You can deploy this model and start earning money today!

jcunado/
TinyBERT-tagalog-fake-news

Name: TinyBERT-tagalog-fake-news
Availability: InStock

generated_from_trainer

huawei-noah/TinyBERT_General_4L_312D

finetune

autotrain_compatible

endpoints_compatible

Views

No views yet

results

This model is a fine-tuned version of huawei-noah/TinyBERT_General_4L_312D on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.3834
F1: 0.9083
Accuracy: 0.9085

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: 50

Training results

Training Loss	Epoch	Step	Validation Loss	F1	Accuracy
No log	1.0	71	0.4559	0.8309	0.8316
0.546	2.0	142	0.4085	0.8409	0.8420
0.3931	3.0	213	0.3813	0.8534	0.8545
0.3931	4.0	284	0.3663	0.8602	0.8607
0.335	5.0	355	0.3290	0.8813	0.8815
0.2867	6.0	426	0.3259	0.8815	0.8815
0.2867	7.0	497	0.3021	0.8898	0.8898
0.2491	8.0	568	0.3021	0.9001	0.9002
0.2397	9.0	639	0.3516	0.8873	0.8877
0.1659	10.0	710	0.2847	0.9064	0.9064
0.1659	11.0	781	0.3251	0.9106	0.9106
0.1229	12.0	852	0.3607	0.9083	0.9085
0.0793	13.0	923	0.3834	0.9083	0.9085

Framework versions

Transformers 4.52.4
Pytorch 2.6.0+cu124
Datasets 4.0.0
Tokenizers 0.21.2

jcunado/TinyBERT-tagalog-fake-news

results

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

jcunado/
TinyBERT-tagalog-fake-news