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

added cache_dir=model_args.cache_dir to all example with cache_dir arg (#11220)

Browse Source
This commit is contained in:
Philipp Schmid
2021-04-13 18:35:18 +02:00
committed by GitHub
parent 3312e96bfb
commit 9fa2995993
12 changed files with 37 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/text-classification/run_glue.py
View File

@@ -239,7 +239,7 @@ def main():
# download the dataset.
if data_args.task_name is not None:
# Downloading and loading a dataset from the hub.
datasets = load_dataset("glue", data_args.task_name)
datasets = load_dataset("glue", data_args.task_name, cache_dir=model_args.cache_dir)
else:
# Loading a dataset from your local files.
# CSV/JSON training and evaluation files are needed.
@@ -263,10 +263,10 @@ def main():
if data_args.train_file.endswith(".csv"):
# Loading a dataset from local csv files
datasets = load_dataset("csv", data_files=data_files)
datasets = load_dataset("csv", data_files=data_files, cache_dir=model_args.cache_dir)
else:
# Loading a dataset from local json files
datasets = load_dataset("json", data_files=data_files)
datasets = load_dataset("json", data_files=data_files, cache_dir=model_args.cache_dir)
# See more about loading any type of standard or custom dataset at
# https://huggingface.co/docs/datasets/loading_datasets.html.

10
examples/text-classification/run_xnli.py
View File

@@ -209,17 +209,19 @@ def main():
# Downloading and loading xnli dataset from the hub.
if training_args.do_train:
if model_args.train_language is None:
train_dataset = load_dataset("xnli", model_args.language, split="train")
train_dataset = load_dataset("xnli", model_args.language, split="train", cache_dir=model_args.cache_dir)
else:
train_dataset = load_dataset("xnli", model_args.train_language, split="train")
train_dataset = load_dataset(
"xnli", model_args.train_language, split="train", cache_dir=model_args.cache_dir
)
label_list = train_dataset.features["label"].names
if training_args.do_eval:
eval_dataset = load_dataset("xnli", model_args.language, split="validation")
eval_dataset = load_dataset("xnli", model_args.language, split="validation", cache_dir=model_args.cache_dir)
label_list = eval_dataset.features["label"].names
if training_args.do_predict:
test_dataset = load_dataset("xnli", model_args.language, split="test")
test_dataset = load_dataset("xnli", model_args.language, split="test", cache_dir=model_args.cache_dir)
label_list = test_dataset.features["label"].names
# Labels