From 8232d89f0d3a04fc052a3af092dcc36071ca2f89 Mon Sep 17 00:00:00 2001
From: s424714 <filpat@st.amu.edu.pl>
Date: Sun, 7 May 2023 19:12:15 +0200
Subject: [PATCH] feat: add jenkins training process

---
 Jenkinsfile-training | 61 ++++++++++++++++++++++++++++++++++++++++++++
 src/main.py          | 20 ++++++++++-----
 2 files changed, 74 insertions(+), 7 deletions(-)
 create mode 100644 Jenkinsfile-training

diff --git a/Jenkinsfile-training b/Jenkinsfile-training
new file mode 100644
index 0000000..7542f0b
--- /dev/null
+++ b/Jenkinsfile-training
@@ -0,0 +1,61 @@
+node {
+    stage('Preparation') { 
+        properties([
+            parameters([
+                string(
+                    defaultValue: '2',
+                    description: 'Batch size for training process',
+                    name: 'BATCH_SIZE',
+                    trim: false
+                ),
+                string(
+                    defaultValue: '3',
+                    description: 'Number of training epochs',
+                    name: 'NUM_EPOCHS',
+                    trim: false
+                ),
+                string(
+                    defaultValue: '1e-6',
+                    description: 'Learning rate',
+                    name: 'LR',
+                    trim: false
+                ),
+            ])
+        ])
+    }
+
+    stage('Git clone') {
+        //cloning git repo
+        checkout([$class: 'GitSCM', branches: [[name: '*/master']], extensions: [], userRemoteConfigs: [[credentialsId: 's424714', url: 'https://git.wmi.amu.edu.pl/s424714/ium_424714']]])
+    }
+
+    stage('Dockerfile build') {
+
+
+            sh "chmod +x -R ${env.WORKSPACE}"
+
+            def dockerImage = docker.build("s424714-model")
+
+            dockerImage.inside {
+            stage("Docker: cloning artifacts"){
+                copyArtifacts fingerprintArtifacts: true, projectName: 's424714-create-dataset', selector: buildParameter('BUILD_SELECTOR')
+                sh 'mkdir -p ./data/dataset'
+                sh 'mv -t ./data/dataset train.csv test.csv val.csv'
+            }
+            stage("Docker: Running training model")
+            
+            {
+                sh 'python ./src/main.py --train --lr=$LR --batch=$BATCH_SIZE --epochs=$NUM_EPOCHS'
+                sh "cp ./results/model.pt ${WORKSPACE}" 
+            }
+
+        }
+
+    }
+
+    stage('Saving artefacts') {
+        echo 'Goodbye!'
+        sh 'ls'
+        archiveArtifacts artifacts: '*.pt' 
+    }
+}
\ No newline at end of file
diff --git a/src/main.py b/src/main.py
index b5f136f..a81190a 100644
--- a/src/main.py
+++ b/src/main.py
@@ -10,13 +10,6 @@ from evaluate import evaluate
 
 # SEED = 2137
 
-# Hyperparameters
-
-INITIAL_LR = 1e-6
-NUM_EPOCHS = 2
-BATCH_SIZE = 2
-
-
 # argument parser
 
 parser = argparse.ArgumentParser(
@@ -27,12 +20,25 @@ parser.add_argument("--train", action="store_true", default=False)
 parser.add_argument("--test", action="store_true", default=False)
 parser.add_argument("--model_path", type=str, default="results/model.pt")
 parser.add_argument("--results_path", type=str, default="results/results.csv")
+# HYPER PARAMETERS
+parser.add_argument("--batch", "-b", type=int, default=2)
+parser.add_argument("--learning_rate", "--lr", type=float, default=1e-6)
+parser.add_argument("--num_epochs", "--epochs", "-e", type=int, default=3)
 
 
 if __name__ == "__main__":
     args = parser.parse_args()
 
+    INITIAL_LR = args.learning_rate
+    NUM_EPOCHS = args.num_epochs
+    BATCH_SIZE = args.batch
+
+    print("INITIAL_LR: ", INITIAL_LR)
+    print("NUM_EPOCHS: ", NUM_EPOCHS)
+    print("BATCH_SIZE: ", BATCH_SIZE)
     print("CUDA: ", torch.cuda.is_available())
+
+    # raise
     # loading & spliting data
     news_dataset = NewsDataset(data_dir_path="data", data_lenght=1000)