Hi @<1523701205467926528:profile|AgitatedDove14>, @<1523709867745873920:profile|KindChimpanzee37>, @<1523701070390366208:profile|CostlyOstrich36> i am replicating the code provided in below link to explore clearml servig and monitoring part. <https://gith

Answered

Hi @<1523701205467926528:profile|AgitatedDove14> , @<1523709867745873920:profile|KindChimpanzee37> , @<1523701070390366208:profile|CostlyOstrich36> i am replicating the code provided in below link to explore clearml servig and monitoring part. None ,please could you answer me below questions.
1.what this query will do:

clearml-serving --id <serving_service_id_here> metrics add --endpoint test_model_sklearn --variable-scalar
x0=0,0.1,0.5,1,10 x1=0,0.1,0.5,1,10 y=0,0.1,0.5,0.75,1

2.how can we check the data stored in db

  				
Posted 
	one year ago

					More
				  		
  Report
		
					SuperiorCockroach75
				
					0
					 × 1

Votes Newest

Answers 2

Hi @<1533257278776414208:profile|SuperiorCockroach75> , #1 will add these metrics to be logged in buckets in the DB (prometheus). Regarding #2, see here in the readme in the section titled "Grafana model performance example"

  				
Posted 
	one year ago

					More
				  		
  Report
		
					SuccessfulKoala55
				
					0
					 × 1

@<1523701087100473344:profile|SuccessfulKoala55>
1.

clearml-serving --id <serving_service_id_here> metrics add --endpoint test_model_sklearn --variable-scalar
x0=0,0.1,0.5,1,10 x1=0,0.1,0.5,1,10 y=0,0.1,0.5,0.75,1

2.100 * increase(test_model_sklearn:_latency_bucket[1m]) / increase(test_model_sklearn:_latency_sum[1m])

after running above this query i am not getting what this graph is

  				
Posted 
	one year ago

					More
				  		
  Report
		
					SuperiorCockroach75
				
					0
					 × 1

Write your answer

869 Views

2 Answers

one year ago