SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

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

Browse Source
This commit is contained in:
VictorSanh
2018-11-04 16:28:10 -05:00
parent 3d291dea4a
commit d55c3ae83f
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
run_classifier.py
View File

@@ -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(

2
run_squad.py
View File

@@ -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(