checkpoint only on rank=0 now

2026-09-13 12:50:26 +08:00 · 2019-07-03 18:17:12 -04:00
parent f101152650
commit a9acae3ed0
1 changed files with 1 additions and 1 deletions
@@ -367,7 +367,7 @@ class Trainer(TrainerIO):
            self.batch_loss_value = 0  # accumulated grads

            # init progbar when requested
-            if self.progress_bar:
+            if self.progress_bar and self.proc_rank == 0:
                self.prog_bar = tqdm.tqdm(range(self.total_batches), position=self.process_position)

            for batch_nb, data_batch in enumerate(self.tng_dataloader):