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

[examples] max samples can't be bigger than the len of dataset (#16501)

Browse Source 
* [examples] max samples can't be bigger than then len of dataset

* do tf and flax
This commit is contained in:
Stas Bekman
2022-03-30 12:33:16 -07:00
committed by GitHub
parent c4deb7b3ae
commit a73281e3e4
26 changed files with 154 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
examples/pytorch/token-classification/run_ner.py
View File

@@ -431,7 +431,8 @@ def main():
raise ValueError("--do_train requires a train dataset")
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))
max_train_samples = min(len(train_dataset), data_args.max_train_samples)
train_dataset = train_dataset.select(range(max_train_samples))
with training_args.main_process_first(desc="train dataset map pre-processing"):
train_dataset = train_dataset.map(
tokenize_and_align_labels,
@@ -446,7 +447,8 @@ def main():
raise ValueError("--do_eval requires a validation dataset")
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))
max_eval_samples = min(len(eval_dataset), data_args.max_eval_samples)
eval_dataset = eval_dataset.select(range(max_eval_samples))
with training_args.main_process_first(desc="validation dataset map pre-processing"):
eval_dataset = eval_dataset.map(
tokenize_and_align_labels,
@@ -461,7 +463,8 @@ def main():
raise ValueError("--do_predict requires a test dataset")
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))
max_predict_samples = min(len(predict_dataset), data_args.max_predict_samples)
predict_dataset = predict_dataset.select(range(max_predict_samples))
with training_args.main_process_first(desc="prediction dataset map pre-processing"):
predict_dataset = predict_dataset.map(
tokenize_and_align_labels,