Skip to content
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

Removes default bert scorer init #234

Merged
merged 4 commits into from
Jul 24, 2024
Merged

Removes default bert scorer init #234

Changes from 2 commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
ce2b3bf
move init of bertscorer to avoid downloading model by default
clefourrier Jul 18, 2024
d7b141e
Merge branch 'main' into bert_scorer_import
NathanHB Jul 23, 2024
a4731cd
Update src/lighteval/metrics/metrics_sample.py
clefourrier Jul 23, 2024
2170010
Merge branch 'main' into bert_scorer_import
clefourrier Jul 23, 2024
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
10 changes: 7 additions & 3 deletions src/lighteval/metrics/metrics_sample.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -424,9 +424,7 @@ def __init__(
normalize_pred (callable, optional): Function to use to normalize the predicted strings.
Defaults to None if no normalization is applied.
"""
self.bert_scorer = BERTScorer(
model_type="microsoft/deberta-large-mnli", lang="en", rescale_with_baseline=True, num_layers=9
)
self.bert_scorer = None

self.normalize_gold = normalize_gold
self.normalize_pred = normalize_pred
Expand All @@ -441,6 +439,12 @@ def compute(self, golds: list[str], predictions: list[str]) -> dict:
Returns:
dict: Scores over the current sample's items.
"""
if self.bert_scorer is None:
hlog_warn("The first metric computation step might be a bit long as we need to download the model.")
clefourrier marked this conversation as resolved.
Show resolved Hide resolved
# We only initialize on first compute
self.bert_scorer = BERTScorer(
model_type="microsoft/deberta-large-mnli", lang="en", rescale_with_baseline=True, num_layers=9
)
golds = as_list(golds)
predictions = as_list(predictions)
# Normalize
Expand Down
Loading