-
Notifications
You must be signed in to change notification settings - Fork 39
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 regression task and fix stsb to use it #505
Add regression task and fix stsb to use it #505
Conversation
Codecov ReportAll modified and coverable lines are covered by tests ✅
Additional details and impacted files@@ Coverage Diff @@
## main #505 +/- ##
=======================================
Coverage 94.13% 94.14%
=======================================
Files 194 197 +3
Lines 7803 7816 +13
=======================================
+ Hits 7345 7358 +13
Misses 458 458 ☔ View full report in Codecov by Sentry. |
add_to_catalog( | ||
OutputQuantizingTemplate( | ||
input_format=""" | ||
Given this text: '{text1}' and this text: '{text2}', on a scale of {min_value} to {max_value}, what is the {type_of_value} of this texts? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Why not keep to existing format?
Given this sentence: '{text1}', on a scale of {min_value} to {max_value}, what is the {type_of_relation} to this text {text2}
prepare/cards/stsb.py
Outdated
} | ||
), | ||
AddFields( | ||
fields={"type_of_value": "similarity", "min_value": "1", "max_value": "5"} |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
type_of_value -> type_of_relation
"templates.regression.bounded.pair.simple", | ||
] | ||
), | ||
"templates.regression.bounded.pair.all", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I think it should be more clear:
templates.regression.bounded.pair -> templates.regression.two_texts
Is there a need for an unbounded regression between text?
.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Please see separate comments.
add_to_catalog( | ||
OutputQuantizingTemplate( | ||
input_format=""" | ||
Given this text: '{text1}', on a scale of {min_value} to {max_value}, what is the {type_of_value} of this text? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
type_of_value -> attribute
[ Maybe a better name could be found? ]
c590956
to
6a90b07
Compare
Signed-off-by: Elron Bandel <elron.bandel@ibm.com>
Signed-off-by: Elron Bandel <elron.bandel@ibm.com>
6a90b07
to
d23ee23
Compare
No description provided.