Update README.md

README.md

@@ -32,18 +32,10 @@ Other training configuration:
 
 Evaluation Results on GLUE after pretraining (30k steps):
 
-| Task            | Score     |
-|----------------------|-----------|
-| CoLA-MattCorr         | 20.0      |
-| MRPC-F1             | 83.6    |
-| STS-B-Pearson             | 82.7      |
-| SST-2-Acc           | 89.7      |
-| QQP-F1           | 89.0      |
-| MNLI-m    | 79.7      |
-| MNLI-mm              | 80.1      |
-| QNLI-Acc              | 89.3      |
-| WNLI-Acc              | 31.0      |
-| RTE-Acc              | 57.4      |
+| Model           | CoLA-MattCorr | MRPC-F1 | STS-B-Pearson | SST-2-Acc | QQP-F1 | MNLI-m | MNLI-mm | QNLI-Acc | WNLI-Acc | RTE-Acc |
+|----------------|---------------|---------|---------------|-----------|--------|--------|---------|----------|----------|---------|
+| RoBERTa-medium (ours)         | 20.0          | 83.6    | 82.7          | 89.7      | 89.0   | 79.7   | 80.1    | 89.3     | 31.0     | 57.4    |
+| [BERT-medium](https://huggingface.co/google/bert_uncased_L-8_H-512_A-8) | 38.0 | 86.3 | 87.7 | 88.9 | 89.4 | 80.6 | 81.0 | 89.2 | 29.6 | 63.9 |
 
 Evaluation Scores Curve (AVG of scores) during pretraining: