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
076372ee
Unverified
Commit
076372ee
authored
Jan 23, 2024
by
Lintang Sutawika
Committed by
GitHub
Jan 22, 2024
Browse files
Fix Issue regarding stderr (#1327)
* add fix fordeciding if stderr is N/A or not * process N/A
parent
181ccf43
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
20 additions
and
12 deletions
+20
-12
lm_eval/evaluator.py
lm_eval/evaluator.py
+20
-12
No files found.
lm_eval/evaluator.py
View file @
076372ee
...
...
@@ -492,10 +492,13 @@ def evaluate(
]:
stderr
=
"_stderr,"
.
join
(
metric
.
split
(
","
))
stderr_score
=
results
[
task
][
stderr
]
var_score
=
stderr_score
**
2
metric_score
=
results
[
task
][
metric
]
if
stderr_score
==
"N/A"
:
var_score
=
"N/A"
else
:
var_score
=
stderr_score
**
2
all_stderr
.
append
(
stderr
)
all_stderr
.
append
(
stderr
)
metric_score
=
results
[
task
][
metric
]
if
metric
in
results
[
group
]:
results
[
group
][
metric
]
=
(
...
...
@@ -503,15 +506,20 @@ def evaluate(
+
metric_score
*
current_size
)
/
(
total_size
+
current_size
)
# $$s_z^2 = \frac{(n-1) s_x^2 + (m-1) s_y^2}{n+m-1} + \frac{nm(\bar x - \bar y)^2}{(n+m)(n+m-1)}.$$
results
[
group
][
stderr
]
=
(
(
total_size
-
1
)
*
results
[
group
][
stderr
]
+
(
current_size
-
1
)
*
var_score
)
/
(
total_size
+
current_size
-
1
)
+
total_size
*
current_size
/
(
(
total_size
+
current_size
)
*
(
total_size
+
current_size
-
1
)
)
*
(
results
[
group
][
metric
]
-
metric_score
)
**
2
if
var_score
==
"N/A"
:
results
[
group
][
stderr
]
=
"N/A"
else
:
results
[
group
][
stderr
]
=
(
(
total_size
-
1
)
*
results
[
group
][
stderr
]
+
(
current_size
-
1
)
*
var_score
)
/
(
total_size
+
current_size
-
1
)
+
total_size
*
current_size
/
(
(
total_size
+
current_size
)
*
(
total_size
+
current_size
-
1
)
)
*
(
results
[
group
][
metric
]
-
metric_score
)
**
2
else
:
results
[
group
][
metric
]
=
metric_score
results
[
group
][
stderr
]
=
var_score
...
...
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