Removed Albert from benchmarks as it is too small and its perplexity is high.

README.md

@@ -181,7 +181,6 @@ EmuBert achieves a [(pseudo-)perplexity](https://doi.org/10.18653/v1/2020.acl-ma
 | -------------- | ---------- |
 | **EmuBert**    | **2.05**   |
 | Roberta        | 2.38       |
-| Albert v2      | 3.49       |
 | Bert (cased)   | 2.18       |
 | Bert (uncased) | 2.41       |