Modelpublic

AptaArkana/indonesian-brand-indoBERT-finetuned

sourceHugging Facemitupdated 3y agoView on Hugging Face

0likes17downloads

Model Card

indonesian-brand-indoBERT-finetuned

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

—Loss: 0.6848
—Accuracy: 0.8601
—Precision: 0.8601
—Recall: 0.8601
—F1: 0.8601

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: 1e-05
—trainbatchsize: 16
—evalbatchsize: 16
—seed: 42
—optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
—lrschedulertype: linear
—lrschedulerwarmup_ratio: 0.01
—num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
No log	1.0	304	0.4935	0.8132	0.8132	0.8132	0.8132
0.5911	2.0	608	0.4046	0.8362	0.8362	0.8362	0.8362
0.5911	3.0	912	0.4873	0.8305	0.8305	0.8305	0.8305
0.3204	4.0	1216	0.4774	0.8560	0.8560	0.8560	0.8560
0.2154	5.0	1520	0.5759	0.8486	0.8486	0.8486	0.8486
0.2154	6.0	1824	0.6334	0.8568	0.8568	0.8568	0.8568
0.1454	7.0	2128	0.6848	0.8601	0.8601	0.8601	0.8601
0.1454	8.0	2432	0.7325	0.8560	0.8560	0.8560	0.8560
0.0982	9.0	2736	0.7782	0.8568	0.8568	0.8568	0.8568
0.0729	10.0	3040	0.7979	0.8584	0.8584	0.8584	0.8584

Framework versions

—Transformers 4.38.2
—Pytorch 2.2.1+cu121
—Datasets 2.18.0
—Tokenizers 0.15.2