metadata
license: mit
base_model: cahya/bert-base-indonesian-1.5G
tags:
- generated_from_trainer
metrics:
- precision
- recall
- f1
- accuracy
model-index:
- name: belajarner_bert_case
results: []
belajarner_bert_case
This model is a fine-tuned version of cahya/bert-base-indonesian-1.5G on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.3302
- Precision: 0.8314
- Recall: 0.8484
- F1: 0.8398
- Accuracy: 0.9471
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: 2e-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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.1904 | 1.0 | 1567 | 0.2090 | 0.7825 | 0.8298 | 0.8054 | 0.9385 |
| 0.1195 | 2.0 | 3134 | 0.2141 | 0.8312 | 0.8237 | 0.8274 | 0.9446 |
| 0.0772 | 3.0 | 4701 | 0.2200 | 0.8220 | 0.8427 | 0.8322 | 0.9457 |
| 0.0463 | 4.0 | 6268 | 0.2636 | 0.8158 | 0.8498 | 0.8324 | 0.9446 |
| 0.0342 | 5.0 | 7835 | 0.2878 | 0.8351 | 0.8392 | 0.8372 | 0.9456 |
| 0.0223 | 6.0 | 9402 | 0.3066 | 0.8267 | 0.8414 | 0.8340 | 0.9454 |
| 0.0139 | 7.0 | 10969 | 0.3250 | 0.8302 | 0.8476 | 0.8388 | 0.9466 |
| 0.0096 | 8.0 | 12536 | 0.3302 | 0.8314 | 0.8484 | 0.8398 | 0.9471 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2