generated_from_trainer

<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->

t5-small-finetuned-de-to-en-swd

This model is a fine-tuned version of t5-small on the wmt16 dataset. It achieves the following results on the evaluation set:

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:

Training results

Training Loss Epoch Step Validation Loss Bleu Gen Len
No log 1.0 272 2.1658 3.8987 17.6419
2.6679 2.0 544 2.0659 6.4465 17.4758
2.6679 3.0 816 2.0210 7.3632 17.3708
2.4322 4.0 1088 1.9929 8.1559 17.3721
2.4322 5.0 1360 1.9744 8.6269 17.3518
2.3315 6.0 1632 1.9607 8.9017 17.3741
2.3315 7.0 1904 1.9515 9.1157 17.3484
2.2955 8.0 2176 1.9471 9.1308 17.3488
2.2955 9.0 2448 1.9432 9.2239 17.3414
2.2676 10.0 2720 1.9422 9.2293 17.3454

Framework versions