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
2a817535
Commit
2a817535
authored
May 07, 2024
by
lintangsutawika
Browse files
add version for groups
parent
9f698c20
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
7 additions
and
4 deletions
+7
-4
lm_eval/evaluator.py
lm_eval/evaluator.py
+7
-4
No files found.
lm_eval/evaluator.py
View file @
2a817535
...
@@ -528,6 +528,7 @@ def evaluate(
...
@@ -528,6 +528,7 @@ def evaluate(
def
process_group
(
def
process_group
(
results
,
results
,
versions
,
task_dict
,
task_dict
,
task_root
=
None
,
task_root
=
None
,
task_hierarchy
=
None
,
task_hierarchy
=
None
,
...
@@ -556,8 +557,9 @@ def evaluate(
...
@@ -556,8 +557,9 @@ def evaluate(
group_or_task
group_or_task
)
)
else
:
else
:
results
,
_task_hierarchy
,
show_group_table
=
process_group
(
results
,
versions
,
_task_hierarchy
,
show_group_table
=
process_group
(
results
,
results
,
versions
,
group_or_task_info
,
group_or_task_info
,
group_or_task
,
group_or_task
,
task_hierarchy
,
task_hierarchy
,
...
@@ -620,10 +622,11 @@ def evaluate(
...
@@ -620,10 +622,11 @@ def evaluate(
# results[group][stderr] = lm_eval.api.metrics.combined_sample_stderr(stderrs, sizes, metrics=metrics)
# results[group][stderr] = lm_eval.api.metrics.combined_sample_stderr(stderrs, sizes, metrics=metrics)
results
[
group_or_task
][
"samples"
]
=
sum
(
sizes
)
results
[
group_or_task
][
"samples"
]
=
sum
(
sizes
)
return
results
,
task_hierarchy
,
show_group_table
versions
[
group_or_task
]
=
group_config
[
"version"
]
return
results
,
versions
,
task_hierarchy
,
show_group_table
results
,
task_hierarchy
,
show_group_table
=
process_group
(
results
,
versions
,
task_hierarchy
,
show_group_table
=
process_group
(
results
,
task_dict
results
,
versions
,
task_dict
)
)
results_agg
,
group_agg
=
prepare_print_tasks
(
task_dict
,
results
)
results_agg
,
group_agg
=
prepare_print_tasks
(
task_dict
,
results
)
...
...
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