Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Answered
Hello! I Was Wondering If There'S A Way To Have A Time Series Chart When Comparing Experiments? The Bar Chart Isn'T Ideal For Me: Context: Doing A Classification Task Where An Llm Decides The Output Class. Trying To Determine Which Prompt Performs The B

Hello!

I was wondering if there's a way to have a time series chart when comparing experiments? The bar chart isn't ideal for me:

Context: doing a classification task where an llm decides the output class. Trying to determine which prompt performs the best. The first picture is what the clearml web ui looks like. I would like to have a chart like the 2nd picture. Currently, I'm saving my metrics each experiment using logger.report_single_value for metrics like precision, recall, etc..
image
image

  
  
Posted 4 months ago
Votes Newest

Answers


Hi @<1726410010763726848:profile|DistinctToad76>
Why not just report scalars, the x-axis you can use as "iterations" if this is a running in real time to collect the prompts.
If this is a summary then just report a scatter plot (you can also specify the names of the axis and the series)
None

  
  
Posted 4 months ago
391 Views
1 Answer
4 months ago
4 months ago
Tags