Skip to content

Fix typos in math_comparison.py and sample_comparison.py #1186

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

Fix typos in math_comparison.py and sample_comparison.py #1186

Show file tree
Hide file tree
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
2 changes: 1 addition & 1 deletion src/lighteval/metrics/utils/math_comparison.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -496,7 +496,7 @@ def sympy_expr_eq(gold: Basic | MatrixBase, pred: Basic | MatrixBase, precision:
except Exception: # noqa: E722
pass

# If the target is relational, but the refernce is not, it's possible it's a case of a=x+1+z, so we just take x+1+z
# If the target is relational, but the reference is not, it's possible it's a case of a=x+1+z, so we just take x+1+z
# We only do this if the lhs of the first equation is fully symbolic, to prevent simplifying x+y+2z = 1
if is_assignment_relation(gold) and not is_equation(pred):
gold = take_last_relation(gold).rhs
Expand Down
2 changes: 1 addition & 1 deletion tests/slow_tests/sample_comparison.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,7 +71,7 @@ def _compare_model_responses(current, reference):

# Special handling for logprobs field
if field_name in ["input_tokens", "output_tokens"]:
# input and ouput tokens are lists of tensors, we need to convert
# input and output tokens are lists of tensors, we need to convert
# them to plain lists
current_val = _to_plain_list(current_val)
reference_val = _to_plain_list(reference_val)
Expand Down