Small fixes when resuming training #688
Workflow file for this run
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Run non-FA2-related unit tests | |
| on: | |
| push: | |
| branches: [ main ] | |
| # Only run tests if we modify the following files | |
| paths: | |
| - "src/**/*.py" | |
| - "examples/**/*.py" | |
| - "tests/**/*.py" | |
| pull_request: | |
| branches: [ '**' ] | |
| paths: | |
| - "src/**/*.py" | |
| - "examples/**/*.py" | |
| - "tests/**/*.py" | |
| jobs: | |
| tests: | |
| runs-on: | |
| group: aws-g4dn-metal | |
| container: | |
| image: runpod/pytorch:2.1.1-py3.10-cuda12.1.1-devel-ubuntu22.04 | |
| ports: | |
| - 80 | |
| options: --gpus all --shm-size "8G" | |
| steps: | |
| - uses: actions/checkout@v3 | |
| - name: Python environment | |
| run: | | |
| which python | |
| python --version | |
| - name: Check Pytorch version | |
| run: | | |
| nvidia-smi | |
| python -c "import torch; print('torch:', torch.__version__, torch)" | |
| python -c "import torch; print('CUDA available:', torch.cuda.is_available())" | |
| - name: Install nanotron's dependencies | |
| run: | | |
| python -m pip install --upgrade pip | |
| pip install packaging | |
| pip install wheel | |
| pip install -e . | |
| pip install -e .[dev] | |
| pip install -e .[test] | |
| pip install -e .[nanosets] | |
| - name: Show installed libraries and their versions | |
| run: pip freeze | tee installed.txt | |
| - name: Run nanotron tests | |
| # NOTE: -m "not fa2" will run all the unit tests that don't have the mark | |
| # "fa2" (these are FA2-related tests, we can't run it on T4) | |
| run: | | |
| pytest \ | |
| -m "not fa2" \ | |
| --color=yes \ | |
| --durations=0 \ | |
| --ignore tests/kernels \ | |
| --ignore tests/fp8 \ | |
| --verbose \ | |
| tests/ | |
| # NOTE: T4 can't run FA2, DoReMi's LLaMa needs FÀ | |
| # - name: Run DoReMi tests | |
| # # NOTE: -m "not fa2" will run all the unit tests that don't have the mark | |
| # # "fa2" (these are FA2-related tests, we can't run it on T4) | |
| # run: | | |
| # pip install -r examples/doremi/requirements.txt && \ | |
| # pytest \ | |
| # --color=yes \ | |
| # --durations=0 \ | |
| # --verbose \ | |
| # examples/doremi/tests/ |