update to display failed model

src/pages/submit.py

@@ -9,6 +9,7 @@ def show_submit_page(index: int):
         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)
     with gr.TabItem("🚀 Submit! ", elem_id="llm-benchmark-tab-table", id=index):
         
@@ -24,6 +25,17 @@ def show_submit_page(index: int):
                         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.Accordion(
                 f"⏳ Pending Evaluation Queue ({len(pending_eval_queue_df)})",

src/populate.py

@@ -45,7 +45,9 @@ 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"].startswith("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]