Hi Everyone! Is Anybody Using Log-Scale Parameter Ranges For Hyper-Parameter Optimization? It Seems That There Is A Bug In The Hpbandster Module. I'M Getting Negative Learning Rates..

Unanswered

from clearml.automation.parameters import LogUniformParameterRange
sampler = LogUniformParameterRange(name='test', min_value=-3.0, max_value=1.0, step_size=0.5)
http://sampler.to _list()

  				
Posted 
	2 years ago

					More
				  		
  Report
		
					GreasyLeopard35
				
					0
					 × 1

167 Views

0 Answers

2 years ago

one year ago