README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - wmt16
metrics:
  - bleu
model-index:
  - name: opus-mt-de-en-finetuned-de-to-en-second
    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: 37.9762

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

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

• Loss: 1.2282
• Bleu: 37.9762
• Gen Len: 25.3696

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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	157	1.1837	38.8278	25.22
No log	2.0	314	1.2057	38.3047	25.2908
No log	3.0	471	1.2167	38.231	25.316
1.4808	4.0	628	1.2256	37.9871	25.3556
1.4808	5.0	785	1.2282	37.9762	25.3696

Framework versions

• Transformers 4.12.5
• Pytorch 1.10.0+cu111
• Datasets 1.16.1
• Tokenizers 0.10.3