# Can trainer.predict() return multiple generations for each sample? **URL:** \ **Category:** 🤗Transformers\ **Created:** [June 1, 2021, 2:21pm UTC](https://discuss.huggingface.co/t/can-trainer-predict-return-multiple-generations-for-each-sample/6508 "2021-06-01T14:21:59Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![berkayberabi](https://avatars.discourse-cdn.com/v4/letter/b/258eb7/32.png) [@berkayberabi](https://discuss.huggingface.co/u/berkayberabi)\ **Post date:** [June 1, 2021, 2:21pm UTC](https://discuss.huggingface.co/t/can-trainer-predict-return-multiple-generations-for-each-sample/6508/1 "2021-06-01T14:21:59Z")
I am looking for a similar feature as in model.generate() which takes a parameter **num\_return\_sequences**. It decides how many generations should be returned for each sample. It is especially useful when using beam search and analyzing the effect of beam search on the metrics. Trainer.predict() does not seem to support this feature. Is there a workaround? I can use model.generate() but then it was very slow last time because I have to create a for loop iterating over batches whereas trainer.predict automatically handles the data loading separating ---
**Author:** ![silvia-casola](https://avatars.discourse-cdn.com/v4/letter/s/ee7513/32.png) [@silvia-casola](https://discuss.huggingface.co/u/silvia-casola)\ **Post date:** [November 25, 2021, 8:16am UTC](https://discuss.huggingface.co/t/can-trainer-predict-return-multiple-generations-for-each-sample/6508/2 "2021-11-25T08:16:27Z")
Hi @berkayberabi! I have a similar problem. Did you manage to solve this issue? ---
**Author:** ![berkayberabi](https://avatars.discourse-cdn.com/v4/letter/b/258eb7/32.png) [@berkayberabi](https://discuss.huggingface.co/u/berkayberabi)\ **Post date:** [January 18, 2022, 9:39pm UTC](https://discuss.huggingface.co/t/can-trainer-predict-return-multiple-generations-for-each-sample/6508/3 "2022-01-18T21:39:51Z")
Hi Silvia, No unfortunately, I could not solve it