Skip to content
Open
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions FSDP_Workshop/main_training.py
Original file line number Diff line number Diff line change
Expand Up @@ -224,7 +224,7 @@ def train(
optimizer.step()

ddp_loss[0] += loss.item()
ddp_loss[1] += len(batch)
ddp_loss[1] += 1

if rank == 0:
inner_pbar.update(1)
Expand Down Expand Up @@ -262,7 +262,7 @@ def validation(model, local_rank, rank, world_size, test_loader):
labels=batch["target_ids"],
)
ddp_loss[0] += output["loss"].item() # sum up batch loss
ddp_loss[1] += len(batch)
ddp_loss[1] += 1

if rank == 0:
inner_pbar.update(1)
Expand Down Expand Up @@ -633,4 +633,4 @@ def fsdp_main(args):
# torch run start
fsdp_main(args)