wandgibaut's picture
Upload README.md
5504bff
metadata
license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - wmt16
metrics:
  - bleu
model-index:
  - name: opus-mt-en-de-finetuned-en-to-de
    results:
      - task:
          name: Sequence-to-sequence Language Modeling
          type: text2text-generation
        dataset:
          name: wmt16
          type: wmt16
          args: de-en
        metrics:
          - name: Bleu
            type: bleu
            value: 29.4312

opus-mt-en-de-finetuned-en-to-de

This model is a fine-tuned version of Helsinki-NLP/opus-mt-en-de on the wmt16 dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4083
  • Bleu: 29.4312
  • Gen Len: 24.746

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 Bleu Gen Len
1.978 1.0 568611 1.4083 29.4312 24.746

Framework versions

  • Transformers 4.12.5
  • Pytorch 1.10.0+cu102
  • Datasets 1.16.1
  • Tokenizers 0.10.3