Making sense of best_trial_evaluation from HPO #1348
Unanswered
MSBradshaw
asked this question in
Q&A
Replies: 1 comment 3 replies
-
Lines 342 to 345 in c94213c It corresponds to the optimization metric you have selected. If you do not explicitly select a metric, it will default to mean reciprocal rank (MRR). |
Beta Was this translation helpful? Give feedback.
3 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
I am running a hyperparameter optimization pipeline for rotatE on the Hetionet data set using NSSA loss. The best pipeline reported in
study_name/best_pipeline/pipeline_config.json
lists thebest_trial_evaluation
as 0.1697545349597931. I assume this corresponds to the specified loss function and that this is the same as thevalue
column of 'study_name/trials.tsv'. But the confusing part is thattrials.tsv
lists numerous trials that had lower and higher values than that reported asbest_trial_evaluation
, as low as 0.0018553906319438273 and as high as 0.2494133854768465.I hope I am just misunderstanding something.
Exactly what value is reported in
study_name/best_pipeline/pipeline_config.json
:best_trial_evaluation
?How is that used to choose the best pipeline?
My code for running the pipeline:
Pykeen version info:
Beta Was this translation helpful? Give feedback.
All reactions