NusaBERT-base-NERP
This model is a fine-tuned version of LazarusNLP/NusaBERT-base on the indonlu dataset. It achieves the following results on the evaluation set:
- Loss: 0.1254
- Precision: 0.8061
- Recall: 0.8406
- F1: 0.8229
- Accuracy: 0.9634
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: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
---|---|---|---|---|---|---|---|
No log | 1.0 | 420 | 0.1444 | 0.7415 | 0.8272 | 0.7820 | 0.9543 |
0.2385 | 2.0 | 840 | 0.1276 | 0.7879 | 0.8187 | 0.8030 | 0.9586 |
0.1143 | 3.0 | 1260 | 0.1260 | 0.7815 | 0.8510 | 0.8148 | 0.9597 |
0.0903 | 4.0 | 1680 | 0.1305 | 0.7836 | 0.8516 | 0.8162 | 0.9596 |
0.07 | 5.0 | 2100 | 0.1342 | 0.8158 | 0.8255 | 0.8206 | 0.9605 |
0.0582 | 6.0 | 2520 | 0.1343 | 0.8172 | 0.8408 | 0.8288 | 0.9606 |
0.0582 | 7.0 | 2940 | 0.1440 | 0.7936 | 0.8476 | 0.8197 | 0.9594 |
0.0521 | 8.0 | 3360 | 0.1447 | 0.8069 | 0.8453 | 0.8257 | 0.9605 |
0.0446 | 9.0 | 3780 | 0.1512 | 0.7996 | 0.8453 | 0.8218 | 0.9599 |
0.0417 | 10.0 | 4200 | 0.1524 | 0.8078 | 0.8453 | 0.8261 | 0.9606 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.1
- Downloads last month
- 21
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for LazarusNLP/NusaBERT-base-NERP
Base model
LazarusNLP/NusaBERT-baseDataset used to train LazarusNLP/NusaBERT-base-NERP
Space using LazarusNLP/NusaBERT-base-NERP 1
Evaluation results
- Precision on indonluvalidation set self-reported0.806
- Recall on indonluvalidation set self-reported0.841
- F1 on indonluvalidation set self-reported0.823
- Accuracy on indonluvalidation set self-reported0.963