Update README.md

README.md

@@ -18,7 +18,7 @@ This model is a fine-tuned version of [distilbert-base-uncased](https://huggingf
 
 ## Model description
 
-More information needed
+This is an initial example of knowledge-distillation where the student loss is all cross-entropy loss $L_{CE}$ of the ground-truth labels and none of the distillation loss.
 
 ## Intended uses & limitations
 
@@ -26,7 +26,7 @@ More information needed
 
 ## Training and evaluation data
 
-The training and evaluation data come straight from the `train` and `validation` splits in the clinc_oos dataset, respectively; and tokenized using the distilbert-base-uncased tokenization.
+The training and evaluation data come straight from the `train` and `validation` splits in the clinc_oos dataset, respectively; and tokenized using the `distilbert-base-uncased` tokenization.
 
 ## Training procedure