Update README.md

README.md

@@ -52,9 +52,10 @@ Ikväll blir det grillat och det ser jag fram emot!"
 ```
 ## Training information
 
-`AI-Sweden-Models/Llama-3-8B` is a continuation of the pretraining process from `meta-llama/Meta-Llama-3-8B`. It was trained on a subset from [The Nordic Pile](https://arxiv.org/abs/2303.17183) containing Swedish, Norwegian and Danish.
+`AI-Sweden-Models/Llama-3-8B` is a continuation of the pretraining process from `meta-llama/Meta-Llama-3-8B`. 
+It was trained on a subset from [The Nordic Pile](https://arxiv.org/abs/2303.17183) containing Swedish, Norwegian and Danish.
 
-A total of 92 A100 GPUs were used, and roughly 250GB of data was processed.
+The dataset consists of 227 105 079 296 tokens.
 
 ## Benchmarks