debugging fp32 training.

megatron/optimizer/distrib_optimizer.py

@@ -31,6 +31,7 @@ from .optimizer import MixedPrecisionOptimizer, _zero_grad_group_helper
 from lutil import pax, tp, print_seq
 # <<<
 
+
 class Range:
 
     def __init__(self, start, end):

megatron/training.py

@@ -52,10 +52,6 @@ from megatron.schedules import get_forward_backward_func
 from megatron.utils import report_memory
 from megatron.model.vision.knn_monitor import compute_feature_bank
 
-# >>>
-from lutil import pax, tp, print_seq
-# <<<
-
 
 def print_datetime(string):
     """Note that this call will sync across all ranks."""