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

15
examples/tensorflow/question-answering/run_qa.py
View File

@@ -438,7 +438,8 @@ def main():
train_dataset = datasets["train"]
if data_args.max_train_samples is not None:
# We will select sample from whole data if agument is specified
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))
# Create train feature from dataset
train_dataset = train_dataset.map(
prepare_train_features,
@@ -449,7 +450,8 @@ def main():
)
if data_args.max_train_samples is not None:
# Number of samples might increase during Feature Creation, We select only specified max samples
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))
processed_datasets["train"] = train_dataset
# Validation preprocessing
@@ -505,7 +507,8 @@ def main():
eval_examples = datasets["validation"]
if data_args.max_eval_samples is not None:
# We will select sample from whole data
eval_examples = eval_examples.select(range(data_args.max_eval_samples))
max_eval_samples = min(len(eval_examples), data_args.max_eval_samples)
eval_examples = eval_examples.select(range(max_eval_samples))
# Validation Feature Creation
eval_dataset = eval_examples.map(
prepare_validation_features,
@@ -516,7 +519,8 @@ def main():
)
if data_args.max_eval_samples is not None:
# During Feature creation dataset samples might increase, we will select required samples again
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))
processed_datasets["validation"] = eval_dataset
if training_args.do_predict:
@@ -536,7 +540,8 @@ def main():
)
if data_args.max_predict_samples is not None:
# During Feature creation dataset samples might increase, we will select required samples again
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))
processed_datasets["test"] = predict_dataset
# endregion