indobert-fiqhqa-qa-tuned
This model is a fine-tuned version of indobenchmark/indobert-base-p1 on the FiqhQA dataset. It achieves the following results on the evaluation set:
- Loss: 1.8045
- Exact Match: 7.9137
- F1: 32.4187
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: 1e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Exact Match | F1 |
|---|---|---|---|---|---|
| 1.9981 | 1.0 | 228 | 1.8396 | 5.7554 | 29.8856 |
| 1.7602 | 2.0 | 456 | 1.7735 | 8.6331 | 33.8904 |
| 1.6801 | 3.0 | 684 | 1.8045 | 7.9137 | 32.4187 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.1+cu128
- Datasets 4.4.1
- Tokenizers 0.22.1
- Downloads last month
- 91
Model tree for mhdafifan/indobert-fiqhqa-qa-tuned
Base model
indobenchmark/indobert-base-p1