Update README.md

README.md

@@ -13,7 +13,7 @@ base_model:
 ## Model summary
 
 This model is part of the 📐 [FineMath](https://huggingface.co/datasets/HuggingFaceTB/finemath) ablations, we continue pretraining [Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) base on different math datasets for 60B tokens.
-The model has 3.21B parameters and 4096 context length. It was trained on **160B tokens** using a mix of 40% [FineWeb-Edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) and 30% FineMath-3+ and 30% InfiWebMath-3+ from the  📐 [FineMath](https://huggingface.co/datasets/HuggingFaceTB/finemath) dataset.
+The model has 3.21B parameters and 4096 context length. It was trained on **60B tokens** using a mix of 50% FineMath-3+ and 50% InfiWebMath-3+ from the  📐 [FineMath](https://huggingface.co/datasets/HuggingFaceTB/finemath) dataset.
 
 - **License**: Apache-2
 - **Languages**: English