indonesian_bert_gelu_new
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: 2.9961
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 |
|---|---|---|---|
| 4.2587 | 1.0 | 574 | 3.9221 |
| 3.747 | 2.0 | 1148 | 3.6187 |
| 3.428 | 3.0 | 1722 | 3.4702 |
| 3.2973 | 4.0 | 2296 | 3.3101 |
| 3.1319 | 5.0 | 2870 | 3.3198 |
| 3.0804 | 6.0 | 3444 | 3.0687 |
| 2.9809 | 7.0 | 4018 | 3.1006 |
| 2.9337 | 8.0 | 4592 | 3.0906 |
| 2.8881 | 9.0 | 5166 | 3.0720 |
| 2.8466 | 10.0 | 5740 | 2.9961 |
Framework versions
- Transformers 4.45.2
- Pytorch 2.5.1+cu124
- Datasets 2.19.0
- Tokenizers 0.20.3
- Downloads last month
- 11
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for pijarcandra22/indonesian_bert_gelu_new
Base model
google-bert/bert-base-multilingual-cased