mlcommons / mlcommons/inference

BERT-99 v5.0 startup failure, script error

Open
#2,291 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.6k
Forks
650
Avg merge
1d 22h
Merged PRs (30d)
6

Description

Hello everyone. Today I tried to run BERT-99. I tried running version 5.0 and 5.1.
I got errors in both cases. I also tried to run the benchmark on the processor and it similarly failed.
It seems that now is the moment of transition from 5.0 to 5.1, perhaps the problem is related to this? I attach the log below

bert99_v5.0_bad_run.txt

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reading the attached bert99_v5.0_bad_run.txt log and reproducing the BERT-99 startup failure with versions 5.0 and 5.1, including the processor benchmark run. Compare the failures and version-transition context; done means identifying a reproducible cause and confirming that the affected benchmark starts successfully or documenting the remaining blocker.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.