tdobrxl's picture
Create README.md
b4eb6c5
|
raw
history blame
565 Bytes

Overview

This is a fine-tuned version of the model Helsinki-NLP/opus-mt-en-vi on the dataset IWSLT'15 English-Vietnamese. Performance in terms of sacrebleu on the test set is as follows:

  • Original opus-mt-en-vi: 29.83
  • Fine-tuned opus-mt-en-vi: 37.35

Parameters

  • learning_rate=2e-5
  • batch_size: 32
  • weight_decay=0.01
  • num_train_epochs=1