Upload README.md with huggingface_hub

README.md

@@ -27,13 +27,13 @@ This model is part of the [StepLaw-N_1.0B-D_19.0B](https://huggingface.co/collec
 
 ### Training Parameters
 - **Learning rate (lr)**: 2.762e-03
-- **Batch size (bs)**: 2048
+- **Batch size (bs)**: 4194304
 - **Training iterations**: 4768
 - **Training tokens (D)**: 20.0B
 
 ## Model Description
 
-StepLaw models are trained with various hyperparameter settings to enable research on scaling laws and hyperparameter optimization. This specific model was trained with learning rate 2.762e-03 and batch size 2048 for 4768 iterations, using a total of 20.0B training tokens.
+StepLaw models are trained with various hyperparameter settings to enable research on scaling laws and hyperparameter optimization. This specific model was trained with learning rate 2.762e-03 and batch size 4194304 for 4768 iterations, using a total of 20.0B training tokens.
 
 ## Usage Example