datnth1709's picture
update model card README.md
dae05c5
metadata
license: apache-2.0
tags:
  - translation
  - generated_from_trainer
metrics:
  - bleu
model-index:
  - name: finetuned_HelsinkiNLP-opus-mt-vi-en_PhoMT
    results: []

finetuned_HelsinkiNLP-opus-mt-vi-en_PhoMT

This model is a fine-tuned version of Helsinki-NLP/opus-mt-vi-en on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1783
  • Bleu: 37.7741

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: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Bleu
1.3717 1.0 186125 1.2371 35.8549
1.2926 2.0 372250 1.2113 36.7328
1.2505 3.0 558375 1.1954 37.0998
1.2025 4.0 744500 1.1847 37.5538
1.1853 5.0 930625 1.1783 37.7761

Framework versions

  • Transformers 4.22.1
  • Pytorch 1.10.1+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1