indonesian_bert_gelu
This model is a fine-tuned version of bert-base-multilingual-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0877
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: 60
- eval_batch_size: 60
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.2396 | 1.0 | 574 | 3.9663 |
| 3.7096 | 2.0 | 1148 | 3.6484 |
| 3.503 | 3.0 | 1722 | 3.4823 |
| 3.3305 | 4.0 | 2296 | 3.3819 |
| 3.1933 | 5.0 | 2870 | 3.2650 |
| 3.1 | 6.0 | 3444 | 3.1498 |
| 2.9911 | 7.0 | 4018 | 3.1189 |
| 2.9157 | 8.0 | 4592 | 3.1153 |
| 2.8633 | 9.0 | 5166 | 3.1107 |
| 2.7958 | 10.0 | 5740 | 3.0877 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 2.19.0
- Tokenizers 0.20.3
- Downloads last month
- 39
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for pijarcandra22/indonesian_bert_gelu
Base model
google-bert/bert-base-multilingual-cased