Update README.md

README.md

@@ -41,7 +41,7 @@ TODO: add example inference usage.
 
 ## Training Resources
 
-GALPACA 30B was fine-tuned in about 6 hours using 16 A100 80GB GPUS at an effective batch-size of 1024 and with a maximum context window of 384 tokens. This model was trained using DeepSpeed Stage 3 optimizations.
+GALPACA 30B was fine-tuned in about 6 hours using 16 A100 80GB GPUS using 16-bit mixed-precision at an effective batch-size of 1024 and with a maximum context window of 384 tokens. This model was trained using DeepSpeed Stage 3 optimizations.
 
 ## Performance and Limitations