Update dependencies and Dockerfile configuration

Dockerfile

@@ -1,11 +1,21 @@
 # Use an official Python runtime as a parent image
 FROM python:3.11.1
 
+# Set up user and paths
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+# WORKDIR $HOME/app
+# COPY --chown=user . $HOME/app
+
 # Set the working directory in the container
-WORKDIR /app
+WORKDIR $HOME/app
 
 # Copy the current directory contents into the container at /usr/src/app
-COPY . .
+# COPY . .
+COPY --chown=user . $HOME/app
 
 # Install dependencies
 # RUN poetry config virtualenvs.create false \
@@ -13,8 +23,18 @@ COPY . .
 # Streamlit must be installed separately. Potentially this will cause an issue with dependencies in the future, but it's the only way it works.
 # RUN pip3 install streamlit  
 
+# Run the container as root
+USER root
+
+# Install Rust and Cargo
+RUN apt-get update 
+# RUN apt-get install -y curl build-essential 
+# RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y && \
+#     . $HOME/.cargo/env
+RUN pip install --upgrade pip
+
 #  Install dependencies
-RUN pip3 install -r requirements.txt
+RUN pip install -r requirements.txt
 
 # Make a port available to the world outside this container
 # The EXPOSE instruction informs Docker that the container listens on the specified network ports at runtime. Your container needs to listen to Streamlit’s (default) port 8501.
@@ -26,9 +46,6 @@ HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
 # Set the permissions for the script file
 # RUN chmod +x python 3 train_llm.py
 
-# Run the container as root
-USER root
-
 # Change permissions of the working directory
 # RUN chmod 777 /app  # Gives all users read, write, and exec permissions in the app directory.
 

poetry.lock

@@ -258,6 +258,17 @@ doc = ["Sphinx", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-
 test = ["anyio[trio]", "coverage[toml] (>=4.5)", "hypothesis (>=4.0)", "mock (>=4)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
 trio = ["trio (<0.22)"]
 
+[[package]]
+name = "appnope"
+version = "0.1.3"
+description = "Disable App Nap on macOS >= 10.9"
+optional = false
+python-versions = "*"
+files = [
+    {file = "appnope-0.1.3-py2.py3-none-any.whl", hash = "sha256:265a455292d0bd8a72453494fa24df5a11eb18373a60c7c0430889f22548605e"},
+    {file = "appnope-0.1.3.tar.gz", hash = "sha256:02bd91c4de869fbb1e1c50aafc4098827a7a54ab2f39d9dcba6c9547ed920e24"},
+]
+
 [[package]]
 name = "arrow"
 version = "1.3.0"
@@ -277,6 +288,24 @@ types-python-dateutil = ">=2.8.10"
 doc = ["doc8", "sphinx (>=7.0.0)", "sphinx-autobuild", "sphinx-autodoc-typehints", "sphinx_rtd_theme (>=1.3.0)"]
 test = ["dateparser (==1.*)", "pre-commit", "pytest", "pytest-cov", "pytest-mock", "pytz (==2021.1)", "simplejson (==3.*)"]
 
+[[package]]
+name = "asttokens"
+version = "2.4.1"
+description = "Annotate AST trees with source code positions"
+optional = false
+python-versions = "*"
+files = [
+    {file = "asttokens-2.4.1-py2.py3-none-any.whl", hash = "sha256:051ed49c3dcae8913ea7cd08e46a606dba30b79993209636c4875bc1d637bc24"},
+    {file = "asttokens-2.4.1.tar.gz", hash = "sha256:b03869718ba9a6eb027e134bfdf69f38a236d681c83c160d510768af11254ba0"},
+]
+
+[package.dependencies]
+six = ">=1.12.0"
+
+[package.extras]
+astroid = ["astroid (>=1,<2)", "astroid (>=2,<4)"]
+test = ["astroid (>=1,<2)", "astroid (>=2,<4)", "pytest"]
+
 [[package]]
 name = "attrs"
 version = "23.1.0"
@@ -765,6 +794,23 @@ colorama = {version = "*", markers = "sys_platform == \"win32\""}
 [package.extras]
 development = ["black", "flake8", "mypy", "pytest", "types-colorama"]
 
+[[package]]
+name = "comm"
+version = "0.2.0"
+description = "Jupyter Python Comm implementation, for usage in ipykernel, xeus-python etc."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "comm-0.2.0-py3-none-any.whl", hash = "sha256:2da8d9ebb8dd7bfc247adaff99f24dce705638a8042b85cb995066793e391001"},
+    {file = "comm-0.2.0.tar.gz", hash = "sha256:a517ea2ca28931c7007a7a99c562a0fa5883cfb48963140cf642c41c948498be"},
+]
+
+[package.dependencies]
+traitlets = ">=4"
+
+[package.extras]
+test = ["pytest"]
+
 [[package]]
 name = "contourpy"
 version = "1.2.0"
@@ -845,19 +891,19 @@ tests = ["pytest", "pytest-cov", "pytest-xdist"]
 
 [[package]]
 name = "datasets"
-version = "2.14.4"
+version = "2.14.7"
 description = "HuggingFace community-driven open-source library of datasets"
 optional = false
 python-versions = ">=3.8.0"
 files = [
-    {file = "datasets-2.14.4-py3-none-any.whl", hash = "sha256:29336bd316a7d827ccd4da2236596279b20ca2ac78f64c04c9483da7cbc2459b"},
-    {file = "datasets-2.14.4.tar.gz", hash = "sha256:ef29c2b5841de488cd343cfc26ab979bff77efa4d2285af51f1ad7db5c46a83b"},
+    {file = "datasets-2.14.7-py3-none-any.whl", hash = "sha256:1a64041a7da4f4130f736fc371c1f528b8ddd208cebe156400f65719bdbba79d"},
+    {file = "datasets-2.14.7.tar.gz", hash = "sha256:394cf9b4ec0694b25945977b16ad5d18d5c15fb0e94141713eb8ead7452caf9e"},
 ]
 
 [package.dependencies]
 aiohttp = "*"
 dill = ">=0.3.0,<0.3.8"
-fsspec = {version = ">=2021.11.1", extras = ["http"]}
+fsspec = {version = ">=2023.1.0,<=2023.10.0", extras = ["http"]}
 huggingface-hub = ">=0.14.0,<1.0.0"
 multiprocess = "*"
 numpy = ">=1.17"
@@ -865,6 +911,7 @@ packaging = "*"
 pandas = "*"
 Pillow = {version = ">=6.2.1", optional = true, markers = "extra == \"vision\""}
 pyarrow = ">=8.0.0"
+pyarrow-hotfix = "*"
 pyyaml = ">=5.1"
 requests = ">=2.19.0"
 tqdm = ">=4.62.1"
@@ -886,6 +933,44 @@ tests = ["Pillow (>=6.2.1)", "absl-py", "apache-beam (>=2.26.0,<2.44.0)", "elast
 torch = ["torch"]
 vision = ["Pillow (>=6.2.1)"]
 
+[[package]]
+name = "debugpy"
+version = "1.8.0"
+description = "An implementation of the Debug Adapter Protocol for Python"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "debugpy-1.8.0-cp310-cp310-macosx_11_0_x86_64.whl", hash = "sha256:7fb95ca78f7ac43393cd0e0f2b6deda438ec7c5e47fa5d38553340897d2fbdfb"},
+    {file = "debugpy-1.8.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ef9ab7df0b9a42ed9c878afd3eaaff471fce3fa73df96022e1f5c9f8f8c87ada"},
+    {file = "debugpy-1.8.0-cp310-cp310-win32.whl", hash = "sha256:a8b7a2fd27cd9f3553ac112f356ad4ca93338feadd8910277aff71ab24d8775f"},
+    {file = "debugpy-1.8.0-cp310-cp310-win_amd64.whl", hash = "sha256:5d9de202f5d42e62f932507ee8b21e30d49aae7e46d5b1dd5c908db1d7068637"},
+    {file = "debugpy-1.8.0-cp311-cp311-macosx_11_0_universal2.whl", hash = "sha256:ef54404365fae8d45cf450d0544ee40cefbcb9cb85ea7afe89a963c27028261e"},
+    {file = "debugpy-1.8.0-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:60009b132c91951354f54363f8ebdf7457aeb150e84abba5ae251b8e9f29a8a6"},
+    {file = "debugpy-1.8.0-cp311-cp311-win32.whl", hash = "sha256:8cd0197141eb9e8a4566794550cfdcdb8b3db0818bdf8c49a8e8f8053e56e38b"},
+    {file = "debugpy-1.8.0-cp311-cp311-win_amd64.whl", hash = "sha256:a64093656c4c64dc6a438e11d59369875d200bd5abb8f9b26c1f5f723622e153"},
+    {file = "debugpy-1.8.0-cp38-cp38-macosx_11_0_x86_64.whl", hash = "sha256:b05a6b503ed520ad58c8dc682749113d2fd9f41ffd45daec16e558ca884008cd"},
+    {file = "debugpy-1.8.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3c6fb41c98ec51dd010d7ed650accfd07a87fe5e93eca9d5f584d0578f28f35f"},
+    {file = "debugpy-1.8.0-cp38-cp38-win32.whl", hash = "sha256:46ab6780159eeabb43c1495d9c84cf85d62975e48b6ec21ee10c95767c0590aa"},
+    {file = "debugpy-1.8.0-cp38-cp38-win_amd64.whl", hash = "sha256:bdc5ef99d14b9c0fcb35351b4fbfc06ac0ee576aeab6b2511702e5a648a2e595"},
+    {file = "debugpy-1.8.0-cp39-cp39-macosx_11_0_x86_64.whl", hash = "sha256:61eab4a4c8b6125d41a34bad4e5fe3d2cc145caecd63c3fe953be4cc53e65bf8"},
+    {file = "debugpy-1.8.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:125b9a637e013f9faac0a3d6a82bd17c8b5d2c875fb6b7e2772c5aba6d082332"},
+    {file = "debugpy-1.8.0-cp39-cp39-win32.whl", hash = "sha256:57161629133113c97b387382045649a2b985a348f0c9366e22217c87b68b73c6"},
+    {file = "debugpy-1.8.0-cp39-cp39-win_amd64.whl", hash = "sha256:e3412f9faa9ade82aa64a50b602544efcba848c91384e9f93497a458767e6926"},
+    {file = "debugpy-1.8.0-py2.py3-none-any.whl", hash = "sha256:9c9b0ac1ce2a42888199df1a1906e45e6f3c9555497643a85e0bf2406e3ffbc4"},
+    {file = "debugpy-1.8.0.zip", hash = "sha256:12af2c55b419521e33d5fb21bd022df0b5eb267c3e178f1d374a63a2a6bdccd0"},
+]
+
+[[package]]
+name = "decorator"
+version = "5.1.1"
+description = "Decorators for Humans"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "decorator-5.1.1-py3-none-any.whl", hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186"},
+    {file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
+]
+
 [[package]]
 name = "diffusers"
 version = "0.21.4"
@@ -988,6 +1073,20 @@ tensorflow-gpu = ["tensorflow-gpu (>=2.2.0,!=2.6.0,!=2.6.1)"]
 tests = ["Werkzeug (>=1.0.1)", "absl-py", "bert-score (>=0.3.6)", "jiwer", "mauve-text", "pytest", "pytest-datadir", "pytest-xdist", "requests-file (>=1.5.1)", "rouge-score (>=0.1.2)", "sacrebleu", "sacremoses", "scikit-learn", "scipy", "sentencepiece", "seqeval", "six (>=1.15.0,<1.16.0)", "tensorflow (>=2.3,!=2.6.0,!=2.6.1)", "texttable (>=1.6.3)", "tldextract (>=3.1.0)", "toml (>=0.10.1)", "torch", "transformers", "trectools", "unidecode (>=1.3.4)"]
 torch = ["torch"]
 
