metadata
tags:
- generated_from_trainer
model-index:
- name: Bartpho_spelling_correction
results: []
license: apache-2.0
datasets:
- ShynBui/Vietnamese_spelling_error
language:
- vi
metrics:
- bleu
library_name: transformers
pipeline_tag: translation
Bartpho_spelling_correction
This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0025
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0122 | 0.0842 | 2000 | 0.0067 |
| 0.0084 | 0.1684 | 4000 | 0.0053 |
| 0.007 | 0.2526 | 6000 | 0.0045 |
| 0.0062 | 0.3369 | 8000 | 0.0040 |
| 0.0054 | 0.4211 | 10000 | 0.0036 |
| 0.0051 | 0.5053 | 12000 | 0.0034 |
| 0.0046 | 0.5895 | 14000 | 0.0032 |
| 0.0043 | 0.6737 | 16000 | 0.0029 |
| 0.0039 | 0.7579 | 18000 | 0.0027 |
| 0.0038 | 0.8421 | 20000 | 0.0026 |
| 0.0035 | 0.9263 | 22000 | 0.0025 |
Framework versions
- Transformers 4.42.4
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1