metadata
license: mit
base_model: indobenchmark/indobert-base-p2
tags:
- generated_from_trainer
metrics:
- accuracy
- f1
- precision
- recall
model-index:
- name: koneksi_model
results: []
koneksi_model
This model is a fine-tuned version of indobenchmark/indobert-base-p2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4885
- Accuracy: 0.8177
- F1: 0.8087
- Precision: 0.8916
- Recall: 0.74
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: 16
- eval_batch_size: 16
- 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 | F1 | Precision | Recall |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 96 | 0.4936 | 0.7760 | 0.7817 | 0.7938 | 0.77 |
| No log | 2.0 | 192 | 0.4885 | 0.8177 | 0.8087 | 0.8916 | 0.74 |
| No log | 3.0 | 288 | 0.6119 | 0.7552 | 0.7662 | 0.7624 | 0.77 |
| No log | 4.0 | 384 | 1.0256 | 0.7552 | 0.7314 | 0.8533 | 0.64 |
| No log | 5.0 | 480 | 1.2790 | 0.7604 | 0.7629 | 0.7872 | 0.74 |
| 0.2515 | 6.0 | 576 | 1.3453 | 0.7656 | 0.7716 | 0.7835 | 0.76 |
| 0.2515 | 7.0 | 672 | 1.4966 | 0.7708 | 0.7864 | 0.7642 | 0.81 |
| 0.2515 | 8.0 | 768 | 1.4197 | 0.7708 | 0.7660 | 0.8182 | 0.72 |
| 0.2515 | 9.0 | 864 | 1.5297 | 0.7760 | 0.7861 | 0.7822 | 0.79 |
| 0.2515 | 10.0 | 960 | 1.5265 | 0.7708 | 0.78 | 0.78 | 0.78 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.15.0
- Tokenizers 0.15.0