From a6d001aaffe755af23b94f7cb6ae0ce5cd908c27 Mon Sep 17 00:00:00 2001 From: Kevin Maik Jablonka Date: Sat, 25 Mar 2023 18:45:48 +0100 Subject: [PATCH 1/4] chore: disable pre-commit autocommit --- .pre-commit-config.yaml | 64 +++++++++++++++++++++-------------------- 1 file changed, 33 insertions(+), 31 deletions(-) diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index f258d8dda..d09df7ae1 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,39 +1,41 @@ --- ci: - autoupdate_schedule: quarterly + autoupdate_schedule: quarterly + autofix_prs: false + submodules: false repos: - - repo: https://github.com/pre-commit/pre-commit-hooks - rev: v4.4.0 - hooks: - - id: check-json - - id: check-yaml - - id: end-of-file-fixer - - id: trailing-whitespace - exclude: miscellaneous/structures/SiO2.xyz + - repo: https://github.com/pre-commit/pre-commit-hooks + rev: v4.4.0 + hooks: + - id: check-json + - id: check-yaml + - id: end-of-file-fixer + - id: trailing-whitespace + exclude: miscellaneous/structures/SiO2.xyz - - repo: https://github.com/jumanjihouse/pre-commit-hook-yamlfmt - rev: 0.2.2 - hooks: - - id: yamlfmt - exclude: ^experiments/configs + - repo: https://github.com/jumanjihouse/pre-commit-hook-yamlfmt + rev: 0.2.2 + hooks: + - id: yamlfmt + exclude: ^experiments/configs - - repo: https://github.com/psf/black - rev: 22.12.0 - hooks: - - id: black - language_version: python3 # Should be a command that runs python3.6+ + - repo: https://github.com/psf/black + rev: 22.12.0 + hooks: + - id: black + language_version: python3 # Should be a command that runs python3.6+ - - repo: https://github.com/PyCQA/flake8 - rev: 6.0.0 - hooks: - - id: flake8 - args: [--count, --show-source, --statistics] - additional_dependencies: - - flake8-bugbear==22.7.1 + - repo: https://github.com/PyCQA/flake8 + rev: 6.0.0 + hooks: + - id: flake8 + args: [--count, --show-source, --statistics] + additional_dependencies: + - flake8-bugbear==22.7.1 - - repo: https://github.com/pycqa/isort - rev: 5.12.0 - hooks: - - id: isort - args: [--profile, black, --filter-files] + - repo: https://github.com/pycqa/isort + rev: 5.12.0 + hooks: + - id: isort + args: [--profile, black, --filter-files] From a857a2c71c4f0a600f86a52ebfa457e430d066f4 Mon Sep 17 00:00:00 2001 From: Kevin Maik Jablonka Date: Sat, 25 Mar 2023 18:47:41 +0100 Subject: [PATCH 2/4] break too long line --- experiments/data/prepare_chemrxiv.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/experiments/data/prepare_chemrxiv.py b/experiments/data/prepare_chemrxiv.py index 3e161b2c3..ee1d903c4 100644 --- a/experiments/data/prepare_chemrxiv.py +++ b/experiments/data/prepare_chemrxiv.py @@ -39,5 +39,6 @@ # execute gpt-neox processing gpt_tool_path = f"{args.gptneox_dir}/tools/preprocess_data.py" os.system( - f"python {gpt_tool_path} --input {data_path} --output-prefix {save_path}/data --vocab /fsx/pile/20B_tokenizer.json --dataset-impl mmap --tokenizer-type HFTokenizer --append-eod" + f"python {gpt_tool_path} --input {data_path} --output-prefix {save_path}/data \ + --vocab /fsx/pile/20B_tokenizer.json --dataset-impl mmap --tokenizer-type HFTokenizer --append-eod" ) From 4e6652462ae319e974e53413c0e43f48e4b46361 Mon Sep 17 00:00:00 2001 From: Kevin Maik Jablonka Date: Sat, 25 Mar 2023 18:50:28 +0100 Subject: [PATCH 3/4] update yamls --- .pre-commit-config.yaml | 66 ++++++++++++++++++++--------------------- 1 file changed, 33 insertions(+), 33 deletions(-) diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index d09df7ae1..757033acc 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,41 +1,41 @@ --- ci: - autoupdate_schedule: quarterly - autofix_prs: false - submodules: false + autoupdate_schedule: quarterly + autofix_prs: false + submodules: false repos: - - repo: https://github.com/pre-commit/pre-commit-hooks - rev: v4.4.0 - hooks: - - id: check-json - - id: check-yaml - - id: end-of-file-fixer - - id: trailing-whitespace - exclude: miscellaneous/structures/SiO2.xyz + - repo: https://github.com/pre-commit/pre-commit-hooks + rev: v4.4.0 + hooks: + - id: check-json + - id: check-yaml + - id: end-of-file-fixer + - id: trailing-whitespace + exclude: miscellaneous/structures/SiO2.xyz - - repo: https://github.com/jumanjihouse/pre-commit-hook-yamlfmt - rev: 0.2.2 - hooks: - - id: yamlfmt - exclude: ^experiments/configs + - repo: https://github.com/jumanjihouse/pre-commit-hook-yamlfmt + rev: 0.2.2 + hooks: + - id: yamlfmt + exclude: ^experiments/configs - - repo: https://github.com/psf/black - rev: 22.12.0 - hooks: - - id: black - language_version: python3 # Should be a command that runs python3.6+ + - repo: https://github.com/psf/black + rev: 22.12.0 + hooks: + - id: black + language_version: python3 # Should be a command that runs python3.6+ - - repo: https://github.com/PyCQA/flake8 - rev: 6.0.0 - hooks: - - id: flake8 - args: [--count, --show-source, --statistics] - additional_dependencies: - - flake8-bugbear==22.7.1 + - repo: https://github.com/PyCQA/flake8 + rev: 6.0.0 + hooks: + - id: flake8 + args: [--count, --show-source, --statistics] + additional_dependencies: + - flake8-bugbear==22.7.1 - - repo: https://github.com/pycqa/isort - rev: 5.12.0 - hooks: - - id: isort - args: [--profile, black, --filter-files] + - repo: https://github.com/pycqa/isort + rev: 5.12.0 + hooks: + - id: isort + args: [--profile, black, --filter-files] From 1b5b0caa35230c247c42aea6edaff8110baa2b61 Mon Sep 17 00:00:00 2001 From: Kevin Maik Jablonka Date: Sun, 26 Mar 2023 17:30:06 +0200 Subject: [PATCH 4/4] chore: don't break line --- experiments/data/prepare_chemrxiv.py | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/experiments/data/prepare_chemrxiv.py b/experiments/data/prepare_chemrxiv.py index ee1d903c4..5a1735756 100644 --- a/experiments/data/prepare_chemrxiv.py +++ b/experiments/data/prepare_chemrxiv.py @@ -39,6 +39,5 @@ # execute gpt-neox processing gpt_tool_path = f"{args.gptneox_dir}/tools/preprocess_data.py" os.system( - f"python {gpt_tool_path} --input {data_path} --output-prefix {save_path}/data \ - --vocab /fsx/pile/20B_tokenizer.json --dataset-impl mmap --tokenizer-type HFTokenizer --append-eod" + f"python {gpt_tool_path} --input {data_path} --output-prefix {save_path}/data --vocab /fsx/pile/20B_tokenizer.json --dataset-impl mmap --tokenizer-type HFTokenizer --append-eod" # noqa: E501 )