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: 0.9868
- Balanced Accuracy: 0.5178
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: 32
- eval_batch_size: 32
- 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 |
|---|---|---|---|---|
| 1.5005 | 1.0 | 75 | 1.2434 | 0.3803 |
| 1.0016 | 2.0 | 150 | 1.1184 | 0.4835 |
| 0.9022 | 3.0 | 225 | 1.0876 | 0.4952 |
| 0.5408 | 4.0 | 300 | 0.9868 | 0.5178 |
| 0.5569 | 5.0 | 375 | 1.0562 | 0.5062 |
| 0.3193 | 6.0 | 450 | 1.1570 | 0.5065 |
| 0.2545 | 7.0 | 525 | 1.2337 | 0.5328 |
| 0.2079 | 8.0 | 600 | 1.2565 | 0.5404 |
| 0.2004 | 9.0 | 675 | 1.3088 | 0.5403 |
| 0.1072 | 10.0 | 750 | 1.3097 | 0.5498 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1