Update README.md
Browse files
README.md
CHANGED
|
@@ -29,6 +29,9 @@ There is an [mt5](https://huggingface.co/google/mt5-base) that includes Norwegia
|
|
| 29 |
## Finetuning - BLEU-SCORE 88.16 🎉
|
| 30 |
Training for [30] epochs with a learning rate of [7e-4], a batch size of [32] and a max source and target length of [512] fine tuning reached a SACREBLEU score of [87.94] at training and a test score of [**88.16**] after training.
|
| 31 |
|
|
|
|
|
|
|
|
|
|
| 32 |
## How to use the model
|
| 33 |
```python
|
| 34 |
# Set up the pipeline
|
|
|
|
| 29 |
## Finetuning - BLEU-SCORE 88.16 🎉
|
| 30 |
Training for [30] epochs with a learning rate of [7e-4], a batch size of [32] and a max source and target length of [512] fine tuning reached a SACREBLEU score of [87.94] at training and a test score of [**88.16**] after training.
|
| 31 |
|
| 32 |
+
## This is not a translator
|
| 33 |
+
We found out that we were able to get almost identical BLEU-score with training it both ways, and letting the model decide if the input is in Bokmål or Nynorsk. This way we can train one model instead of two. We call it a language switcher.
|
| 34 |
+
|
| 35 |
## How to use the model
|
| 36 |
```python
|
| 37 |
# Set up the pipeline
|