unlearn-so_cifar100_resnet-50_neggrad_8_13 – AI Model by jialicheng | AlphaNeural AI

You can deploy this model and start earning money today!

jialicheng/
unlearn-so_cifar100_resnet-50_neggrad_8_13

like

0

image-classification

generated_from_trainer

microsoft/resnet-50

Views

No views yet

13

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: -16.2026
Accuracy: 0.0369
Dt Accuracy: 0.0369
Df Accuracy: 0.0375
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: 13
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	32	-1.0148	0.7738	0.3746	0.3746	None
No log	2.0	64	-2.8363	0.5533	0.5544	0.5544	None
No log	3.0	96	-5.8124	0.336	0	0	None
-3.2849	4.0	128	-8.7228	0.1998	0	0	None
-3.2849	5.0	160	-11.1928	0.1115	0	0	None
-3.2849	6.0	192	-13.3497	0.0683	0	0	None
-12.0353	7.0	224	-14.4803	0.0505	0	0	None
-12.0353	8.0	256	-15.5303	0.044	0	0	None
-12.0353	9.0	288	-16.1535	0.0395	0	0	None
-17.656	10.0	320	-16.2026	0.0375	0	0	None

Framework versions

Transformers 4.39.3
Pytorch 2.2.2+cu118
Datasets 2.19.0
Tokenizers 0.15.2