Skip to content

Fix local_evaluation.py syntax error #13

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
ghmark675 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix local_evaluation.py syntax error #13

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
6 changes: 3 additions & 3 deletions local_evaluation.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -182,7 +182,7 @@ def generate_predictions(dataset_path, participant_model):
return queries, ground_truths, predictions


def evaluate_predictions(queries, ground_truths_list, predictions, evaluation_model_name):
def evaluate_predictions(queries, ground_truths_list, predictions, evaluation_model_name, openai_client):
"""
Evaluates the predictions generated by a model against ground truth answers.

Expand All @@ -199,7 +199,7 @@ def evaluate_predictions(queries, ground_truths_list, predictions, evaluation_mo

if "chat" in evaluation_model_name.lower():
# now we are using chatgpt
openai_client = OpenAI()
# openai_client = OpenAI()
n_miss, n_correct = 0, 0
system_message = get_system_message()

Expand All @@ -211,6 +211,7 @@ def evaluate_predictions(queries, ground_truths_list, predictions, evaluation_mo
# trim prediction to 75 tokens using Llama2 tokenizer
prediction = trim_predictions_to_max_token_length(prediction)
prediction = prediction.strip()
prediction_lowercase = prediction.lower()

if "i don't know" in prediction_lowercase:
n_miss += 1
Expand All @@ -220,7 +221,6 @@ def evaluate_predictions(queries, ground_truths_list, predictions, evaluation_mo

for ground_truth in ground_truths:
ground_truth_lowercase = ground_truth.lower()
prediction_lowercase = prediction.lower()
messages = [
{"role": "system", "content": system_message},
{
Expand Down