metadata

language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: nerui-base-3
    results: []

nerui-base-3

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

Loss: 0.0518
Location Precision: 0.9222
Location Recall: 0.9651
Location F1: 0.9432
Location Number: 86
Organization Precision: 0.9333
Organization Recall: 0.9438
Organization F1: 0.9385
Organization Number: 178
Person Precision: 0.9843
Person Recall: 0.9766
Person F1: 0.9804
Person Number: 128
Overall Precision: 0.9471
Overall Recall: 0.9592
Overall F1: 0.9531
Overall Accuracy: 0.9889

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: 16
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Location Precision	Location Recall	Location F1	Location Number	Organization Precision	Organization Recall	Organization F1	Organization Number	Person Precision	Person Recall	Person F1	Person Number	Overall Precision	Overall Recall	Overall F1	Overall Accuracy
0.241	1.0	96	0.0559	0.8039	0.9535	0.8723	86	0.9086	0.8933	0.9008	178	0.9538	0.9688	0.9612	128	0.8968	0.9311	0.9136	0.9833
0.0545	2.0	192	0.0551	0.8454	0.9535	0.8962	86	0.9011	0.9213	0.9111	178	0.9841	0.9688	0.9764	128	0.9136	0.9439	0.9285	0.9827
0.0286	3.0	288	0.0485	0.8586	0.9884	0.9189	86	0.9480	0.9213	0.9345	178	0.9841	0.9688	0.9764	128	0.9372	0.9515	0.9443	0.9870
0.0151	4.0	384	0.0570	0.9121	0.9651	0.9379	86	0.9375	0.9270	0.9322	178	0.9766	0.9766	0.9766	128	0.9443	0.9515	0.9479	0.9873
0.0088	5.0	480	0.0518	0.9222	0.9651	0.9432	86	0.9333	0.9438	0.9385	178	0.9843	0.9766	0.9804	128	0.9471	0.9592	0.9531	0.9889

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2