From 0ed7696191f4c8cdf2d1fce8771fd4472d36bce8 Mon Sep 17 00:00:00 2001 From: Thomas Wolf Date: Thu, 8 Nov 2018 00:39:42 +0100 Subject: [PATCH] Updated MRPC results --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 0316696ec..5375ebb27 100644 --- a/README.md +++ b/README.md @@ -166,7 +166,7 @@ python run_classifier.py \ --output_dir /tmp/mrpc_output/ ``` -Our test ran on a few seeds with [the original implementation hyper-parameters](https://github.com/google-research/bert#sentence-and-sentence-pair-classification-tasks) gave evaluation results between 82 and 87. +Our test ran on a few seeds with [the original implementation hyper-parameters](https://github.com/google-research/bert#sentence-and-sentence-pair-classification-tasks) gave evaluation results between 84% and 88%. The second example fine-tunes `BERT-Base` on the SQuAD question answering task.