metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_trainer
model-index:
- name: text-classification
results: []
text-classification
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: 1.4783
- Balanced Accuracy: 0.5328
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 |
|---|---|---|---|---|
| 0.2974 | 1.0 | 150 | 1.4783 | 0.5328 |
| 0.2406 | 2.0 | 300 | 1.6163 | 0.5288 |
| 0.3334 | 3.0 | 450 | 1.7306 | 0.5253 |
| 0.2145 | 4.0 | 600 | 1.6787 | 0.5254 |
| 0.1358 | 5.0 | 750 | 1.9275 | 0.5482 |
| 0.081 | 6.0 | 900 | 1.8528 | 0.5372 |
| 0.2184 | 7.0 | 1050 | 1.9453 | 0.5604 |
| 0.0593 | 8.0 | 1200 | 1.9722 | 0.5558 |
| 0.0068 | 9.0 | 1350 | 2.0153 | 0.5561 |
| 0.0531 | 10.0 | 1500 | 2.0004 | 0.5429 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1