Update execution_strategy option default value (#18183)

* update execution_strategy option default value
test=develop

* fix doc error
test=develop

paddle/fluid/framework/parallel_executor.cc

@@ -647,7 +647,7 @@ void ParallelExecutor::FeedAndSplitTensorIntoLocalScopes(
           "The number(%d) of samples of "
           "current batch is less than the count(%d) of "
           "devices(%s), currently, it is not allowed. ",
-          member_->places_.size(), lod_tensors.size(),
+          lod_tensors.size(), member_->places_.size(),
           (is_cpu_place ? "CPU" : "GPU"));
       if (is_cpu_place) {
         error_info +=

paddle/fluid/pybind/pybind.cc

@@ -1179,7 +1179,8 @@ All parameter, weight, gradient are variables in Paddle.
           },
           R"DOC(The type is BOOL, allow_op_delay represents whether to delay the
                 communication operators to run, it may make the execution faster.
-                Note that in some models, allow_op_delay may cause program hang. Default False.)DOC")
+                Note that this option is invalid now, and it will be removed in
+                next version. Default False.)DOC")
       .def_property(
           "num_iteration_per_drop_scope",
           [](const ExecutionStrategy &self) {
@@ -1191,7 +1192,8 @@ All parameter, weight, gradient are variables in Paddle.
           R"DOC(The type is INT, num_iteration_per_drop_scope indicates how
                 many iterations to clean up the temp variables which
                 is generated during execution. It may make the execution faster,
-                because the temp variable's shape maybe the same between two iterations. Default 100.
+                because the temp variable's shape maybe the same between two iterations.
+                Default 1.
 
                 NOTES:
                     1. If you fetch data when calling the 'run', the ParallelExecutor