metadata
license: mit
base_model: indobenchmark/indobert-large-p2
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
model-index:
- name: wrete-indonlu
results: []
wrete-indonlu
This model is a fine-tuned version of indobenchmark/indobert-large-p2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2132
- Accuracy: 0.96
- Precision: 0.96
- Recall: 0.96
- F1 Score: 0.9595
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-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 Score |
|---|---|---|---|---|---|---|---|
| 0.1827 | 1.0 | 88 | 0.5099 | 0.92 | 0.92 | 0.92 | 0.9190 |
| 0.1296 | 2.0 | 176 | 0.3912 | 0.92 | 0.92 | 0.92 | 0.9190 |
| 0.0752 | 3.0 | 264 | 0.3517 | 0.94 | 0.94 | 0.94 | 0.9388 |
| 0.0706 | 4.0 | 352 | 0.3343 | 0.94 | 0.94 | 0.94 | 0.9388 |
| 0.0591 | 5.0 | 440 | 0.2691 | 0.94 | 0.94 | 0.94 | 0.9388 |
| 0.0556 | 6.0 | 528 | 0.2263 | 0.96 | 0.96 | 0.96 | 0.9595 |
| 0.0472 | 7.0 | 616 | 0.2132 | 0.96 | 0.96 | 0.96 | 0.9595 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.1.2
- Datasets 2.1.0
- Tokenizers 0.15.2