diff --git a/JenkinsfileEval b/JenkinsfileEval
new file mode 100644
index 0000000..55fde7d
--- /dev/null
+++ b/JenkinsfileEval
@@ -0,0 +1,20 @@
+node {
+ stage('Preparation') {
+    checkout scm
+     copyArtifacts projectName: 's470618-metrics', filter: 'metrics.txt', fingerprintArtifacts: true, selector: lastSuccessful(), optional: true, target: './train-eval'
+     copyArtifacts projectName: 's470618-training', filter: '*.pt', fingerprintArtifacts: true, selector: lastSuccessful(), target: '.'
+ 
+ stage('Evaluate metrics') {
+            sh "pip install matplotlib"
+            sh "cd train-eval && ./eval.py"
+            sh "./plot_metrics.py"
+     }
+ }
+
+ stage('artifacts') {
+         echo 'saving artifacts'
+         archiveArtifacts 'metrics.txt', 'prediction.tsv', 'metrics.png'
+}
+}
+}
+
diff --git a/JenkinsfileTrain b/JenkinsfileTrain
index a3d613b..571b08c 100644
--- a/JenkinsfileTrain
+++ b/JenkinsfileTrain
@@ -1,6 +1,6 @@
 node {
     checkout scm
-    def dockerimage = docker.build("train-image", "./train-eval")
+    def dockerimage = docker.build("train-image", "dockerfile_train")
     dockerimage.inside {
  stage('Preparation') {
      properties([
diff --git a/train-eval/eval.py b/train-eval/eval.py
index 8368e49..936c717 100755
--- a/train-eval/eval.py
+++ b/train-eval/eval.py
@@ -45,7 +45,7 @@ print ("The accuracy is", acc)
 print ("The precission score is ", prec)
 print ("The recall score is ", recall)
 
-file = open('metrics.txt', 'w')
+file = open('metrics.txt', 'a')
 file.write(str(acc)  + '\t' + str(prec) + '\t' + str(recall))
 file.close()
 
diff --git a/train-eval/learning.py b/train-eval/learning.py
index 6ccaf74..8927fd5 100755
--- a/train-eval/learning.py
+++ b/train-eval/learning.py
@@ -3,7 +3,7 @@ import numpy as np
 import torch
 from torch import nn
 import pandas as pd
-import subprocess
+# import subprocess
 import sys
 
 from sklearn.model_selection import train_test_split
@@ -47,7 +47,7 @@ if __name__ == "__main__":
     Y = df[['Survived']]
     X.loc[:,('Sex')].replace(['female', 'male'], [0,1], inplace=True) #categorical data transformed to 
 
-    X_train, X_test, Y_train, Y_test = train_test_split(X,Y, random_state=45, test_size=0.2, shuffle=True) #split the date into train and test sets
+    X_train, X_test, Y_train, Y_test = train_test_split(X,Y, test_size=0.2, shuffle=True) #split the date into train and test sets
 
     testing_data = pd.concat([X_test, Y_test], axis=1)
     testing_data.to_csv('testing_data.csv', sep=',')
diff --git a/train-eval/plot_metrics.py b/train-eval/plot_metrics.py
new file mode 100755
index 0000000..4669e6c
--- /dev/null
+++ b/train-eval/plot_metrics.py
@@ -0,0 +1,19 @@
+#!/usr/bin/python3
+import matplotlib
+import matplotlib.pyplot as plt 
+
+data = []
+with open('metrics.txt', 'r') as metrics:
+    for line in metrics:
+        data.append(line.strip().split('\t'))
+
+
+# print(acc)
+labels = ['accuracy','precision','recall']
+builds = [x for x in range(len(data))]
+fig = plt.figure()
+ax = fig.add_subplot(1,1,1)
+for i in range(3):
+    ax.plot(builds, [data[x][i] for x in range(len(data))], label=labels[i])
+plt.legend()
+plt.savefig('metrics.png')
\ No newline at end of file