Interrupt dynamics when forces explode
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- Half a day
- Newbie friendliness
- 45/100
- Issue type
- Feature
- Clarity
- Mostly clear
- Activity status
- Quiet
- Tech stack
- python
- Domain
- machine-learning
Research direction
Read the linked comment in issue #669 for context, then find the dynamics classes that advance a simulation and expose forces. Decide where an interrupt callback can be attached, likely in a shared dynamics utility, and test with a model that produces exploding forces above 10e6. Done when dynamics can abort on runaway forces, with a focused test or example documenting the threshold.
Written by the indexing model from the issue text.
Description
should we bump this up to maybe 2K steps? e.g. mace-mp-0a finishes in ~800 for me so could be a little tight on some models finishing under the threshold?
The downside to this is for models that explode, they'll end up doing 2000 potentially very slow steps... I think merge this, but can I suggest we look at a (general utility) function we attach to dynamics that interrupts if forces become say 10e6?
Originally posted by @ElliottKasoar in https://github.com/ddmms/ml-peg/issues/669#issuecomment-5132182541
- Dominant language
- Python
- Stars
- 69
- Forks
- 68
- Avg merge
- 3d 8h
- Merged PRs (30d)
- 22
Getting set up
- No Dockerfile or Docker Compose file
- Has a pull request template
- Read the contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from ddmms/ml-peg
-
Sort modelsOpenenhancement good first issue
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
Maintainers usually reply within 1 day
-
PytestUnknownMarkWarning for speed markers when analysis tests import calc modulesPossibly taken @adityaanikam claimed this today. Openbug
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
ddmms/ml-peg#922 · 2 comments ·
Maintainers usually reply within 1 day
-
enhancement
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
Maintainers usually reply within 1 day
-
enhancement
Difficulty 2/5 1-3 hours Newbie friendliness 62/100
Maintainers usually reply within 1 day
-
new benchmark
Difficulty 4/5 3-5 days Newbie friendliness 35/100
Maintainers usually reply within 1 day
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
huggingface/sentence-transformers#4186 ·
Maintainers usually reply within 5 days
-
documentation
Difficulty 1/5 Under an hour Newbie friendliness 92/100
QuantEcon/QuantEcon.py#988 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
fabriziosalmi/certmate#1247 ·
Maintainers usually reply within 1 day
-
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
Maintainers usually reply within 1 day
-
documentation good first issue
Difficulty 2/5 Half a day Newbie friendliness 72/100
sujithputta02/Esapay#13 ·