Skip to content

Update save sizes into GiB #2143

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

Merged
merged 1 commit into from
Dec 10, 2024
Merged

Update save sizes into GiB #2143

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
2 changes: 1 addition & 1 deletion recipes/quantize.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,7 +107,7 @@ def save_checkpoint(self, cfg: DictConfig):
torch.save(ckpt_dict, checkpoint_file)
logger.info(
"Model checkpoint of size "
f"{os.path.getsize(checkpoint_file) / 1000**3:.2f} GB "
f"{os.path.getsize(checkpoint_file) / 1024**3:.2f} GiB "
f"saved to {checkpoint_file}"
)

Expand Down
22 changes: 11 additions & 11 deletions torchtune/training/checkpointing/_checkpointer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -288,7 +288,7 @@ def save_checkpoint(
torch.save(state_dict[training.MODEL_KEY], output_path)
logger.info(
"Model checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)

Expand All @@ -300,7 +300,7 @@ def save_checkpoint(
torch.save(state_dict[training.ADAPTER_KEY], output_path)
logger.info(
"Adapter checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)

Expand All @@ -321,7 +321,7 @@ def save_checkpoint(
torch.save(state_dict, output_path)
logger.info(
"Recipe checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)
else:
Expand Down Expand Up @@ -723,7 +723,7 @@ def save_checkpoint(

logger.info(
"Model checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)

Expand Down Expand Up @@ -768,7 +768,7 @@ def save_checkpoint(
torch.save(state_dict[training.ADAPTER_KEY], output_path)
logger.info(
"Adapter checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)

Expand Down Expand Up @@ -806,7 +806,7 @@ def save_checkpoint(
)
logger.info(
"Adapter checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)
elif adapter_only:
Expand Down Expand Up @@ -838,7 +838,7 @@ def save_checkpoint(
json.dump(state_dict[training.ADAPTER_CONFIG], f)
logger.info(
"Adapter checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)

Expand All @@ -855,7 +855,7 @@ def save_checkpoint(
torch.save(state_dict, output_path)
logger.info(
"Recipe checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)
else:
Expand Down Expand Up @@ -1065,7 +1065,7 @@ def save_checkpoint(
torch.save(state_dict[training.MODEL_KEY], checkpoint_file)
logger.info(
"Model checkpoint of size "
f"{os.path.getsize(checkpoint_file) / 1000**3:.2f} GB "
f"{os.path.getsize(checkpoint_file) / 1024**3:.2f} GiB "
f"saved to {checkpoint_file}"
)

Expand All @@ -1077,7 +1077,7 @@ def save_checkpoint(
torch.save(state_dict[training.ADAPTER_KEY], output_path)
logger.info(
"Adapter checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)

Expand All @@ -1099,7 +1099,7 @@ def save_checkpoint(
torch.save(state_dict, output_path)
logger.info(
"Recipe checkpoint of size "
f"{os.path.getsize(output_path) / 1000**3:.2f} GB "
f"{os.path.getsize(output_path) / 1024**3:.2f} GiB "
f"saved to {output_path}"
)
else:
Expand Down
Loading