File tree Expand file tree Collapse file tree 2 files changed +3
-3
lines changed
Expand file tree Collapse file tree 2 files changed +3
-3
lines changed Original file line number Diff line number Diff line change @@ -45,7 +45,7 @@ vec-inf metrics 13014393
4545
4646And you will see the performance metrics streamed to your console, note that the metrics are updated with a 10-second interval.
4747
48- <img width =" 400 " alt =" metrics_img " src =" https://github.com/user-attachments/assets/6732215b-96f3-407c-ba45-6334b2061706 " >
48+ <img width =" 400 " alt =" metrics_img " src =" https://github.com/user-attachments/assets/e5ff2cd5-659b-4c88-8ebc-d8f3fdc023a4 " >
4949
5050Finally, when you're finished using a model, you can shut it down by providing the Slurm job ID:
5151``` bash
Original file line number Diff line number Diff line change @@ -326,18 +326,18 @@ def metrics(slurm_job_id: int, log_dir: Optional[str] = None) -> None:
326326 status_cmd = f"scontrol show job { slurm_job_id } --oneliner"
327327 output = utils .run_bash_command (status_cmd )
328328 slurm_job_name = output .split (" " )[1 ].split ("=" )[1 ]
329- out_logs = utils .read_slurm_log (slurm_job_name , slurm_job_id , "out" , log_dir )
330329
331330 with Live (refresh_per_second = 1 , console = CONSOLE ) as live :
332331 while True :
332+ out_logs = utils .read_slurm_log (slurm_job_name , slurm_job_id , "out" , log_dir )
333333 metrics = utils .get_latest_metric (out_logs )
334334 table = utils .create_table (key_title = "Metric" , value_title = "Value" )
335335 for key , value in metrics .items ():
336336 table .add_row (key , value )
337337
338338 live .update (table )
339339
340- time .sleep (10 )
340+ time .sleep (2 )
341341
342342
343343if __name__ == "__main__" :
You can’t perform that action at this time.
0 commit comments