metadata

license: mit
base_model: cahya/bert-base-indonesian-NER
tags:
  - generated_from_trainer
datasets:
  - indonlu_nergrit
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: belajarner
    results:
      - task:
          name: Token Classification
          type: token-classification
        dataset:
          name: indonlu_nergrit
          type: indonlu_nergrit
          config: indonlu_nergrit_source
          split: validation
          args: indonlu_nergrit_source
        metrics:
          - name: Precision
            type: precision
            value: 0.7716312056737589
          - name: Recall
            type: recall
            value: 0.8217522658610272
          - name: F1
            type: f1
            value: 0.7959034381858083
          - name: Accuracy
            type: accuracy
            value: 0.9477048970719857

belajarner

This model is a fine-tuned version of cahya/bert-base-indonesian-NER on the indonlu_nergrit dataset. It achieves the following results on the evaluation set:

Loss: 0.2621
Precision: 0.7716
Recall: 0.8218
F1: 0.7959
Accuracy: 0.9477

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: 8
eval_batch_size: 8
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	209	0.1633	0.7678	0.8142	0.7903	0.9476
No log	2.0	418	0.1623	0.7631	0.8127	0.7871	0.9462
0.1633	3.0	627	0.1978	0.7535	0.8172	0.7841	0.9459
0.1633	4.0	836	0.2103	0.7573	0.8202	0.7875	0.9460
0.0423	5.0	1045	0.2236	0.7757	0.8097	0.7923	0.9487
0.0423	6.0	1254	0.2529	0.7843	0.8293	0.8062	0.9474
0.0423	7.0	1463	0.2559	0.77	0.8142	0.7915	0.9467
0.0136	8.0	1672	0.2621	0.7716	0.8218	0.7959	0.9477

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu121
Datasets 2.17.0
Tokenizers 0.15.2