Update README.md

README.md

@@ -42,9 +42,11 @@ The model is trained using multiple Danish datasets and a context length of 512
 
 The model weights are initialized from the English [bert-base-uncased model](https://huggingface.co/bert-base-uncased) with new word token embeddings created for Danish using [WECHSEL](https://github.com/CPJKU/wechsel).
 
-Initially, only the word token embeddings are trained using XXXX samples. Finally, the whole model is trained using XXXX samples.
+Initially, only the word token embeddings are trained using 1.000.000 samples. Finally, the whole model is trained for 8 epochs.
 
 
 # Evaluation
 
-TO DO
+Performance of pretrained model was evaluated using [ScandEval](https://github.com/ScandEval/ScandEval).
+
+RESULTS