 0.0001
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	79	2.0064	0.5852	0	0	None
0.0	2.0	158	6.8551	0.1894	0	0	None
0.0	3.0	237	9.1406	0.0504	0	0	None
0.0	4.0	316	9.6828	0.0186	0	0	None
0.0	5.0	395	12.4165	0.0126	0	0	None
0.0	6.0	474	12.7691	0.0128	0	0	None
0.0	7.0	553	12.9277	0.0164	0	0	None
0.0	8.0	632	12.1123	0.0184	0	0	None
0.0	9.0	711	12.3159	0.0168	0	0	None
0.0	10.0	790	12.5414	0.0166	0	0	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.19.0
Tokenizers 0.15.2