Update README.md

README.md

@@ -35,9 +35,9 @@ After de-duplicating the data, we were left with a total of 54.5 GB of Bulgarian
 
 # Benchmark performance
 
-We tested performance of XLMR-BERTovski on benchmarks of XPOS, UPOS and NER. For Bulgarian, we used the data from the [Universal Dependencies](https://universaldependencies.org/) project. For Macedonian, we used the data sets created in the [babushka-bench](https://github.com/clarinsi/babushka-bench/) project. We also tested on a human translated version of the COPA data set. We compare performance to [BERTovski](https://huggingface.co/RVN/BERTovski) and the strong multi-lingual models XLMR-base and XLMR-large. For details regarding the fine-tuning procedure you can checkout our [Github](https://github.com/macocu/LanguageModels).
+We tested performance of XLMR-BERTovski on benchmarks of XPOS, UPOS and NER. For Bulgarian, we used the data from the [Universal Dependencies](https://universaldependencies.org/) project. For Macedonian, we used the data sets created in the [babushka-bench](https://github.com/clarinsi/babushka-bench/) project. We also tested on a human translated version of the COPA data set (for details see our [Github repo](https://github.com/RikVN/COPA)). We compare performance to [BERTovski](https://huggingface.co/RVN/BERTovski) and the strong multi-lingual models XLMR-base and XLMR-large. For details regarding the fine-tuning procedure you can checkout our [Github](https://github.com/macocu/LanguageModels).
 
-Scores are averages of three runs. We use the same hyperparameter settings for all models.
+Scores are averages of three runs, except for COPA, for which we use 10 runs. We use the same hyperparameter settings for all models.
 
 ## Bulgarian