We have started to fine-tune the ProphetNet model on a custom dataset. We are using fairseq==v0.9.0 version. Currently, only perplexity is supported while training, however, we would like also to validate the trained model on BLEU-4, METEOR, and ROUGE metrics.
Can anyone provide any insights on this?
Because the "--scoring" parameter in fairseq v0.9 is not supported.
We have started to fine-tune the ProphetNet model on a custom dataset. We are using fairseq==v0.9.0 version. Currently, only perplexity is supported while training, however, we would like also to validate the trained model on BLEU-4, METEOR, and ROUGE metrics. Can anyone provide any insights on this? Because the "--scoring" parameter in fairseq v0.9 is not supported.