Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add replication logs for MSMARCO passage, document and CovidQA. #82

Merged
merged 1 commit into from
Sep 10, 2020

Conversation

LizzyZhang-tutu
Copy link
Contributor

Colab Environment

OS: macOS Catalina Version 10.15.5 (19F101)
Java: openjdk 11.0.8 2020-07-14
Python: Python 3.6.9
GPU: Tesla T4 on Colab

Replication Results

all Identical

Time taken
MS MARCO Passage Retrieval:

monoBERT: 51:25
monoT5: 37:29

MS MARCO Document Retrieval:

monoT5
first half: 3:56:53
second half: 4:15:11

CovidQA:

Random: <1s
BM25: 9s
monoT5: 16:05

Issue encountered:
CovidQA replication doc: https://github.com/castorini/pygaggle/blob/master/docs/experiments-CovidQA.md does not have a Data Prep section as https://github.com/castorini/pygaggle/blob/daeb78c8d020112a7824dfd4d487905860372892/docs/experiments-msmarco-passage.md#data-prep, I simply ran the script sh scripts/update-index.sh to get the data.

@ronakice
Copy link
Member

Hey @LizzyZhang-tutu , thanks for replicating! We do say this in the Installation section in the main README so I wouldn't worry about it for now! Thanks again :)

@ronakice ronakice merged commit a1461f5 into castorini:master Sep 10, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants