Skip to content
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

Jump to bottom

Minor tqdm fixes #5754

Merged
merged 1 commit into from
Apr 20, 2023
Merged

Minor tqdm fixes #5754

Show file tree
Hide file tree
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
4 changes: 2 additions & 2 deletions src/datasets/arrow_dataset.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1437,8 +1437,8 @@ def save_to_disk(
else:
pbar.update(content)
else:
for kwargs in kwargs_per_job:
with pbar:
with pbar:
for kwargs in kwargs_per_job:
for job_id, done, content in Dataset._save_to_disk_single(**kwargs):
if done:
shards_done += 1
Expand Down
46 changes: 24 additions & 22 deletions src/datasets/builder.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1485,13 +1485,14 @@ def _prepare_split(
result = None
gen_kwargs = split_generator.gen_kwargs
job_id = 0
for job_id, done, content in self._prepare_split_single(
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
):
if done:
result = content
else:
pbar.update(content)
with pbar:
for job_id, done, content in self._prepare_split_single(
gen_kwargs=gen_kwargs, job_id=job_id, **_prepare_split_args
):
if done:
result = content
else:
pbar.update(content)
# wrapping everything into lists for consistency with the multiprocessed code path
assert result is not None, "Failed to retrieve results from prepare_split"
examples_per_job, bytes_per_job, features_per_job, shards_per_job, shard_lengths_per_job = [
Expand All @@ -1513,21 +1514,22 @@ def _prepare_split(
shard_lengths_per_job = [None] * num_jobs

with Pool(num_proc) as pool:
for job_id, done, content in iflatmap_unordered(
pool, self._prepare_split_single, kwargs_iterable=kwargs_per_job
):
if done:
# the content is the result of the job
(
examples_per_job[job_id],
bytes_per_job[job_id],
features_per_job[job_id],
shards_per_job[job_id],
shard_lengths_per_job[job_id],
) = content
else:
# the content is the number of examples progress update
pbar.update(content)
with pbar:
for job_id, done, content in iflatmap_unordered(
pool, self._prepare_split_single, kwargs_iterable=kwargs_per_job
):
if done:
# the content is the result of the job
(
examples_per_job[job_id],
bytes_per_job[job_id],
features_per_job[job_id],
shards_per_job[job_id],
shard_lengths_per_job[job_id],
) = content
else:
# the content is the number of examples progress update
pbar.update(content)

assert (
None not in examples_per_job
Expand Down