Examples: query, "exact match", wildcard*, wild?ard, wild*rd
Fuzzy search: cake~ (finds cakes, bake)
Term boost: "red velvet"^4, chocolate^2
Field grouping: tags:(+work -"fun-stuff")
Escaping: Escape characters +-&|!(){}[]^"~*?:\ with \, e.g. \+
Range search: properties.timestamp:[1587729413488 TO *] (inclusive), properties.title:{A TO Z}(excluding A and Z)
Combinations: chocolate AND vanilla, chocolate OR vanilla, (chocolate OR vanilla) NOT "vanilla pudding"
Field search: properties.title:"The Title" AND text
Profile picture
UnevenDolphin73
Moderator
106 Questions, 749 Answers
  Active since 10 January 2023
  Last activity 9 months ago

Reputation

0

Badges 1

662 × Eureka!
0 Votes
3 Answers
1K Views
0 Votes 3 Answers 1K Views
Does ClearML have any suggestions on GPU and non-GPU AMIs for the AutoScaler? The two default ones in the documentation are either: Non-existent (too old) - ...
2 years ago
0 Votes
19 Answers
1K Views
0 Votes 19 Answers 1K Views
For remote execution where the queue has poetry as the default package manager, can the user decide to e.g. ignore the lock file?
2 years ago
0 Votes
7 Answers
1K Views
0 Votes 7 Answers 1K Views
Can we report a pandas table with styling to be retained in the WebUI? It would be nice to report e.g. df.style.background_gradient(cmap='coolwarm', axis=Non...
2 years ago
0 Votes
9 Answers
1K Views
0 Votes 9 Answers 1K Views
Hey! Probably missed something, but I recently upgraded to 1.1.1, and I've just noticed that png artifacts are not displayed in the preview. Is this intentio...
3 years ago
0 Votes
14 Answers
998 Views
0 Votes 14 Answers 998 Views
Automatic logging for generated matplotlib works nicely, but for some reason it names the graphs as "00 untitled" and uses series "plot image" in ClearML UI ...
2 years ago
0 Votes
23 Answers
1K Views
0 Votes 23 Answers 1K Views
We're using Ray and ClearML together, and suddenly we're seeing some hanging threads, and finally we got an error message: 2022-01-10 09:58:56,803 [ERROR] [C...
2 years ago
0 Votes
6 Answers
998 Views
0 Votes 6 Answers 998 Views
The comparison page seems to resize the experiments so that all tags will fit in the screen, but then the experiments are pretty much impossible to compare
2 years ago
0 Votes
30 Answers
1K Views
0 Votes 30 Answers 1K Views
Is it possible to avoid the clearml-agent for local installations, and have the file server automatically use an S3 bucket? I've found https://clearml.slack....
2 years ago
0 Votes
7 Answers
1K Views
0 Votes 7 Answers 1K Views
Is it expected that K8s helm chart also starts a ClearML worker?
2 years ago
0 Votes
3 Answers
990 Views
0 Votes 3 Answers 990 Views
Can we temporarily disable the autologging feature? (specifically for matplotlib ?)
one year ago
0 Votes
16 Answers
1K Views
0 Votes 16 Answers 1K Views
We’re running clearml-agent on k8s and I first noticed some warnings from the pod about Python 3.6..? > /usr/lib/python3/dist-packages/secretstorage/dhcrypto...
one year ago
0 Votes
0 Answers
991 Views
0 Votes 0 Answers 991 Views
I have a project filled with failed attempts at onboarding to clearml by now πŸ˜…
3 years ago
0 Votes
11 Answers
1K Views
0 Votes 11 Answers 1K Views
Back to autoscaler; is there any way to ensure the environment variables on the services queue (where the scaler runs) will be automatically exposed to new E...
2 years ago
0 Votes
23 Answers
976 Views
0 Votes 23 Answers 976 Views
Back to this ClearML Monitor: Could not detect iteration reporting, falling back to iterations as seconds-from-start 😒 Hanging for the past ~45m like this
2 years ago
0 Votes
6 Answers
946 Views
0 Votes 6 Answers 946 Views
Is there some automated migration for existing tasks from other MLOps frameworks to ClearML? (Specifically, interested in migrating from mlflow)
2 years ago
0 Votes
10 Answers
1K Views
0 Votes 10 Answers 1K Views
Is there anywhere in the web UI where one can see the clearml server version running? I keep getting "version 1.1.1 is now available" even though I'm pretty ...
3 years ago
0 Votes
12 Answers
1K Views
0 Votes 12 Answers 1K Views
When uploading an artifact, can I list it in some grouping (like with parameters, having e.g. Args/foo , Args/bar )?
2 years ago
0 Votes
4 Answers
976 Views
0 Votes 4 Answers 976 Views
Is there an easy way to apply the uncommitted changes, logged by ClearML, locally to a dev environment?
2 years ago
0 Votes
10 Answers
1K Views
0 Votes 10 Answers 1K Views
Is there any way in the WebUI to search by task name? I see the search bar only goes through projects
2 years ago
0 Votes
10 Answers
996 Views
0 Votes 10 Answers 996 Views
More clarification on documentation (ClearML Data): > Dataset changes are stored using differentiable storage, meaning a version will store the change-set fr...
2 years ago
0 Votes
8 Answers
992 Views
0 Votes 8 Answers 992 Views
Can I somehow change a project settings via the Python SDK?
one year ago
0 Votes
1 Answers
1K Views
0 Votes 1 Answers 1K Views
We're moving from on-premise to AWS - is there an easy way to migrate wall the tasks, projects, etc to the new instance?
2 years ago
0 Votes
7 Answers
1K Views
0 Votes 7 Answers 1K Views
Bug report? We noticed that the AWS autoscaler will lose track of instances crashing due to no space left on device, and the ec2 instance will remain running...
one year ago
0 Votes
30 Answers
1K Views
0 Votes 30 Answers 1K Views
For some reason the agent is now trying to use Python 2.7 all of a sudden, any idea why? πŸ€” I see the following in the task's console output: New python exec...
2 years ago
0 Votes
13 Answers
1K Views
0 Votes 13 Answers 1K Views
We use environment variables in our clearml.conf , but those might only be available later down the line (after dotenv.load_dotenv is called). When those env...
2 years ago
0 Votes
27 Answers
984 Views
0 Votes 27 Answers 984 Views
Is there an autoscaler equivalent for K8s? That is, a service that will launch pods based on incoming requests?
one year ago
0 Votes
11 Answers
1K Views
0 Votes 11 Answers 1K Views
Pipelines suddenly no longer appear in the Pipelines tab, what could/should I look into? EDIT: Using latest ClearML (agent, server, SDK), and creating the pi...
one year ago
0 Votes
5 Answers
1K Views
0 Votes 5 Answers 1K Views
We’re randomly getting the following message - 2023-03-07 11:07:26,123 [WARNING] [urllib3.connectionpool]: Retrying (Retry(total=237, connect=237, read=240, ...
one year ago
0 Votes
9 Answers
1K Views
0 Votes 9 Answers 1K Views
Is there a way to interface with ClearML agent (CLI?) to handle model repositories and data versioning (but so, not experimentation, tight integration, pipel...
3 years ago
0 Votes
6 Answers
1K Views
0 Votes 6 Answers 1K Views
Can I run an autoscaler listening to a regular queue (i.e. combine autoscaling with on premise machines)? Or does it run the danger of creating an EC2 instan...
2 years ago
Show more results questions
0 Clearml Server V1.2.0 Has Just Been Released!

Perfect now πŸ‘Œ (also nice cleanup of default_new_data_root duplicate code :D)

2 years ago
0 Does The Clearml Team Still Post Updates In This Channel When New Clearml Versions Come Out? If Not, What'S The Easiest Way To Keep Track Of Various Release Candidates Etc (Short Of Signing Up And Registering For Notifications On Pypi)

And agent too, I hope..?

I'd be happy to join a #releases channel just for these!

Just randomly decided to check and saw there's a server 1.4 ready πŸŽ‰

2 years ago
0 Hi There, I Used

The Task.init is called at a later stage of the process, so I think this relates again to the whole setup process we've been discussing both here and in #340... I promise to try ;)

2 years ago
0 What Would Be The Best Way To Approach This Flow?

And last but not least, for dictionary for example, it would be really cool if one could do:
my_config = task.connect_configuration(my_config, name=name) my_other_config = task.connect_configuration(my_other_config, name=other_name) my_other_config['bar'] = my_config # Creates the link automatically between the dictionaries

2 years ago
0 We'Re Running Into Errors Such As This:

Running a self-hosted server indeed. It's part of a code that simply adds or uploads an artifact πŸ€”

2 years ago
0 One More Follow-Up Still; We'Re Trying To Run Non-Gpu Scaler, And I'Ve Finally Sorted Out Subnet And Security Groups Issues, Only To Run Into This:

That's enabled; I was aiming if there are flags to add to pip install CLI, such as --no-use-pep517

2 years ago
0 When Uploading An Artifact, Can I List It In Some Grouping (Like With Parameters, Having E.G.

So basically I'm wondering if it's possible to add some kind of small hierarchy in the artifacts, be it sections, groupings, tabs, folders, whatever.

2 years ago
0 Can One Compare Experiments/Tasks From Different Projects? Edit: I Mean, I Can Manually Navigate To Some

I can navigate through the projects, but selecting one task in one project, then navigating to another project and selecting a different task -> there is no suggestion to compare the tasks.

In the projects page if I show all - I just see the projects. If I search for a task of similar name, I get results, but I can't compare them via the UI.

The only way I managed so far was to create a pseudo-comparison between unrelated tasks in the same project, then remove one task from comparion, and u...

2 years ago
0 What Happens To File That Are Downloaded To A Remote_Execution Via Storagemanager? Are They Removed At The End Of The Run, Or Does It Continuously Increases Disk Space?

As the meme goes, well yes but actually no, since the input path is provided via argparse? I'm also not sure how this would help debug from the WebUI - you can't really see the contents of a zipped file/the configuration tab is too messy for such a nested configuration as the one we have. It's best suited as an artifact.

EDIT: Or am I missing something? Point being, when the remote execution begins, the entry point tries to run e.g. python train.py --config_file path/to/local/file.yaml ...

2 years ago
0 I Think Something Is Messed Up In My Remote Agents Environment, Could Someone Lend A Hand? I'M Getting This During Remote Execution (Poetry Queue):

Latest (1.5.1 I believe?), full log incoming, but it's like I've posted elsewhere already πŸ€”
It just sets up the environment and immediately crashes when trying to run the code.
The setup itself is done correctly.

one year ago
0 Is There Any Testing Suite That Ships With Clearml? If We'D Like To Make Some Unit Tests For Our Code?

Another example - trying to validate dataset interactions ends with

` else:
self._created_task = True
dataset_project, parent_project = self._build_hidden_project_name(dataset_project, dataset_name)
task = Task.create(
project_name=dataset_project, task_name=dataset_name, task_type=Task.TaskTypes.data_processing)
if bool(Session.check_min_api_server_version(Dataset.__min_api_version)):
get_or_create_proje...

2 years ago
0 I Have Some Code That Launches Ml Tasks And It Accepts A Yaml File,

You mean at the container level or at clearml?

Yes, the container level (when these docker shell scripts run).
The per user ID would be nice, except I upload the .env file before the Task is created (it's only available really early in the code).

3 years ago
0 How Can I Send A Composed Chunk Of Code For Remote Execution

Interesting, why won’t it be possible? Quite easy to get the source code using e.g. dill .

10 months ago
0 How Can I Send A Composed Chunk Of Code For Remote Execution

I think also the script path in the created task will cause some issues, but let’s see…

10 months ago
one year ago
0 I Guess One Experiment Is Running Backwards In Time

I have seen this quite frequently as well tbh!

2 years ago
0 Is There An Autoscaler Equivalent For K8S? That Is, A Service That Will Launch Pods Based On Incoming Requests?

Anything else you’d recommend paying attention to when setting the clearml-agent helm chart?

one year ago
0 Is There An Autoscaler Equivalent For K8S? That Is, A Service That Will Launch Pods Based On Incoming Requests?

We’re using karpenter (more magic keywords for me), so my understanding is that that will manage the scaling part.

one year ago
0 Is There Any Testing Suite That Ships With Clearml? If We'D Like To Make Some Unit Tests For Our Code?

I'll try it out, but I would not like to rewrite that code myself maintain it, that's my point πŸ˜…

Or are you suggesting I Task.import_offline_session ?

2 years ago
0 We'Re Trying To Use The Aws Autoscaler And Have Managed To Get It Up And Running With Spinning Up Instances. However, It Does Not Seem To Pull Any Of The Tasks For The Remote Instances. We See It Gets

From our IT dept:

Not really, when you launch the instance, the launch has to already be in the right VPC/Subnet. Configuration tools are irrelevant here.

2 years ago
0 Does Clearml Have Any Suggestions On Gpu And Non-Gpu Amis For The Autoscaler? The Two Default Ones In The Documentation Are Either:

I'd like to set up both with and without GPUs. I can use any region, preferably some EU one.

2 years ago
0 Are The Docs Broken?

No, fixed πŸ™‚

2 years ago
0 We'Re Trying To Use The Aws Autoscaler And Have Managed To Get It Up And Running With Spinning Up Instances. However, It Does Not Seem To Pull Any Of The Tasks For The Remote Instances. We See It Gets

I'll see if we can do that still (as the queue name suggests, this was a POC, so I'm trying to fix things before they give up πŸ˜› ).
Any other thoughts? The original thread https://clearml.slack.com/archives/CTK20V944/p1641490355015400 suggests this PR solved the issue

2 years ago
0 Is There A Way To Generate Usage Stats And Reports For Queues? For Example, How Often Is A Queue Used, How Much Cpu Does

CostlyOstrich36 That looks promising, but I don't see any documentation on the returned schema (i.e. workers.worker_stats is not specified anywhere?)

2 years ago
Show more results compactanswers