def _log_results_as_table()

in lm_eval/loggers/wandb_logger.py [0:0]

• 39 lines of code
• 11 McCabe index (conditional complexity)

    def _log_results_as_table(self) -> None:
        """Generate and log evaluation results as a table to W&B."""
        columns = [
            "Version",
            "Filter",
            "num_fewshot",
            "Metric",
            "Value",
            "Stderr",
        ]

        def make_table(columns: List[str], key: str = "results"):
            import wandb

            table = wandb.Table(columns=columns)
            results = copy.deepcopy(self.results)

            for k, dic in results.get(key).items():
                if k in self.group_names and not key == "groups":
                    continue
                version = results.get("versions").get(k)
                if version == "N/A":
                    version = None
                n = results.get("n-shot").get(k)

                for (mf), v in dic.items():
                    m, _, f = mf.partition(",")
                    if m.endswith("_stderr"):
                        continue
                    if m == "alias":
                        continue

                    if m + "_stderr" + "," + f in dic:
                        se = dic[m + "_stderr" + "," + f]
                        if se != "N/A":
                            se = "%.4f" % se
                        table.add_data(*[k, version, f, n, m, str(v), str(se)])
                    else:
                        table.add_data(*[k, version, f, n, m, str(v), ""])

            return table

        # log the complete eval result to W&B Table
        table = make_table(["Tasks"] + columns, "results")
        self.run.log({"evaluation/eval_results": table})

        if "groups" in self.results.keys():
            table = make_table(["Groups"] + columns, "groups")
            self.run.log({"evaluation/group_eval_results": table})