README.md

metadata

license: mit
base_model: VietAI/vit5-base
tags:
  - generated_from_trainer
datasets:
  - mt_eng_vietnamese
metrics:
  - bleu
model-index:
  - name: my_translator_vi-en
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: mt_eng_vietnamese
          type: mt_eng_vietnamese
          config: iwslt2015-vi-en
          split: test[:2%]
          args: iwslt2015-vi-en
        metrics:
          - name: Bleu
            type: bleu
            value: 2.6085

my_translator_vi-en

This model is a fine-tuned version of VietAI/vit5-base on the mt_eng_vietnamese dataset. It achieves the following results on the evaluation set:

• Loss: 3.3819
• Bleu: 2.6085
• Gen Len: 18.36

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 2

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
3.9425	1.0	667	3.5155	2.3213	17.32
3.2655	2.0	1334	3.3819	2.6085	18.36

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1