unlearn-so_cifar100_resnet-50_bad_teaching_4_42 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_resnet-50_bad_teaching_4_42

like

0

image-classification

generated_from_trainer

microsoft/resnet-50

endpoints_compatible

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: 2.3456
Accuracy: 0.5166
Dt Accuracy: 0.5166
Df Accuracy: 0.5295
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
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	32	0.6461	0.886	0.2201	0.2201	None
No log	2.0	64	0.8341	0.8415	0.2858	0.2858	None
No log	3.0	96	1.1049	0.7735	0.3734	0.3734	None
0.0	4.0	128	1.3709	0.7105	0.4411	0.4411	None
0.0	5.0	160	1.7585	0.646	0	0	None
0.0	6.0	192	1.8462	0.6195	0	0	None
0.0	7.0	224	2.0485	0.591	0	0	None
0.0	8.0	256	2.0877	0.562	0	0	None
0.0	9.0	288	2.2768	0.533	0	0	None
0.0	10.0	320	2.3456	0.5295	0	0	None

Framework versions

Transformers 4.48.0
Pytorch 2.2.2+cu118
Datasets 3.2.0
Tokenizers 0.21.0