Update README.md

README.md

@@ -95,7 +95,7 @@ Current SEA-LION models, including this commercially permissive release, have no
 
 ## Technical Specifications
 ### Fine-Tuning Details
-The Gemma2 9B CPT SEA-LIONv3.0 Instruct was fully fine-tuned, and aligned using 8x H100-80GB. 
+Gemma2 9B CPT SEA-LIONv3.0 Instruct was built using a combination of a full parameter fine-tune, alignment, alongside model merges of the best performing checkpoints. The training process for fine-tuning was approximately 15 hours, with alignment taking 2 hours on 8x H100-80GB GPUs.
 
 ## Data
 Gemma2 9B CPT SEA-LIONv3.0 Instruct was trained on a wide range of synthetic instructions alongside those hand-curated by the team, with the assistance of native speakers. In addition, special care was taken to ensure that the datasets used had commercially permissive licenses through verification with the original data source.