Fix(Early Stopping): move best score to device (#7959)

Author: awaelchli

pytorch_lightning/callbacks/early_stopping.py

@@ -190,7 +190,7 @@ def _run_early_stopping_check(self, trainer) -> None:
         # when in dev debugging
         trainer.dev_debugger.track_early_stopping_history(self, current)
 
-        should_stop, reason = self._evalute_stopping_criteria(current)
+        should_stop, reason = self._evalute_stopping_criteria(current, trainer)
 
         # stop every ddp process if any world process decides to stop
         should_stop = trainer.training_type_plugin.reduce_boolean_decision(should_stop)
@@ -200,7 +200,7 @@ def _run_early_stopping_check(self, trainer) -> None:
         if reason and self.verbose:
             self._log_info(trainer, reason)
 
-    def _evalute_stopping_criteria(self, current: torch.Tensor) -> Tuple[bool, str]:
+    def _evalute_stopping_criteria(self, current: torch.Tensor, trainer: 'pl.Trainer') -> Tuple[bool, str]:
         should_stop = False
         reason = None
         if self.check_finite and not torch.isfinite(current):
@@ -223,7 +223,7 @@ def _evalute_stopping_criteria(self, current: torch.Tensor) -> Tuple[bool, str]:
                 f" {self.monitor} = {current} {self.order_dict[self.mode]} {self.divergence_threshold}."
                 " Signaling Trainer to stop."
             )
-        elif self.monitor_op(current - self.min_delta, self.best_score):
+        elif self.monitor_op(current - self.min_delta, self.best_score.to(trainer.lightning_module.device)):
             should_stop = False
             reason = self._improvement_message(current)
             self.best_score = current