diff --git a/model/reward/instructor/README.md b/model/reward/instructor/README.md index a8b5ef33..29716dca 100644 --- a/model/reward/instructor/README.md +++ b/model/reward/instructor/README.md @@ -1,10 +1,31 @@ # Sections to train Reward Model (RM) +Trainer code based on huggingface. Should be compatible with deepspeed or accelerate -Currently we format + + +Requirements + +``` +wandb +evaluate +datasets +transformers +torch==1.12 +``` + +To train your model run this ```bash +python trainer.py configs/electra-base-dis-webgpt.yml +``` + + +## Dataset + +For now we only supports webgpt and summary dataset from OpenAI. Once open-asisstant dataset are available it will be added here. + + -``` \ No newline at end of file diff --git a/model/reward/instructor/requirements.txt b/model/reward/instructor/requirements.txt new file mode 100644 index 00000000..9fc45917 --- /dev/null +++ b/model/reward/instructor/requirements.txt @@ -0,0 +1,140 @@ +aiohttp==3.8.3 +aiosignal==1.3.1 +anyio==3.6.2 +argon2-cffi==21.3.0 +argon2-cffi-bindings==21.2.0 +arrow==1.2.3 +asttokens==2.2.1 +async-timeout==4.0.2 +attrs==22.2.0 +autopep8==2.0.1 +backcall==0.2.0 +beautifulsoup4==4.11.1 +bleach==5.0.1 +certifi==2022.12.7 +cffi==1.15.1 +charset-normalizer==2.1.1 +click==8.1.3 +comm==0.1.2 +datasets==2.8.0 +debugpy==1.6.4 +decorator==5.1.1 +defusedxml==0.7.1 +dill==0.3.6 +docker-pycreds==0.4.0 +entrypoints==0.4 +evaluate==0.4.0 +exceptiongroup==1.1.0 +executing==1.2.0 +fastjsonschema==2.16.2 +filelock==3.9.0 +fqdn==1.5.1 +frozenlist==1.3.3 +fsspec==2022.11.0 +gitdb==4.0.10 +GitPython==3.1.30 +huggingface-hub==0.11.1 +idna==3.4 +iniconfig==1.1.1 +ipykernel==6.19.4 +ipython==8.7.0 +ipython-genutils==0.2.0 +ipywidgets==8.0.4 +isoduration==20.11.0 +jedi==0.18.2 +Jinja2==3.1.2 +joblib==1.2.0 +jsonpointer==2.3 +jsonschema==4.17.3 +jupyter==1.0.0 +jupyter-console==6.4.4 +jupyter-events==0.5.0 +jupyter_client==7.4.8 +jupyter_core==5.1.1 +jupyter_server==2.0.6 +jupyter_server_terminals==0.4.3 +jupyterlab-pygments==0.2.2 +jupyterlab-widgets==3.0.5 +lightning-utilities==0.5.0 +MarkupSafe==2.1.1 +matplotlib-inline==0.1.6 +mistune==2.0.4 +multidict==6.0.4 +multiprocess==0.70.14 +nbclassic==0.4.8 +nbclient==0.7.2 +nbconvert==7.2.7 +nbformat==5.7.1 +nest-asyncio==1.5.6 +notebook==6.5.2 +notebook_shim==0.2.2 +numpy==1.24.1 +packaging==22.0 +pandas==1.5.2 +pandocfilters==1.5.0 +parso==0.8.3 +pathtools==0.1.2 +pexpect==4.8.0 +pickleshare==0.7.5 +platformdirs==2.6.2 +pluggy==1.0.0 +prometheus-client==0.15.0 +promise==2.3 +prompt-toolkit==3.0.36 +protobuf==3.20.1 +psutil==5.9.4 +ptyprocess==0.7.0 +pure-eval==0.2.2 +pyarrow==10.0.1 +pycodestyle==2.10.0 +pycparser==2.21 +Pygments==2.13.0 +pyrsistent==0.19.3 +pytest==7.2.0 +python-dateutil==2.8.2 +python-json-logger==2.0.4 +pytorch-lightning==1.8.6 +pytz==2022.7 +PyYAML==6.0 +pyzmq==24.0.1 +qtconsole==5.4.0 +QtPy==2.3.0 +regex==2022.10.31 +requests==2.28.1 +responses==0.18.0 +rfc3339-validator==0.1.4 +rfc3986-validator==0.1.1 +scikit-learn==1.2.0 +scipy==1.9.3 +Send2Trash==1.8.0 +sentry-sdk==1.12.1 +setproctitle==1.3.2 +shortuuid==1.0.11 +six==1.16.0 +smmap==5.0.0 +sniffio==1.3.0 +soupsieve==2.3.2.post1 +stack-data==0.6.2 +tensorboardX==2.5.1 +terminado==0.17.1 +threadpoolctl==3.1.0 +tinycss2==1.2.1 +tokenizers==0.13.2 +tomli==2.0.1 +torch==1.12.1+cu116 +torchmetrics==0.11.0 +tornado==6.2 +tqdm==4.64.1 +traitlets==5.8.0 +transformers==4.25.1 +typing_extensions==4.4.0 +uri-template==1.2.0 +urllib3==1.26.13 +wandb==0.13.7 +wcwidth==0.2.5 +webcolors==1.12 +webencodings==0.5.1 +websocket-client==1.4.2 +widgetsnbextension==4.0.5 +xxhash==3.2.0 +yarl==1.8.2