SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Update legacy Repository usage in various example files (#29085)

Browse Source 
* Update legacy Repository usage in `examples/pytorch/text-classification/run_glue_no_trainer.py`

Marked for deprecation here https://huggingface.co/docs/huggingface_hub/guides/upload#legacy-upload-files-with-git-lfs

* Fix import order

* Replace all example usage of deprecated Repository

* Fix remaining repo call and rename args variable

* Revert removing creation of gitignore files and don't change research examples
This commit is contained in:
Hilco van der Wilk
2024-03-12 14:20:49 +01:00
committed by GitHub
parent f1a565a39f
commit b6404866cd
24 changed files with 338 additions and 163 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
examples/pytorch/language-modeling/run_clm_no_trainer.py
View File

@@ -37,7 +37,7 @@ from accelerate import Accelerator, DistributedType
from accelerate.logging import get_logger
from accelerate.utils import set_seed
from datasets import load_dataset
from huggingface_hub import Repository, create_repo
from huggingface_hub import HfApi
from torch.utils.data import DataLoader
from tqdm.auto import tqdm
@@ -304,9 +304,8 @@ def main():
if repo_name is None:
repo_name = Path(args.output_dir).absolute().name
# Create repo and retrieve repo_id
repo_id = create_repo(repo_name, exist_ok=True, token=args.hub_token).repo_id
# Clone repo locally
repo = Repository(args.output_dir, clone_from=repo_id, token=args.hub_token)
api = HfApi()
repo_id = api.create_repo(repo_name, exist_ok=True, token=args.hub_token).repo_id
with open(os.path.join(args.output_dir, ".gitignore"), "w+") as gitignore:
if "step_*" not in gitignore:
@@ -682,8 +681,12 @@ def main():
)
if accelerator.is_main_process:
tokenizer.save_pretrained(args.output_dir)
repo.push_to_hub(
commit_message=f"Training in progress epoch {epoch}", blocking=False, auto_lfs_prune=True
api.upload_folder(
commit_message=f"Training in progress epoch {epoch}",
folder_path=args.output_dir,
repo_id=repo_id,
repo_type="model",
token=args.hub_token,
)
if args.checkpointing_steps == "epoch":
@@ -704,8 +707,13 @@ def main():
if accelerator.is_main_process:
tokenizer.save_pretrained(args.output_dir)
if args.push_to_hub:
repo.push_to_hub(commit_message="End of training", auto_lfs_prune=True)
api.upload_folder(
commit_message="End of training",
folder_path=args.output_dir,
repo_id=repo_id,
repo_type="model",
token=args.hub_token,
)
with open(os.path.join(args.output_dir, "all_results.json"), "w") as f:
json.dump({"perplexity": perplexity}, f)

24
examples/pytorch/language-modeling/run_mlm_no_trainer.py
View File

@@ -37,7 +37,7 @@ from accelerate import Accelerator, DistributedType
from accelerate.logging import get_logger
from accelerate.utils import set_seed
from datasets import load_dataset
from huggingface_hub import Repository, create_repo
from huggingface_hub import HfApi
from torch.utils.data import DataLoader
from tqdm.auto import tqdm
@@ -311,9 +311,8 @@ def main():
if repo_name is None:
repo_name = Path(args.output_dir).absolute().name
# Create repo and retrieve repo_id
repo_id = create_repo(repo_name, exist_ok=True, token=args.hub_token).repo_id
# Clone repo locally
repo = Repository(args.output_dir, clone_from=repo_id, token=args.hub_token)
api = HfApi()
repo_id = api.create_repo(repo_name, exist_ok=True, token=args.hub_token).repo_id
with open(os.path.join(args.output_dir, ".gitignore"), "w+") as gitignore:
if "step_*" not in gitignore:
@@ -720,8 +719,12 @@ def main():
)
if accelerator.is_main_process:
tokenizer.save_pretrained(args.output_dir)
repo.push_to_hub(
commit_message=f"Training in progress epoch {epoch}", blocking=False, auto_lfs_prune=True
api.upload_folder(
commit_message=f"Training in progress epoch {epoch}",
folder_path=args.output_dir,
repo_id=repo_id,
repo_type="model",
token=args.hub_token,
)
if args.checkpointing_steps == "epoch":
@@ -742,8 +745,13 @@ def main():
if accelerator.is_main_process:
tokenizer.save_pretrained(args.output_dir)
if args.push_to_hub:
repo.push_to_hub(commit_message="End of training", auto_lfs_prune=True)
api.upload_folder(
commit_message="End of training",
folder_path=args.output_dir,
repo_id=repo_id,
repo_type="model",
token=args.hub_token,
)
with open(os.path.join(args.output_dir, "all_results.json"), "w") as f:
json.dump({"perplexity": perplexity}, f)