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: 39.0666

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: 1.1615
• Bleu: 39.0666
• Gen Len: 25.2812

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	157	1.1450	39.429	25.2412
No log	2.0	314	1.1531	39.1045	25.2136
No log	3.0	471	1.1560	39.1684	25.2308
1.954	4.0	628	1.1604	39.1528	25.2544
1.954	5.0	785	1.1615	39.0666	25.2812

Framework versions

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