Skip to content

GitLab

Unverified Commit 9f8fa4e9 authored by Eliza Szczechla's avatar Eliza Szczechla Committed by GitHub
Browse files

Use DataCollatorForSeq2Seq in run_summarization in all cases (#10856) 


Co-authored-by: default avatarEliza <eliza@habanero.tiger.com.pl>
parent a8d4d677
Show whitespace changes
Inline Side-by-side
Showing with 6 additions and 10 deletions
examples/seq2seq/run_summarization.py
View file @ 9f8fa4e9
...@@ -38,7 +38,6 @@ from transformers import ( ...@@ -38,7 +38,6 @@ from transformers import (
HfArgumentParser, HfArgumentParser,
Seq2SeqTrainer, Seq2SeqTrainer,
Seq2SeqTrainingArguments, Seq2SeqTrainingArguments,
default_data_collator,
set_seed, set_seed,
) )
from transformers.file_utils import is_offline_mode from transformers.file_utils import is_offline_mode
...@@ -466,9 +465,6 @@ def main(): ...@@ -466,9 +465,6 @@ def main():
# Data collator # Data collator
label_pad_token_id = -100 if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id label_pad_token_id = -100 if data_args.ignore_pad_token_for_loss else tokenizer.pad_token_id
if data_args.pad_to_max_length:
data_collator = default_data_collator
else:
data_collator = DataCollatorForSeq2Seq( data_collator = DataCollatorForSeq2Seq(
tokenizer, tokenizer,
model=model, model=model,
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment