Update README.md

README.md

@@ -17,7 +17,7 @@ Memphis-CoT is a finetune of [StableLM 3b 4e1t](stabilityai/stablelm-3b-4e1t) on
 Finetuning was performed using my [supertrainer2000](https://github.com/euclaise/supertrainer2000) framework, using my Adalite optimizer.
 
 
-### Training Procedure
+## Training Procedure
 I finetuned the model using an iterative rationale-bootstrapping procedure inspired by [STaR](https://research.google/pubs/star-self-taught-reasoner-bootstrapping-reasoning-with-reasoning/) and [SPIN](https://arxiv.org/abs/2401.01335)
 
 First, I finetuned the model on all the datasets using a [MixCE](https://arxiv.org/abs/2305.16958) loss and [NEFTune](https://arxiv.org/abs/2310.05914), for 2 epochs.
@@ -28,7 +28,7 @@ I then performed the following steps 3 times:
 
 This should be more efficient than either STaR or SPIN, as it uses a ranking loss rather than rejection sampling (unlike STaR), and verifies correctness instead of assuming all model responses are incorrect (unlike SPIN).
 
-### Hyperparameters
+## Hyperparameters
 
 For the initial supervised finetuning step:
 - Adalite optimizer, default hyperparameters of supertrainer2000 unless otherwise specified