Hi there. I am trying to train the nhits and autofomer models, but I have a few questions and am seeking assistance. 1. It seems that futr_exog_list and hist_exog_list are not working properly. For instance, when I give the futr_exog_list argument in nhits, all prediction results come out as nan values. 2. While training on the GPU, if GPU memory is insufficient, is it a correct decision to increase the training iterations when adjusting batch size or windows_batch_size? 3. I am curious if having data with around 40,000 records and column counts ranging from 16 to 20 is a suitable amount for training nhits or autofomer models. Thank you for checking my lengthy question. If you have any information on this, I would appreciate it if you could share it. Have a great day.

Hi @허성민! 1. Can you try running our examples on exogenous variables: https://nixtla.github.io/neuralforecast/examples/exogenous_variables.html. There might be an issue with your data or the way you are passing the variables. 2. Yes, adding more training iterations might help to converge. Remember adding a validation set (

val_size>0

) and early stopping (

early_stop_patience_steps>0

) to prevent overfitting. 3. Yes, its more than enough! We have examples where

NHITS

produce SOTA results with a lot less records (see the Getting Started with AirPassengers for example).

I received your answer well. As you mentioned, I tried again using the sample code and was able to get the result normally. Thank you.