diff --git a/justfile b/justfile
index b19850e..90f64bd 100644
--- a/justfile
+++ b/justfile
@@ -11,6 +11,7 @@ sft:
 
     cp accelerate_configs/deepspeed_zero3.yaml alignment-handbook/recipes/accelerate_configs/deepspeed_zero3b.yaml
     cp training_configs/llama-3-2-1b-base-sft.yaml alignment-handbook/recipes/llama-3-2-1b-base-sft.yaml
+    # .venv/src/alignment-handbook/
     cd alignment-handbook
     ACCELERATE_LOG_LEVEL=info accelerate launch --config_file recipes/accelerate_configs/deepspeed_zero3b.yaml --num_processes=1 scripts/run_sft.py recipes/llama-3-2-1b-base-sft.yaml
     # ACCELERATE_LOG_LEVEL=info accelerate launch --config_file ../accelerate_configs/deepspeed_zero3.yaml --num_processes=1 scripts/run_sft.py ../training_configs/llama-3-2-1b-base-sft.yaml
@@ -32,6 +33,7 @@ install:
     mamba install pytorch torchvision torchaudio pytorch-cuda=12.4 -c pytorch -c nvidia
 
     # install alignment handbook
+    # or use .venv/src/alignment-handbook/
     git clone https://github.com/huggingface/alignment-handbook.git
     cd ./alignment-handbook/
     python -m pip install .
diff --git a/poetry.lock b/poetry.lock
index 7d678e2..09ee235 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -394,6 +394,20 @@ files = [
     {file = "charset_normalizer-3.3.2-py3-none-any.whl", hash = "sha256:3e4d1f6587322d2788836a99c69062fbb091331ec940e02d12d179c1d53e25fc"},
 ]
 
+[[package]]
+name = "click"
+version = "8.1.7"
+description = "Composable command line interface toolkit"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "click-8.1.7-py3-none-any.whl", hash = "sha256:ae74fb96c20a0277a1d615f1e4d73c8414f5a98db8b799a7931d1582f3390c28"},
+    {file = "click-8.1.7.tar.gz", hash = "sha256:ca9853ad459e787e2192211578cc907e7594e294c7ccc834310722b41b9ca6de"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "platform_system == \"Windows\""}
+
 [[package]]
 name = "colorama"
 version = "0.4.6"
@@ -499,6 +513,20 @@ files = [
 graph = ["objgraph (>=1.7.2)"]
 profile = ["gprof2dot (>=2022.7.29)"]
 
+[[package]]
+name = "docker-pycreds"
+version = "0.4.0"
+description = "Python bindings for the docker credentials store API"
+optional = false
+python-versions = "*"
+files = [
+    {file = "docker-pycreds-0.4.0.tar.gz", hash = "sha256:6ce3270bcaf404cc4c3e27e4b6c70d3521deae82fb508767870fdbf772d584d4"},
+    {file = "docker_pycreds-0.4.0-py2.py3-none-any.whl", hash = "sha256:7266112468627868005106ec19cd0d722702d2b7d5912a28e19b826c3d37af49"},
+]
+
+[package.dependencies]
+six = ">=1.4.0"
+
 [[package]]
 name = "docstring-parser"
 version = "0.16"
@@ -715,6 +743,38 @@ test-downstream = ["aiobotocore (>=2.5.4,<3.0.0)", "dask-expr", "dask[dataframe,
 test-full = ["adlfs", "aiohttp (!=4.0.0a0,!=4.0.0a1)", "cloudpickle", "dask", "distributed", "dropbox", "dropboxdrivefs", "fastparquet", "fusepy", "gcsfs", "jinja2", "kerchunk", "libarchive-c", "lz4", "notebook", "numpy", "ocifs", "pandas", "panel", "paramiko", "pyarrow", "pyarrow (>=1)", "pyftpdlib", "pygit2", "pytest", "pytest-asyncio (!=0.22.0)", "pytest-benchmark", "pytest-cov", "pytest-mock", "pytest-recording", "pytest-rerunfailures", "python-snappy", "requests", "smbprotocol", "tqdm", "urllib3", "zarr", "zstandard"]
 tqdm = ["tqdm"]
 
+[[package]]
+name = "gitdb"
+version = "4.0.11"
+description = "Git Object Database"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "gitdb-4.0.11-py3-none-any.whl", hash = "sha256:81a3407ddd2ee8df444cbacea00e2d038e40150acfa3001696fe0dcf1d3adfa4"},
+    {file = "gitdb-4.0.11.tar.gz", hash = "sha256:bf5421126136d6d0af55bc1e7c1af1c397a34f5b7bd79e776cd3e89785c2b04b"},
+]
+
+[package.dependencies]
+smmap = ">=3.0.1,<6"
+
+[[package]]
+name = "gitpython"
+version = "3.1.43"
+description = "GitPython is a Python library used to interact with Git repositories"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "GitPython-3.1.43-py3-none-any.whl", hash = "sha256:eec7ec56b92aad751f9912a73404bc02ba212a23adb2c7098ee668417051a1ff"},
+    {file = "GitPython-3.1.43.tar.gz", hash = "sha256:35f314a9f878467f5453cc1fee295c3e18e52f1b99f10f6cf5b1682e968a9e7c"},
+]
+
+[package.dependencies]
+gitdb = ">=4.0.1,<5"
+
+[package.extras]
+doc = ["sphinx (==4.3.2)", "sphinx-autodoc-typehints", "sphinx-rtd-theme", "sphinxcontrib-applehelp (>=1.0.2,<=1.0.4)", "sphinxcontrib-devhelp (==1.0.2)", "sphinxcontrib-htmlhelp (>=2.0.0,<=2.0.1)", "sphinxcontrib-qthelp (==1.0.3)", "sphinxcontrib-serializinghtml (==1.1.5)"]
