Downloads · 30 days
20
2% of all-time downloads
indonesian_bert_base_NER_indoNLU
AptaArkana/indonesian_bert_base_NER_indoNLU
indonesian_bert_base_NER_indoNLU is a token classification model from AptaArkana. Use it when you need labels on individual words, such as names. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
1K
Public
Parameters
110M
1.8 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors440 MB · 100%
At a glance
- Task
- Token Classification
- Library
- transformers
- License
- mit
- Model type
- bert
- Access
- Public
- Created
- Feb 13, 2024
- Updated
- Feb 19, 2024
- SHA
- 6a16f227
Try a prompt
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
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
- Task
- Token Classification
- Library
- transformers
- Type
- bert
- License
- mit
- Created
- Feb 13, 2024
- Updated
- Feb 19, 2024