Update README.md

README.md

@@ -12,8 +12,14 @@ base_model:
 
 Simple model that was RL FT for 20 steps / epochs after SFT to reverse text using [prime-rl](https://github.com/PrimeIntellect-ai/prime-rl/) (RL Training) and [reverse-text](https://github.com/PrimeIntellect-ai/prime-environments/tree/main/environments/reverse_text) (RL Environment). See the improvement in results:
 
+## Comparison with SFT (base) model
+
+The reward (correctness score) distribution has improved for the RLFT model across all rollouts.
 ![](comparison.png)
 
+At an instance level, if we compare the best scores across rollouts, we see a mean improvement of 3.73%. But a maximum of ~30% and reduction of ~3%
+![](instance-level.png)
+
 ## Example Prompt & Reward
 
 **Task:** `reverse-text`