Update evaluation results

README.md

@@ -194,12 +194,9 @@ learning rate warmup for 10,000 steps and linear decay of the learning rate afte
 
 When fine-tuned on downstream tasks, this model achieves the following results:
 
-Glue test results:
-
-| Task | MNLI-(m/mm) | QQP  | QNLI | SST-2 | CoLA | STS-B | MRPC | RTE  | Average |
-|:----:|:-----------:|:----:|:----:|:-----:|:----:|:-----:|:----:|:----:|:-------:|
-|      | 84.6/83.4   | 71.2 | 90.5 | 93.5  | 52.1 | 85.8  | 88.9 | 66.4 | 79.6    |
-
+Model                                    | SQUAD 1.1 F1/EM | Multi NLI Accuracy
+---------------------------------------- | :-------------: | :----------------:
+BERT-Large, Uncased (Original)           | 91.0/84.3       | 86.05
 
 ### BibTeX entry and citation info