huynguyen208's picture
update model card README.md
b6437eb
metadata
license: apache-2.0
tags:
  - translation
  - generated_from_trainer
datasets:
  - kde4
metrics:
  - bleu
model-index:
  - name: marian-finetuned-kde4-en-to-vi
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: kde4
          type: kde4
          config: en-vi
          split: train
          args: en-vi
        metrics:
          - name: Bleu
            type: bleu
            value: 51.20851369397996

marian-finetuned-kde4-en-to-vi

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-vi on the kde4 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.2134
  • Bleu: 51.2085

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: 32
  • eval_batch_size: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3
  • mixed_precision_training: Native AMP

Training results

Framework versions

  • Transformers 4.21.3
  • Pytorch 1.12.1+cu113
  • Datasets 2.4.0
  • Tokenizers 0.12.1