+test = ["coverage[toml]", "ddt (>=1.1.1,!=1.4.3)", "mock", "mypy", "pre-commit", "pytest (>=7.3.1)", "pytest-cov", "pytest-instafail", "pytest-mock", "pytest-sugar", "typing-extensions"]
+
 [[package]]
 name = "grpcio"
 version = "1.66.2"
@@ -1242,6 +1302,51 @@ files = [
 [package.extras]
 test = ["codecov (>=2.0.5)", "coverage (>=4.2)", "flake8 (>=3.0.4)", "pytest (>=4.5.0)", "pytest-cov (>=2.7.1)", "pytest-runner (>=5.1)", "pytest-virtualenv (>=1.7.0)", "virtualenv (>=15.0.3)"]
 
+[[package]]
+name = "numpy"
+version = "1.26.4"
+description = "Fundamental package for array computing in Python"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "numpy-1.26.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:9ff0f4f29c51e2803569d7a51c2304de5554655a60c5d776e35b4a41413830d0"},
+    {file = "numpy-1.26.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:2e4ee3380d6de9c9ec04745830fd9e2eccb3e6cf790d39d7b98ffd19b0dd754a"},
+    {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d209d8969599b27ad20994c8e41936ee0964e6da07478d6c35016bc386b66ad4"},
+    {file = "numpy-1.26.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ffa75af20b44f8dba823498024771d5ac50620e6915abac414251bd971b4529f"},
+    {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:62b8e4b1e28009ef2846b4c7852046736bab361f7aeadeb6a5b89ebec3c7055a"},
+    {file = "numpy-1.26.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:a4abb4f9001ad2858e7ac189089c42178fcce737e4169dc61321660f1a96c7d2"},
+    {file = "numpy-1.26.4-cp310-cp310-win32.whl", hash = "sha256:bfe25acf8b437eb2a8b2d49d443800a5f18508cd811fea3181723922a8a82b07"},
+    {file = "numpy-1.26.4-cp310-cp310-win_amd64.whl", hash = "sha256:b97fe8060236edf3662adfc2c633f56a08ae30560c56310562cb4f95500022d5"},
+    {file = "numpy-1.26.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:4c66707fabe114439db9068ee468c26bbdf909cac0fb58686a42a24de1760c71"},
+    {file = "numpy-1.26.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:edd8b5fe47dab091176d21bb6de568acdd906d1887a4584a15a9a96a1dca06ef"},
+    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7ab55401287bfec946ced39700c053796e7cc0e3acbef09993a9ad2adba6ca6e"},
+    {file = "numpy-1.26.4-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:666dbfb6ec68962c033a450943ded891bed2d54e6755e35e5835d63f4f6931d5"},
+    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:96ff0b2ad353d8f990b63294c8986f1ec3cb19d749234014f4e7eb0112ceba5a"},
+    {file = "numpy-1.26.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:60dedbb91afcbfdc9bc0b1f3f402804070deed7392c23eb7a7f07fa857868e8a"},
+    {file = "numpy-1.26.4-cp311-cp311-win32.whl", hash = "sha256:1af303d6b2210eb850fcf03064d364652b7120803a0b872f5211f5234b399f20"},
+    {file = "numpy-1.26.4-cp311-cp311-win_amd64.whl", hash = "sha256:cd25bcecc4974d09257ffcd1f098ee778f7834c3ad767fe5db785be9a4aa9cb2"},
+    {file = "numpy-1.26.4-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:b3ce300f3644fb06443ee2222c2201dd3a89ea6040541412b8fa189341847218"},
+    {file = "numpy-1.26.4-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:03a8c78d01d9781b28a6989f6fa1bb2c4f2d51201cf99d3dd875df6fbd96b23b"},
+    {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9fad7dcb1aac3c7f0584a5a8133e3a43eeb2fe127f47e3632d43d677c66c102b"},
+    {file = "numpy-1.26.4-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:675d61ffbfa78604709862923189bad94014bef562cc35cf61d3a07bba02a7ed"},
+    {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:ab47dbe5cc8210f55aa58e4805fe224dac469cde56b9f731a4c098b91917159a"},
+    {file = "numpy-1.26.4-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:1dda2e7b4ec9dd512f84935c5f126c8bd8b9f2fc001e9f54af255e8c5f16b0e0"},
+    {file = "numpy-1.26.4-cp312-cp312-win32.whl", hash = "sha256:50193e430acfc1346175fcbdaa28ffec49947a06918b7b92130744e81e640110"},
+    {file = "numpy-1.26.4-cp312-cp312-win_amd64.whl", hash = "sha256:08beddf13648eb95f8d867350f6a018a4be2e5ad54c8d8caed89ebca558b2818"},
+    {file = "numpy-1.26.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:7349ab0fa0c429c82442a27a9673fc802ffdb7c7775fad780226cb234965e53c"},
