Predictions for individual queries

[hlncrg]

It seems that the code will output metrics. I wonder if there is a way to output the actual predictions per query?

[ArvinZhuang]

Hi @hlncrg,

You can simply change trainer.train() to trainer.predict(valid_dataset) for the DSI task in run.py
and you can write the ranking list into a file in def compute_metrics(eval_preds):.