metadata
license: mit
base_model: indobenchmark/indobert-base-p1
tags:
- generated_from_trainer
model-index:
- name: text-classification-p1
results: []
text-classification-p1
This model is a fine-tuned version of indobenchmark/indobert-base-p1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2636
- Balanced Accuracy: 0.7994
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 |
|---|---|---|---|---|
| 0.7964 | 1.0 | 166 | 0.9239 | 0.7087 |
| 0.6617 | 2.0 | 332 | 0.8031 | 0.7454 |
| 0.3777 | 3.0 | 498 | 0.8557 | 0.7721 |
| 0.227 | 4.0 | 664 | 0.9777 | 0.7939 |
| 0.1234 | 5.0 | 830 | 1.0658 | 0.7928 |
| 0.1506 | 6.0 | 996 | 1.1731 | 0.7920 |
| 0.0913 | 7.0 | 1162 | 1.2047 | 0.7927 |
| 0.132 | 8.0 | 1328 | 1.2619 | 0.7978 |
| 0.0599 | 9.0 | 1494 | 1.2636 | 0.7994 |
| 0.0259 | 10.0 | 1660 | 1.2661 | 0.7992 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1