def _maybe_log_save_evaluate()

in optimum/graphcore/trainer.py [0:0]

• 27 lines of code
• 6 McCabe index (conditional complexity)

    def _maybe_log_save_evaluate(self, tr_loss, model, epoch, ignore_keys_for_eval):
        if self.control.should_log:
            logs: Dict[str, float] = {}

            tr_loss_scalar = tr_loss.mean().item()

            # reset tr_loss to zero
            tr_loss -= tr_loss

            logs["loss"] = round(tr_loss_scalar / (self.state.global_step - self._globalstep_last_logged), 4)
            logs["learning_rate"] = self._get_learning_rate()

            self._total_loss_scalar += tr_loss_scalar
            self._globalstep_last_logged = self.state.global_step
            self.store_flos()

            self.log(logs)

        metrics = None
        if self.control.should_evaluate:
            self._detach_training_model()
            if isinstance(self.eval_dataset, dict):
                for eval_dataset_name, eval_dataset in self.eval_dataset.items():
                    metrics = self.evaluate(
                        eval_dataset=eval_dataset,
                        ignore_keys=ignore_keys_for_eval,
                        metric_key_prefix=f"eval_{eval_dataset_name}",
                    )
            else:
                metrics = self.evaluate(ignore_keys=ignore_keys_for_eval)
            self._reattach_training_model()

        if self.control.should_save:
            self._save_checkpoint(model, metrics=metrics)
            self.control = self.callback_handler.on_save(self.args, self.state, self.control)