Normalization script in preprocessing pipeline logs the number of lines in the data set, which is then used in the subsampling step. Include all in the slurm file.
Also, only print normalized data to a limited number of decimal places, perhaps ~6 (8?) decimal places.
Normalization script in preprocessing pipeline logs the number of lines in the data set, which is then used in the subsampling step. Include all in the slurm file.
Also, only print normalized data to a limited number of decimal places, perhaps ~6 (8?) decimal places.