Adds predict stage for glue tasks, and generate result files which can be submitted to gluebenchmark.com (#4463)

* Adds predict stage for glue tasks, and generate result files which could be submitted to gluebenchmark.com website.

* Use Split enum + always output the label name

Co-authored-by: Julien Chaumond <chaumond@gmail.com>
This commit is contained in:
Zhangyx
2020-05-21 21:17:44 +08:00
committed by GitHub
parent 271bedb485
commit 49296533ca
6 changed files with 140 additions and 45 deletions

View File

@@ -419,7 +419,7 @@ def main():
logger.info("Training/evaluation parameters %s", args)
# Prepare dataset for the GLUE task
eval_dataset = GlueDataset(args, tokenizer=tokenizer, evaluate=True)
eval_dataset = GlueDataset(args, tokenizer=tokenizer, mode="dev")
if args.data_subset > 0:
eval_dataset = Subset(eval_dataset, list(range(min(args.data_subset, len(eval_dataset)))))
eval_sampler = SequentialSampler(eval_dataset) if args.local_rank == -1 else DistributedSampler(eval_dataset)