Skip to content

feat(utils): show count of evaluated samples in Markdown summary table #1188

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.

Sign up for GitHub

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

Open
anzzyspeaksgit wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(utils): show count of evaluated samples in Markdown summary table #1188

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 13 additions & 3 deletions src/lighteval/utils/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -249,24 +249,34 @@ def make_results_table(result_dict):
# Returns markdown table with task, version, metric, value, ±, stderr columns
"""
md_writer = MarkdownTableWriter()
md_writer.headers = ["Task", "Version", "Metric", "Value", "", "Stderr"]
md_writer.headers = ["Task", "Version", "Metric", "Value", "", "Stderr", "Count"]

values = []

for k in sorted(result_dict["results"].keys()):
dic = result_dict["results"][k]
version = result_dict["versions"][k] if k in result_dict["versions"] else ""

count = ""
# The number of items is stored in summary_tasks under each task dict (for sub-tasks)
if "summary_tasks" in result_dict and k in result_dict["summary_tasks"]:
count = str(result_dict["summary_tasks"][k].get("number_of_samples", ""))
# If the key is 'all', grab it from summary_general
elif k == "all" and "summary_general" in result_dict:
count = str(result_dict["summary_general"].get("number_of_samples", ""))

for m, v in dic.items():
if m.endswith("_stderr"):
continue

if m + "_stderr" in dic:
se = dic[m + "_stderr"]
values.append([k, version, m, "%.4f" % v, "±", "%.4f" % se])
values.append([k, version, m, "%.4f" % v, "±", "%.4f" % se, count])
else:
values.append([k, version, m, "%.4f" % v, "", ""])
values.append([k, version, m, "%.4f" % v, "", "", count])
k = ""
version = ""
count = ""
md_writer.value_matrix = values

return md_writer.dumps()
Expand Down