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_5
results: []
22best_berita_bert_model_fold_5
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: 1.2244
- Accuracy: 0.8436
- Precision: 0.8477
- Recall: 0.8429
- F1: 0.8431
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 | 0.8179 | 0.6919 | 0.7903 | 0.6727 | 0.6450 |
| No log | 2.0 | 212 | 0.5844 | 0.7773 | 0.7841 | 0.7778 | 0.7766 |
| No log | 3.0 | 318 | 1.0969 | 0.7393 | 0.7562 | 0.7439 | 0.7378 |
| No log | 4.0 | 424 | 0.9975 | 0.8246 | 0.8247 | 0.8236 | 0.8232 |
| 0.404 | 5.0 | 530 | 1.1275 | 0.8104 | 0.8108 | 0.8067 | 0.8071 |
| 0.404 | 6.0 | 636 | 1.1943 | 0.8199 | 0.8188 | 0.8191 | 0.8189 |
| 0.404 | 7.0 | 742 | 1.2244 | 0.8436 | 0.8477 | 0.8429 | 0.8431 |
| 0.404 | 8.0 | 848 | 1.2554 | 0.8341 | 0.8370 | 0.8335 | 0.8336 |
| 0.404 | 9.0 | 954 | 1.2681 | 0.8294 | 0.8316 | 0.8288 | 0.8289 |
| 0.0067 | 10.0 | 1060 | 1.2894 | 0.8246 | 0.8264 | 0.8241 | 0.8242 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1