Manuel
07/24/2023, 10:45 AMCristian (Nixtla)
07/24/2023, 3:25 PMbatch_size
series, and then windows_batch_size
windows from those time series. If batch_size*max_steps>n_series
, then the model would have observed windows from all time series.
⢠We believe that (for general purposes) it is more flexible to train based on steps. It is much easier to define defaults and control the training times based on steps. Training by epochs is completely determined by the number of time series, so a fixed number (eg. 10) can be too little or too much, producing sub-par performance (excessive training time, overfitting, etc) in many cases.Manuel
07/24/2023, 3:39 PMsteps_in_epoch = np.ceil(Y_train_df["unique_id"].nunique() / batch_size)
Cristian (Nixtla)
07/24/2023, 7:53 PMManuel
07/24/2023, 8:16 PMCristian (Nixtla)
07/24/2023, 9:36 PMStefan Otte
08/01/2023, 6:30 AM