CostlyOstrich36

0 Questions, 4175 Answers

Active since 10 January 2023

Last activity 2 years ago

Reputation

Answers 4175

0 Hi There, We Have A Task That We Are Trying To Execute Remotely, If We Initiate It From One Computer The Task Executed Remotely Successfully But If We Initiate It From Another Computer The Task Failed. We Have One Remote Machine At The Worker Queue So It

Hi @<1544491305910931456:profile|SoggyPuppy25> , can you please attach logs of the two runs? Are both runs executed on the same worker? What are the main environment differences between the machines that ran the experiment locally - OS/Python/ETC

2 years ago

0 Hi, I Currently Try To Set Up A Way To Do Hyperparameter Optimization On 2 Machines. My Plan Would Be To Set Up A Clearml Worker On Each Of Those 2 Machines, With A Schedule To Pull New Task At Certain Times. Since We Are Still A Small Team, Those Machin

Hi @<1826066729852211200:profile|DullSwallow71> , I would suggest looking at it from another perspective. Check machine availability and only then push a job into a queue. You can see all the related information to usage in the 'Workers' screen in the 'Orchestration' tab.

Then you can either push jobs manually according to usage or write your own service to sample usage and push jobs accordingly.

4 months ago

0 Hello, I Encountered An Issue While Deploying A Self-Hosted Clearml Server, By Following The Official Docker Compose

Browser thinks it's the same backend because of the domain

2 years ago

0 Hi, I Was Wondering If There Is A Way To Attach Files That Are Not Committed To Git To Task Run? I'M Aware To The Option Of

Hi @<1594863230964994048:profile|DangerousBee35> , I don't think there is such a mechanism currently. What would the expected/optimal behaviour would be in your use case?

4 months ago

0 Hi, Question Regarding

If you killed all processes directly, there can't be any workers on that machine. It means that these two workers are running somewhere else...

3 years ago

0 Hi, I'Ve Run Into A Problem And Would Appreciate Some Help. I Installed Clearml Locally. When I Run A New Task On A Remote Server And In The Python Training Code I Set It To Only Train On One Gpu. Everything Works Fine And I See All The Scalars Automatica

What versions of clearml-agent & clearml are you using? Is it a self hosted server?

9 months ago

0 Hi , In Clearml How Do I Configure My Agent To Launch A Job On Multiple Gpus? Sometimes I Need 2 Gpus And Sometimes 4,. Lets Say I Have 4 Gpus On My Pc. If I Configure My Agent With All 4 Gpus, And Launch A Job With 2, Would I Still Be Able To Use The Ot

Hi @<1554638166823014400:profile|ExuberantBat24> , you mean dynamic GPU allocation on the same machine?

one year ago

0 Been Looking All Over And Can'T Find The Solution To This One. If I Have A User Id Hash (The 32 Alphanumeric), How Do I Find The User'S Name Which Is Associated With This Id Using Clearml Python Sdk? Cheers.

You certainly can do it with the python APIClient OR through the requests library

2 years ago

I think it is supported only through the API 🙂

2 years ago

0 After Saving Models During Training I Cant Reuse The Same Task To Continue Training Is There Any Way To Continue Task Even Though There Are Models Saved? Alternatively Is There Any Way To Make Torch.Save Not Automatically Save The Model?

StaleButterfly40 Hi!
You could clone the original task and edit the input model of the new task as the output model of the previous task 🙂

3 years ago

0 Hello! I Faced An Issue With Environment Variables With Remote Agent I Set The In Clearml.Conf In Section:

Hi @<1706116294329241600:profile|MinuteMouse44> , you need to run in docker mode with --docker tag to be able to inject env variables

one year ago

0 Hi, I Have Another Bug To Report For Clearml-Server 1.2 (Self Hosted) In The Console Logs Of An Experiments, I Cannot See The Latest Logs. Eg My Experiment Is Done, But I Can Only See The Logs Of To The Installation Of The Packages. If I Download The Log

JitteryCoyote63 , if you go to a completed experiment you only see the packages stage installed in the log?
What OS/ClearML-Agent are you running?

3 years ago

0 Hi, I Have A Remote Task That I Want To Run On Some Of The Gpus Of The Remote Machine. I Set The Agent In The Remote Machine On Two Of The Gpus. How Do I Query The Agent What Are His Gpu So That My Code Will Use Only Them

Hi @<1546303277010784256:profile|LivelyBadger26> , when you run the agent, you can specify which CPUs to use using the --gpus argument like you used

2 years ago

0 Hi All, I Hope I'M In The Right Channel, We(

StaleButterfly40 , do the inputs/outputs have previews or are they just file links?

3 years ago

0 Hi, I Am Trying To Use Agent, But I Have A Problem. Execution Of Task Stucks Like This

btw what os are you on?

