|
--- |
|
license: mit |
|
base_model: ayameRushia/roberta-base-indonesian-sentiment-analysis-smsa |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
- f1 |
|
model-index: |
|
- name: best_roberta_model_fold_3 |
|
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_roberta_model_fold_3 |
|
|
|
This model is a fine-tuned version of [ayameRushia/roberta-base-indonesian-sentiment-analysis-smsa](https://huggingface.co/ayameRushia/roberta-base-indonesian-sentiment-analysis-smsa) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.6566 |
|
- Accuracy: 0.8566 |
|
- Precision: 0.8385 |
|
- Recall: 0.8215 |
|
- F1: 0.8286 |
|
|
|
## 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 | 0.6056 | 0.8307 | 0.8493 | 0.7768 | 0.7998 | |
|
| 0.4224 | 2.0 | 504 | 0.6566 | 0.8566 | 0.8385 | 0.8215 | 0.8286 | |
|
| 0.4224 | 3.0 | 756 | 0.8546 | 0.8506 | 0.8410 | 0.8094 | 0.8211 | |
|
| 0.1153 | 4.0 | 1008 | 0.9318 | 0.8446 | 0.8220 | 0.8093 | 0.8146 | |
|
| 0.1153 | 5.0 | 1260 | 1.0414 | 0.8367 | 0.8297 | 0.7856 | 0.7984 | |
|
| 0.0403 | 6.0 | 1512 | 1.1900 | 0.8327 | 0.8118 | 0.7848 | 0.7945 | |
|
| 0.0403 | 7.0 | 1764 | 1.1295 | 0.8406 | 0.8143 | 0.8041 | 0.8086 | |
|
| 0.0107 | 8.0 | 2016 | 1.2422 | 0.8327 | 0.8164 | 0.7927 | 0.8004 | |
|
| 0.0107 | 9.0 | 2268 | 1.1965 | 0.8386 | 0.8170 | 0.8013 | 0.8079 | |
|
| 0.0003 | 10.0 | 2520 | 1.2360 | 0.8426 | 0.8212 | 0.8025 | 0.8103 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.19.2 |
|
- Tokenizers 0.19.1 |
|
|