+[[package]]
+name = "executing"
+version = "2.0.1"
+description = "Get the currently executing AST node of a frame, and other information"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "executing-2.0.1-py2.py3-none-any.whl", hash = "sha256:eac49ca94516ccc753f9fb5ce82603156e590b27525a8bc32cce8ae302eb61bc"},
+    {file = "executing-2.0.1.tar.gz", hash = "sha256:35afe2ce3affba8ee97f2d69927fa823b08b472b7b994e36a52a964b93d16147"},
+]
+
+[package.extras]
+tests = ["asttokens (>=2.1.0)", "coverage", "coverage-enable-subprocess", "ipython", "littleutils", "pytest", "rich"]
+
 [[package]]
 name = "fastapi"
 version = "0.104.1"
@@ -1187,13 +1286,13 @@ files = [
 
 [[package]]
 name = "fsspec"
-version = "2023.12.2"
+version = "2023.10.0"
 description = "File-system specification"
 optional = false
 python-versions = ">=3.8"
 files = [
-    {file = "fsspec-2023.12.2-py3-none-any.whl", hash = "sha256:d800d87f72189a745fa3d6b033b9dc4a34ad069f60ca60b943a63599f5501960"},
-    {file = "fsspec-2023.12.2.tar.gz", hash = "sha256:8548d39e8810b59c38014934f6b31e57f40c1b20f911f4cc2b85389c7e9bf0cb"},
+    {file = "fsspec-2023.10.0-py3-none-any.whl", hash = "sha256:346a8f024efeb749d2a5fca7ba8854474b1ff9af7c3faaf636a4548781136529"},
+    {file = "fsspec-2023.10.0.tar.gz", hash = "sha256:330c66757591df346ad3091a53bd907e15348c2ba17d63fd54f5c39c4457d2a5"},
 ]
 
 [package.dependencies]
@@ -1769,6 +1868,93 @@ files = [
     {file = "ipadic-1.0.0.tar.gz", hash = "sha256:f5923d31eca6131acaaf18ed28d8998665b1347b640d3a6476f64650e9a71c07"},
 ]
 
+[[package]]
+name = "ipykernel"
+version = "6.27.1"
+description = "IPython Kernel for Jupyter"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "ipykernel-6.27.1-py3-none-any.whl", hash = "sha256:dab88b47f112f9f7df62236511023c9bdeef67abc73af7c652e4ce4441601686"},
+    {file = "ipykernel-6.27.1.tar.gz", hash = "sha256:7d5d594b6690654b4d299edba5e872dc17bb7396a8d0609c97cb7b8a1c605de6"},
+]
+
+[package.dependencies]
+appnope = {version = "*", markers = "platform_system == \"Darwin\""}
+comm = ">=0.1.1"
+debugpy = ">=1.6.5"
+ipython = ">=7.23.1"
+jupyter-client = ">=6.1.12"
+jupyter-core = ">=4.12,<5.0.dev0 || >=5.1.dev0"
+matplotlib-inline = ">=0.1"
+nest-asyncio = "*"
+packaging = "*"
+psutil = "*"
+pyzmq = ">=20"
+tornado = ">=6.1"
+traitlets = ">=5.4.0"
+
+[package.extras]
+cov = ["coverage[toml]", "curio", "matplotlib", "pytest-cov", "trio"]
+docs = ["myst-parser", "pydata-sphinx-theme", "sphinx", "sphinx-autodoc-typehints", "sphinxcontrib-github-alt", "sphinxcontrib-spelling", "trio"]
+pyqt5 = ["pyqt5"]
+pyside6 = ["pyside6"]
+test = ["flaky", "ipyparallel", "pre-commit", "pytest (>=7.0)", "pytest-asyncio", "pytest-cov", "pytest-timeout"]
+
+[[package]]
+name = "ipython"
+version = "8.18.1"
+description = "IPython: Productive Interactive Computing"
+optional = false
+python-versions = ">=3.9"
+files = [
+    {file = "ipython-8.18.1-py3-none-any.whl", hash = "sha256:e8267419d72d81955ec1177f8a29aaa90ac80ad647499201119e2f05e99aa397"},
+    {file = "ipython-8.18.1.tar.gz", hash = "sha256:ca6f079bb33457c66e233e4580ebfc4128855b4cf6370dddd73842a9563e8a27"},
+]
+
+[package.dependencies]
+colorama = {version = "*", markers = "sys_platform == \"win32\""}
+decorator = "*"
+jedi = ">=0.16"
+matplotlib-inline = "*"
+pexpect = {version = ">4.3", markers = "sys_platform != \"win32\""}
+prompt-toolkit = ">=3.0.41,<3.1.0"
+pygments = ">=2.4.0"
+stack-data = "*"
+traitlets = ">=5"
+
+[package.extras]
+all = ["black", "curio", "docrepr", "exceptiongroup", "ipykernel", "ipyparallel", "ipywidgets", "matplotlib", "matplotlib (!=3.2.0)", "nbconvert", "nbformat", "notebook", "numpy (>=1.22)", "pandas", "pickleshare", "pytest (<7)", "pytest (<7.1)", "pytest-asyncio (<0.22)", "qtconsole", "setuptools (>=18.5)", "sphinx (>=1.3)", "sphinx-rtd-theme", "stack-data", "testpath", "trio", "typing-extensions"]
+black = ["black"]
+doc = ["docrepr", "exceptiongroup", "ipykernel", "matplotlib", "pickleshare", "pytest (<7)", "pytest (<7.1)", "pytest-asyncio (<0.22)", "setuptools (>=18.5)", "sphinx (>=1.3)", "sphinx-rtd-theme", "stack-data", "testpath", "typing-extensions"]
+kernel = ["ipykernel"]
+nbconvert = ["nbconvert"]
+nbformat = ["nbformat"]
+notebook = ["ipywidgets", "notebook"]
+parallel = ["ipyparallel"]
+qtconsole = ["qtconsole"]
+test = ["pickleshare", "pytest (<7.1)", "pytest-asyncio (<0.22)", "testpath"]
+test-extra = ["curio", "matplotlib (!=3.2.0)", "nbformat", "numpy (>=1.22)", "pandas", "pickleshare", "pytest (<7.1)", "pytest-asyncio (<0.22)", "testpath", "trio"]
+
+[[package]]
+name = "jedi"
+version = "0.19.1"
+description = "An autocompletion tool for Python that can be used for text editors."
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "jedi-0.19.1-py2.py3-none-any.whl", hash = "sha256:e983c654fe5c02867aef4cdfce5a2fbb4a50adc0af145f70504238f18ef5e7e0"},
+    {file = "jedi-0.19.1.tar.gz", hash = "sha256:cf0496f3651bc65d7174ac1b7d043eff454892c708a87d1b683e57b569927ffd"},
+]
+
+[package.dependencies]
+parso = ">=0.8.3,<0.9.0"
+
+[package.extras]
+docs = ["Jinja2 (==2.11.3)", "MarkupSafe (==1.1.1)", "Pygments (==2.8.1)", "alabaster (==0.7.12)", "babel (==2.9.1)", "chardet (==4.0.0)", "commonmark (==0.8.1)", "docutils (==0.17.1)", "future (==0.18.2)", "idna (==2.10)", "imagesize (==1.2.0)", "mock (==1.0.1)", "packaging (==20.9)", "pyparsing (==2.4.7)", "pytz (==2021.1)", "readthedocs-sphinx-ext (==2.1.4)", "recommonmark (==0.5.0)", "requests (==2.25.1)", "six (==1.15.0)", "snowballstemmer (==2.1.0)", "sphinx (==1.8.5)", "sphinx-rtd-theme (==0.4.3)", "sphinxcontrib-serializinghtml (==1.1.4)", "sphinxcontrib-websupport (==1.2.4)", "urllib3 (==1.26.4)"]
+qa = ["flake8 (==5.0.4)", "mypy (==0.971)", "types-setuptools (==67.2.0.1)"]
+testing = ["Django", "attrs", "colorama", "docopt", "pytest (<7.0.0)"]
+
 [[package]]
 name = "jinja2"
 version = "3.1.2"
@@ -1861,6 +2047,48 @@ files = [
 [package.dependencies]
 referencing = ">=0.31.0"
 