+    {file = "numpy-1.26.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:52b8b60467cd7dd1e9ed082188b4e6bb35aa5cdd01777621a1658910745b90be"},
+    {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d5241e0a80d808d70546c697135da2c613f30e28251ff8307eb72ba696945764"},
+    {file = "numpy-1.26.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f870204a840a60da0b12273ef34f7051e98c3b5961b61b0c2c1be6dfd64fbcd3"},
+    {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:679b0076f67ecc0138fd2ede3a8fd196dddc2ad3254069bcb9faf9a79b1cebcd"},
+    {file = "numpy-1.26.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:47711010ad8555514b434df65f7d7b076bb8261df1ca9bb78f53d3b2db02e95c"},
+    {file = "numpy-1.26.4-cp39-cp39-win32.whl", hash = "sha256:a354325ee03388678242a4d7ebcd08b5c727033fcff3b2f536aea978e15ee9e6"},
+    {file = "numpy-1.26.4-cp39-cp39-win_amd64.whl", hash = "sha256:3373d5d70a5fe74a2c1bb6d2cfd9609ecf686d47a2d7b1d37a8f3b6bf6003aea"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:afedb719a9dcfc7eaf2287b839d8198e06dcd4cb5d276a3df279231138e83d30"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:95a7476c59002f2f6c590b9b7b998306fba6a5aa646b1e22ddfeaf8f78c3a29c"},
+    {file = "numpy-1.26.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:7e50d0a0cc3189f9cb0aeb3a6a6af18c16f59f004b866cd2be1c14b36134a4a0"},
+    {file = "numpy-1.26.4.tar.gz", hash = "sha256:2a02aba9ed12e4ac4eb3ea9421c420301a0c6460d9830d74a9df87efa4912010"},
+]
+
 [[package]]
 name = "numpy"
 version = "2.1.1"
@@ -1523,9 +1628,9 @@ files = [
 
 [package.dependencies]
 numpy = [
+    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
     {version = ">=1.22.4", markers = "python_version < \"3.11\""},
     {version = ">=1.23.2", markers = "python_version == \"3.11\""},
-    {version = ">=1.26.0", markers = "python_version >= \"3.12\""},
 ]
 python-dateutil = ">=2.8.2"
 pytz = ">=2020.1"
@@ -1585,6 +1690,22 @@ docs-specific = ["black", "hf-doc-builder"]
 quality = ["black", "hf-doc-builder", "ruff (>=0.6.1,<0.7.0)"]
 test = ["black", "datasets", "diffusers (<0.21.0)", "hf-doc-builder", "parameterized", "pytest", "pytest-cov", "pytest-xdist", "ruff (>=0.6.1,<0.7.0)", "scipy"]
 
+[[package]]
+name = "platformdirs"
+version = "4.3.6"
+description = "A small Python package for determining appropriate platform-specific dirs, e.g. a `user data dir`."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "platformdirs-4.3.6-py3-none-any.whl", hash = "sha256:73e575e1408ab8103900836b97580d5307456908a03e92031bab39e4554cc3fb"},
+    {file = "platformdirs-4.3.6.tar.gz", hash = "sha256:357fb2acbc885b0419afd3ce3ed34564c13c9b95c89360cd9563f73aa5e2b907"},
+]
+
+[package.extras]
+docs = ["furo (>=2024.8.6)", "proselint (>=0.14)", "sphinx (>=8.0.2)", "sphinx-autodoc-typehints (>=2.4)"]
+test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=8.3.2)", "pytest-cov (>=5)", "pytest-mock (>=3.14)"]
+type = ["mypy (>=1.11.2)"]
+
 [[package]]
 name = "pluggy"
 version = "1.5.0"
@@ -1737,8 +1858,8 @@ files = [
 annotated-types = ">=0.6.0"
 pydantic-core = "2.23.4"
 typing-extensions = [
-    {version = ">=4.6.1", markers = "python_version < \"3.13\""},
     {version = ">=4.12.2", markers = "python_version >= \"3.13\""},
+    {version = ">=4.6.1", markers = "python_version < \"3.13\""},
 ]
 
 [package.extras]
@@ -2373,6 +2494,157 @@ files = [
     {file = "sentencepiece-0.2.0.tar.gz", hash = "sha256:a52c19171daaf2e697dc6cbe67684e0fa341b1248966f6aebb541de654d15843"},
 ]
 
+[[package]]
+name = "sentry-sdk"
+version = "2.14.0"
+description = "Python client for Sentry (https://sentry.io)"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "sentry_sdk-2.14.0-py2.py3-none-any.whl", hash = "sha256:b8bc3dc51d06590df1291b7519b85c75e2ced4f28d9ea655b6d54033503b5bf4"},
+    {file = "sentry_sdk-2.14.0.tar.gz", hash = "sha256:1e0e2eaf6dad918c7d1e0edac868a7bf20017b177f242cefe2a6bcd47955961d"},
+]
+
+[package.dependencies]
+certifi = "*"
+urllib3 = ">=1.26.11"
+
+[package.extras]
+aiohttp = ["aiohttp (>=3.5)"]
+anthropic = ["anthropic (>=0.16)"]
+arq = ["arq (>=0.23)"]
+asyncpg = ["asyncpg (>=0.23)"]
+beam = ["apache-beam (>=2.12)"]
+bottle = ["bottle (>=0.12.13)"]
+celery = ["celery (>=3)"]
+celery-redbeat = ["celery-redbeat (>=2)"]
+chalice = ["chalice (>=1.16.0)"]
+clickhouse-driver = ["clickhouse-driver (>=0.2.0)"]
+django = ["django (>=1.8)"]
+falcon = ["falcon (>=1.4)"]
+fastapi = ["fastapi (>=0.79.0)"]
+flask = ["blinker (>=1.1)", "flask (>=0.11)", "markupsafe"]
+grpcio = ["grpcio (>=1.21.1)", "protobuf (>=3.8.0)"]
+httpx = ["httpx (>=0.16.0)"]
+huey = ["huey (>=2)"]
+huggingface-hub = ["huggingface-hub (>=0.22)"]
+langchain = ["langchain (>=0.0.210)"]
+litestar = ["litestar (>=2.0.0)"]
+loguru = ["loguru (>=0.5)"]
+openai = ["openai (>=1.0.0)", "tiktoken (>=0.3.0)"]
+opentelemetry = ["opentelemetry-distro (>=0.35b0)"]
+opentelemetry-experimental = ["opentelemetry-distro"]
+pure-eval = ["asttokens", "executing", "pure-eval"]
+pymongo = ["pymongo (>=3.1)"]
+pyspark = ["pyspark (>=2.4.4)"]
+quart = ["blinker (>=1.1)", "quart (>=0.16.1)"]
+rq = ["rq (>=0.6)"]
+sanic = ["sanic (>=0.8)"]
+sqlalchemy = ["sqlalchemy (>=1.2)"]
+starlette = ["starlette (>=0.19.1)"]
+starlite = ["starlite (>=1.48)"]
+tornado = ["tornado (>=6)"]
+
+[[package]]
+name = "setproctitle"
+version = "1.3.3"
+description = "A Python module to customize the process title"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "setproctitle-1.3.3-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:897a73208da48db41e687225f355ce993167079eda1260ba5e13c4e53be7f754"},
+    {file = "setproctitle-1.3.3-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8c331e91a14ba4076f88c29c777ad6b58639530ed5b24b5564b5ed2fd7a95452"},
+    {file = "setproctitle-1.3.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bbbd6c7de0771c84b4aa30e70b409565eb1fc13627a723ca6be774ed6b9d9fa3"},
+    {file = "setproctitle-1.3.3-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c05ac48ef16ee013b8a326c63e4610e2430dbec037ec5c5b58fcced550382b74"},
+    {file = "setproctitle-1.3.3-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1342f4fdb37f89d3e3c1c0a59d6ddbedbde838fff5c51178a7982993d238fe4f"},
+    {file = "setproctitle-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc74e84fdfa96821580fb5e9c0b0777c1c4779434ce16d3d62a9c4d8c710df39"},
+    {file = "setproctitle-1.3.3-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:9617b676b95adb412bb69645d5b077d664b6882bb0d37bfdafbbb1b999568d85"},
+    {file = "setproctitle-1.3.3-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:6a249415f5bb88b5e9e8c4db47f609e0bf0e20a75e8d744ea787f3092ba1f2d0"},
+    {file = "setproctitle-1.3.3-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:38da436a0aaace9add67b999eb6abe4b84397edf4a78ec28f264e5b4c9d53cd5"},
+    {file = "setproctitle-1.3.3-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:da0d57edd4c95bf221b2ebbaa061e65b1788f1544977288bdf95831b6e44e44d"},
+    {file = "setproctitle-1.3.3-cp310-cp310-win32.whl", hash = "sha256:a1fcac43918b836ace25f69b1dca8c9395253ad8152b625064415b1d2f9be4fb"},
+    {file = "setproctitle-1.3.3-cp310-cp310-win_amd64.whl", hash = "sha256:200620c3b15388d7f3f97e0ae26599c0c378fdf07ae9ac5a13616e933cbd2086"},
+    {file = "setproctitle-1.3.3-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:334f7ed39895d692f753a443102dd5fed180c571eb6a48b2a5b7f5b3564908c8"},
+    {file = "setproctitle-1.3.3-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:950f6476d56ff7817a8fed4ab207727fc5260af83481b2a4b125f32844df513a"},
+    {file = "setproctitle-1.3.3-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:195c961f54a09eb2acabbfc90c413955cf16c6e2f8caa2adbf2237d1019c7dd8"},
+    {file = "setproctitle-1.3.3-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f05e66746bf9fe6a3397ec246fe481096664a9c97eb3fea6004735a4daf867fd"},
+    {file = "setproctitle-1.3.3-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b5901a31012a40ec913265b64e48c2a4059278d9f4e6be628441482dd13fb8b5"},
+    {file = "setproctitle-1.3.3-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:64286f8a995f2cd934082b398fc63fca7d5ffe31f0e27e75b3ca6b4efda4e353"},
+    {file = "setproctitle-1.3.3-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:184239903bbc6b813b1a8fc86394dc6ca7d20e2ebe6f69f716bec301e4b0199d"},
+    {file = "setproctitle-1.3.3-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:664698ae0013f986118064b6676d7dcd28fefd0d7d5a5ae9497cbc10cba48fa5"},
+    {file = "setproctitle-1.3.3-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:e5119a211c2e98ff18b9908ba62a3bd0e3fabb02a29277a7232a6fb4b2560aa0"},
