metadata
license: mit
base_model: ayameRushia/roberta-base-indonesian-sentiment-analysis-smsa
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: 22best_berita_roberta_model_fold_1
results: []
22best_berita_roberta_model_fold_1
This model is a fine-tuned version of ayameRushia/roberta-base-indonesian-sentiment-analysis-smsa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.8575
- Accuracy: 0.8868
- Precision: 0.8904
- Recall: 0.8843
- F1: 0.8870
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: 8
- eval_batch_size: 8
- 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 | Accuracy | Precision | Recall | F1 |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 106 | 0.9177 | 0.5472 | 0.7029 | 0.6055 | 0.5274 |
| No log | 2.0 | 212 | 0.8990 | 0.7264 | 0.7612 | 0.7252 | 0.7101 |
| No log | 3.0 | 318 | 0.7968 | 0.8491 | 0.8478 | 0.8622 | 0.8496 |
| No log | 4.0 | 424 | 0.8026 | 0.8396 | 0.8400 | 0.8413 | 0.8353 |
| 0.5042 | 5.0 | 530 | 1.0039 | 0.8443 | 0.8579 | 0.8603 | 0.8488 |
| 0.5042 | 6.0 | 636 | 0.8274 | 0.8774 | 0.8743 | 0.8850 | 0.8780 |
| 0.5042 | 7.0 | 742 | 0.8575 | 0.8868 | 0.8904 | 0.8843 | 0.8870 |
| 0.5042 | 8.0 | 848 | 0.9014 | 0.8821 | 0.8806 | 0.8906 | 0.8830 |
| 0.5042 | 9.0 | 954 | 0.9622 | 0.8726 | 0.8723 | 0.8859 | 0.8741 |
| 0.0373 | 10.0 | 1060 | 0.9673 | 0.8726 | 0.8723 | 0.8859 | 0.8741 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1