Added basic Docker build and smoke test

Author: David Thrower

.github/workflows/automerge.yml

@@ -6,7 +6,7 @@ name: Python application
 on:
   push:
 
-    branches: [ "main", "307-tiny-stories-96-seq-len-hpo-run-from-305" ]
+    branches: [ "main", "309-from-307-dockerize-the-best-run-from-hpo-study" ]
 
 
 permissions:
@@ -35,12 +35,17 @@ jobs:
         flake8 . --count --select=E9,F63,F7,F82 --show-source --statistics
         # exit-zero treats all errors as warnings. The GitHub editor is 127 chars wide
         # flake8 . --count --exit-zero --max-complexity=10 --max-line-length=127 --statistics
+    - name: Build Docker Image
+      run: docker build -t davidt101/cerebros-llm:0001 .
+    - name: Run Smoke Test
+      run: docker run --rm davidt101/cerebros-llm:0001
+
 #    - name: Train Cerebros Composite LLM
 #      run: python3 temp-train-a-generative-llm.py
 #      timeout-minutes: 45
-    - name: HPO on LLM with Cerebros
-      run: python3 llm_train_hpo_script.py # python3 train_a_generative_llm.py
-      timeout-minutes: 120
+#    - name: HPO on LLM with Cerebros
+#      run: python3 llm_train_hpo_script.py # python3 train_a_generative_llm.py
+#      timeout-minutes: 120
 #    - name: Test distributed random search Ames by running
 #      run: python3 regression-example-ames-no-preproc.py
 #    - name: Test distributed random search Ames by running - Val set

Dockerfile

@@ -0,0 +1,14 @@
+
+FROM tensorflow/tensorflow:2.20.0-gpu
+
+# Add a volume to collect artifacts and cp -r [.] [path-to-folder]
+
+WORKDIR /opt
+RUN git clone https://github.com/david-thrower/cerebros-core-algorithm-alpha.git
+RUN git checkout 309-from-307-dockerize-the-best-run-from-hpo-study
+RUN git fetch
+RUN git checkout 309-from-307-dockerize-the-best-run-from-hpo-study
+RUN git pull origin 309-from-307-dockerize-the-best-run-from-hpo-study
+WORKDIR /opt/cerebros-core-algorithm-alpha
+RUN pip install -r docker-requirements.txt
+RUN python train_a_generative_llm.py

docker-requirements.txt

@@ -0,0 +1,22 @@
+# jax==0.5.3
+# jaxlib==0.5.3
+pendulum==3.0.0
+# tensorflow==2.20.0
+# numpy==2.3.5
+# pandas==2.3.3
+# pyvis==0.3.2
+# plotly==5.20.0
+matplotlib==3.10.7
+# imageio==2.37.2
+tqdm==4.67.1
+
+## from cicd req
+
+# tensorflow-text==2.19.0
+# keras-nlp==0.19.0
+scikit-learn==1.4.1.post1
+# tensorflow-hub==0.16.1
+transformers==4.54.0
+datasets==4.5.0
+# optuna==4.6.0
+mlflow==3.8.1