Update README.md

README.md

@@ -24,6 +24,10 @@ The GOAT-70B-Storytelling model has been developed as an integral component with
  - **License:** llama2
  - **Context window length:** 4096 tokens
 
+### Training details
+
+For training, we apply the standard recipe with learning rate 1e-5, batch size per GPU 6, optimizer AdamW without weight decay and we train the model via ZeRO-3 on 64xH100 GPU cluster 
+
 ### Learn more
 
 - **Blog:** TBA