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_3
results: []
22best_berita_bert_model_fold_3
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: 1.6989
- Accuracy: 0.7915
- Precision: 0.8007
- Recall: 0.8070
- F1: 0.7911
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 | 0.5874 | 0.7346 | 0.7387 | 0.7359 | 0.7275 |
| No log | 2.0 | 212 | 0.8650 | 0.7678 | 0.7865 | 0.7559 | 0.7646 |
| No log | 3.0 | 318 | 1.0826 | 0.7725 | 0.7782 | 0.7795 | 0.7730 |
| No log | 4.0 | 424 | 2.0331 | 0.6967 | 0.7339 | 0.7168 | 0.6891 |
| 0.3602 | 5.0 | 530 | 1.6682 | 0.7678 | 0.7803 | 0.7796 | 0.7682 |
| 0.3602 | 6.0 | 636 | 1.6989 | 0.7915 | 0.8007 | 0.8070 | 0.7911 |
| 0.3602 | 7.0 | 742 | 1.7597 | 0.7725 | 0.7742 | 0.7811 | 0.7709 |
| 0.3602 | 8.0 | 848 | 1.8278 | 0.7725 | 0.7742 | 0.7811 | 0.7709 |
| 0.3602 | 9.0 | 954 | 1.8531 | 0.7725 | 0.7742 | 0.7811 | 0.7709 |
| 0.0126 | 10.0 | 1060 | 1.8599 | 0.7725 | 0.7742 | 0.7811 | 0.7709 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1