Update README.md

README.md

@@ -11,6 +11,11 @@ First Version of Fine Tuned Bloomz-7B1 model on CoT dataset from Flan Data Colle
 
 * Epochs: 8
 * Batch Size : 5 instantaneous per device x 2 gradient accumulation steps x 8 gpus = 80
+* Max Length : 1024
+* Weight Decay : 0
+* Learning Rate : 5e-5
+* Learning Rate Scheduler Type : Linear
+* Number of warmup steps : 0
 * Machine : 8xA100 80GB
 
 **Dataset Details :**