@@ -254351,6 +254351,16 @@ async def list_model_evaluation_runs(
254351254351 "judge_model_uuid": "str", # Optional. Judge model used to
254352254352 score responses.
254353254353 "name": "str", # Optional. Name of the evaluation run.
254354+ "progress": {
254355+ "candidate_rows_evaluated": 0, # Optional. Dataset
254356+ rows whose candidate model call has completed (success or failure).
254357+ "judge_rows_evaluated": 0, # Optional.
254358+ Candidate-success rows the judge has finished (scored or skipped).
254359+ Caps at the number of candidate successes, which may be below
254360+ total_rows.
254361+ "total_rows": 0 # Optional. Total dataset rows for
254362+ the run, sourced from the evaluation dataset.
254363+ },
254354254364 "status": "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED" #
254355254365 Optional. Default value is "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED".
254356254366 Model Evaluation Run Statuses. Known values are:
@@ -254929,6 +254939,15 @@ async def get_model_evaluation_run(
254929254939 }
254930254940 ],
254931254941 "name": "str", # Optional. Name of the evaluation run.
254942+ "progress": {
254943+ "candidate_rows_evaluated": 0, # Optional. Dataset rows
254944+ whose candidate model call has completed (success or failure).
254945+ "judge_rows_evaluated": 0, # Optional. Candidate-success
254946+ rows the judge has finished (scored or skipped). Caps at the number of
254947+ candidate successes, which may be below total_rows.
254948+ "total_rows": 0 # Optional. Total dataset rows for the run,
254949+ sourced from the evaluation dataset.
254950+ },
254932254951 "result_summary": {
254933254952 "end_time": "2020-02-20 00:00:00", # Optional. Aggregated
254934254953 result summary for a completed model evaluation run.
@@ -255402,6 +255421,15 @@ async def cancel_model_evaluation_run(
255402255421 "judge_model_uuid": "str", # Optional. Judge model used to score
255403255422 responses.
255404255423 "name": "str", # Optional. Name of the evaluation run.
255424+ "progress": {
255425+ "candidate_rows_evaluated": 0, # Optional. Dataset rows
255426+ whose candidate model call has completed (success or failure).
255427+ "judge_rows_evaluated": 0, # Optional. Candidate-success
255428+ rows the judge has finished (scored or skipped). Caps at the number of
255429+ candidate successes, which may be below total_rows.
255430+ "total_rows": 0 # Optional. Total dataset rows for the run,
255431+ sourced from the evaluation dataset.
255432+ },
255405255433 "status": "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED" # Optional.
255406255434 Default value is "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED". Model Evaluation
255407255435 Run Statuses. Known values are: "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED",
@@ -255482,6 +255510,15 @@ async def cancel_model_evaluation_run(
255482255510 "judge_model_uuid": "str", # Optional. Judge model used to score
255483255511 responses.
255484255512 "name": "str", # Optional. Name of the evaluation run.
255513+ "progress": {
255514+ "candidate_rows_evaluated": 0, # Optional. Dataset rows
255515+ whose candidate model call has completed (success or failure).
255516+ "judge_rows_evaluated": 0, # Optional. Candidate-success
255517+ rows the judge has finished (scored or skipped). Caps at the number of
255518+ candidate successes, which may be below total_rows.
255519+ "total_rows": 0 # Optional. Total dataset rows for the run,
255520+ sourced from the evaluation dataset.
255521+ },
255485255522 "status": "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED" # Optional.
255486255523 Default value is "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED". Model Evaluation
255487255524 Run Statuses. Known values are: "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED",
@@ -255565,6 +255602,15 @@ async def cancel_model_evaluation_run(
255565255602 "judge_model_uuid": "str", # Optional. Judge model used to score
255566255603 responses.
255567255604 "name": "str", # Optional. Name of the evaluation run.
255605+ "progress": {
255606+ "candidate_rows_evaluated": 0, # Optional. Dataset rows
255607+ whose candidate model call has completed (success or failure).
255608+ "judge_rows_evaluated": 0, # Optional. Candidate-success
255609+ rows the judge has finished (scored or skipped). Caps at the number of
255610+ candidate successes, which may be below total_rows.
255611+ "total_rows": 0 # Optional. Total dataset rows for the run,
255612+ sourced from the evaluation dataset.
255613+ },
255568255614 "status": "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED" # Optional.
255569255615 Default value is "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED". Model Evaluation
255570255616 Run Statuses. Known values are: "MODEL_EVALUATION_RUN_STATUS_UNSPECIFIED",
0 commit comments