metadata

language:
  - id
license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
model-index:
  - name: nerui-base-0
    results: []

nerui-base-0

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: 0.0540
Location Precision: 0.8544
Location Recall: 0.9362
Location F1: 0.8934
Location Number: 94
Organization Precision: 0.9119
Organization Recall: 0.8683
Organization F1: 0.8896
Organization Number: 167
Person Precision: 0.9926
Person Recall: 0.9781
Person F1: 0.9853
Person Number: 137
Overall Precision: 0.9244
Overall Recall: 0.9221
Overall F1: 0.9233
Overall Accuracy: 0.9851

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
0.2529	1.0	96	0.0478	0.9438	0.8936	0.9180	94	0.8556	0.9222	0.8876	167	0.9776	0.9562	0.9668	137	0.9156	0.9271	0.9213	0.9851
0.0617	2.0	192	0.0545	0.87	0.9255	0.8969	94	0.88	0.9222	0.9006	167	0.9571	0.9781	0.9675	137	0.9036	0.9422	0.9225	0.9815
0.0309	3.0	288	0.0539	0.8447	0.9255	0.8832	94	0.8868	0.8443	0.8650	167	0.9708	0.9708	0.9708	137	0.9048	0.9070	0.9059	0.9829
0.0178	4.0	384	0.0556	0.8878	0.9255	0.9062	94	0.8941	0.9102	0.9021	167	0.9853	0.9781	0.9817	137	0.9233	0.9372	0.9302	0.9845
0.0103	5.0	480	0.0540	0.8544	0.9362	0.8934	94	0.9119	0.8683	0.8896	167	0.9926	0.9781	0.9853	137	0.9244	0.9221	0.9233	0.9851

Framework versions

Transformers 4.39.3
Pytorch 2.3.0+cu121
Datasets 2.19.1
Tokenizers 0.15.2