Update README.md

README.md

@@ -77,7 +77,7 @@ r = pipe(
 
 ### Training Data
 
-The model has been on a proprietary dataset of ~1.35M examples consisting of
+The model has been trained on a proprietary dataset of ~1.35M examples consisting of
  * High quality swedish instruct data
    * Single turn
    * Multi-turn
@@ -88,14 +88,14 @@ The model has been on a proprietary dataset of ~1.35M examples consisting of
 For training we used hugginface Accelerate and TRL.
 
 
-#### Preprocessing [optional]
+#### Preprocessing
 
 For efficiency, we packed all the examples into 8K context windows, reducing the number examples to ~12% of their original count. 
 
 
 #### Training Hyperparameters
 
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+- **Training regime:** 
 
 
 [More Information Needed]
@@ -104,8 +104,10 @@ For efficiency, we packed all the examples into 8K context windows, reducing the
 
 The model has been evaluated on [Scandeval](https://scandeval.com/swedish-nlg/) swedish subset. 
 
+The result of the individual metrics compared to other top scoring models
 ![metrics](assets/metrics.png)
 
+The mean score of all metrics compared to other models in the Swedish NLG category.
 ![mean-score](assets/mean_score.png)