Use correct default for round robin gradients (#1258)

* Make round robin gradient partitioning configurable (default False)

* Use the correct default

* Log config setting

deepspeed/runtime/zero/config.py

@@ -189,4 +189,4 @@ class DeepSpeedZeroConfig(DeepSpeedConfigObject):
         self.round_robin_gradients = get_scalar_param(
             zero_config_dict,
             ZERO_OPTIMIZATION_ROUND_ROBIN_GRADIENTS,
-            ZERO3_OPTIMIZATION_CONTIGUOUS_GRADIENTS_DEFAULT)
+            ZERO_OPTIMIZATION_ROUND_ROBIN_GRADIENTS_DEFAULT)

deepspeed/runtime/zero/stage2.py

@@ -106,6 +106,7 @@ class FP16_DeepSpeedZeroOptimizer(object):
             logger.info(f"Reduce bucket size {reduce_bucket_size}")
             logger.info(f"Allgather bucket size {allgather_bucket_size}")
             logger.info(f"CPU Offload: {cpu_offload}")
+            logger.info(f'Round robin gradient partitioning: {round_robin_gradients}')
         # The fused optimizer does all the work. We need this layer for two reason:
         # 1. maintain same user API from apex.fp16_utils
         # 2. keep common stuff here in case we need to add ne552w fused optimizer later