+[[package]]
+name = "jupyter-client"
+version = "8.6.0"
+description = "Jupyter protocol implementation and client libraries"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "jupyter_client-8.6.0-py3-none-any.whl", hash = "sha256:909c474dbe62582ae62b758bca86d6518c85234bdee2d908c778db6d72f39d99"},
+    {file = "jupyter_client-8.6.0.tar.gz", hash = "sha256:0642244bb83b4764ae60d07e010e15f0e2d275ec4e918a8f7b80fbbef3ca60c7"},
+]
+
+[package.dependencies]
+jupyter-core = ">=4.12,<5.0.dev0 || >=5.1.dev0"
+python-dateutil = ">=2.8.2"
+pyzmq = ">=23.0"
+tornado = ">=6.2"
+traitlets = ">=5.3"
+
+[package.extras]
+docs = ["ipykernel", "myst-parser", "pydata-sphinx-theme", "sphinx (>=4)", "sphinx-autodoc-typehints", "sphinxcontrib-github-alt", "sphinxcontrib-spelling"]
+test = ["coverage", "ipykernel (>=6.14)", "mypy", "paramiko", "pre-commit", "pytest", "pytest-cov", "pytest-jupyter[client] (>=0.4.1)", "pytest-timeout"]
+
+[[package]]
+name = "jupyter-core"
+version = "5.5.1"
+description = "Jupyter core package. A base package on which Jupyter projects rely."
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "jupyter_core-5.5.1-py3-none-any.whl", hash = "sha256:220dfb00c45f0d780ce132bb7976b58263f81a3ada6e90a9b6823785a424f739"},
+    {file = "jupyter_core-5.5.1.tar.gz", hash = "sha256:1553311a97ccd12936037f36b9ab4d6ae8ceea6ad2d5c90d94a909e752178e40"},
+]
+
+[package.dependencies]
+platformdirs = ">=2.5"
+pywin32 = {version = ">=300", markers = "sys_platform == \"win32\" and platform_python_implementation != \"PyPy\""}
+traitlets = ">=5.3"
+
+[package.extras]
+docs = ["myst-parser", "pydata-sphinx-theme", "sphinx-autodoc-typehints", "sphinxcontrib-github-alt", "sphinxcontrib-spelling", "traitlets"]
+test = ["ipykernel", "pre-commit", "pytest", "pytest-cov", "pytest-timeout"]
+
 [[package]]
 name = "kiwisolver"
 version = "1.4.5"
@@ -2182,6 +2410,20 @@ pillow = ">=8"
 pyparsing = ">=2.3.1"
 python-dateutil = ">=2.7"
 
+[[package]]
+name = "matplotlib-inline"
+version = "0.1.6"
+description = "Inline Matplotlib backend for Jupyter"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "matplotlib-inline-0.1.6.tar.gz", hash = "sha256:f887e5f10ba98e8d2b150ddcf4702c1e5f8b3a20005eb0f74bfdbd360ee6f304"},
+    {file = "matplotlib_inline-0.1.6-py3-none-any.whl", hash = "sha256:f1f41aab5328aa5aaea9b16d083b128102f8712542f819fe7e6a420ff581b311"},
+]
+
+[package.dependencies]
+traitlets = "*"
+
 [[package]]
 name = "mdurl"
 version = "0.1.2"
@@ -2337,6 +2579,17 @@ check = ["check-manifest", "flake8", "flake8-black", "isort (>=5.0.3)", "pygment
 test = ["coverage[toml] (>=5.2)", "coveralls (>=2.1.1)", "hypothesis", "pyannotate", "pytest", "pytest-cov"]
 type = ["mypy", "mypy-extensions"]
 
+[[package]]
+name = "nest-asyncio"
+version = "1.5.8"
+description = "Patch asyncio to allow nested event loops"
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "nest_asyncio-1.5.8-py3-none-any.whl", hash = "sha256:accda7a339a70599cb08f9dd09a67e0c2ef8d8d6f4c07f96ab203f2ae254e48d"},
+    {file = "nest_asyncio-1.5.8.tar.gz", hash = "sha256:25aa2ca0d2a5b5531956b9e273b45cf664cae2b145101d73b86b199978d48fdb"},
+]
+
 [[package]]
 name = "networkx"
 version = "3.2.1"
@@ -2786,6 +3039,21 @@ sql-other = ["SQLAlchemy (>=1.4.36)"]
 test = ["hypothesis (>=6.46.1)", "pytest (>=7.3.2)", "pytest-xdist (>=2.2.0)"]
 xml = ["lxml (>=4.8.0)"]
 
+[[package]]
+name = "parso"
+version = "0.8.3"
+description = "A Python Parser"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "parso-0.8.3-py2.py3-none-any.whl", hash = "sha256:c001d4636cd3aecdaf33cbb40aebb59b094be2a74c556778ef5576c175e19e75"},
+    {file = "parso-0.8.3.tar.gz", hash = "sha256:8c07be290bb59f03588915921e29e8a50002acaf2cdc5fa0e0114f91709fafa0"},
+]
+
+[package.extras]
+qa = ["flake8 (==3.8.3)", "mypy (==0.782)"]
+testing = ["docopt", "pytest (<6.0.0)"]
+
 [[package]]
 name = "peft"
 version = "0.7.1"
@@ -2815,6 +3083,20 @@ docs-specific = ["hf-doc-builder"]
 quality = ["black (>=22.0,<23.0)", "ruff (>=0.0.241)", "urllib3 (<=2.0.0)"]
 test = ["black (>=22.0,<23.0)", "datasets", "diffusers (<0.21.0)", "hf-doc-builder", "parameterized", "pytest", "pytest-cov", "pytest-xdist", "ruff (>=0.0.241)", "scipy", "urllib3 (<=2.0.0)"]
 
+[[package]]
+name = "pexpect"
+version = "4.9.0"
+description = "Pexpect allows easy control of interactive console applications."
+optional = false
+python-versions = "*"
+files = [
+    {file = "pexpect-4.9.0-py2.py3-none-any.whl", hash = "sha256:7236d1e080e4936be2dc3e326cec0af72acf9212a7e1d060210e70a47e253523"},
+    {file = "pexpect-4.9.0.tar.gz", hash = "sha256:ee7d41123f3c9911050ea2c2dac107568dc43b2d3b0c7557a33212c398ead30f"},
+]
+
+[package.dependencies]
+ptyprocess = ">=0.5"
+
 [[package]]
 name = "pillow"
 version = "10.0.0"
@@ -2884,6 +3166,35 @@ files = [
 docs = ["furo", "olefile", "sphinx (>=2.4)", "sphinx-copybutton", "sphinx-inline-tabs", "sphinx-removed-in", "sphinxext-opengraph"]
 tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"]
 
+[[package]]
+name = "platformdirs"
+version = "4.1.0"
+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-4.1.0-py3-none-any.whl", hash = "sha256:11c8f37bcca40db96d8144522d925583bdb7a31f7b0e37e3ed4318400a8e2380"},
+    {file = "platformdirs-4.1.0.tar.gz", hash = "sha256:906d548203468492d432bcb294d4bc2fff751bf84971fbb2c10918cc206ee420"},
+]
+
+[package.extras]
+docs = ["furo (>=2023.7.26)", "proselint (>=0.13)", "sphinx (>=7.1.1)", "sphinx-autodoc-typehints (>=1.24)"]
+test = ["appdirs (==1.4.4)", "covdefaults (>=2.3)", "pytest (>=7.4)", "pytest-cov (>=4.1)", "pytest-mock (>=3.11.1)"]
+
+[[package]]
+name = "prompt-toolkit"
+version = "3.0.43"
+description = "Library for building powerful interactive command lines in Python"
+optional = false
+python-versions = ">=3.7.0"
+files = [
+    {file = "prompt_toolkit-3.0.43-py3-none-any.whl", hash = "sha256:a11a29cb3bf0a28a387fe5122cdb649816a957cd9261dcedf8c9f1fef33eacf6"},
+    {file = "prompt_toolkit-3.0.43.tar.gz", hash = "sha256:3527b7af26106cbc65a040bcc84839a3566ec1b051bb0bfe953631e704b0ff7d"},
+]
+
+[package.dependencies]
+wcwidth = "*"
+
 [[package]]
 name = "protobuf"
 version = "4.23.4"
@@ -2934,6 +3245,31 @@ files = [
 [package.extras]
 test = ["enum34", "ipaddress", "mock", "pywin32", "wmi"]
 
+[[package]]
+name = "ptyprocess"
+version = "0.7.0"
+description = "Run a subprocess in a pseudo terminal"
+optional = false
+python-versions = "*"
+files = [
+    {file = "ptyprocess-0.7.0-py2.py3-none-any.whl", hash = "sha256:4b41f3967fce3af57cc7e94b888626c18bf37a083e3651ca8feeb66d492fef35"},
+    {file = "ptyprocess-0.7.0.tar.gz", hash = "sha256:5c5d0a3b48ceee0b48485e0c26037c0acd7d29765ca3fbb5cb3831d347423220"},
+]
+
+[[package]]
+name = "pure-eval"
+version = "0.2.2"
+description = "Safely evaluate AST nodes without side effects"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pure_eval-0.2.2-py3-none-any.whl", hash = "sha256:01eaab343580944bc56080ebe0a674b39ec44a945e6d09ba7db3cb8cec289350"},
+    {file = "pure_eval-0.2.2.tar.gz", hash = "sha256:2b45320af6dfaa1750f543d714b6d1c520a1688dec6fd24d339063ce0aaa9ac3"},
+]
+
+[package.extras]
+tests = ["pytest"]
+
 [[package]]
 name = "py-cpuinfo"
 version = "9.0.0"
@@ -3023,6 +3359,17 @@ files = [
 [package.dependencies]
 numpy = ">=1.16.6"
 