+    {file = "setproctitle-1.3.3-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:417de6b2e214e837827067048f61841f5d7fc27926f2e43954567094051aff18"},
+    {file = "setproctitle-1.3.3-cp311-cp311-win32.whl", hash = "sha256:6a143b31d758296dc2f440175f6c8e0b5301ced3b0f477b84ca43cdcf7f2f476"},
+    {file = "setproctitle-1.3.3-cp311-cp311-win_amd64.whl", hash = "sha256:a680d62c399fa4b44899094027ec9a1bdaf6f31c650e44183b50d4c4d0ccc085"},
+    {file = "setproctitle-1.3.3-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:d4460795a8a7a391e3567b902ec5bdf6c60a47d791c3b1d27080fc203d11c9dc"},
+    {file = "setproctitle-1.3.3-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:bdfd7254745bb737ca1384dee57e6523651892f0ea2a7344490e9caefcc35e64"},
+    {file = "setproctitle-1.3.3-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:477d3da48e216d7fc04bddab67b0dcde633e19f484a146fd2a34bb0e9dbb4a1e"},
+    {file = "setproctitle-1.3.3-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ab2900d111e93aff5df9fddc64cf51ca4ef2c9f98702ce26524f1acc5a786ae7"},
+    {file = "setproctitle-1.3.3-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:088b9efc62d5aa5d6edf6cba1cf0c81f4488b5ce1c0342a8b67ae39d64001120"},
+    {file = "setproctitle-1.3.3-cp312-cp312-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a6d50252377db62d6a0bb82cc898089916457f2db2041e1d03ce7fadd4a07381"},
+    {file = "setproctitle-1.3.3-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:87e668f9561fd3a457ba189edfc9e37709261287b52293c115ae3487a24b92f6"},
+    {file = "setproctitle-1.3.3-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:287490eb90e7a0ddd22e74c89a92cc922389daa95babc833c08cf80c84c4df0a"},
+    {file = "setproctitle-1.3.3-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:4fe1c49486109f72d502f8be569972e27f385fe632bd8895f4730df3c87d5ac8"},
+    {file = "setproctitle-1.3.3-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4a6ba2494a6449b1f477bd3e67935c2b7b0274f2f6dcd0f7c6aceae10c6c6ba3"},
+    {file = "setproctitle-1.3.3-cp312-cp312-win32.whl", hash = "sha256:2df2b67e4b1d7498632e18c56722851ba4db5d6a0c91aaf0fd395111e51cdcf4"},
+    {file = "setproctitle-1.3.3-cp312-cp312-win_amd64.whl", hash = "sha256:f38d48abc121263f3b62943f84cbaede05749047e428409c2c199664feb6abc7"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:816330675e3504ae4d9a2185c46b573105d2310c20b19ea2b4596a9460a4f674"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:68f960bc22d8d8e4ac886d1e2e21ccbd283adcf3c43136161c1ba0fa509088e0"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:00e6e7adff74796ef12753ff399491b8827f84f6c77659d71bd0b35870a17d8f"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:53bc0d2358507596c22b02db079618451f3bd720755d88e3cccd840bafb4c41c"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ad6d20f9541f5f6ac63df553b6d7a04f313947f550eab6a61aa758b45f0d5657"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:c1c84beab776b0becaa368254801e57692ed749d935469ac10e2b9b825dbdd8e"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:507e8dc2891021350eaea40a44ddd887c9f006e6b599af8d64a505c0f718f170"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:b1067647ac7aba0b44b591936118a22847bda3c507b0a42d74272256a7a798e9"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:2e71f6365744bf53714e8bd2522b3c9c1d83f52ffa6324bd7cbb4da707312cd8"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-win32.whl", hash = "sha256:7f1d36a1e15a46e8ede4e953abb104fdbc0845a266ec0e99cc0492a4364f8c44"},
+    {file = "setproctitle-1.3.3-cp37-cp37m-win_amd64.whl", hash = "sha256:c9a402881ec269d0cc9c354b149fc29f9ec1a1939a777f1c858cdb09c7a261df"},
+    {file = "setproctitle-1.3.3-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:ff814dea1e5c492a4980e3e7d094286077054e7ea116cbeda138819db194b2cd"},
+    {file = "setproctitle-1.3.3-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:accb66d7b3ccb00d5cd11d8c6e07055a4568a24c95cf86109894dcc0c134cc89"},
+    {file = "setproctitle-1.3.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:554eae5a5b28f02705b83a230e9d163d645c9a08914c0ad921df363a07cf39b1"},
+    {file = "setproctitle-1.3.3-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a911b26264dbe9e8066c7531c0591cfab27b464459c74385b276fe487ca91c12"},
+    {file = "setproctitle-1.3.3-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:2982efe7640c4835f7355fdb4da313ad37fb3b40f5c69069912f8048f77b28c8"},
