0

I have a question: a have neural net file model.py with some parameters set. I have sent it to the slurm queue. When doing squeue I can see that it is still waiting because there are other jobs running. Now, I want to send another variation of model.py but changing the params. Do you know if I change it right now, will it change the params of the first instance sent to the queue?

I mean: suppose that the first instance has param = 20. I send it to the queue. Still not running. Now, I change it to param = 50 and send the second instance to the machine. Will the first have param = 20 or param = 50 ?

Thank you in advance!

alienflow
  • 400
  • 7
  • 19
  • If the parameter is a command line parameter, there will be no interference. But take into account that when the job starts, it will run the current version of the code, whatever it is. – Poshi May 18 '20 at 11:51
  • It is not a command line, it is in code parameter. Then I guess it will be changed, right? – alienflow May 18 '20 at 12:18
  • Any change in code will be into effect when the code is started. The code used will be whatever is found when the code is loaded from disk. – Poshi May 18 '20 at 14:03
  • @BubEspinja yes, it does – alienflow May 18 '20 at 21:05

0 Answers0