+[[package]]
+name = "pyarrow-hotfix"
+version = "0.6"
+description = ""
+optional = false
+python-versions = ">=3.5"
+files = [
+    {file = "pyarrow_hotfix-0.6-py3-none-any.whl", hash = "sha256:dcc9ae2d220dff0083be6a9aa8e0cdee5182ad358d4931fce825c545e5c89178"},
+    {file = "pyarrow_hotfix-0.6.tar.gz", hash = "sha256:79d3e030f7ff890d408a100ac16d6f00b14d44a502d7897cd9fc3e3a534e9945"},
+]
+
 [[package]]
 name = "pyasn1"
 version = "0.5.1"
@@ -3463,6 +3810,20 @@ files = [
 [package.dependencies]
 six = ">=1.5"
 
+[[package]]
+name = "python-dotenv"
+version = "1.0.0"
+description = "Read key-value pairs from a .env file and set them as environment variables"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "python-dotenv-1.0.0.tar.gz", hash = "sha256:a8df96034aae6d2d50a4ebe8216326c61c3eb64836776504fcca410e5937a3ba"},
+    {file = "python_dotenv-1.0.0-py3-none-any.whl", hash = "sha256:f5971a9226b701070a4bf2c38c89e5a3f0d64de8debda981d1db98583009122a"},
+]
+
+[package.extras]
+cli = ["click (>=5.0)"]
+
 [[package]]
 name = "python-multipart"
 version = "0.0.6"
@@ -3525,6 +3886,29 @@ files = [
 [package.dependencies]
 numpy = ">=1.22.4,<2.0"
 
+[[package]]
+name = "pywin32"
+version = "306"
+description = "Python for Window Extensions"
+optional = false
+python-versions = "*"
+files = [
+    {file = "pywin32-306-cp310-cp310-win32.whl", hash = "sha256:06d3420a5155ba65f0b72f2699b5bacf3109f36acbe8923765c22938a69dfc8d"},
+    {file = "pywin32-306-cp310-cp310-win_amd64.whl", hash = "sha256:84f4471dbca1887ea3803d8848a1616429ac94a4a8d05f4bc9c5dcfd42ca99c8"},
+    {file = "pywin32-306-cp311-cp311-win32.whl", hash = "sha256:e65028133d15b64d2ed8f06dd9fbc268352478d4f9289e69c190ecd6818b6407"},
+    {file = "pywin32-306-cp311-cp311-win_amd64.whl", hash = "sha256:a7639f51c184c0272e93f244eb24dafca9b1855707d94c192d4a0b4c01e1100e"},
+    {file = "pywin32-306-cp311-cp311-win_arm64.whl", hash = "sha256:70dba0c913d19f942a2db25217d9a1b726c278f483a919f1abfed79c9cf64d3a"},
+    {file = "pywin32-306-cp312-cp312-win32.whl", hash = "sha256:383229d515657f4e3ed1343da8be101000562bf514591ff383ae940cad65458b"},
+    {file = "pywin32-306-cp312-cp312-win_amd64.whl", hash = "sha256:37257794c1ad39ee9be652da0462dc2e394c8159dfd913a8a4e8eb6fd346da0e"},
+    {file = "pywin32-306-cp312-cp312-win_arm64.whl", hash = "sha256:5821ec52f6d321aa59e2db7e0a35b997de60c201943557d108af9d4ae1ec7040"},
+    {file = "pywin32-306-cp37-cp37m-win32.whl", hash = "sha256:1c73ea9a0d2283d889001998059f5eaaba3b6238f767c9cf2833b13e6a685f65"},
+    {file = "pywin32-306-cp37-cp37m-win_amd64.whl", hash = "sha256:72c5f621542d7bdd4fdb716227be0dd3f8565c11b280be6315b06ace35487d36"},
+    {file = "pywin32-306-cp38-cp38-win32.whl", hash = "sha256:e4c092e2589b5cf0d365849e73e02c391c1349958c5ac3e9d5ccb9a28e017b3a"},
+    {file = "pywin32-306-cp38-cp38-win_amd64.whl", hash = "sha256:e8ac1ae3601bee6ca9f7cb4b5363bf1c0badb935ef243c4733ff9a393b1690c0"},
+    {file = "pywin32-306-cp39-cp39-win32.whl", hash = "sha256:e25fd5b485b55ac9c057f67d94bc203f3f6595078d1fb3b458c9c28b7153a802"},
+    {file = "pywin32-306-cp39-cp39-win_amd64.whl", hash = "sha256:39b61c15272833b5c329a2989999dcae836b1eed650252ab1b7bfbe1d59f30f4"},
+]
+
 [[package]]
 name = "pyyaml"
 version = "6.0.1"
@@ -3584,6 +3968,111 @@ files = [
     {file = "PyYAML-6.0.1.tar.gz", hash = "sha256:bfdf460b1736c775f2ba9f6a92bca30bc2095067b8a9d77876d1fad6cc3b4a43"},
 ]
 
