From a9aa7456ac824c9027385b149f405e4f5649273f Mon Sep 17 00:00:00 2001 From: Hao Tan Date: Tue, 26 May 2020 21:13:07 -0400 Subject: [PATCH] Add back --do_lower_case to uncased models (#4245) The option `--do_lower_case` is currently required by the uncased models (i.e., bert-base-uncased, bert-large-uncased). Results: BERT-BASE without --do_lower_case: 'exact': 73.83, 'f1': 82.22 BERT-BASE with --do_lower_case: 'exact': 81.02, 'f1': 88.34 --- examples/question-answering/README.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/examples/question-answering/README.md b/examples/question-answering/README.md index 4cbbe58651..d524957b1b 100644 --- a/examples/question-answering/README.md +++ b/examples/question-answering/README.md @@ -28,6 +28,7 @@ python run_squad.py \ --model_name_or_path bert-base-uncased \ --do_train \ --do_eval \ + --do_lower_case \ --train_file $SQUAD_DIR/train-v1.1.json \ --predict_file $SQUAD_DIR/dev-v1.1.json \ --per_gpu_train_batch_size 12 \ @@ -56,6 +57,7 @@ python -m torch.distributed.launch --nproc_per_node=8 ./examples/question-answer --model_name_or_path bert-large-uncased-whole-word-masking \ --do_train \ --do_eval \ + --do_lower_case \ --train_file $SQUAD_DIR/train-v1.1.json \ --predict_file $SQUAD_DIR/dev-v1.1.json \ --learning_rate 3e-5 \