metadata

license: mit
base_model: indolem/indobert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - id_nergrit_corpus
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: KIPBERT
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: id_nergrit_corpus
          type: id_nergrit_corpus
          config: ner
          split: test
          args: ner
        metrics:
          - name: Precision
            type: precision
            value: 0.8057702776265651
          - name: Recall
            type: recall
            value: 0.8325084364454444
          - name: F1
            type: f1
            value: 0.8189211618257262
          - name: Accuracy
            type: accuracy
            value: 0.9503167154516874

KIPBERT

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

Loss: 0.1731
Precision: 0.8058
Recall: 0.8325
F1: 0.8189
Accuracy: 0.9503

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: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.4926	1.0	784	0.1810	0.7860	0.8172	0.8013	0.9450
0.1627	2.0	1568	0.1731	0.8058	0.8325	0.8189	0.9503

Framework versions

Transformers 4.33.2
Pytorch 2.0.1+cu118
Datasets 2.14.5
Tokenizers 0.13.3