metadata
license: mit
base_model: ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa
tags:
- generated_from_trainer
metrics:
- accuracy
- precision
- recall
- f1
model-index:
- name: 22best_berita_bert_model_fold_4
results: []
22best_berita_bert_model_fold_4
This model is a fine-tuned version of ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1396
- Accuracy: 0.8057
- Precision: 0.8138
- Recall: 0.7996
- F1: 0.7924
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 | 0.6557 | 0.7678 | 0.7861 | 0.7624 | 0.7495 |
| No log | 2.0 | 212 | 0.6617 | 0.7536 | 0.7876 | 0.7501 | 0.7503 |
| No log | 3.0 | 318 | 1.0532 | 0.7915 | 0.7915 | 0.7884 | 0.7810 |
| No log | 4.0 | 424 | 1.2506 | 0.7678 | 0.7711 | 0.7673 | 0.7570 |
| 0.4542 | 5.0 | 530 | 1.1396 | 0.8057 | 0.8138 | 0.7996 | 0.7924 |
| 0.4542 | 6.0 | 636 | 1.3945 | 0.7962 | 0.7889 | 0.7917 | 0.7876 |
| 0.4542 | 7.0 | 742 | 1.4381 | 0.7962 | 0.7920 | 0.7910 | 0.7852 |
| 0.4542 | 8.0 | 848 | 1.4871 | 0.7962 | 0.7899 | 0.7920 | 0.7867 |
| 0.4542 | 9.0 | 954 | 1.5004 | 0.7962 | 0.7899 | 0.7920 | 0.7867 |
| 0.0149 | 10.0 | 1060 | 1.5096 | 0.7962 | 0.7899 | 0.7920 | 0.7867 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1