Khmer Orthographic Correction System
This model is a fine-tuned version of facebook/mbart-large-50 on the khmer-orthography-correction-dataset dataset. It achieves the following results on the evaluation set:
- Loss: 0.1291
- Cer: 0.0408
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Cer |
|---|---|---|---|---|
| 0.2408 | 1.0 | 842 | 0.1824 | 0.0497 |
| 0.1211 | 2.0 | 1684 | 0.1434 | 0.0438 |
| 0.0756 | 3.0 | 2526 | 0.1291 | 0.0408 |
Framework versions
- Transformers 4.57.1
- Pytorch 2.9.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1