|
--- |
|
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: best_bert_model_fold_2 |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# best_bert_model_fold_2 |
|
|
|
This model is a fine-tuned version of [ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa](https://huggingface.co/ayameRushia/bert-base-indonesian-1.5G-sentiment-analysis-smsa) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1931 |
|
- Accuracy: 0.8606 |
|
- Precision: 0.8353 |
|
- Recall: 0.8104 |
|
- F1: 0.8211 |
|
|
|
## 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 | 252 | 0.5154 | 0.8347 | 0.8228 | 0.7436 | 0.7630 | |
|
| 0.5197 | 2.0 | 504 | 0.5658 | 0.8466 | 0.8122 | 0.7892 | 0.7981 | |
|
| 0.5197 | 3.0 | 756 | 0.8319 | 0.8526 | 0.8328 | 0.7857 | 0.8007 | |
|
| 0.1558 | 4.0 | 1008 | 0.8339 | 0.8526 | 0.8230 | 0.8138 | 0.8180 | |
|
| 0.1558 | 5.0 | 1260 | 1.0511 | 0.8486 | 0.8241 | 0.7922 | 0.8052 | |
|
| 0.0472 | 6.0 | 1512 | 1.1080 | 0.8546 | 0.8313 | 0.8008 | 0.8135 | |
|
| 0.0472 | 7.0 | 1764 | 1.1492 | 0.8566 | 0.8315 | 0.8093 | 0.8189 | |
|
| 0.005 | 8.0 | 2016 | 1.1661 | 0.8566 | 0.8289 | 0.8084 | 0.8175 | |
|
| 0.005 | 9.0 | 2268 | 1.1931 | 0.8606 | 0.8353 | 0.8104 | 0.8211 | |
|
| 0.0031 | 10.0 | 2520 | 1.1820 | 0.8586 | 0.8335 | 0.8020 | 0.8149 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
