Hello, I Would Like To Use Spot Instances Together With The Aws Autoscaler To Train Models With Pytorch/Ignite And I Am Wondering How To Support Interruptions During The Training (In Case The Instance Is Terminated By Aws). Is There Anything Already Built

Unanswered

After you call task.set_initial_iteration(0) what do you get with task.get_initial_iteration() , is it 0 ?

  				
Posted 
	3 years ago

					More
				  		
  Report
		
					AgitatedDove14
				
					0
					 × 1

167 Views

0 Answers

3 years ago

one year ago