Update README.md

README.md

@@ -11,13 +11,13 @@ License: mit
 ---
 hyperparams used to train this model:
 
-lr = 5e-4
-lr_schedule = constant
-wd=0.1
-adam_beta1=0.9, adam_beta2 = 0.95
-context length=512
-batch size=80
-gradient accumulation steps=16
+lr = 5e-4,
+lr_schedule = constant, 
+wd=0.1,
+adam_beta1=0.9, adam_beta2 = 0.95,
+context_length=512,
+batch_size=80,
+gradient_accumulation_steps=16
 
 ------ EXAMPLE USAGE ---