README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - mt_eng_vietnamese
metrics:
  - rouge
  - bleu
model-index:
  - name: bart-base-translate-en-vi
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: mt_eng_vietnamese
          type: mt_eng_vietnamese
          config: iwslt2015-en-vi
          split: validation
          args: iwslt2015-en-vi
        metrics:
          - name: Rouge1
            type: rouge
            value: 8.5193
          - name: Bleu
            type: bleu
            value: 0

bart-base-translate-en-vi

This model is a fine-tuned version of facebook/bart-base on the mt_eng_vietnamese dataset. It achieves the following results on the evaluation set:

• Loss: 0.0211
• Rouge1: 8.5193
• Rouge2: 1.09
• Rougel: 7.7119
• Rougelsum: 7.7159
• Bleu: 0.0
• Gen Len: 20.0

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 1
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu	Gen Len
0.0223	1.0	16665	0.0211	8.5193	1.09	7.7119	7.7159	0.0	20.0

Framework versions

• Transformers 4.26.1
• Pytorch 2.1.0+cu118
• Datasets 2.10.1
• Tokenizers 0.13.3