+    {file = "setproctitle-1.3.3-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:df3f4274b80709d8bcab2f9a862973d453b308b97a0b423a501bcd93582852e3"},
+    {file = "setproctitle-1.3.3-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:af2c67ae4c795d1674a8d3ac1988676fa306bcfa1e23fddb5e0bd5f5635309ca"},
+    {file = "setproctitle-1.3.3-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:af4061f67fd7ec01624c5e3c21f6b7af2ef0e6bab7fbb43f209e6506c9ce0092"},
+    {file = "setproctitle-1.3.3-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:37a62cbe16d4c6294e84670b59cf7adcc73faafe6af07f8cb9adaf1f0e775b19"},
+    {file = "setproctitle-1.3.3-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:a83ca086fbb017f0d87f240a8f9bbcf0809f3b754ee01cec928fff926542c450"},
+    {file = "setproctitle-1.3.3-cp38-cp38-win32.whl", hash = "sha256:059f4ce86f8cc92e5860abfc43a1dceb21137b26a02373618d88f6b4b86ba9b2"},
+    {file = "setproctitle-1.3.3-cp38-cp38-win_amd64.whl", hash = "sha256:ab92e51cd4a218208efee4c6d37db7368fdf182f6e7ff148fb295ecddf264287"},
+    {file = "setproctitle-1.3.3-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c7951820b77abe03d88b114b998867c0f99da03859e5ab2623d94690848d3e45"},
+    {file = "setproctitle-1.3.3-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5bc94cf128676e8fac6503b37763adb378e2b6be1249d207630f83fc325d9b11"},
+    {file = "setproctitle-1.3.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f5d9027eeda64d353cf21a3ceb74bb1760bd534526c9214e19f052424b37e42"},
+    {file = "setproctitle-1.3.3-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:2e4a8104db15d3462e29d9946f26bed817a5b1d7a47eabca2d9dc2b995991503"},
+    {file = "setproctitle-1.3.3-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c32c41ace41f344d317399efff4cffb133e709cec2ef09c99e7a13e9f3b9483c"},
+    {file = "setproctitle-1.3.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:cbf16381c7bf7f963b58fb4daaa65684e10966ee14d26f5cc90f07049bfd8c1e"},
+    {file = "setproctitle-1.3.3-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:e18b7bd0898398cc97ce2dfc83bb192a13a087ef6b2d5a8a36460311cb09e775"},
+    {file = "setproctitle-1.3.3-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:69d565d20efe527bd8a9b92e7f299ae5e73b6c0470f3719bd66f3cd821e0d5bd"},
+    {file = "setproctitle-1.3.3-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:ddedd300cd690a3b06e7eac90ed4452348b1348635777ce23d460d913b5b63c3"},
+    {file = "setproctitle-1.3.3-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:415bfcfd01d1fbf5cbd75004599ef167a533395955305f42220a585f64036081"},
+    {file = "setproctitle-1.3.3-cp39-cp39-win32.whl", hash = "sha256:21112fcd2195d48f25760f0eafa7a76510871bbb3b750219310cf88b04456ae3"},
+    {file = "setproctitle-1.3.3-cp39-cp39-win_amd64.whl", hash = "sha256:5a740f05d0968a5a17da3d676ce6afefebeeeb5ce137510901bf6306ba8ee002"},
+    {file = "setproctitle-1.3.3-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:6b9e62ddb3db4b5205c0321dd69a406d8af9ee1693529d144e86bd43bcb4b6c0"},
+    {file = "setproctitle-1.3.3-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:9e3b99b338598de0bd6b2643bf8c343cf5ff70db3627af3ca427a5e1a1a90dd9"},
+    {file = "setproctitle-1.3.3-pp310-pypy310_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:38ae9a02766dad331deb06855fb7a6ca15daea333b3967e214de12cfae8f0ef5"},
+    {file = "setproctitle-1.3.3-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:200ede6fd11233085ba9b764eb055a2a191fb4ffb950c68675ac53c874c22e20"},
+    {file = "setproctitle-1.3.3-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:0d3a953c50776751e80fe755a380a64cb14d61e8762bd43041ab3f8cc436092f"},
+    {file = "setproctitle-1.3.3-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e5e08e232b78ba3ac6bc0d23ce9e2bee8fad2be391b7e2da834fc9a45129eb87"},
+    {file = "setproctitle-1.3.3-pp37-pypy37_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f1da82c3e11284da4fcbf54957dafbf0655d2389cd3d54e4eaba636faf6d117a"},
+    {file = "setproctitle-1.3.3-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:aeaa71fb9568ebe9b911ddb490c644fbd2006e8c940f21cb9a1e9425bd709574"},
+    {file = "setproctitle-1.3.3-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:59335d000c6250c35989394661eb6287187854e94ac79ea22315469ee4f4c244"},