+[[package]]
+name = "pyzmq"
+version = "25.1.2"
+description = "Python bindings for 0MQ"
+optional = false
+python-versions = ">=3.6"
+files = [
+    {file = "pyzmq-25.1.2-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:e624c789359f1a16f83f35e2c705d07663ff2b4d4479bad35621178d8f0f6ea4"},
+    {file = "pyzmq-25.1.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:49151b0efece79f6a79d41a461d78535356136ee70084a1c22532fc6383f4ad0"},
+    {file = "pyzmq-25.1.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d9a5f194cf730f2b24d6af1f833c14c10f41023da46a7f736f48b6d35061e76e"},
+    {file = "pyzmq-25.1.2-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:faf79a302f834d9e8304fafdc11d0d042266667ac45209afa57e5efc998e3872"},
+    {file = "pyzmq-25.1.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7f51a7b4ead28d3fca8dda53216314a553b0f7a91ee8fc46a72b402a78c3e43d"},
+    {file = "pyzmq-25.1.2-cp310-cp310-manylinux_2_28_x86_64.whl", hash = "sha256:0ddd6d71d4ef17ba5a87becf7ddf01b371eaba553c603477679ae817a8d84d75"},
+    {file = "pyzmq-25.1.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:246747b88917e4867e2367b005fc8eefbb4a54b7db363d6c92f89d69abfff4b6"},
+    {file = "pyzmq-25.1.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:00c48ae2fd81e2a50c3485de1b9d5c7c57cd85dc8ec55683eac16846e57ac979"},
+    {file = "pyzmq-25.1.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:5a68d491fc20762b630e5db2191dd07ff89834086740f70e978bb2ef2668be08"},
+    {file = "pyzmq-25.1.2-cp310-cp310-win32.whl", hash = "sha256:09dfe949e83087da88c4a76767df04b22304a682d6154de2c572625c62ad6886"},
+    {file = "pyzmq-25.1.2-cp310-cp310-win_amd64.whl", hash = "sha256:fa99973d2ed20417744fca0073390ad65ce225b546febb0580358e36aa90dba6"},
+    {file = "pyzmq-25.1.2-cp311-cp311-macosx_10_15_universal2.whl", hash = "sha256:82544e0e2d0c1811482d37eef297020a040c32e0687c1f6fc23a75b75db8062c"},
+    {file = "pyzmq-25.1.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:01171fc48542348cd1a360a4b6c3e7d8f46cdcf53a8d40f84db6707a6768acc1"},
+    {file = "pyzmq-25.1.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:bc69c96735ab501419c432110016329bf0dea8898ce16fab97c6d9106dc0b348"},
+    {file = "pyzmq-25.1.2-cp311-cp311-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3e124e6b1dd3dfbeb695435dff0e383256655bb18082e094a8dd1f6293114642"},
+    {file = "pyzmq-25.1.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7598d2ba821caa37a0f9d54c25164a4fa351ce019d64d0b44b45540950458840"},
+    {file = "pyzmq-25.1.2-cp311-cp311-manylinux_2_28_x86_64.whl", hash = "sha256:d1299d7e964c13607efd148ca1f07dcbf27c3ab9e125d1d0ae1d580a1682399d"},
+    {file = "pyzmq-25.1.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:4e6f689880d5ad87918430957297c975203a082d9a036cc426648fcbedae769b"},
+    {file = "pyzmq-25.1.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:cc69949484171cc961e6ecd4a8911b9ce7a0d1f738fcae717177c231bf77437b"},
+    {file = "pyzmq-25.1.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:9880078f683466b7f567b8624bfc16cad65077be046b6e8abb53bed4eeb82dd3"},
+    {file = "pyzmq-25.1.2-cp311-cp311-win32.whl", hash = "sha256:4e5837af3e5aaa99a091302df5ee001149baff06ad22b722d34e30df5f0d9097"},
+    {file = "pyzmq-25.1.2-cp311-cp311-win_amd64.whl", hash = "sha256:25c2dbb97d38b5ac9fd15586e048ec5eb1e38f3d47fe7d92167b0c77bb3584e9"},
+    {file = "pyzmq-25.1.2-cp312-cp312-macosx_10_15_universal2.whl", hash = "sha256:11e70516688190e9c2db14fcf93c04192b02d457b582a1f6190b154691b4c93a"},
+    {file = "pyzmq-25.1.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:313c3794d650d1fccaaab2df942af9f2c01d6217c846177cfcbc693c7410839e"},
+    {file = "pyzmq-25.1.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1b3cbba2f47062b85fe0ef9de5b987612140a9ba3a9c6d2543c6dec9f7c2ab27"},
+    {file = "pyzmq-25.1.2-cp312-cp312-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:fc31baa0c32a2ca660784d5af3b9487e13b61b3032cb01a115fce6588e1bed30"},
+    {file = "pyzmq-25.1.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:02c9087b109070c5ab0b383079fa1b5f797f8d43e9a66c07a4b8b8bdecfd88ee"},
+    {file = "pyzmq-25.1.2-cp312-cp312-manylinux_2_28_x86_64.whl", hash = "sha256:f8429b17cbb746c3e043cb986328da023657e79d5ed258b711c06a70c2ea7537"},
+    {file = "pyzmq-25.1.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:5074adeacede5f810b7ef39607ee59d94e948b4fd954495bdb072f8c54558181"},
+    {file = "pyzmq-25.1.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:7ae8f354b895cbd85212da245f1a5ad8159e7840e37d78b476bb4f4c3f32a9fe"},
+    {file = "pyzmq-25.1.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:b264bf2cc96b5bc43ce0e852be995e400376bd87ceb363822e2cb1964fcdc737"},
+    {file = "pyzmq-25.1.2-cp312-cp312-win32.whl", hash = "sha256:02bbc1a87b76e04fd780b45e7f695471ae6de747769e540da909173d50ff8e2d"},
+    {file = "pyzmq-25.1.2-cp312-cp312-win_amd64.whl", hash = "sha256:ced111c2e81506abd1dc142e6cd7b68dd53747b3b7ae5edbea4578c5eeff96b7"},
+    {file = "pyzmq-25.1.2-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:7b6d09a8962a91151f0976008eb7b29b433a560fde056ec7a3db9ec8f1075438"},
+    {file = "pyzmq-25.1.2-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:967668420f36878a3c9ecb5ab33c9d0ff8d054f9c0233d995a6d25b0e95e1b6b"},
+    {file = "pyzmq-25.1.2-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5edac3f57c7ddaacdb4d40f6ef2f9e299471fc38d112f4bc6d60ab9365445fb0"},
+    {file = "pyzmq-25.1.2-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:0dabfb10ef897f3b7e101cacba1437bd3a5032ee667b7ead32bbcdd1a8422fe7"},
+    {file = "pyzmq-25.1.2-cp36-cp36m-musllinux_1_1_aarch64.whl", hash = "sha256:2c6441e0398c2baacfe5ba30c937d274cfc2dc5b55e82e3749e333aabffde561"},
+    {file = "pyzmq-25.1.2-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:16b726c1f6c2e7625706549f9dbe9b06004dfbec30dbed4bf50cbdfc73e5b32a"},
+    {file = "pyzmq-25.1.2-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:a86c2dd76ef71a773e70551a07318b8e52379f58dafa7ae1e0a4be78efd1ff16"},
+    {file = "pyzmq-25.1.2-cp36-cp36m-win32.whl", hash = "sha256:359f7f74b5d3c65dae137f33eb2bcfa7ad9ebefd1cab85c935f063f1dbb245cc"},
+    {file = "pyzmq-25.1.2-cp36-cp36m-win_amd64.whl", hash = "sha256:55875492f820d0eb3417b51d96fea549cde77893ae3790fd25491c5754ea2f68"},
+    {file = "pyzmq-25.1.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b8c8a419dfb02e91b453615c69568442e897aaf77561ee0064d789705ff37a92"},
+    {file = "pyzmq-25.1.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8807c87fa893527ae8a524c15fc505d9950d5e856f03dae5921b5e9aa3b8783b"},
+    {file = "pyzmq-25.1.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5e319ed7d6b8f5fad9b76daa0a68497bc6f129858ad956331a5835785761e003"},
+    {file = "pyzmq-25.1.2-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:3c53687dde4d9d473c587ae80cc328e5b102b517447456184b485587ebd18b62"},
+    {file = "pyzmq-25.1.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:9add2e5b33d2cd765ad96d5eb734a5e795a0755f7fc49aa04f76d7ddda73fd70"},
+    {file = "pyzmq-25.1.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:e690145a8c0c273c28d3b89d6fb32c45e0d9605b2293c10e650265bf5c11cfec"},
+    {file = "pyzmq-25.1.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:00a06faa7165634f0cac1abb27e54d7a0b3b44eb9994530b8ec73cf52e15353b"},
+    {file = "pyzmq-25.1.2-cp37-cp37m-win32.whl", hash = "sha256:0f97bc2f1f13cb16905a5f3e1fbdf100e712d841482b2237484360f8bc4cb3d7"},
+    {file = "pyzmq-25.1.2-cp37-cp37m-win_amd64.whl", hash = "sha256:6cc0020b74b2e410287e5942e1e10886ff81ac77789eb20bec13f7ae681f0fdd"},
+    {file = "pyzmq-25.1.2-cp38-cp38-macosx_10_15_universal2.whl", hash = "sha256:bef02cfcbded83473bdd86dd8d3729cd82b2e569b75844fb4ea08fee3c26ae41"},
+    {file = "pyzmq-25.1.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:e10a4b5a4b1192d74853cc71a5e9fd022594573926c2a3a4802020360aa719d8"},
+    {file = "pyzmq-25.1.2-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:8c5f80e578427d4695adac6fdf4370c14a2feafdc8cb35549c219b90652536ae"},
+    {file = "pyzmq-25.1.2-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:5dde6751e857910c1339890f3524de74007958557593b9e7e8c5f01cd919f8a7"},
+    {file = "pyzmq-25.1.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ea1608dd169da230a0ad602d5b1ebd39807ac96cae1845c3ceed39af08a5c6df"},
+    {file = "pyzmq-25.1.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:0f513130c4c361201da9bc69df25a086487250e16b5571ead521b31ff6b02220"},
+    {file = "pyzmq-25.1.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:019744b99da30330798bb37df33549d59d380c78e516e3bab9c9b84f87a9592f"},
+    {file = "pyzmq-25.1.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:2e2713ef44be5d52dd8b8e2023d706bf66cb22072e97fc71b168e01d25192755"},
+    {file = "pyzmq-25.1.2-cp38-cp38-win32.whl", hash = "sha256:07cd61a20a535524906595e09344505a9bd46f1da7a07e504b315d41cd42eb07"},
+    {file = "pyzmq-25.1.2-cp38-cp38-win_amd64.whl", hash = "sha256:eb7e49a17fb8c77d3119d41a4523e432eb0c6932187c37deb6fbb00cc3028088"},
+    {file = "pyzmq-25.1.2-cp39-cp39-macosx_10_15_universal2.whl", hash = "sha256:94504ff66f278ab4b7e03e4cba7e7e400cb73bfa9d3d71f58d8972a8dc67e7a6"},
+    {file = "pyzmq-25.1.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:6dd0d50bbf9dca1d0bdea219ae6b40f713a3fb477c06ca3714f208fd69e16fd8"},
+    {file = "pyzmq-25.1.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:004ff469d21e86f0ef0369717351073e0e577428e514c47c8480770d5e24a565"},
+    {file = "pyzmq-25.1.2-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:c0b5ca88a8928147b7b1e2dfa09f3b6c256bc1135a1338536cbc9ea13d3b7add"},
+    {file = "pyzmq-25.1.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2c9a79f1d2495b167119d02be7448bfba57fad2a4207c4f68abc0bab4b92925b"},
+    {file = "pyzmq-25.1.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:518efd91c3d8ac9f9b4f7dd0e2b7b8bf1a4fe82a308009016b07eaa48681af82"},
+    {file = "pyzmq-25.1.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:1ec23bd7b3a893ae676d0e54ad47d18064e6c5ae1fadc2f195143fb27373f7f6"},
+    {file = "pyzmq-25.1.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:db36c27baed588a5a8346b971477b718fdc66cf5b80cbfbd914b4d6d355e44e2"},
+    {file = "pyzmq-25.1.2-cp39-cp39-win32.whl", hash = "sha256:39b1067f13aba39d794a24761e385e2eddc26295826530a8c7b6c6c341584289"},
+    {file = "pyzmq-25.1.2-cp39-cp39-win_amd64.whl", hash = "sha256:8e9f3fabc445d0ce320ea2c59a75fe3ea591fdbdeebec5db6de530dd4b09412e"},
+    {file = "pyzmq-25.1.2-pp310-pypy310_pp73-macosx_10_9_x86_64.whl", hash = "sha256:a8c1d566344aee826b74e472e16edae0a02e2a044f14f7c24e123002dcff1c05"},
+    {file = "pyzmq-25.1.2-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:759cfd391a0996345ba94b6a5110fca9c557ad4166d86a6e81ea526c376a01e8"},
+    {file = "pyzmq-25.1.2-pp310-pypy310_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7c61e346ac34b74028ede1c6b4bcecf649d69b707b3ff9dc0fab453821b04d1e"},
+    {file = "pyzmq-25.1.2-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4cb8fc1f8d69b411b8ec0b5f1ffbcaf14c1db95b6bccea21d83610987435f1a4"},
+    {file = "pyzmq-25.1.2-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:3c00c9b7d1ca8165c610437ca0c92e7b5607b2f9076f4eb4b095c85d6e680a1d"},
+    {file = "pyzmq-25.1.2-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:df0c7a16ebb94452d2909b9a7b3337940e9a87a824c4fc1c7c36bb4404cb0cde"},
+    {file = "pyzmq-25.1.2-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:45999e7f7ed5c390f2e87ece7f6c56bf979fb213550229e711e45ecc7d42ccb8"},
+    {file = "pyzmq-25.1.2-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:ac170e9e048b40c605358667aca3d94e98f604a18c44bdb4c102e67070f3ac9b"},
+    {file = "pyzmq-25.1.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d1b604734bec94f05f81b360a272fc824334267426ae9905ff32dc2be433ab96"},
+    {file = "pyzmq-25.1.2-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:a793ac733e3d895d96f865f1806f160696422554e46d30105807fdc9841b9f7d"},
+    {file = "pyzmq-25.1.2-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:0806175f2ae5ad4b835ecd87f5f85583316b69f17e97786f7443baaf54b9bb98"},
+    {file = "pyzmq-25.1.2-pp38-pypy38_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:ef12e259e7bc317c7597d4f6ef59b97b913e162d83b421dd0db3d6410f17a244"},
+    {file = "pyzmq-25.1.2-pp38-pypy38_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:ea253b368eb41116011add00f8d5726762320b1bda892f744c91997b65754d73"},
+    {file = "pyzmq-25.1.2-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1b9b1f2ad6498445a941d9a4fee096d387fee436e45cc660e72e768d3d8ee611"},
+    {file = "pyzmq-25.1.2-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:8b14c75979ce932c53b79976a395cb2a8cd3aaf14aef75e8c2cb55a330b9b49d"},
+    {file = "pyzmq-25.1.2-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:889370d5174a741a62566c003ee8ddba4b04c3f09a97b8000092b7ca83ec9c49"},
+    {file = "pyzmq-25.1.2-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9a18fff090441a40ffda8a7f4f18f03dc56ae73f148f1832e109f9bffa85df15"},
+    {file = "pyzmq-25.1.2-pp39-pypy39_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:99a6b36f95c98839ad98f8c553d8507644c880cf1e0a57fe5e3a3f3969040882"},
+    {file = "pyzmq-25.1.2-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4345c9a27f4310afbb9c01750e9461ff33d6fb74cd2456b107525bbeebcb5be3"},
+    {file = "pyzmq-25.1.2-pp39-pypy39_pp73-manylinux_2_28_x86_64.whl", hash = "sha256:3516e0b6224cf6e43e341d56da15fd33bdc37fa0c06af4f029f7d7dfceceabbc"},
+    {file = "pyzmq-25.1.2-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:146b9b1f29ead41255387fb07be56dc29639262c0f7344f570eecdcd8d683314"},
+    {file = "pyzmq-25.1.2.tar.gz", hash = "sha256:93f1aa311e8bb912e34f004cf186407a4e90eec4f0ecc0efd26056bf7eda0226"},
+]
+
+[package.dependencies]
+cffi = {version = "*", markers = "implementation_name == \"pypy\""}
+
 [[package]]
 name = "pyzstd"
 version = "0.15.9"
@@ -4636,6 +5125,25 @@ postgresql-psycopgbinary = ["psycopg[binary] (>=3.0.7)"]
 pymysql = ["pymysql"]
 sqlcipher = ["sqlcipher3-binary"]
 
