The problem occurs in main.py line 89 where I try to generate texts based on a NeruIPS dataset. This line calls the sample function that generates subsequent sentences based on the start_text. However the texts generated on macOS, Windows, and Linux are very different even though the seed is fixed in the config.yml.
Repo of the project where the bug is spotted:
https://github.com/l1xiangyi/GPT2/tree/main
What is the problem
The problem occurs in main.py line 89 where I try to generate texts based on a NeruIPS dataset. This line calls the sample function that generates subsequent sentences based on the
start_text
. However the texts generated on macOS, Windows, and Linux are very different even though the seed is fixed in theconfig.yml
.sumbit/samples.txt
sumbit/sample_windows.txt
sumbit/sample_linux.txt
Strange words like "Zombie" pop up a lot in the Windows and Linux generated texts.
How to reproduce this problem
Linux
The simplest way is go create a new Colab notebook and run the following commands:
Then check the
samples.txt
in thesubmit
folder.Windows
Similar steps to the Linux version. Just drop the special sign before each commands: