metadata
license: mit
base_model: cahya/distilbert-base-indonesian
tags:
- generated_from_trainer
model-index:
- name: distilbert-base-indonesian-finetuned-PRDECT-ID
results: []
widget:
- text: Ibu sedang memasak [MASK].
example_title: Contoh
distilbert-base-indonesian-finetuned-PRDECT-ID
This model is a fine-tuned version of cahya/distilbert-base-indonesian on an unknown dataset. Perplexity: ~31
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: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9507 | 1.0 | 41 | 0.8377 |
| 0.0765 | 2.0 | 82 | 0.0212 |
| 0.0025 | 3.0 | 123 | 0.0020 |
| 0.0013 | 4.0 | 164 | 0.0013 |
| 0.0009 | 5.0 | 205 | 0.0009 |
| 0.0007 | 6.0 | 246 | 0.0007 |
| 0.0005 | 7.0 | 287 | 0.0006 |
| 0.0004 | 8.0 | 328 | 0.0005 |
| 0.0003 | 9.0 | 369 | 0.0004 |
| 0.0002 | 10.0 | 410 | 0.0003 |
| 0.0002 | 11.0 | 451 | 0.0003 |
| 0.0002 | 12.0 | 492 | 0.0003 |
| 0.0002 | 13.0 | 533 | 0.0002 |
| 0.0001 | 14.0 | 574 | 0.0002 |
| 0.0001 | 15.0 | 615 | 0.0002 |
| 0.0001 | 16.0 | 656 | 0.0002 |
| 0.0001 | 17.0 | 697 | 0.0002 |
| 0.0001 | 18.0 | 738 | 0.0002 |
| 0.0001 | 19.0 | 779 | 0.0002 |
| 0.0001 | 20.0 | 820 | 0.0002 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2
- Datasets 2.19.2
- Tokenizers 0.19.1