+[[package]]
+name = "stack-data"
+version = "0.6.3"
+description = "Extract data from python stack frames and tracebacks for informative displays"
+optional = false
+python-versions = "*"
+files = [
+    {file = "stack_data-0.6.3-py3-none-any.whl", hash = "sha256:d5558e0c25a4cb0853cddad3d77da9891a08cb85dd9f9f91b9f8cd66e511e695"},
+    {file = "stack_data-0.6.3.tar.gz", hash = "sha256:836a778de4fec4dcd1dcd89ed8abff8a221f58308462e1c4aa2a3cf30148f0b9"},
+]
+
+[package.dependencies]
+asttokens = ">=2.1.0"
+executing = ">=1.2.0"
+pure-eval = "*"
+
+[package.extras]
+tests = ["cython", "littleutils", "pygments", "pytest", "typeguard"]
+
 [[package]]
 name = "starlette"
 version = "0.27.0"
@@ -4966,6 +5474,26 @@ typing-extensions = "*"
 dynamo = ["jinja2"]
 opt-einsum = ["opt-einsum (>=3.3)"]
 
+[[package]]
+name = "tornado"
+version = "6.4"
+description = "Tornado is a Python web framework and asynchronous networking library, originally developed at FriendFeed."
+optional = false
+python-versions = ">= 3.8"
+files = [
+    {file = "tornado-6.4-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:02ccefc7d8211e5a7f9e8bc3f9e5b0ad6262ba2fbb683a6443ecc804e5224ce0"},
+    {file = "tornado-6.4-cp38-abi3-macosx_10_9_x86_64.whl", hash = "sha256:27787de946a9cffd63ce5814c33f734c627a87072ec7eed71f7fc4417bb16263"},
+    {file = "tornado-6.4-cp38-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f7894c581ecdcf91666a0912f18ce5e757213999e183ebfc2c3fdbf4d5bd764e"},
+    {file = "tornado-6.4-cp38-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e43bc2e5370a6a8e413e1e1cd0c91bedc5bd62a74a532371042a18ef19e10579"},
+    {file = "tornado-6.4-cp38-abi3-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:f0251554cdd50b4b44362f73ad5ba7126fc5b2c2895cc62b14a1c2d7ea32f212"},
+    {file = "tornado-6.4-cp38-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:fd03192e287fbd0899dd8f81c6fb9cbbc69194d2074b38f384cb6fa72b80e9c2"},
+    {file = "tornado-6.4-cp38-abi3-musllinux_1_1_i686.whl", hash = "sha256:88b84956273fbd73420e6d4b8d5ccbe913c65d31351b4c004ae362eba06e1f78"},
+    {file = "tornado-6.4-cp38-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:71ddfc23a0e03ef2df1c1397d859868d158c8276a0603b96cf86892bff58149f"},
+    {file = "tornado-6.4-cp38-abi3-win32.whl", hash = "sha256:6f8a6c77900f5ae93d8b4ae1196472d0ccc2775cc1dfdc9e7727889145c45052"},
+    {file = "tornado-6.4-cp38-abi3-win_amd64.whl", hash = "sha256:10aeaa8006333433da48dec9fe417877f8bcc21f48dda8d661ae79da357b2a63"},
+    {file = "tornado-6.4.tar.gz", hash = "sha256:72291fa6e6bc84e626589f1c29d90a5a6d593ef5ae68052ee2ef000dfd273dee"},
+]
+
 [[package]]
 name = "tqdm"
 version = "4.65.0"
@@ -4986,6 +5514,21 @@ notebook = ["ipywidgets (>=6)"]
 slack = ["slack-sdk"]
 telegram = ["requests"]
 
+[[package]]
+name = "traitlets"
+version = "5.14.0"
+description = "Traitlets Python configuration system"
+optional = false
+python-versions = ">=3.8"
+files = [
+    {file = "traitlets-5.14.0-py3-none-any.whl", hash = "sha256:f14949d23829023013c47df20b4a76ccd1a85effb786dc060f34de7948361b33"},
+    {file = "traitlets-5.14.0.tar.gz", hash = "sha256:fcdaa8ac49c04dfa0ed3ee3384ef6dfdb5d6f3741502be247279407679296772"},
+]
+
+[package.extras]
+docs = ["myst-parser", "pydata-sphinx-theme", "sphinx"]
+test = ["argcomplete (>=3.0.3)", "mypy (>=1.7.0)", "pre-commit", "pytest (>=7.0,<7.5)", "pytest-mock", "pytest-mypy-testing"]
+
 [[package]]
 name = "transformers"
 version = "4.36.1"
@@ -5177,16 +5720,6 @@ brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
 socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
 zstd = ["zstandard (>=0.18.0)"]
 
-[[package]]
-name = "uuid"
-version = "1.30"
-description = "UUID object and generation functions (Python 2.3 or higher)"
-optional = false
-python-versions = "*"
-files = [
-    {file = "uuid-1.30.tar.gz", hash = "sha256:1f87cc004ac5120466f36c5beae48b4c48cc411968eed0eaecd3da82aa96193f"},
-]
-
 [[package]]
 name = "uvicorn"
 version = "0.22.0"
@@ -5205,6 +5738,17 @@ h11 = ">=0.8"
 [package.extras]
 standard = ["colorama (>=0.4)", "httptools (>=0.5.0)", "python-dotenv (>=0.13)", "pyyaml (>=5.1)", "uvloop (>=0.14.0,!=0.15.0,!=0.15.1)", "watchfiles (>=0.13)", "websockets (>=10.4)"]
 
+[[package]]
+name = "wcwidth"
+version = "0.2.12"
+description = "Measures the displayed width of unicode strings in a terminal"
+optional = false
+python-versions = "*"
+files = [
+    {file = "wcwidth-0.2.12-py2.py3-none-any.whl", hash = "sha256:f26ec43d96c8cbfed76a5075dac87680124fa84e0855195a6184da9c187f133c"},
+    {file = "wcwidth-0.2.12.tar.gz", hash = "sha256:f01c104efdf57971bcb756f054dd58ddec5204dd15fa31d6503ea57947d97c02"},
+]
+
 [[package]]
 name = "websockets"
 version = "11.0.3"
@@ -5580,4 +6124,4 @@ testing = ["big-O", "jaraco.functools", "jaraco.itertools", "more-itertools", "p
 [metadata]
 lock-version = "2.0"
 python-versions = "^3.11"
-content-hash = "7043b289eff772088234ae5d29887102871190fd7cba56cc9a1f6286806593e8"
+content-hash = "d4dab1c7e21632afaa4a10172b526d671b7c2b333d9de45f7c2dc1fb3703d5b4"

pyproject.toml

@@ -7,10 +7,10 @@ readme = "README.md"
 
 [tool.poetry.dependencies]
 python = "^3.11"
-jsonlines = "^4.0.0"
-uuid = "^1.30"
-pandas = "^2.1.4"
 autotrain-advanced = "^0.6.59"
+jsonlines = "^4.0.0"
+ipykernel = "^6.27.1"
+python-dotenv = "^1.0.0"
 
 
 [build-system]

requirements.txt

@@ -8,7 +8,9 @@ alembic==1.13.0
 altair==5.2.0
 annotated-types==0.6.0
 anyio==3.7.1
+appnope==0.1.3
 arrow==1.3.0
+asttokens==2.4.1
 attrs==23.1.0
 autotrain-advanced==0.6.59
 bitsandbytes==0.41.0
@@ -20,20 +22,24 @@ click==8.1.7
 cmaes==0.10.0
 codecarbon==2.2.3
 colorlog==6.8.0
+comm==0.2.0
 contourpy==1.2.0
 cycler==0.12.1
-datasets==2.14.4
+datasets==2.14.7
+debugpy==1.8.0
+decorator==5.1.1
 diffusers==0.21.4
 dill==0.3.7
 docstring-parser==0.15
 einops==0.6.1
 evaluate==0.3.0
+executing==2.0.1
 fastapi==0.104.1
 ffmpy==0.3.1
 filelock==3.13.1
 fonttools==4.47.0
 frozenlist==1.4.1
-fsspec==2023.12.2
+fsspec==2023.10.0
 fuzzywuzzy==0.18.0
 google-auth==2.25.2
 google-auth-oauthlib==1.2.0
@@ -41,7 +47,6 @@ gradio==3.41.0
 gradio_client==0.5.0
 grpcio==1.60.0
 h11==0.14.0
-hf_transfer==0.1.4
 httpcore==1.0.2
 httpx==0.25.2
 huggingface-hub==0.19.4
@@ -52,12 +57,17 @@ importlib-resources==6.1.1
 inflate64==1.0.0
 invisible-watermark==0.2.0
 ipadic==1.0.0
+ipykernel==6.27.1
+ipython==8.18.1
+jedi==0.19.1
 Jinja2==3.1.2
 jiwer==3.0.2
 joblib==1.3.1
 jsonlines==4.0.0
 jsonschema==4.20.0
 jsonschema-specifications==2023.11.2
+jupyter_client==8.6.0
+jupyter_core==5.5.1
 kiwisolver==1.4.5
 lazy_loader==0.3
 loguru==0.7.0
@@ -66,11 +76,13 @@ Markdown==3.5.1
 markdown-it-py==3.0.0
 MarkupSafe==2.1.3
 matplotlib==3.8.2
+matplotlib-inline==0.1.6
 mdurl==0.1.2
 mpmath==1.3.0
 multidict==6.0.4
 multiprocess==0.70.15
 multivolumefile==0.2.3
+nest-asyncio==1.5.8
 networkx==3.2.1
 nltk==3.8.1
 numpy==1.26.2
@@ -81,13 +93,20 @@ optuna==3.3.0
 orjson==3.9.10
 packaging==23.1
 pandas==2.1.4
+parso==0.8.3
 peft==0.7.1
+pexpect==4.9.0
 Pillow==10.0.0
+platformdirs==4.1.0
+prompt-toolkit==3.0.43
 protobuf==4.23.4
 psutil==5.9.7
+ptyprocess==0.7.0
+pure-eval==0.2.2
 py-cpuinfo==9.0.0
 py7zr==0.20.6
 pyarrow==14.0.2
+pyarrow-hotfix==0.6
 pyasn1==0.5.1
 pyasn1-modules==0.3.0
 pybcj==1.0.2
@@ -101,10 +120,12 @@ pynvml==11.5.0
 pyparsing==3.1.1
 pyppmd==1.0.0
 python-dateutil==2.8.2
+python-dotenv==1.0.0
 python-multipart==0.0.6
 pytz==2023.3.post1
 PyWavelets==1.5.0
 PyYAML==6.0.1
+pyzmq==25.1.2
 pyzstd==0.15.9
 qudida==0.0.4
 rapidfuzz==2.13.7
@@ -128,6 +149,7 @@ shtab==1.6.5
 six==1.16.0
 sniffio==1.3.0
 SQLAlchemy==2.0.23
+stack-data==0.6.3
 starlette==0.27.0
 sympy==1.12
 tensorboard==2.15.1
@@ -139,7 +161,9 @@ tiktoken==0.5.1
 tokenizers==0.15.0
 toolz==0.12.0
 torch==2.1.2
+tornado==6.4
 tqdm==4.65.0
+traitlets==5.14.0
 transformers==4.36.1
 trl==0.7.4
 types-python-dateutil==2.8.19.14
@@ -147,8 +171,8 @@ typing_extensions==4.9.0
 tyro==0.6.0
 tzdata==2023.3
 urllib3==2.1.0
-uuid==1.30
 uvicorn==0.22.0
+wcwidth==0.2.12
 websockets==11.0.3
 Werkzeug==2.3.6
 xgboost==1.7.6

train_llm.ipynb

@@ -0,0 +1,83 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "import jsonlines\n",
+    "from uuid import uuid4\n",
+    "import pandas as pd\n",
+    "\n",
+    "from datasets import load_dataset\n",
+    "import subprocess\n",
+    "\n",
+    "from dotenv import load_dotenv,find_dotenv\n",
+    "load_dotenv(find_dotenv(),override=True)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ValueError",
+     "evalue": "Invalid pattern: '**' can only be an entire path component",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[6], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m dataset_name \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m'\u001b[39m\u001b[38;5;124mai-aerospace/ams_data_train_generic_v0.1_100\u001b[39m\u001b[38;5;124m'\u001b[39m\n\u001b[0;32m----> 2\u001b[0m dataset\u001b[38;5;241m=\u001b[39m\u001b[43mload_dataset\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdataset_name\u001b[49m\u001b[43m)\u001b[49m\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/datasets/load.py:2112\u001b[0m, in \u001b[0;36mload_dataset\u001b[0;34m(path, name, data_dir, data_files, split, cache_dir, features, download_config, download_mode, verification_mode, ignore_verifications, keep_in_memory, save_infos, revision, token, use_auth_token, task, streaming, num_proc, storage_options, **config_kwargs)\u001b[0m\n\u001b[1;32m   2107\u001b[0m verification_mode \u001b[38;5;241m=\u001b[39m VerificationMode(\n\u001b[1;32m   2108\u001b[0m     (verification_mode \u001b[38;5;129;01mor\u001b[39;00m VerificationMode\u001b[38;5;241m.\u001b[39mBASIC_CHECKS) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m save_infos \u001b[38;5;28;01melse\u001b[39;00m VerificationMode\u001b[38;5;241m.\u001b[39mALL_CHECKS\n\u001b[1;32m   2109\u001b[0m )\n\u001b[1;32m   2111\u001b[0m \u001b[38;5;66;03m# Create a dataset builder\u001b[39;00m\n\u001b[0;32m-> 2112\u001b[0m builder_instance \u001b[38;5;241m=\u001b[39m \u001b[43mload_dataset_builder\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   2113\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpath\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2114\u001b[0m \u001b[43m    \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2115\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdata_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2116\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdata_files\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata_files\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2117\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2118\u001b[0m \u001b[43m    \u001b[49m\u001b[43mfeatures\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfeatures\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2119\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdownload_config\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdownload_config\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2120\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdownload_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdownload_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2121\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2122\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2123\u001b[0m \u001b[43m    \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstorage_options\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2124\u001b[0m \u001b[43m    \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mconfig_kwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   2125\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   2127\u001b[0m \u001b[38;5;66;03m# Return iterable dataset in case of streaming\u001b[39;00m\n\u001b[1;32m   2128\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m streaming:\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/datasets/load.py:1798\u001b[0m, in \u001b[0;36mload_dataset_builder\u001b[0;34m(path, name, data_dir, data_files, cache_dir, features, download_config, download_mode, revision, token, use_auth_token, storage_options, **config_kwargs)\u001b[0m\n\u001b[1;32m   1796\u001b[0m     download_config \u001b[38;5;241m=\u001b[39m download_config\u001b[38;5;241m.\u001b[39mcopy() \u001b[38;5;28;01mif\u001b[39;00m download_config \u001b[38;5;28;01melse\u001b[39;00m DownloadConfig()\n\u001b[1;32m   1797\u001b[0m     download_config\u001b[38;5;241m.\u001b[39mstorage_options\u001b[38;5;241m.\u001b[39mupdate(storage_options)\n\u001b[0;32m-> 1798\u001b[0m dataset_module \u001b[38;5;241m=\u001b[39m \u001b[43mdataset_module_factory\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1799\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1800\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1801\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdownload_config\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdownload_config\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1802\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdownload_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdownload_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1803\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdata_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1804\u001b[0m \u001b[43m    \u001b[49m\u001b[43mdata_files\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata_files\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1805\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1806\u001b[0m \u001b[38;5;66;03m# Get dataset builder class from the processing script\u001b[39;00m\n\u001b[1;32m   1807\u001b[0m builder_kwargs \u001b[38;5;241m=\u001b[39m dataset_module\u001b[38;5;241m.\u001b[39mbuilder_kwargs\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/datasets/load.py:1495\u001b[0m, in \u001b[0;36mdataset_module_factory\u001b[0;34m(path, revision, download_config, download_mode, dynamic_modules_path, data_dir, data_files, **download_kwargs)\u001b[0m\n\u001b[1;32m   1490\u001b[0m             \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(e1, \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m):\n\u001b[1;32m   1491\u001b[0m                 \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m(\n\u001b[1;32m   1492\u001b[0m                     \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCouldn\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt find a dataset script at \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrelative_to_absolute_path(combined_path)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m or any data file in the same directory. \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1493\u001b[0m                     \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCouldn\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt find \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m on the Hugging Face Hub either: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mtype\u001b[39m(e1)\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00me1\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1494\u001b[0m                 ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1495\u001b[0m             \u001b[38;5;28;01mraise\u001b[39;00m e1 \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m   1496\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1497\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m(\n\u001b[1;32m   1498\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCouldn\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt find a dataset script at \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrelative_to_absolute_path(combined_path)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m or any data file in the same directory.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m   1499\u001b[0m     )\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/datasets/load.py:1479\u001b[0m, in \u001b[0;36mdataset_module_factory\u001b[0;34m(path, revision, download_config, download_mode, dynamic_modules_path, data_dir, data_files, **download_kwargs)\u001b[0m\n\u001b[1;32m   1464\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m HubDatasetModuleFactoryWithScript(\n\u001b[1;32m   1465\u001b[0m             path,\n\u001b[1;32m   1466\u001b[0m             revision\u001b[38;5;241m=\u001b[39mrevision,\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m   1469\u001b[0m             dynamic_modules_path\u001b[38;5;241m=\u001b[39mdynamic_modules_path,\n\u001b[1;32m   1470\u001b[0m         )\u001b[38;5;241m.\u001b[39mget_module()\n\u001b[1;32m   1471\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1472\u001b[0m         \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mHubDatasetModuleFactoryWithoutScript\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1473\u001b[0m \u001b[43m            \u001b[49m\u001b[43mpath\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1474\u001b[0m \u001b[43m            \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1475\u001b[0m \u001b[43m            \u001b[49m\u001b[43mdata_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1476\u001b[0m \u001b[43m            \u001b[49m\u001b[43mdata_files\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdata_files\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1477\u001b[0m \u001b[43m            \u001b[49m\u001b[43mdownload_config\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdownload_config\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1478\u001b[0m \u001b[43m            \u001b[49m\u001b[43mdownload_mode\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdownload_mode\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m-> 1479\u001b[0m \u001b[43m        \u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mget_module\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1480\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m (\n\u001b[1;32m   1481\u001b[0m     \u001b[38;5;167;01mException\u001b[39;00m\n\u001b[1;32m   1482\u001b[0m ) \u001b[38;5;28;01mas\u001b[39;00m e1:  \u001b[38;5;66;03m# noqa all the attempts failed, before raising the error we should check if the module is already cached.\u001b[39;00m\n\u001b[1;32m   1483\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/datasets/load.py:1034\u001b[0m, in \u001b[0;36mHubDatasetModuleFactoryWithoutScript.get_module\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1029\u001b[0m metadata_configs \u001b[38;5;241m=\u001b[39m MetadataConfigs\u001b[38;5;241m.\u001b[39mfrom_dataset_card_data(dataset_card_data)\n\u001b[1;32m   1030\u001b[0m dataset_infos \u001b[38;5;241m=\u001b[39m DatasetInfosDict\u001b[38;5;241m.\u001b[39mfrom_dataset_card_data(dataset_card_data)\n\u001b[1;32m   1031\u001b[0m patterns \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m   1032\u001b[0m     sanitize_patterns(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdata_files)\n\u001b[1;32m   1033\u001b[0m     \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdata_files \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[0;32m-> 1034\u001b[0m     \u001b[38;5;28;01melse\u001b[39;00m \u001b[43mget_data_patterns\u001b[49m\u001b[43m(\u001b[49m\u001b[43mbase_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdownload_config\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdownload_config\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1035\u001b[0m )\n\u001b[1;32m   1036\u001b[0m data_files \u001b[38;5;241m=\u001b[39m DataFilesDict\u001b[38;5;241m.\u001b[39mfrom_patterns(\n\u001b[1;32m   1037\u001b[0m     patterns,\n\u001b[1;32m   1038\u001b[0m     base_path\u001b[38;5;241m=\u001b[39mbase_path,\n\u001b[1;32m   1039\u001b[0m     allowed_extensions\u001b[38;5;241m=\u001b[39mALL_ALLOWED_EXTENSIONS,\n\u001b[1;32m   1040\u001b[0m     download_config\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdownload_config,\n\u001b[1;32m   1041\u001b[0m )\n\u001b[1;32m   1042\u001b[0m module_name, default_builder_kwargs \u001b[38;5;241m=\u001b[39m infer_module_for_data_files(\n\u001b[1;32m   1043\u001b[0m     data_files\u001b[38;5;241m=\u001b[39mdata_files,\n\u001b[1;32m   1044\u001b[0m     path\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mname,\n\u001b[1;32m   1045\u001b[0m     download_config\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdownload_config,\n\u001b[1;32m   1046\u001b[0m )\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/datasets/data_files.py:457\u001b[0m, in \u001b[0;36mget_data_patterns\u001b[0;34m(base_path, download_config)\u001b[0m\n\u001b[1;32m    455\u001b[0m resolver \u001b[38;5;241m=\u001b[39m partial(resolve_pattern, base_path\u001b[38;5;241m=\u001b[39mbase_path, download_config\u001b[38;5;241m=\u001b[39mdownload_config)\n\u001b[1;32m    456\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 457\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43m_get_data_files_patterns\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresolver\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    458\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m:\n\u001b[1;32m    459\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m EmptyDatasetError(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mThe directory at \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mbase_path\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m doesn\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mt contain any data files\u001b[39m\u001b[38;5;124m\"\u001b[39m) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/datasets/data_files.py:248\u001b[0m, in \u001b[0;36m_get_data_files_patterns\u001b[0;34m(pattern_resolver)\u001b[0m\n\u001b[1;32m    246\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m pattern \u001b[38;5;129;01min\u001b[39;00m patterns:\n\u001b[1;32m    247\u001b[0m     \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 248\u001b[0m         data_files \u001b[38;5;241m=\u001b[39m \u001b[43mpattern_resolver\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpattern\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    249\u001b[0m     \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m:\n\u001b[1;32m    250\u001b[0m         \u001b[38;5;28;01mcontinue\u001b[39;00m\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/datasets/data_files.py:332\u001b[0m, in \u001b[0;36mresolve_pattern\u001b[0;34m(pattern, base_path, allowed_extensions, download_config)\u001b[0m\n\u001b[1;32m    330\u001b[0m     base_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    331\u001b[0m pattern, storage_options \u001b[38;5;241m=\u001b[39m _prepare_path_and_storage_options(pattern, download_config\u001b[38;5;241m=\u001b[39mdownload_config)\n\u001b[0;32m--> 332\u001b[0m fs, _, _ \u001b[38;5;241m=\u001b[39m \u001b[43mget_fs_token_paths\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpattern\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mstorage_options\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mstorage_options\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    333\u001b[0m fs_base_path \u001b[38;5;241m=\u001b[39m base_path\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m::\u001b[39m\u001b[38;5;124m\"\u001b[39m)[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m://\u001b[39m\u001b[38;5;124m\"\u001b[39m)[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m] \u001b[38;5;129;01mor\u001b[39;00m fs\u001b[38;5;241m.\u001b[39mroot_marker\n\u001b[1;32m    334\u001b[0m fs_pattern \u001b[38;5;241m=\u001b[39m pattern\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m::\u001b[39m\u001b[38;5;124m\"\u001b[39m)[\u001b[38;5;241m0\u001b[39m]\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m://\u001b[39m\u001b[38;5;124m\"\u001b[39m)[\u001b[38;5;241m-\u001b[39m\u001b[38;5;241m1\u001b[39m]\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/fsspec/core.py:653\u001b[0m, in \u001b[0;36mget_fs_token_paths\u001b[0;34m(urlpath, mode, num, name_function, storage_options, protocol, expand)\u001b[0m\n\u001b[1;32m    651\u001b[0m     paths \u001b[38;5;241m=\u001b[39m _expand_paths(paths, name_function, num)\n\u001b[1;32m    652\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m*\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m paths:\n\u001b[0;32m--> 653\u001b[0m     paths \u001b[38;5;241m=\u001b[39m [f \u001b[38;5;28;01mfor\u001b[39;00m f \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28msorted\u001b[39m(\u001b[43mfs\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mglob\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpaths\u001b[49m\u001b[43m)\u001b[49m) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m fs\u001b[38;5;241m.\u001b[39misdir(f)]\n\u001b[1;32m    654\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m    655\u001b[0m     paths \u001b[38;5;241m=\u001b[39m [paths]\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/fsspec/spec.py:606\u001b[0m, in \u001b[0;36mAbstractFileSystem.glob\u001b[0;34m(self, path, maxdepth, **kwargs)\u001b[0m\n\u001b[1;32m    602\u001b[0m         depth \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m    604\u001b[0m allpaths \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfind(root, maxdepth\u001b[38;5;241m=\u001b[39mdepth, withdirs\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, detail\u001b[38;5;241m=\u001b[39m\u001b[38;5;28;01mTrue\u001b[39;00m, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[0;32m--> 606\u001b[0m pattern \u001b[38;5;241m=\u001b[39m \u001b[43mglob_translate\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpath\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m+\u001b[39;49m\u001b[43m \u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43mends_with_sep\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    607\u001b[0m pattern \u001b[38;5;241m=\u001b[39m re\u001b[38;5;241m.\u001b[39mcompile(pattern)\n\u001b[1;32m    609\u001b[0m out \u001b[38;5;241m=\u001b[39m {\n\u001b[1;32m    610\u001b[0m     p: info\n\u001b[1;32m    611\u001b[0m     \u001b[38;5;28;01mfor\u001b[39;00m p, info \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28msorted\u001b[39m(allpaths\u001b[38;5;241m.\u001b[39mitems())\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    618\u001b[0m     )\n\u001b[1;32m    619\u001b[0m }\n",
+      "File \u001b[0;32m~/Documents/HuggingFace/autotrain-playground/.venv/lib/python3.11/site-packages/fsspec/utils.py:734\u001b[0m, in \u001b[0;36mglob_translate\u001b[0;34m(pat)\u001b[0m\n\u001b[1;32m    732\u001b[0m     \u001b[38;5;28;01mcontinue\u001b[39;00m\n\u001b[1;32m    733\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m**\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m part:\n\u001b[0;32m--> 734\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m    735\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mInvalid pattern: \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m**\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m can only be an entire path component\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    736\u001b[0m     )\n\u001b[1;32m    737\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m part:\n\u001b[1;32m    738\u001b[0m     results\u001b[38;5;241m.\u001b[39mextend(_translate(part, \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mnot_sep\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m*\u001b[39m\u001b[38;5;124m\"\u001b[39m, not_sep))\n",
+      "\u001b[0;31mValueError\u001b[0m: Invalid pattern: '**' can only be an entire path component"
+     ]
+    }
+   ],
+   "source": [
+    "dataset_name = 'ai-aerospace/ams_data_train_generic_v0.1_100'\n",
+    "dataset=load_dataset(dataset_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

train_llm.py

@@ -5,14 +5,13 @@ import pandas as pd
 
 from datasets import load_dataset
 import subprocess
-from tqdm.notebook import tqdm
 
 # from dotenv import load_dotenv,find_dotenv
 # load_dotenv(find_dotenv(),override=True)
 
 # Load dataset
 dataset_name = 'ai-aerospace/ams_data_train_generic_v0.1_100'
-dataset=load_dataset(dataset_name,cache_dir='./cache')
+dataset=load_dataset(dataset_name)
 
 # Write dataset files into data directory
 data_directory = './fine_tune_data/'