metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: text-classification-indobert
results: []
text-classification-indobert
This model is a fine-tuned version of indolem/indobert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9707
- Balanced Accuracy: 0.7916
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: 16
- 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 | Balanced Accuracy |
|---|---|---|---|---|
| 1.7367 | 1.0 | 166 | 1.4765 | 0.4090 |
| 1.2086 | 2.0 | 332 | 1.0634 | 0.6459 |
| 0.8858 | 3.0 | 498 | 0.7958 | 0.7412 |
| 0.715 | 4.0 | 664 | 0.8339 | 0.7167 |
| 0.358 | 5.0 | 830 | 0.7969 | 0.7732 |
| 0.4572 | 6.0 | 996 | 0.8822 | 0.7848 |
| 0.2681 | 7.0 | 1162 | 0.8832 | 0.7730 |
| 0.1724 | 8.0 | 1328 | 0.9523 | 0.7876 |
| 0.1618 | 9.0 | 1494 | 0.9707 | 0.7916 |
| 0.2215 | 10.0 | 1660 | 0.9926 | 0.7887 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1