lmh2011's picture
End of training
fa010aa
|
raw
history blame
1.51 kB
metadata
license: apache-2.0
base_model: Helsinki-NLP/opus-mt-en-vi
tags:
  - opus-mt-en-vi
  - generated_from_trainer
datasets:
  - mt_eng_vietnamese
metrics:
  - bleu
model-index:
  - name: opus-mt-en-vi-finetuned-en-to-vi
    results: []

opus-mt-en-vi-finetuned-en-to-vi

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

  • Loss: 1.2726
  • Bleu: 37.3293
  • Gen Len: 28.4736

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: 1

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
1.4833 1.0 8333 1.2726 37.3293 28.4736

Framework versions

  • Transformers 4.40.1
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1