mobilebert-fake-news-filipino – AI Model by jcunado | AlphaNeural AI

You can deploy this model and start earning money today!

jcunado/
mobilebert-fake-news-filipino

like

0

text-classification

generated_from_trainer

google/mobilebert-uncased

autotrain_compatible

endpoints_compatible

Views

No views yet

results

This model is a fine-tuned version of google/mobilebert-uncased on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1988
F1: 0.9501
Accuracy: 0.9501

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: 2e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
optimizer: Use OptimizerNames.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	F1	Accuracy
No log	1.0	71	0.4297	0.8144	0.8170
658333.8	2.0	142	0.2422	0.8978	0.8981
1.5207	3.0	213	0.1964	0.9313	0.9314
1.5207	4.0	284	0.1708	0.9292	0.9293
0.1728	5.0	355	0.1618	0.9376	0.9376
0.1303	6.0	426	0.1645	0.9459	0.9459
0.1303	7.0	497	0.1638	0.9459	0.9459
0.0886	8.0	568	0.2003	0.9480	0.9480
0.0636	9.0	639	0.1941	0.9501	0.9501
0.0438	10.0	710	0.1988	0.9501	0.9501

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2