--- 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: 26.4396 --- # opus-mt-en-de-finetuned-en-to-de This model is a fine-tuned version of [Helsinki-NLP/opus-mt-en-de](https://huggingface.co/Helsinki-NLP/opus-mt-en-de) on the wmt16 dataset. It achieves the following results on the evaluation set: - Loss: 1.6798 - Bleu: 26.4396 - Gen Len: 24.8156 ## 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: 0.0002 - 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 | |:-------------:|:-----:|:------:|:---------------:|:-------:|:-------:| | 2.0864 | 1.0 | 568611 | 1.6798 | 26.4396 | 24.8156 | ### Framework versions - Transformers 4.12.5 - Pytorch 1.9.0.dev20210415+cu101 - Datasets 1.16.1 - Tokenizers 0.10.3