Add FAILED evaluations dropdown

app.py

@@ -90,11 +90,12 @@ def init_space():
         finished_eval_queue_df,
         running_eval_queue_df,
         pending_eval_queue_df,
+        failed_eval_queue_df
     ) = get_evaluation_queue_df(EVAL_REQUESTS_PATH, EVAL_COLS)
 
-    return leaderboard_df, original_df, plot_df, finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df
+    return leaderboard_df, original_df, plot_df, finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df, failed_eval_queue_df
 
-leaderboard_df, original_df, plot_df, finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df = init_space()
+leaderboard_df, original_df, plot_df, finished_eval_queue_df, running_eval_queue_df, pending_eval_queue_df, failed_eval_queue_df = init_space()
 
 
 # Searching and filtering
@@ -403,6 +404,17 @@ with demo:
                                 datatype=EVAL_TYPES,
                                 row_count=5,
                             )
+                    with gr.Accordion(
+                        f"❌ Failed Evaluations ({len(failed_eval_queue_df)})",
+                        open=False,
+                    ):
+                        with gr.Row():
+                            failed_eval_table = gr.components.Dataframe(
+                                value=failed_eval_queue_df,
+                                headers=EVAL_COLS,
+                                datatype=EVAL_TYPES,
+                                row_count=5,
+                            )
             with gr.Row():
                 gr.Markdown("# ✉️✨ Submit your model here!", elem_classes="markdown-text")
 

src/populate.py

@@ -54,7 +54,9 @@ def get_evaluation_queue_df(save_path: str, cols: list) -> list[pd.DataFrame]:
     pending_list = [e for e in all_evals if e["status"] in ["PENDING", "RERUN"]]
     running_list = [e for e in all_evals if e["status"] == "RUNNING"]
     finished_list = [e for e in all_evals if e["status"].startswith("FINISHED") or e["status"] == "PENDING_NEW_EVAL"]
+    failed_list = [e for e in all_evals if e["status"] == "FAILED"]
     df_pending = pd.DataFrame.from_records(pending_list, columns=cols)
     df_running = pd.DataFrame.from_records(running_list, columns=cols)
     df_finished = pd.DataFrame.from_records(finished_list, columns=cols)
-    return df_finished[cols], df_running[cols], df_pending[cols]
+    df_failed = pd.DataFrame.from_records(failed_list, columns=cols)
+    return df_finished[cols], df_running[cols], df_pending[cols], df_failed[cols]