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

[Examples] Added context manager to datasets map (#12367)

Browse Source 
* added cotext manager to datasets map

* fixed style and spaces

* fixed warning of deprecation

* changed desc
This commit is contained in:
Bhadresh Savani
2021-06-28 21:44:00 +05:30
committed by GitHub
parent d25ad34c82
commit 04dbea31a9
12 changed files with 242 additions and 213 deletions
Download Patch File Download Diff File Expand all files Collapse all files

45
examples/pytorch/token-classification/run_ner.py
View File

@@ -390,13 +390,14 @@ def main():
train_dataset = raw_datasets["train"]
if data_args.max_train_samples is not None:
train_dataset = train_dataset.select(range(data_args.max_train_samples))
train_dataset = train_dataset.map(
tokenize_and_align_labels,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
desc="Running tokenizer on train dataset",
)
with training_args.main_process_first(desc="train dataset map pre-processing"):
train_dataset = train_dataset.map(
tokenize_and_align_labels,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
desc="Running tokenizer on train dataset",
)
if training_args.do_eval:
if "validation" not in raw_datasets:
@@ -404,13 +405,14 @@ def main():
eval_dataset = raw_datasets["validation"]
if data_args.max_eval_samples is not None:
eval_dataset = eval_dataset.select(range(data_args.max_eval_samples))
eval_dataset = eval_dataset.map(
tokenize_and_align_labels,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
desc="Running tokenizer on validation dataset",
)
with training_args.main_process_first(desc="validation dataset map pre-processing"):
eval_dataset = eval_dataset.map(
tokenize_and_align_labels,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
desc="Running tokenizer on validation dataset",
)
if training_args.do_predict:
if "test" not in raw_datasets:
@@ -418,13 +420,14 @@ def main():
predict_dataset = raw_datasets["test"]
if data_args.max_predict_samples is not None:
predict_dataset = predict_dataset.select(range(data_args.max_predict_samples))
predict_dataset = predict_dataset.map(
tokenize_and_align_labels,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
desc="Running tokenizer on prediction dataset",
)
with training_args.main_process_first(desc="prediction dataset map pre-processing"):
predict_dataset = predict_dataset.map(
tokenize_and_align_labels,
batched=True,
num_proc=data_args.preprocessing_num_workers,
load_from_cache_file=not data_args.overwrite_cache,
desc="Running tokenizer on prediction dataset",
)
# Data collator
data_collator = DataCollatorForTokenClassification(tokenizer, pad_to_multiple_of=8 if training_args.fp16 else None)