2 years ago

0 For Some Reason The Installed Packages Are Not Reflecting The One From The

I think this is what you're looking for then - None
Task.add_requirements

9 months ago

0 Hi Everyone How Can I Pass Manual Input During Git Action When The Command I Use Asking Me To Input Clearml Configuration. I'M Running 'Clearml-Init' Command On Git Action, How To Put The Configuration When It Ask For "Paste Copied Configuration Here: ",

Hi MoodyCentipede68 ,

I'm not sure how to do it in the bash way (I'm sure there's a solution on google). However for a quick fix - clearml-init basically creates a configuration file. You can simply inject the file itself into ~/clearml.conf
What do you think?

3 years ago

0 Hi, I Am Trying To Upload An Optimization Task And I Have The Following Message At The Bottom Of The App. Also When I Try To Upload The Task, It Fails With The Following Error ((Private - Removed) - Is Just Instead Of The Real Id):

AbruptWorm50 , the guys tell me that it's under progress and we will be updated in the following minutes 🙂

3 years ago

0 Hi Community! I Use The Tensorflow Object Detection Api And Trying To Get "Pretrained Checkpoint" Input Model To Store On The Server. If I Set Output_Uri=True In Task.Init, I Get The Output Models Stored On The Server As Expected But The Input Model Still

Hi 🙂

Regarding the input issue - Try defining in your ~/clearml.conf the following: sdk.development.default_output_uri to wherever you want it uploaded. I'm guessing that when you're running the original input model is created through the script and downloaded?

Regarding tagging - I think you need to connect tags individually to output models if you wanna connect it only to outputs

3 years ago

0 Hi Everyone! I Created A Pipeline From One Block, Passed The Initial Parameters. Please Tell Me, Is It Possible To Make A New Launch Of The Pipeline, But With Different Parameters, Just Like In The Draft Mode Of Usual Experiments. Globally, I Want To Init

That's strange indeed. What if you right click one of the pipeline executions and click on run?

2 years ago

0 Hey, Guys, Are Any Of Your Have An Experience Of Configuring Clearml Agent To Use A Custom Non-Aws S3 Cloud Which Uses Http Endpoint. If So, How Did You Do It? I Would Really Like To Use Clearml But I Can'T Figure Out How To Set Up It Properly. I Tried Do

Runs perfectly with Minio too 🙂

2 years ago

0 Hi, By Accident I'Ve Scheduled 1000 Experiments. I Would Like To Abort Them. In The Ui I Can Do "Load More", But It Loads 15 More. Is There Any Option To Do "Abort All"?

Hi RoundMosquito25 , yes you can. You can first filter by enqueued experiments and also in the top left you have a small checkbox. If you click it, you will have an option to select all experiments and not only the ones that are loaded

2 years ago

None

2 years ago

0 How To Create Admin User And Pass On The Clearml Chart 7.14.5? The Ui Log In Is Only Receive Full Name . How To Change It To User Pass And To Add Admin Role?

Looks like it's already there - None

3 months ago

0 Hi, After My Model'S Iterations Ended And Task Turned To Completed I Wanted To Still Train The Model Further For More Iterations. I Found There Is

Hi @<1566596960691949568:profile|UpsetWalrus59> , if I'm not mistaken, your code itself needs to support this

2 years ago

0 I'M Trying To Use The Aws Autoscaler And I'M Having Some Difficulties With The Ami Configuration. From What I Tested The Ami Should Include:

Hi @<1594863230964994048:profile|DangerousBee35> , this is pretty much it. I think the default one suggested is a good one

one year ago

0 I'M Trying To Use Store Some Data In Clearml-Data. Then I Want To Get It Back Elsewhere Using Dataset.Get_Local_Copy. It Returns A Directory But I Don'T Know How To Actually Access And Use That Data, And Remove It When It'S Done. Help Would Be Appreciated

You can delete locally but it should not affect the remote data.

The data itself is stored in the fileserver. Whatever you do locally does not affect the remote storage, only when creating a new version the changes should be stored (Like when using 'clearml-data sync').

3 years ago

VexedCat68 , in the screenshot you provided it looks like the location is being printed. Did you check to see if something is there?

3 years ago

0 How Can I Tell Clearml-Agent Not To Run Pip Install Unless My Requierments.Txt File Was Changed. It Seems To Run Pip Install Every Time I Run A Task Although Nothing Have Changed...

Hi @<1577468638728818688:profile|DelightfulArcticwolf22> , I think this is what you're looking for - CLEARML_AGENT_SKIP_PIP_VENV_INSTALL
CLEARML_AGENT_SKIP_PYTHON_ENV_INSTALL
CLEARML_AGENT_FORCE_SYSTEM_SITE_PACKAGES
None

2 years ago

0 Hi All! When I Set A List As A Task Parameter And Later Try To Retrieve It, What I Get Is A String. Is This The Expected Behavior? I Have Prepared The Following Snippet So That You Can Reproduce It.

get_parameter returns the value of a parameter as documented:
https://clear.ml/docs/latest/docs/references/sdk/task#get_parameter

Maybe try https://clear.ml/docs/latest/docs/references/sdk/task#get_parameters

3 years ago

Show more results