+    {file = "setproctitle-1.3.3-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c3ba57029c9c50ecaf0c92bb127224cc2ea9fda057b5d99d3f348c9ec2855ad3"},
+    {file = "setproctitle-1.3.3-pp38-pypy38_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d876d355c53d975c2ef9c4f2487c8f83dad6aeaaee1b6571453cb0ee992f55f6"},
+    {file = "setproctitle-1.3.3-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:224602f0939e6fb9d5dd881be1229d485f3257b540f8a900d4271a2c2aa4e5f4"},
+    {file = "setproctitle-1.3.3-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:d7f27e0268af2d7503386e0e6be87fb9b6657afd96f5726b733837121146750d"},
+    {file = "setproctitle-1.3.3-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f5e7266498cd31a4572378c61920af9f6b4676a73c299fce8ba93afd694f8ae7"},
+    {file = "setproctitle-1.3.3-pp39-pypy39_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:33c5609ad51cd99d388e55651b19148ea99727516132fb44680e1f28dd0d1de9"},
+    {file = "setproctitle-1.3.3-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:eae8988e78192fd1a3245a6f4f382390b61bce6cfcc93f3809726e4c885fa68d"},
+    {file = "setproctitle-1.3.3.tar.gz", hash = "sha256:c913e151e7ea01567837ff037a23ca8740192880198b7fbb90b16d181607caae"},
+]
+
+[package.extras]
+test = ["pytest"]
+
 [[package]]
 name = "setuptools"
 version = "75.1.0"
@@ -2418,6 +2690,17 @@ files = [
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
 ]
 
+[[package]]
+name = "smmap"
+version = "5.0.1"
+description = "A pure Python implementation of a sliding window memory map manager"
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "smmap-5.0.1-py3-none-any.whl", hash = "sha256:e6d8668fa5f93e706934a62d7b4db19c8d9eb8cf2adbb75ef1b675aa332b69da"},
+    {file = "smmap-5.0.1.tar.gz", hash = "sha256:dceeb6c0028fdb6734471eb07c0cd2aae706ccaecab45965ee83f11c8d3b1f62"},
+]
+
 [[package]]
 name = "sympy"
 version = "1.13.3"
@@ -2756,36 +3039,6 @@ build = ["cmake (>=3.20)", "lit"]
 tests = ["autopep8", "flake8", "isort", "llnl-hatchet", "numpy", "pytest", "scipy (>=1.7.1)"]
 tutorials = ["matplotlib", "pandas", "tabulate"]
 
-[[package]]
-name = "trl"
-version = "0.10.1"
-description = "Train transformer language models with reinforcement learning."
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "trl-0.10.1-py3-none-any.whl", hash = "sha256:4e389c68c3a49e9a19d8517092b7895898af917f707690e5167713cdc893c1bd"},
-    {file = "trl-0.10.1.tar.gz", hash = "sha256:1662e57a95daeb45b30ceea9fa08999b0ceacdc25bdaf615f5fc2807155a7cc7"},
-]
-
-[package.dependencies]
-accelerate = "*"
-datasets = "*"
-numpy = ">=1.18.2"
-torch = ">=1.4.0"
-transformers = ">=4.31.0"
-tyro = ">=0.5.11"
-
-[package.extras]
-benchmark = ["deepspeed", "ghapi", "openrlbenchmark (==0.2.1a5)", "requests", "wandb"]
-deepspeed = ["deepspeed (>=0.14.4)"]
-dev = ["Pillow", "bitsandbytes (<=0.41.1)", "deepspeed", "deepspeed (>=0.14.4)", "diffusers (>=0.18.0)", "ghapi", "huggingface-hub (>=0.22.2)", "liger-kernel-nightly (==0.1.1.dev20240828063745)", "llm-blender (>=0.0.2)", "openai (>=1.23.2)", "openrlbenchmark (==0.2.1a5)", "parameterized", "peft (>=0.8.0)", "pytest", "pytest-cov", "pytest-rerunfailures", "pytest-xdist", "requests", "scikit-learn", "wandb"]
-diffusers = ["diffusers (>=0.18.0)"]
-liger = ["liger-kernel-nightly (==0.1.1.dev20240828063745)"]
-llm-judge = ["huggingface-hub (>=0.22.2)", "llm-blender (>=0.0.2)", "openai (>=1.23.2)"]
-peft = ["peft (>=0.8.0)"]
-quantization = ["bitsandbytes (<=0.41.1)"]
-test = ["Pillow", "llm-blender (>=0.0.2)", "parameterized", "peft (>=0.8.0)", "pytest", "pytest-cov", "pytest-rerunfailures", "pytest-xdist", "scikit-learn"]
-
 [[package]]
 name = "trl"
 version = "0.11.1"
@@ -2800,7 +3053,10 @@ files = [
 [package.dependencies]
 accelerate = "*"
 datasets = "*"
-numpy = {version = ">=1.18.2", markers = "platform_system != \"Windows\""}
+numpy = [
+    {version = ">=1.18.2", markers = "platform_system != \"Windows\""},
+    {version = "<2", markers = "platform_system == \"Windows\""},
+]
 torch = ">=1.4.0"
 transformers = ">=4.40.0"
 tyro = ">=0.5.11"
@@ -2876,6 +3132,51 @@ h2 = ["h2 (>=4,<5)"]
 socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
 zstd = ["zstandard (>=0.18.0)"]
 
+[[package]]
+name = "wandb"
+version = "0.18.2"
+description = "A CLI and library for interacting with the Weights & Biases API."
