metadata
license: mit
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: ModelCP
results: []
ModelCP
This model is a fine-tuned version of cahya/bert-base-indonesian-522M on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1414
- Accuracy: 0.955
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: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 288 | 0.7729 | 0.655 |
| 0.7913 | 2.0 | 576 | 0.4324 | 0.845 |
| 0.7913 | 3.0 | 864 | 0.3035 | 0.91 |
| 0.4859 | 4.0 | 1152 | 0.1832 | 0.94 |
| 0.4859 | 5.0 | 1440 | 0.1414 | 0.955 |
Framework versions
- Transformers 4.22.0
- Pytorch 1.12.1+cu113
- Datasets 2.4.0
- Tokenizers 0.12.1