Skip to content
GitLab
Menu
Projects
Groups
Snippets
Loading...
Help
Help
Support
Community forum
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
Menu
Open sidebar
gaoqiong
lm-evaluation-harness
Commits
93d088c8
Commit
93d088c8
authored
Nov 03, 2023
by
haileyschoelkopf
Browse files
fix gsm8k regexes
parent
b9f0d0d3
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
with
10 additions
and
11 deletions
+10
-11
lm_eval/tasks/gsm8k/gsm8k-cot.yaml
lm_eval/tasks/gsm8k/gsm8k-cot.yaml
+3
-3
lm_eval/tasks/gsm8k/gsm8k.yaml
lm_eval/tasks/gsm8k/gsm8k.yaml
+7
-8
No files found.
lm_eval/tasks/gsm8k/gsm8k-cot.yaml
View file @
93d088c8
...
@@ -20,12 +20,12 @@ metric_list:
...
@@ -20,12 +20,12 @@ metric_list:
aggregation
:
mean
aggregation
:
mean
higher_is_better
:
true
higher_is_better
:
true
ignore_case
:
true
ignore_case
:
true
ignore_whitespace
:
true
ignore_punctuation
:
false
ignore_punctuation
:
false
regexes_to_ignore
:
regexes_to_ignore
:
-
"
,"
-
"
,"
-
"
\\
$"
-
"
\\
$"
-
"
.*###
"
-
"
(?s).*####
"
-
"
\n\n
"
generation_kwargs
:
generation_kwargs
:
until
:
until
:
-
"
Q:"
-
"
Q:"
...
@@ -38,5 +38,5 @@ filter_list:
...
@@ -38,5 +38,5 @@ filter_list:
-
name
:
"
get-answer"
-
name
:
"
get-answer"
filter
:
filter
:
-
function
:
"
regex"
-
function
:
"
regex"
regex_pattern
:
"
The
answer
is
(
\\
-?[0-9
\\
.
\\
,]+)"
regex_pattern
:
"
The
answer
is
(
\\
-?[0-9
\\
.
\\
,]+)
.
"
-
function
:
"
take_first"
-
function
:
"
take_first"
lm_eval/tasks/gsm8k/gsm8k.yaml
View file @
93d088c8
...
@@ -14,12 +14,11 @@ metric_list:
...
@@ -14,12 +14,11 @@ metric_list:
aggregation
:
mean
aggregation
:
mean
higher_is_better
:
true
higher_is_better
:
true
ignore_case
:
true
ignore_case
:
true
ignore_whitespace
:
true
ignore_punctuation
:
false
ignore_punctuation
:
false
regexes_to_ignore
:
regexes_to_ignore
:
-
"
,"
-
"
,"
-
"
\\
$"
-
"
\\
$"
-
"
.*###
"
-
"
(?s)
.*###
#
"
generation_kwargs
:
generation_kwargs
:
until
:
until
:
-
"
\n\n
"
-
"
\n\n
"
...
@@ -28,9 +27,9 @@ generation_kwargs:
...
@@ -28,9 +27,9 @@ generation_kwargs:
temperature
:
0.0
temperature
:
0.0
repeats
:
1
repeats
:
1
num_fewshot
:
5
num_fewshot
:
5
#
filter_list:
filter_list
:
#
- name: "get-answer"
-
name
:
"
get-answer"
#
filter:
filter
:
#
- function: "regex"
-
function
:
"
regex"
#
regex_pattern: "### (\\-?[0-9\\.\\,]+)"
regex_pattern
:
"
###
#
(
\\
-?[0-9
\\
.
\\
,]+)"
#
- function: "take_first"
-
function
:
"
take_first"
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
.
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment