metadata

language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: nerui-base-2
    results: []

nerui-base-2

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: 0.0571
Location Precision: 0.8812
Location Recall: 0.9570
Location F1: 0.9175
Location Number: 93
Organization Precision: 0.9130
Organization Recall: 0.8855
Organization F1: 0.8991
Organization Number: 166
Person Precision: 0.9786
Person Recall: 0.9648
Person F1: 0.9716
Person Number: 142
Overall Precision: 0.9279
Overall Recall: 0.9302
Overall F1: 0.9290
Overall Accuracy: 0.9857

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
0.2624	1.0	96	0.0635	0.7857	0.9462	0.8585	93	0.8545	0.8494	0.8520	166	0.9858	0.9789	0.9823	142	0.8804	0.9177	0.8987	0.9802
0.054	2.0	192	0.0530	0.8318	0.9570	0.89	93	0.8580	0.9096	0.8830	166	0.9787	0.9718	0.9753	142	0.8915	0.9426	0.9164	0.9841
0.0268	3.0	288	0.0673	0.8257	0.9677	0.8911	93	0.8869	0.8976	0.8922	166	0.9857	0.9718	0.9787	142	0.9041	0.9401	0.9218	0.9833
0.0159	4.0	384	0.0546	0.9167	0.9462	0.9312	93	0.8743	0.9217	0.8974	166	0.9786	0.9648	0.9716	142	0.9197	0.9426	0.9310	0.9868
0.0108	5.0	480	0.0571	0.8812	0.9570	0.9175	93	0.9130	0.8855	0.8991	166	0.9786	0.9648	0.9716	142	0.9279	0.9302	0.9290	0.9857

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2