Update README.md

README.md

@@ -31,7 +31,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 Numina-Math is a series of language models that are trained to solve math problems using tool integrated reasoning.
 Numina-Math-7b won the first AI Math Olympiad, with a score of 29/50 on the public and private tests sets.
-This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) with two stages on Math Question answers and multi-step synthetic generations using tool integrated reasoning.
+This model is a fine-tuned version of [deepseek-ai/deepseek-math-7b-base](https://huggingface.co/deepseek-ai/deepseek-math-7b-base) with two stages of training, first on a dataset with 863k math question answer pairs and then on a dataset with 73k examples of multi-step synthetic generations using tool integrated reasoning.
 
 
 ![image/png](https://cdn-uploads.huggingface.co/production/uploads/6200d0a443eb0913fa2df7cc/NyhBs_gzg40iwL995DO9L.png)