ClearML FAQ | Hello! I Get The Following Error In Results->Console After A Task Is Sent For Remote Execution (Using Sdk):

Answered

Hello! I Get The Following Error In Results->Console After A Task Is Sent For Remote Execution (Using Sdk):

Hello! I get the following error in Results->Console after a task is sent for remote execution (using sdk):
clearml_agent: ERROR: Could not find task id=a270d2a56feb475181ef3c9c82111b7f (for host: some_secret_host) Exception: __init__() got an unexpected keyword argument 'types'I followed this example: https://clear.ml/docs/latest/docs/guides/pipeline/pipeline_controller and the task I tried to run is "Step 1"
Any idea why I get this error?

  				
Posted 
	2 years ago

					More
				  		
  Report
		
					BurlyBat54
				
					0
					 × 1

Votes Newest

Answers 32

I think this was fixed in one of the latest versions...

  				
Posted 
	2 years ago

					More
				  		
  Report
		
					SuccessfulKoala55
				
					0
					 × 1

What's strange is that the remote jobs, as soon as they are launched, if I compare their configs while in state pending, they have the right all different configs, but later, while running,

Wait I think I found it, since usuallyu the case with hydra you configure everything from overrides / config, when launched remotely it looks at it by default. But with the launch plugin it should be overwritten with the Task
task = Task.init(...) task.set_parameter(name="Hydra/_allow_omegaconf_edit_", value="True")This should fix it 🤞 (if it does we will add it to the docs, because I'm sure it will be hard to find 😅 )

BTW:
Launch plugin is in the todo list 🙂

  				
Posted 
	2 years ago

					More
				  		
  Report
		
					AgitatedDove14
				
					0
					 × 1

Show more results

Write your answer

22K Views

32 Answers

2 years ago

7 months ago

Tags

Similar posts

How Do I Ensure That If There Is Any Error In A Task, Then The State Is Set To "Failed"? At The Moment, When I Get Errors, The Task Is Still Just Marked As "Completed", Even Though It Did Not "Terminate Successfully" But Stopped As There Was An Error?

To Be Specific, In My Base Task, The Parameters That I Want To Optimize On Appear Under Hyperparameters/General. However When I Execute The Optimization Task, I Get An Error That "Could Not Find Requested Hyper-Parameters"

Hi Everyone, I Have A Question. I Have Deployed The Clearml Server Behind A Load Balancer That Is Using My Company’S Private Certificate For Ssl. Now, When I Try To Execute A Task With The Clearml Sdk I Get Errors Such As:

How Can I Access The Commit And Uncommitted Changes Information Displayed On The Webapp On The Execution Tab Of A Task? I Don'T See Corresponding Functions In The Sdk To Get That Data.

Hello, I Have This Problem Using Clearml While Training A Yolov8 Ultralytics Model. Every Maybe 10 Trainings I Get This Error At Random That I Don'T Understand. The Task Just Stops, It'S Not Even Failed, It'S Just Stuck.

Hi Community, I Am Trying To Run A Pipeline That Has Only A Single Step Defined As A Task, But I Get A Bizarre Error When I Run

Hello, I Have Clearml Autoscaler Setup. Previously, When A New Task Comes Up, An Already Running Worker (If There Is), Will Take It, Apply The New Commit And Run The Task. Now, I Get An Error. So, I Can'T Run A Task On An Already Running Worker. It Has To

Hi, With A Given Task Id, How Do I Get All The Information Of The Tab "Info" In The Python Sdk ? I Struggle To Find That In The Doc

Hello I'M Running A Local Agent . While Its Running The Task I Get This Error. Any Suggestion? Uccessfully Installed Numpy-1.24.4 Found Pytorch Version Torch==2.0.1 Matching Cuda Version 0 Found Pytorch Version Torchaudio==2.0.2 Matching Cuda Version 0 Er

Hey, Why Is It Possible To Remove The Task From The Ui When It'S Published And Then Archived But It'S Not Possible To Remove The Archived And Published Task From The Python Sdk (It Gives Me Error - Cannot Delete Published Task)? Are There Any Other Ways T