Update README.md

README.md

@@ -19,11 +19,12 @@ Pythia-1b supervised finetuned with Anthropic-hh-rlhf dataset for 1 epoch.
 See [Pythia-1b](https://huggingface.co/EleutherAI/pythia-1b) for model details [(paper)](https://arxiv.org/abs/2101.00027). 
 
 
-# Benchmark results:
+# Benchmark raw results:
+
+Results for the base model are taken from the [Pythia paper](https://arxiv.org/abs/2101.00027).
 
 ## Zero shot
 
-Results for the base model are taken from the [Pythia paper](https://arxiv.org/abs/2101.00027).
 
 | Task             | 1B_base             | 1B_sft         |
 |------------------|----------------|----------------|