Skip to content

fix(distributed): call destroy_process_group() on exit to prevent NCC… #1391

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
mandanajignesh-byte wants to merge 1 commit into
base: main
Choose a base branch
from
+47 −41
Open

fix(distributed): call destroy_process_group() on exit to prevent NCC… #1391

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
88 changes: 47 additions & 41 deletions lmms_eval/__main__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -534,47 +534,53 @@ def cli_evaluate(args: Union[argparse.Namespace, None] = None) -> None:
else:
is_main_process = False

for args in args_list:
try:
# if is_main_process and args.wandb_args: # thoughtfully we should only init wandb once, instead of multiple ranks to avoid network traffics and unwanted behaviors.
# wandb_logger = WandbLogger()

results, samples = cli_evaluate_single(args)
results_list.append(results)

if accelerator:
accelerator.wait_for_everyone()
elif torch.distributed.is_available() and torch.distributed.is_initialized():
torch.distributed.barrier()
if is_main_process and args.wandb_args:
try:
wandb_logger.post_init(results)
wandb_logger.log_eval_result()
if args.wandb_log_samples and samples is not None:
wandb_logger.log_eval_samples(samples)
except Exception as e:
eval_logger.info(f"Logging to Weights and Biases failed due to {e}")
# wandb_logger.finish()

except Exception as e:
if args.verbosity == "DEBUG":
raise e
else:
traceback.print_exc()
eval_logger.error(f"Error during evaluation: {e}. Please set `--verbosity=DEBUG` to get more information.")
results_list.append(None)

for args, results in zip(args_list, results_list):
# cli_evaluate will return none if the process is not the main process (rank 0)
if results is not None:
print(f"{args.model} ({args.model_args}), gen_kwargs: ({args.gen_kwargs}), " f"limit: {args.limit}, offset: {args.offset}, num_fewshot: {args.num_fewshot}, " f"batch_size: {args.batch_size}")
print(get_eval_banner(branch=results.get("git_branch"), commit=results.get("git_hash")))
print(make_table(results))
if "groups" in results:
print(make_table(results, "groups"))

if args.wandb_args:
wandb_logger.run.finish()
try:
for args in args_list:
try:
# if is_main_process and args.wandb_args: # thoughtfully we should only init wandb once, instead of multiple ranks to avoid network traffics and unwanted behaviors.
# wandb_logger = WandbLogger()

results, samples = cli_evaluate_single(args)
results_list.append(results)

if accelerator:
accelerator.wait_for_everyone()
elif torch.distributed.is_available() and torch.distributed.is_initialized():
torch.distributed.barrier()
if is_main_process and args.wandb_args:
try:
wandb_logger.post_init(results)
wandb_logger.log_eval_result()
if args.wandb_log_samples and samples is not None:
wandb_logger.log_eval_samples(samples)
except Exception as e:
eval_logger.info(f"Logging to Weights and Biases failed due to {e}")
# wandb_logger.finish()

except Exception as e:
if args.verbosity == "DEBUG":
raise e
else:
traceback.print_exc()
eval_logger.error(f"Error during evaluation: {e}. Please set `--verbosity=DEBUG` to get more information.")
results_list.append(None)

for args, results in zip(args_list, results_list):
# cli_evaluate will return none if the process is not the main process (rank 0)
if results is not None:
print(f"{args.model} ({args.model_args}), gen_kwargs: ({args.gen_kwargs}), " f"limit: {args.limit}, offset: {args.offset}, num_fewshot: {args.num_fewshot}, " f"batch_size: {args.batch_size}")
print(get_eval_banner(branch=results.get("git_branch"), commit=results.get("git_hash")))
print(make_table(results))
if "groups" in results:
print(make_table(results, "groups"))

if args.wandb_args:
wandb_logger.run.finish()
finally:
if accelerator is not None:
accelerator.state.destroy_process_group()
elif torch.distributed.is_available() and torch.distributed.is_initialized():
torch.distributed.destroy_process_group()


def cli_evaluate_single(args: Union[argparse.Namespace, None] = None) -> None:
Expand Down