Skip to content

GitLab

Commit d55c3ae8 authored by VictorSanh's avatar VictorSanh
Browse files

Small logger bug (multi-gpu, distribution) in training

parent 3d291dea
Show whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
run_classifier.py
View file @ d55c3ae8
......@@ -420,7 +420,7 @@ def main():
n_gpu = 1
# Initializes the distributed backend which will take care of sychronizing nodes/GPUs
torch.distributed.init_process_group(backend='nccl')
logger.info("device", device, "n_gpu", n_gpu, "distributed training", bool(args.local_rank != -1))
logger.info("device %s n_gpu %d distributed training %r", device, n_gpu, bool(args.local_rank != -1))
if args.accumulate_gradients < 1:
raise ValueError("Invalid accumulate_gradients parameter: {}, should be >= 1".format(
......
run_squad.py
View file @ d55c3ae8
......@@ -750,7 +750,7 @@ def main():
n_gpu = 1
# Initializes the distributed backend which will take care of sychronizing nodes/GPUs
torch.distributed.init_process_group(backend='nccl')
logger.info("device", device, "n_gpu", n_gpu, "distributed training", bool(args.local_rank != -1))
logger.info("device %s n_gpu %d distributed training %r", device, n_gpu, bool(args.local_rank != -1))
if args.accumulate_gradients < 1:
raise ValueError("Invalid accumulate_gradients parameter: {}, should be >= 1".format(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment