Create README.md

README.md

@@ -0,0 +1,25 @@
+---
+license: bigscience-openrail-m
+datasets:
+- manojpreveen/Instruction_Tuning
+---
+Instruction Tuned Bloomz-7B1 Model on Stanford Alpaca-2 Instruction Tuning dataset (outputs from ChatGPT) (52k data) using ***Colossal AI***
+
+**Base Model:** bigscience/bloomz-7b1
+
+**Training Details :** 
+* Epochs: 5
+* Batch Size : 16 instantaneous per device x 1 gradient accumulation steps x 8 gpus = 128
+* Max Length : 1024
+* Weight Decay : 0
+* Learning Rate : 2e-5
+* Learning Rate Scheduler Type : Cosine
+* Number of warmup steps : 30
+* Machine : 8xA100 80GB
+
+**Dataset Details :**
+
+Dataset : manojpreveen/Instruction_Tuning
+
+Files : 
+* stanford_alpaca_it_v2.csv