[CI] force upgrade HF dependencies & output py env (#2015)

.github/workflows/amd.yml

@@ -38,6 +38,10 @@ jobs:
           sudo apt-get update
           sudo apt-get install -y libaio-dev
 
+      - name: Python environment
+        run: |
+          pip list
+
       - name: Install transformers
         run: |
           git clone https://github.com/huggingface/transformers

.github/workflows/nv-lightning-v100.yml

@@ -34,11 +34,17 @@ jobs:
           pip install torch==1.8.2+cu111 torchvision==0.9.2+cu111 -f https://download.pytorch.org/whl/lts/1.8/torch_lts.html
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
+
+      - name: Python environment
+        run: |
+          pip list
+
       - name: Install deepspeed
         run: |
           pip uninstall --yes deepspeed
           pip install .[dev,autotuning]
           ds_report
+
       - name: PyTorch Lightning Tests
         run: |
           if [[ -d ./torch-extensions ]]; then rm -rf ./torch-extensions; fi

.github/workflows/nv-torch-latest-v100.yml

@@ -45,6 +45,10 @@ jobs:
           pip uninstall --yes transformers
           pip install .
 
+      - name: Python environment
+        run: |
+          pip list
+
       - name: Install deepspeed
         run: |
           pip uninstall --yes deepspeed

.github/workflows/nv-torch-nightly-v100.yml

@@ -38,6 +38,10 @@ jobs:
           pip uninstall --yes transformers
           pip install .
 
+      - name: Python environment
+        run: |
+          pip list
+
       - name: Install deepspeed
         run: |
           pip uninstall --yes deepspeed

.github/workflows/nv-torch12-p40.yml

@@ -35,6 +35,10 @@ jobs:
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
 
+      - name: Python environment
+        run: |
+          pip list
+
       - name: Install transformers
         run: |
           git clone https://github.com/huggingface/transformers

.github/workflows/nv-torch18-v100.yml

@@ -45,6 +45,10 @@ jobs:
           pip uninstall --yes transformers
           pip install .
 
+      - name: Python environment
+        run: |
+          pip list
+
       - name: Install deepspeed
         run: |
           pip uninstall --yes deepspeed

.github/workflows/nv-transformers-v100.yml

@@ -34,11 +34,17 @@ jobs:
           pip install torch==1.8.2+cu111 torchvision==0.9.2+cu111 -f https://download.pytorch.org/whl/lts/1.8/torch_lts.html
           python -c "import torch; print('torch:', torch.__version__, torch)"
           python -c "import torch; print('CUDA available:', torch.cuda.is_available())"
+
+      - name: Python environment
+        run: |
+          pip list
+
       - name: Install deepspeed
         run: |
           pip uninstall --yes deepspeed
           pip install .[dev,autotuning]
           ds_report
+
       - name: HF transformers tests
         run: |
           if [[ -d ./torch-extensions ]]; then rm -rf ./torch-extensions; fi
@@ -50,5 +56,8 @@ jobs:
           # scipy/sklearn required for tests, using the 'dev' extra forces torch re-install
           pip install .[testing]
           # find reqs used in ds integration tests
-          find examples/pytorch  -regextype posix-egrep -regex '.*(language-modeling|question-answering|summarization|image-classification|text-classification|translation).*/requirements.txt' -exec pip install -r {} \;
+          find examples/pytorch -regextype posix-egrep -regex '.*(language-modeling|question-answering|summarization|image-classification|text-classification|translation).*/requirements.txt' -exec grep -v 'torch' {} \; | xargs -I {} pip install --upgrade {}
+          # force protobuf version due to issues
+          pip install "protobuf<4.21.0"
+          pip list
           TORCH_EXTENSIONS_DIR=./torch-extensions RUN_SLOW=1 pytest --color=yes --durations=0 --verbose tests/deepspeed