metadata
license: apache-2.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: polibert-malaysia
results: []
polibert-malaysia
This model is a fine-tuned version of bert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.9318
- Accuracy: 0.8904
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: 8
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 8
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.6482 | 1.0 | 3887 | 0.5960 | 0.8302 |
| 0.4607 | 2.0 | 7774 | 0.5355 | 0.8657 |
| 0.3267 | 3.0 | 11661 | 0.6395 | 0.8820 |
| 0.1983 | 4.0 | 15548 | 0.7489 | 0.8742 |
| 0.1107 | 5.0 | 19435 | 0.7793 | 0.8815 |
| 0.0742 | 6.0 | 23322 | 0.8591 | 0.8864 |
| 0.045 | 7.0 | 27209 | 0.8850 | 0.8903 |
| 0.0201 | 8.0 | 31096 | 0.9318 | 0.8904 |
Framework versions
- Transformers 4.18.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.12.1