t5_small-finetuned-de-to-en

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: 5.1452
• Bleu: 5.5413
• Gen Len: 27.5002

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: 4

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.5401	1.0	3125	5.2850	4.521	28.0959
2.6412	2.0	6250	5.1799	5.2094	27.8515
2.554	3.0	9375	5.1508	5.4598	27.6353
2.5307	4.0	12500	5.1452	5.5413	27.5002

Framework versions

• Transformers 4.38.2
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2