add log

src/tools/plots.py

@@ -19,9 +19,9 @@ def create_scores_df(raw_data: list[EvalResult]) -> pd.DataFrame:
     """
     # Step 1: Ensure 'date' is in datetime format and sort the DataFrame by it
     results_df = pd.DataFrame(raw_data)
-    print("results_df", results_df)
     results_df["date"] = pd.to_datetime(results_df["date"], format="mixed", utc=True)
     results_df.sort_values(by="date", inplace=True)
+    print("results_df", results_df)
 
     # Step 2: Initialize the scores dictionary
     scores = {k: [] for k in BENCHMARK_COLS + [AutoEvalColumn.average.name]}
@@ -46,6 +46,7 @@ def create_scores_df(raw_data: list[EvalResult]) -> pd.DataFrame:
                 else:
                     current_score = 0
 
+            print(current_score,current_max, task.benchmark)
             if current_score > current_max:
                 if current_date == last_date and len(scores[column]) > 0:
                     scores[column][-1] = {"model": current_model, "date": current_date, "score": current_score}