metadata
tags:
- text2text-generation
- generated_from_trainer
metrics:
- sacrebleu
model-index:
- name: nlp_vietnamese_spelling
results: []
nlp_vietnamese_spelling
This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0910
- Sacrebleu: 20.7774
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: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Sacrebleu |
|---|---|---|---|---|
| 0.2706 | 0.5402 | 1000 | 0.1371 | 19.8449 |
| 0.2219 | 1.0805 | 2000 | 0.1153 | 20.2611 |
| 0.1576 | 1.6207 | 3000 | 0.1011 | 20.5536 |
| 0.1252 | 2.1610 | 4000 | 0.0945 | 20.7503 |
| 0.1041 | 2.7012 | 5000 | 0.0910 | 20.7774 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1