Modelpublic

zekaemo/Indobert-Sentiment-Analysis-with-Bayes-Optimization-and-Weighted-Training

sourceHugging Facemitupdated 1y agoView on Hugging Face

0likes2downloads

Model Card

Indobert-Sentiment-Analysis-with-Bayes-Optimization-and-Weighted-Training

This model is a fine-tuned version of indobenchmark/indobert-base-p2 on an unknown dataset. It achieves the following results on the evaluation set:

—Loss: 1.8187
—Accuracy: 0.8105263157894737
—F1: 0.8086037151702786

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
—trainbatchsize: 32
—evalbatchsize: 8
—seed: 42
—optimizer: Use OptimizerNames.ADAMWTORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments
—lrschedulertype: linear
—num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6196	1.0	51	0.4970	0.7719	0.7780
0.4067	2.0	102	0.5441	0.7404	0.7495
0.2248	3.0	153	0.7342	0.7684	0.7669
0.1776	4.0	204	0.6930	0.8	0.8003
0.1137	5.0	255	1.1582	0.7789	0.7707
0.0868	6.0	306	1.1574	0.8	0.7983
0.0609	7.0	357	1.3369	0.7930	0.7871
0.0354	8.0	408	1.2317	0.8105	0.8086
0.0188	9.0	459	1.7317	0.8	0.7859
0.0127	10.0	510	1.6185	0.8035	0.8000
0.0155	11.0	561	1.7635	0.7965	0.7903
0.0106	12.0	612	1.8325	0.7965	0.7884
0.0106	13.0	663	1.8020	0.7930	0.7871
0.0101	14.0	714	1.8116	0.7930	0.7871
0.0105	15.0	765	1.8187	0.7930	0.7871

Framework versions

—Transformers 4.55.1
—Pytorch 2.6.0+cu124
—Datasets 4.0.0
—Tokenizers 0.21.4