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
Hi All, Is There Any Way To Recover The Experiment On Demo Host? I Download All The Logs But Seems It Only Contain The Console Log Not The Scaler Report. This Is A Very Long Time Training And Very Important To My Project, Hope Any One Can Help Me Find It.

Hi all, is there any way to recover the experiment on demo host? I download all the logs but seems it only contain the console log not the scaler report. This is a very long time training and very important to my project, hope any one can help me find it. 🙏

  
  
Posted 3 years ago
Votes Newest

Answers 17


image

  
  
Posted 3 years ago

Hi PompousHawk82 - there is a way to download all scalar logs, but is the demo server was already reset, the data is gone... Is your experiment still there?

  
  
Posted 3 years ago

Can you tell me how can i find out where the scalar log is?

  
  
Posted 3 years ago

There isn't any Task method that does that currently - there's a REST API call that does something similar (using the MultiTaskScalarMetricsIterHistogramRequest)

  
  
Posted 3 years ago

for example i have this experiments of 99 tasks, i’d like to pull all scaler data. How can i achieve this? Thank you!

  
  
Posted 3 years ago

for now i only have these

  
  
Posted 3 years ago

PompousHawk82 how long was this running? The demo is automatically reset every day, so your experiment couldn't have stored more than a day of metrics...

  
  
Posted 3 years ago

image

  
  
Posted 3 years ago

Also, you should really use the ClearML SDK APIClient - it's more convenient and you'll have less chance of getting it wrong 🙂

  
  
Posted 3 years ago

Thank you! another question this method seems need to get the result one by one on the fly. Because i have lots of complete experiments, is there a way that i can pull all scalars at once? Or, can i get experiments list and pull the data?

  
  
Posted 3 years ago

Thanks, i’ll give it a try

  
  
Posted 3 years ago

is there any document for this?

  
  
Posted 3 years ago

I found server API here https://allegro.ai/clearml/docs/rst/references/clearml_api_ref , but not sure how to use it, for example /debug.ping, should i post request on “ http://localhost:8080/debug/ping ” or “ http://localhost:8080/debug.ping ”?

  
  
Posted 3 years ago

Well, the is server automatically reset every day at 7 or 8 GMT, so the data was already cleared. If you can't find the experiment, it means the data was cleared

  
  
Posted 3 years ago

Can you tell me how can i find out where the scalar log is?

Well, if the experiment is not yet cleared from the server, you can get the scalars using Task.get_reported_scalars()

  
  
Posted 3 years ago
971 Views
17 Answers
3 years ago
7 months ago
Tags