Update README.md
Browse files
README.md
CHANGED
|
@@ -11,14 +11,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 11 |
|
| 12 |
# bartpho-syllable-finetuned-vietnamese_corrector
|
| 13 |
|
| 14 |
-
This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable)
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
- Loss: 0.2273
|
| 17 |
- Cer: 0.0246
|
| 18 |
|
| 19 |
-
## Training
|
| 20 |
-
|
| 21 |
-
### Training hyperparameters
|
| 22 |
|
| 23 |
The following hyperparameters were used during training:
|
| 24 |
- learning_rate: 1e-04
|
|
@@ -31,11 +29,3 @@ The following hyperparameters were used during training:
|
|
| 31 |
- lr_scheduler_type: linear
|
| 32 |
- num_epochs: 2
|
| 33 |
- mixed_precision_training: Native AMP
|
| 34 |
-
|
| 35 |
-
|
| 36 |
-
### Framework versions
|
| 37 |
-
|
| 38 |
-
- Transformers 4.26.1
|
| 39 |
-
- Pytorch 1.13.0
|
| 40 |
-
- Datasets 2.1.0
|
| 41 |
-
- Tokenizers 0.13.2
|
|
|
|
| 11 |
|
| 12 |
# bartpho-syllable-finetuned-vietnamese_corrector
|
| 13 |
|
| 14 |
+
This model is a fine-tuned version of [vinai/bartpho-syllable](https://huggingface.co/vinai/bartpho-syllable) for error corrector in Vietnamese task.
|
| 15 |
It achieves the following results on the evaluation set:
|
| 16 |
- Loss: 0.2273
|
| 17 |
- Cer: 0.0246
|
| 18 |
|
| 19 |
+
## Training hyperparameters
|
|
|
|
|
|
|
| 20 |
|
| 21 |
The following hyperparameters were used during training:
|
| 22 |
- learning_rate: 1e-04
|
|
|
|
| 29 |
- lr_scheduler_type: linear
|
| 30 |
- num_epochs: 2
|
| 31 |
- mixed_precision_training: Native AMP
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|