We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent fe73982 commit c4e6458Copy full SHA for c4e6458
train.py
@@ -227,6 +227,7 @@ def train_model(config: ModelConfig):
227
# set the wandb project where this run will be logged
228
project="pytorch-transformer-distributed",
229
# allow resuming existing run with the same name (in case the rank 0 node crashed)
230
+ name=f"global_rank_{config.global_rank}",
231
id=wandb_run_id,
232
resume="allow",
233
group=config.wandb_group,
0 commit comments