mlcommons/algorithmic-efficiency

Add tests for expected number of evals submission and measured times

Open

#452 opened on Jul 25, 2023

View on GitHub
 (0 comments) (0 reactions) (1 assignee)Python (76 forks)auto 404
Good First Issue

Repository metrics

Stars
 (422 stars)
PR merge metrics
 (PR metrics pending)

Description

Description

Add CI test that checks if reported times and number of evals are inline with expectations.

For each submission we report:

  • total wall clock time
  • submission time
  • eval time
  • logging time
  • number of evals

We should add the following tests on at least 1 workload (probably mnist).

  1. We should check that submission_time + eval_time + logging time ~ total _wallclock_time.
  2. We should check that the number of evals is roughly equal to total_submission_time // eval_period

Contributor guide

Research direction
Inspect the existing CI test configuration and the logging code for submissions. Identify how to run a workload like MNIST in tests, then verify that the reported times satisfy the sum to total relationship and the evals count matches the expected formula.
Tech stack
python
Domain
backendtesting
Issue type
Test
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
GitPython
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
75