From 05ac86699f925b8ee0c23f54e97799d77ae52411 Mon Sep 17 00:00:00 2001
From: DanYeong-Lee <81910252+DanYeong-Lee@users.noreply.github.com>
Date: Sun, 11 Jun 2023 15:33:39 +0900
Subject: [PATCH] Update README.md

---
 README.md | 20 +++++++++++++++++++-
 1 file changed, 19 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index b85b5e4..1c551c9 100644
--- a/README.md
+++ b/README.md
@@ -12,4 +12,22 @@ ______________________________________________________________________
 구정현, 이단영, 김상엽
 
 ## Solution Overview
-(WIP)
+(wip)
+
+
+## Running
+### Download dataset
+- Training and test data can be downloaded from [2022 Samsung AI Challenge (Materials Discovery)](https://dacon.io/competitions/official/235953/data).  
+- We assume that you appropriately downloaded the dataset into 'data' directory.
+
+### Train single model
+```
+python train.py configs/gem1.yaml 
+```
+- You can train your model using default hyperparameters we used in competition with above command.  
+- Trained model checkpoints and submission files (test_preds.csv) will be saved in 'outputs' directory. You can directly submit the csv file.
+- Just a single model achieved high performance (public score: 0.65 ~ 0.7), but for further improvement, we used stacking ensemble.
+
+### Stacking ensemble
+(wip)
+