You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
In line 300 in __init__.py, we call the trainer function:
trainer.run(cf, private_cf) without the parameter run_id_contd, which is setto None as default.
Then in the function run(...) in trainer.py the following code is seen:
load model if specified
if run_id_contd is not None:
self.model.load(run_id_contd, epoch_contd)
print(f"Loaded model id={run_id_contd}.")
But because run_id_contd is not provided, it just does not load the model.
This should be passed in as an argument in the _init__.py file in line 300 as:
trainer.run(cf, private_cf, run_id_continue=args.run_id)
What are the steps to reproduce the bug?
as described above
Version
v0.0
Platform (OS and architecture)
linux
Relevant log output
Accompanying data
No response
Organisation
Meteoswiss
The text was updated successfully, but these errors were encountered:
kctezcan
changed the title
providing run_id to the train does not continue training
providing run_id to the train() does not continue training
Mar 17, 2025
What happened?
In line 300 in
__init__.py
, we call the trainer function:trainer.run(cf, private_cf) without the parameter run_id_contd, which is setto None as default.
Then in the function run(...) in trainer.py the following code is seen:
load model if specified
But because run_id_contd is not provided, it just does not load the model.
This should be passed in as an argument in the
_init__.py
file in line 300 as:trainer.run(cf, private_cf, run_id_continue=args.run_id)
What are the steps to reproduce the bug?
as described above
Version
v0.0
Platform (OS and architecture)
linux
Relevant log output
Accompanying data
No response
Organisation
Meteoswiss
The text was updated successfully, but these errors were encountered: