Debug

src/populate.py

@@ -8,6 +8,15 @@ from src.display.utils import AutoEvalColumn, EvalQueueColumn
 from src.leaderboard.read_evals import get_raw_eval_results
 
 
+def get_inspect_log_url(model_name: str, benchmark_type: str, benchmark_name: str, log_dir: str) -> str:
+    """Returns the URL to the log file for a given model and benchmark"""
+    model_name = model_name.replace("/", "_")
+    log_name = f"{model_name}_{benchmark_type}.log"
+    log_path = os.path.join(log_dir, log_name)
+    if os.path.exists(log_path):
+        return log_path
+    return ""
+
 def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchmark_cols: list) -> pd.DataFrame:
     """Creates a dataframe from all the individual experiment results"""
     raw_data = get_raw_eval_results(results_path, requests_path)
@@ -22,7 +31,7 @@ def get_leaderboard_df(results_path: str, requests_path: str, cols: list, benchm
     df = df[has_no_nan_values(df, benchmark_cols)]
 
     # TMP: Debugging
-    print(df.columns)
+    print(df[AutoEvalColumn.model.name].head())
 
     return df