Skip to content

Log regression task metrics in multitask model #3648

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
ntravis22 wants to merge 7 commits into
base: master
Choose a base branch
from
+10 −1
Open

Log regression task metrics in multitask model #3648

Changes from all commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
eab64f5
handle case where not all metrics present
ntravis22 Mar 24, 2025
699377c
small change
ntravis22 Mar 24, 2025
c2e7e77
real fix
ntravis22 Mar 24, 2025
bf608f0
formatting
ntravis22 Mar 24, 2025
f3ea87d
black formatting
ntravis22 Mar 25, 2025
aa375f5
add mse for regression tasks
ntravis22 Mar 25, 2025
6e1e47d
add other regression metrics
ntravis22 Mar 25, 2025
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
11 changes: 10 additions & 1 deletion flair/models/multitask_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,7 +198,16 @@ def evaluate( # type: ignore[override]
# Add metrics so they will be available to _publish_eval_result.
for avg_type in ("micro avg", "macro avg"):
for metric_type in ("f1-score", "precision", "recall"):
scores[(task_id, avg_type, metric_type)] = result.classification_report[avg_type][metric_type]
if result.classification_report.get(avg_type) and result.classification_report[avg_type].get(
metric_type
):
scores[(task_id, avg_type, metric_type)] = result.classification_report[avg_type][metric_type]

# The above metrics only apply to classification tasks. This adds
# regression metrics also.
for metric_type in ("mse", "mae", "pearson", "spearman"):
if result.scores.get(metric_type):
scores[(task_id, metric_type)] = result.scores[metric_type]

scores["loss"] = loss.item() / len(batch_split)

Expand Down