Slackbot
09/07/2023, 2:07 PMJosé Morales
09/07/2023, 4:51 PMJ.
09/17/2023, 1:48 PMJosé Morales
09/18/2023, 4:32 PMJ.
09/20/2023, 10:20 AMJ.
09/20/2023, 11:27 AMJosé Morales
09/20/2023, 2:58 PMJ.
09/24/2023, 12:43 PMJosé Morales
09/25/2023, 4:33 PMCristian (Nixtla)
09/25/2023, 6:21 PMn_windows
only controls the length of the validation set. Each model with a particular configuration is trained once on the train data, and the validation loss is computed once for the entire validation set (consisting of n_windows
). A longer n_windows
only increases the length of the validation set. It does not increase the total time because the inference on the validation set is done efficiently on batches.