riaz.somc/transformers
1
0
Fork 0
mirror of https://github.com/huggingface/transformers.git synced 2025-08-01 02:31:11 +06:00
Code Issues Actions 3 Packages Projects Releases Wiki Activity

Fix args.gradient_accumulation_steps used before assigment.

Browse Source
This commit is contained in:
VictorSanh 2018-11-04 17:31:50 -05:00
parent 649e9774cd
commit 290633b882
2 changed files with 10 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
run_classifier.py
View File

@ -404,6 +404,10 @@ def main():
type=int, type=int,
default=42, default=42,
help="random seed for initialization") help="random seed for initialization")
parser.add_argument('--gradient_accumulation_steps',
type=int,
default=1,
help="Number of updates steps to accumualte before performing a backward/update pass.")
args = parser.parse_args() args = parser.parse_args()
processors = { processors = {
@ -469,7 +473,7 @@ def main():
model = BertForSequenceClassification(bert_config, len(label_list)) model = BertForSequenceClassification(bert_config, len(label_list))
if args.init_checkpoint is not None: if args.init_checkpoint is not None:
model.load_state_dict(torch.load(args.init_checkpoint, map_location='cpu')) model.bert.load_state_dict(torch.load(args.init_checkpoint, map_location='cpu'))
model.to(device) model.to(device)
if args.local_rank != -1: if args.local_rank != -1:

6
run_squad.py
View File

@ -739,7 +739,11 @@ def main():
type=int, type=int,
default=42, default=42,
help="random seed for initialization") help="random seed for initialization")
parser.add_argument('--gradient_accumulation_steps',
type=int,
default=1,
help="Number of updates steps to accumualte before performing a backward/update pass.")
args = parser.parse_args() args = parser.parse_args()
if args.local_rank == -1 or args.no_cuda: if args.local_rank == -1 or args.no_cuda: