Update README.md

README.md

@@ -65,7 +65,7 @@ print(tokenizer.batch_decode(out_tokens, skip_special_tokens=False, clean_up_tok
 
 ## Training Resources
 
-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.
+GALPACA 30B was fine-tuned in about 6 hours using 16 A100 80GB GPUS, 16-bit mixed-precision, 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