+optional = false
+python-versions = ">=3.7"
+files = [
+    {file = "wandb-0.18.2-py3-none-any.whl", hash = "sha256:45eee0a41db776390de97c06dc1d72256acf9ffa63f1be46343670383c9235f7"},
+    {file = "wandb-0.18.2-py3-none-macosx_10_13_x86_64.whl", hash = "sha256:9aa061328605baeda926629ca0907c8c2f7eb7091b48d6be94e2696d20f2e721"},
+    {file = "wandb-0.18.2-py3-none-macosx_11_0_arm64.whl", hash = "sha256:4826089be875ac051e59ccc2af5fbaad534b5c3db0857d9a331e9c2210455855"},
+    {file = "wandb-0.18.2-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:eca6d14e0fcfb9ba9369733b977965cf02b22a5803dcb8a68be1087fda0e2543"},
+    {file = "wandb-0.18.2-py3-none-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ebedaf482e4064ecb9bb977e4c5704bfd23867bda8126700895b284f2cbebff9"},
+    {file = "wandb-0.18.2-py3-none-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:21ca6c2b7e75971fa55256e870bd80f9099b2a0bc31f2a6008c397157cb46aa8"},
+    {file = "wandb-0.18.2-py3-none-musllinux_1_2_x86_64.whl", hash = "sha256:827854221356aecfb749e6f95f09b22101612bff53836ef449779278de22146e"},
+    {file = "wandb-0.18.2-py3-none-win32.whl", hash = "sha256:cb7b1e40da03efac524879272913cea0df256d0ab9a1781c46bcb60ca7f7b18c"},
+    {file = "wandb-0.18.2-py3-none-win_amd64.whl", hash = "sha256:7cff3f0aa3619cec28bc5328c4763ae5e991741db09e52074deb42120863107c"},
+    {file = "wandb-0.18.2.tar.gz", hash = "sha256:1f1f574e311e9af061326ba213efa11d728310c0c3d4549ff17b51c768a62aa9"},
+]
+
+[package.dependencies]
+click = ">=7.1,<8.0.0 || >8.0.0"
+docker-pycreds = ">=0.4.0"
+gitpython = ">=1.0.0,<3.1.29 || >3.1.29"
+platformdirs = "*"
+protobuf = {version = ">=3.19.0,<4.21.0 || >4.21.0,<5.28.0 || >5.28.0,<6", markers = "python_version > \"3.9\" or sys_platform != \"linux\""}
+psutil = ">=5.0.0"
+pyyaml = "*"
+requests = ">=2.0.0,<3"
+sentry-sdk = ">=1.0.0"
+setproctitle = "*"
+setuptools = "*"
+
+[package.extras]
+aws = ["boto3"]
+azure = ["azure-identity", "azure-storage-blob"]
+gcp = ["google-cloud-storage"]
+importers = ["filelock", "mlflow", "polars (<=1.2.1)", "rich", "tenacity"]
+kubeflow = ["google-cloud-storage", "kubernetes", "minio", "sh"]
+launch = ["awscli", "azure-containerregistry", "azure-identity", "azure-storage-blob", "boto3", "botocore", "chardet", "google-auth", "google-cloud-aiplatform", "google-cloud-artifact-registry", "google-cloud-compute", "google-cloud-storage", "iso8601", "jsonschema", "kubernetes", "kubernetes-asyncio", "nbconvert", "nbformat", "optuna", "pydantic", "pyyaml (>=6.0.0)", "tomli", "typing-extensions"]
+media = ["bokeh", "imageio", "moviepy", "numpy", "pillow", "plotly (>=5.18.0)", "rdkit-pypi", "soundfile"]
+models = ["cloudpickle"]
+perf = ["orjson"]
+sweeps = ["sweeps (>=0.2.0)"]
+workspaces = ["wandb-workspaces"]
+
 [[package]]
 name = "werkzeug"
 version = "3.0.4"
@@ -3133,4 +3434,4 @@ multidict = ">=4.0"
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.10.9,<4.0"
-content-hash = "1762cc4fb0290de6ed1845f8edfb3e76f93a5d003995aac932f984226546894f"
+content-hash = "2b17bb7c50debbec5eb25515326a684e62e41e352ec9ca45a30be5ec01abedda"
diff --git a/pyproject.toml b/pyproject.toml
index 6ee15d5..da89f00 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -24,6 +24,7 @@ alignment-handbook = {git = "https://github.com/huggingface/alignment-handbook.g
 deepspeed = "^0.14"
 # transformers="~4.39.3"
 # python -m pip install flash-attn --no-build-isolation
+wandb = "^0.18.2"
 
 [tool.poetry.group.dev.dependencies]
 pytest = "*"
diff --git a/training_configs/llama-3-2-1b-base-sft.yaml b/training_configs/llama-3-2-1b-base-sft.yaml
index 6ed01ad..5392d29 100644
--- a/training_configs/llama-3-2-1b-base-sft.yaml
+++ b/training_configs/llama-3-2-1b-base-sft.yaml
@@ -18,7 +18,7 @@ bf16: true
 do_eval: true
 evaluation_strategy: steps
 eval_steps: 200
-gradient_accumulation_steps: 1
+gradient_accumulation_steps: 4
 gradient_checkpointing: true
 gradient_checkpointing_kwargs:
   use_reentrant: False
@@ -35,8 +35,8 @@ num_train_epochs: 1
 output_dir: /workspace/checkpoints_new/llama-3-2-1b-sft
 run_name: llama-3-2-1b-sft
 overwrite_output_dir: true
-per_device_eval_batch_size: 32
-per_device_train_batch_size: 32
+per_device_eval_batch_size: 8
+per_device_train_batch_size: 8
 push_to_hub: false
 remove_unused_columns: true
 report_to: