From d638b93dfec79f656d8d1b92ca221c9b993eba0c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Cheen=20Hau=2C=20=E4=BF=8A=E8=B1=AA?=
 <33478814+chtanch@users.noreply.github.com>
Date: Wed, 1 Nov 2023 09:39:53 +0800
Subject: [PATCH] Add test script and workflow for qlora fine-tuning (#9295)

* Add test script and workflow for qlora fine-tuning

* Test fix export model

* Download dataset

* Fix export model issue

* Reduce number of training steps

* Rename script

* Correction
---
 .github/workflows/llm_unit_tests.yml         | 19 +++++++++++++-
 python/llm/test/run-llm-example-tests-gpu.sh | 26 ++++++++++++++++++++
 2 files changed, 44 insertions(+), 1 deletion(-)
 create mode 100644 python/llm/test/run-llm-example-tests-gpu.sh

diff --git a/.github/workflows/llm_unit_tests.yml b/.github/workflows/llm_unit_tests.yml
index 698f0720..bb0e9336 100644
--- a/.github/workflows/llm_unit_tests.yml
+++ b/.github/workflows/llm_unit_tests.yml
@@ -207,6 +207,9 @@ jobs:
       - name: Set environment variables
         shell: bash
         run: |
+          echo "DATASET_DIR=${ORIGIN_DIR}/../datasets" >> "$GITHUB_ENV"
+          echo "ABIRATE_ENGLISH_QUOTES_PATH=${ORIGIN_DIR}/../datasets/abirate_english_quotes" >> "$GITHUB_ENV"
+
           echo "LLAMA2_7B_ORIGIN_PATH=${ORIGIN_DIR}/Llama-2-7b-chat-hf" >> "$GITHUB_ENV"
           echo "CHATGLM2_6B_ORIGIN_PATH=${ORIGIN_DIR}/chatglm2-6b" >> "$GITHUB_ENV"
           echo "FALCON_7B_ORIGIN_PATH=${ORIGIN_DIR}/falcon-7b-instruct-with-patch" >> "$GITHUB_ENV"
@@ -241,7 +244,7 @@ jobs:
           source /opt/intel/oneapi/setvars.sh
           bash python/llm/test/run-llm-install-tests.sh
 
-      - name: Download LLMs
+      - name: Download LLMs and datasets
         shell: bash
         run: |
           if [ ! -d $LLAMA2_7B_ORIGIN_PATH ]; then
@@ -260,6 +263,13 @@ jobs:
             echo "Directory $MPT_7B_ORIGIN_PATH not found. Downloading from FTP server..."
             wget -r -nH --no-verbose --cut-dirs=1 $LLM_FTP_URL/llm/mpt-7b-chat -P $ORIGIN_DIR
           fi
+          if [ ! -d $DATASET_DIR ]; then
+            mkdir -p $DATASET_DIR
+          fi
+          if [ ! -d $ABIRATE_ENGLISH_QUOTES_PATH ]; then
+            echo "Directory $ABIRATE_ENGLISH_QUOTES_PATH not found. Downloading from FTP server..."
+            wget -r -nH --no-verbose --cut-dirs=2 $LLM_FTP_URL/llm/datasets/abirate_english_quotes -P $DATASET_DIR
+          fi
           
       - name: Run LLM inference test
         shell: bash
@@ -267,3 +277,10 @@ jobs:
           source /opt/intel/oneapi/setvars.sh
           python -m pip install expecttest einops
           bash python/llm/test/run-llm-inference-tests-gpu.sh
+
+      - name: Run LLM example tests
+        shell: bash
+        run: |
+          python -m pip install transformers==4.34.0 peft==0.5.0 accelerate==0.23.0
+          source /opt/intel/oneapi/setvars.sh
+          bash python/llm/test/run-llm-example-tests-gpu.sh
\ No newline at end of file
diff --git a/python/llm/test/run-llm-example-tests-gpu.sh b/python/llm/test/run-llm-example-tests-gpu.sh
new file mode 100644
index 00000000..7271c432
--- /dev/null
+++ b/python/llm/test/run-llm-example-tests-gpu.sh
@@ -0,0 +1,26 @@
+#!/bin/bash
+
+export ANALYTICS_ZOO_ROOT=${ANALYTICS_ZOO_ROOT}
+
+set -e
+
+echo "# Start testing qlora fine-tuning"
+start=$(date "+%s")
+
+sed -i 's/max_steps=200/max_steps=2/; s/save_steps=100/save_steps=2/; s/logging_steps=20/logging_steps=1/' \
+    ${ANALYTICS_ZOO_ROOT}/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py
+
+python ${ANALYTICS_ZOO_ROOT}/python/llm/example/GPU/QLoRA-FineTuning/qlora_finetuning.py \
+--repo-id-or-model-path ${LLAMA2_7B_ORIGIN_PATH} \
+--dataset ${ABIRATE_ENGLISH_QUOTES_PATH}
+
+python ${ANALYTICS_ZOO_ROOT}/python/llm/example/GPU/QLoRA-FineTuning/export_merged_model.py \
+--repo-id-or-model-path ${LLAMA2_7B_ORIGIN_PATH} \
+--adapter_path ${PWD}/outputs/checkpoint-2 \
+--output_path ${PWD}/outputs/checkpoint-2-merged
+
+now=$(date "+%s")
+time=$((now-start))
+
+echo "qlora fine-tuning test finished"
+echo "Time used:$time seconds"