Update README.race.md

Summary: Pull Request resolved: https://github.com/pytorch/fairseq/pull/1155 Differential Revision: D17509762 Pulled By: myleott fbshipit-source-id: 4de535289c1f35abff0d8142d8580f3ede039f47

Update README.race.md
Summary: Pull Request resolved: https://github.com/pytorch/fairseq/pull/1155 Differential Revision: D17509762 Pulled By: myleott fbshipit-source-id: 4de535289c1f35abff0d8142d8580f3ede039f47
e869c80d · Myle Ott · Facebook Github Bot · 32335404 · e869c80d
Commit e869c80d authored Sep 20, 2019 by Myle Ott Committed by Facebook Github Bot Sep 20, 2019
Show whitespace changes
Inline Side-by-side

Showing with 1 addition and 1 deletion

examples/roberta/README.race.md examples/roberta/README.race.md +1 -1

No files found.
--- a/examples/roberta/README.race.md
+++ b/examples/roberta/README.race.md
@@ -19,7 +19,7 @@ UPDATE_FREQ=8         # Accumulate gradients to simulate training on 8 GPUs.
 DATA_DIR=/path/to/race-output-dir
 ROBERTA_PATH=/path/to/roberta/model.pt

-CUDA_VISIBLE_DEVICES=0,1 fairseq-train $DATA_DIR \
+CUDA_VISIBLE_DEVICES=0,1 fairseq-train $DATA_DIR --ddp-backend=no_c10d \
    --restore-file $ROBERTA_PATH \
    --reset-optimizer --reset-dataloader --reset-meters \
    --best-checkpoint-metric accuracy --maximize-best-checkpoint-metric \