Tested on
In [1]:
!git clone -b resume https://github.com/utensil/Alpaca-CoT.git code
Cloning into 'code'... remote: Enumerating objects: 787, done. remote: Counting objects: 100% (125/125), done. remote: Compressing objects: 100% (77/77), done. remote: Total 787 (delta 70), reused 85 (delta 48), pack-reused 662 Receiving objects: 100% (787/787), 127.14 MiB | 21.82 MiB/s, done. Resolving deltas: 100% (422/422), done.
In [2]:
!ln -s /content /workspace
In [3]:
!python -m pip install bitsandbytes
!python -m pip install datasets
!python -m pip install git+https://github.com/huggingface/transformers.git
!python -m pip install peft
!python -m pip install sentencepiece
!python -m pip install gradio
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting bitsandbytes
Downloading bitsandbytes-0.38.1-py3-none-any.whl (104.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 104.3/104.3 MB 10.1 MB/s eta 0:00:00
Installing collected packages: bitsandbytes
Successfully installed bitsandbytes-0.38.1
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting datasets
Downloading datasets-2.11.0-py3-none-any.whl (468 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 468.7/468.7 kB 20.5 MB/s eta 0:00:00
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.9/dist-packages (from datasets) (6.0)
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.9/dist-packages (from datasets) (1.22.4)
Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.9/dist-packages (from datasets) (9.0.0)
Collecting xxhash
Downloading xxhash-3.2.0-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (212 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 212.2/212.2 kB 27.1 MB/s eta 0:00:00
Collecting huggingface-hub<1.0.0,>=0.11.0
Downloading huggingface_hub-0.13.4-py3-none-any.whl (200 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 200.1/200.1 kB 28.3 MB/s eta 0:00:00
Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.9/dist-packages (from datasets) (4.65.0)
Collecting aiohttp
Downloading aiohttp-3.8.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.0/1.0 MB 40.6 MB/s eta 0:00:00
Collecting multiprocess
Downloading multiprocess-0.70.14-py39-none-any.whl (132 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 132.9/132.9 kB 18.3 MB/s eta 0:00:00
Requirement already satisfied: pandas in /usr/local/lib/python3.9/dist-packages (from datasets) (1.5.3)
Requirement already satisfied: fsspec[http]>=2021.11.1 in /usr/local/lib/python3.9/dist-packages (from datasets) (2023.4.0)
Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.9/dist-packages (from datasets) (2.27.1)
Requirement already satisfied: packaging in /usr/local/lib/python3.9/dist-packages (from datasets) (23.0)
Collecting dill<0.3.7,>=0.3.0
Downloading dill-0.3.6-py3-none-any.whl (110 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 110.5/110.5 kB 400.5 kB/s eta 0:00:00
Collecting responses<0.19
Downloading responses-0.18.0-py3-none-any.whl (38 kB)
Collecting aiosignal>=1.1.2
Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)
Collecting frozenlist>=1.1.1
Downloading frozenlist-1.3.3-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (158 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 158.8/158.8 kB 23.5 MB/s eta 0:00:00
Collecting async-timeout<5.0,>=4.0.0a3
Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)
Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->datasets) (22.2.0)
Collecting yarl<2.0,>=1.0
Downloading yarl-1.8.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (264 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 264.6/264.6 kB 34.9 MB/s eta 0:00:00
Collecting multidict<7.0,>=4.5
Downloading multidict-6.0.4-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 114.2/114.2 kB 16.5 MB/s eta 0:00:00
Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->datasets) (2.0.12)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub<1.0.0,>=0.11.0->datasets) (4.5.0)
Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from huggingface-hub<1.0.0,>=0.11.0->datasets) (3.11.0)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests>=2.19.0->datasets) (1.26.15)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests>=2.19.0->datasets) (3.4)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests>=2.19.0->datasets) (2022.12.7)
Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.9/dist-packages (from pandas->datasets) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.9/dist-packages (from pandas->datasets) (2022.7.1)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)
Installing collected packages: xxhash, multidict, frozenlist, dill, async-timeout, yarl, responses, multiprocess, huggingface-hub, aiosignal, aiohttp, datasets
Successfully installed aiohttp-3.8.4 aiosignal-1.3.1 async-timeout-4.0.2 datasets-2.11.0 dill-0.3.6 frozenlist-1.3.3 huggingface-hub-0.13.4 multidict-6.0.4 multiprocess-0.70.14 responses-0.18.0 xxhash-3.2.0 yarl-1.8.2
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting git+https://github.com/huggingface/transformers.git
Cloning https://github.com/huggingface/transformers.git to /tmp/pip-req-build-_6il8a3f
Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers.git /tmp/pip-req-build-_6il8a3f
Resolved https://github.com/huggingface/transformers.git to commit 4603fe9b1f798d81cf55de65a46691b3276edccd
Installing build dependencies ... done
Getting requirements to build wheel ... done
Preparing metadata (pyproject.toml) ... done
Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from transformers==4.29.0.dev0) (3.11.0)
Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.9/dist-packages (from transformers==4.29.0.dev0) (6.0)
Collecting tokenizers!=0.11.3,<0.14,>=0.11.1
Downloading tokenizers-0.13.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 7.8/7.8 MB 63.9 MB/s eta 0:00:00
Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.9/dist-packages (from transformers==4.29.0.dev0) (4.65.0)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/dist-packages (from transformers==4.29.0.dev0) (23.0)
Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.9/dist-packages (from transformers==4.29.0.dev0) (2022.10.31)
Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from transformers==4.29.0.dev0) (2.27.1)
Requirement already satisfied: huggingface-hub<1.0,>=0.11.0 in /usr/local/lib/python3.9/dist-packages (from transformers==4.29.0.dev0) (0.13.4)
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.9/dist-packages (from transformers==4.29.0.dev0) (1.22.4)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers==4.29.0.dev0) (4.5.0)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->transformers==4.29.0.dev0) (2022.12.7)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->transformers==4.29.0.dev0) (3.4)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->transformers==4.29.0.dev0) (1.26.15)
Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->transformers==4.29.0.dev0) (2.0.12)
Building wheels for collected packages: transformers
Building wheel for transformers (pyproject.toml) ... done
Created wheel for transformers: filename=transformers-4.29.0.dev0-py3-none-any.whl size=6934897 sha256=d3bab574d91eae075ec52bd2109c22a5ac1289543173c83f7fbc069c9af174a3
Stored in directory: /tmp/pip-ephem-wheel-cache-7mgxx5zr/wheels/f7/92/8c/752ff3bfcd3439805d8bbf641614da38ef3226e127ebea86ee
Successfully built transformers
Installing collected packages: tokenizers, transformers
Successfully installed tokenizers-0.13.3 transformers-4.29.0.dev0
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting peft
Downloading peft-0.2.0-py3-none-any.whl (40 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 40.3/40.3 kB 3.5 MB/s eta 0:00:00
Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.9/dist-packages (from peft) (1.22.4)
Collecting accelerate
Downloading accelerate-0.18.0-py3-none-any.whl (215 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 215.3/215.3 kB 15.8 MB/s eta 0:00:00
Requirement already satisfied: pyyaml in /usr/local/lib/python3.9/dist-packages (from peft) (6.0)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/dist-packages (from peft) (23.0)
Requirement already satisfied: psutil in /usr/local/lib/python3.9/dist-packages (from peft) (5.9.4)
Requirement already satisfied: torch>=1.13.0 in /usr/local/lib/python3.9/dist-packages (from peft) (2.0.0+cu118)
Requirement already satisfied: transformers in /usr/local/lib/python3.9/dist-packages (from peft) (4.29.0.dev0)
Requirement already satisfied: networkx in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (3.1)
Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (3.11.0)
Requirement already satisfied: sympy in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (1.11.1)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (3.1.2)
Requirement already satisfied: typing-extensions in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (4.5.0)
Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.9/dist-packages (from torch>=1.13.0->peft) (2.0.0)
Requirement already satisfied: cmake in /usr/local/lib/python3.9/dist-packages (from triton==2.0.0->torch>=1.13.0->peft) (3.25.2)
Requirement already satisfied: lit in /usr/local/lib/python3.9/dist-packages (from triton==2.0.0->torch>=1.13.0->peft) (16.0.1)
Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (4.65.0)
Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (2.27.1)
Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (2022.10.31)
Requirement already satisfied: huggingface-hub<1.0,>=0.11.0 in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (0.13.4)
Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.9/dist-packages (from transformers->peft) (0.13.3)
Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.9/dist-packages (from jinja2->torch>=1.13.0->peft) (2.1.2)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->transformers->peft) (1.26.15)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->transformers->peft) (2022.12.7)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->transformers->peft) (3.4)
Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests->transformers->peft) (2.0.12)
Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.9/dist-packages (from sympy->torch>=1.13.0->peft) (1.3.0)
Installing collected packages: accelerate, peft
Successfully installed accelerate-0.18.0 peft-0.2.0
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting sentencepiece
Downloading sentencepiece-0.1.98-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 40.9 MB/s eta 0:00:00
Installing collected packages: sentencepiece
Successfully installed sentencepiece-0.1.98
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting gradio
Downloading gradio-3.27.0-py3-none-any.whl (17.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 17.3/17.3 MB 84.3 MB/s eta 0:00:00
Collecting semantic-version
Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)
Requirement already satisfied: matplotlib in /usr/local/lib/python3.9/dist-packages (from gradio) (3.7.1)
Collecting mdit-py-plugins<=0.3.3
Downloading mdit_py_plugins-0.3.3-py3-none-any.whl (50 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 50.5/50.5 kB 7.5 MB/s eta 0:00:00
Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from gradio) (2.27.1)
Requirement already satisfied: huggingface-hub>=0.13.0 in /usr/local/lib/python3.9/dist-packages (from gradio) (0.13.4)
Requirement already satisfied: markdown-it-py[linkify]>=2.0.0 in /usr/local/lib/python3.9/dist-packages (from gradio) (2.2.0)
Requirement already satisfied: pandas in /usr/local/lib/python3.9/dist-packages (from gradio) (1.5.3)
Collecting httpx
Downloading httpx-0.24.0-py3-none-any.whl (75 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 75.3/75.3 kB 10.3 MB/s eta 0:00:00
Collecting aiofiles
Downloading aiofiles-23.1.0-py3-none-any.whl (14 kB)
Requirement already satisfied: pyyaml in /usr/local/lib/python3.9/dist-packages (from gradio) (6.0)
Collecting websockets>=10.0
Downloading websockets-11.0.2-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 129.7/129.7 kB 20.1 MB/s eta 0:00:00
Collecting orjson
Downloading orjson-3.8.10-cp39-cp39-manylinux_2_28_x86_64.whl (140 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 140.5/140.5 kB 20.8 MB/s eta 0:00:00
Requirement already satisfied: typing-extensions in /usr/local/lib/python3.9/dist-packages (from gradio) (4.5.0)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.9/dist-packages (from gradio) (3.1.2)
Collecting python-multipart
Downloading python_multipart-0.0.6-py3-none-any.whl (45 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 45.7/45.7 kB 5.3 MB/s eta 0:00:00
Collecting fastapi
Downloading fastapi-0.95.1-py3-none-any.whl (56 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 57.0/57.0 kB 7.5 MB/s eta 0:00:00
Requirement already satisfied: pydantic in /usr/local/lib/python3.9/dist-packages (from gradio) (1.10.7)
Collecting ffmpy
Downloading ffmpy-0.3.0.tar.gz (4.8 kB)
Preparing metadata (setup.py) ... done
Requirement already satisfied: altair>=4.2.0 in /usr/local/lib/python3.9/dist-packages (from gradio) (4.2.2)
Requirement already satisfied: pillow in /usr/local/lib/python3.9/dist-packages (from gradio) (8.4.0)
Requirement already satisfied: aiohttp in /usr/local/lib/python3.9/dist-packages (from gradio) (3.8.4)
Collecting uvicorn
Downloading uvicorn-0.21.1-py3-none-any.whl (57 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 57.8/57.8 kB 9.2 MB/s eta 0:00:00
Requirement already satisfied: numpy in /usr/local/lib/python3.9/dist-packages (from gradio) (1.22.4)
Requirement already satisfied: markupsafe in /usr/local/lib/python3.9/dist-packages (from gradio) (2.1.2)
Collecting gradio-client>=0.1.3
Downloading gradio_client-0.1.3-py3-none-any.whl (286 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 286.2/286.2 kB 32.9 MB/s eta 0:00:00
Collecting pydub
Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)
Requirement already satisfied: entrypoints in /usr/local/lib/python3.9/dist-packages (from altair>=4.2.0->gradio) (0.4)
Requirement already satisfied: toolz in /usr/local/lib/python3.9/dist-packages (from altair>=4.2.0->gradio) (0.12.0)
Requirement already satisfied: jsonschema>=3.0 in /usr/local/lib/python3.9/dist-packages (from altair>=4.2.0->gradio) (4.3.3)
Requirement already satisfied: packaging in /usr/local/lib/python3.9/dist-packages (from gradio-client>=0.1.3->gradio) (23.0)
Requirement already satisfied: fsspec in /usr/local/lib/python3.9/dist-packages (from gradio-client>=0.1.3->gradio) (2023.4.0)
Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub>=0.13.0->gradio) (4.65.0)
Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from huggingface-hub>=0.13.0->gradio) (3.11.0)
Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.9/dist-packages (from markdown-it-py[linkify]>=2.0.0->gradio) (0.1.2)
Collecting linkify-it-py<3,>=1
Downloading linkify_it_py-2.0.0-py3-none-any.whl (19 kB)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.9/dist-packages (from pandas->gradio) (2022.7.1)
Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.9/dist-packages (from pandas->gradio) (2.8.2)
Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.9/dist-packages (from aiohttp->gradio) (1.3.3)
Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.9/dist-packages (from aiohttp->gradio) (1.3.1)
Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->gradio) (2.0.12)
Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->gradio) (1.8.2)
Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->gradio) (22.2.0)
Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.9/dist-packages (from aiohttp->gradio) (6.0.4)
Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.9/dist-packages (from aiohttp->gradio) (4.0.2)
Collecting starlette<0.27.0,>=0.26.1
Downloading starlette-0.26.1-py3-none-any.whl (66 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 66.9/66.9 kB 9.5 MB/s eta 0:00:00
Requirement already satisfied: certifi in /usr/local/lib/python3.9/dist-packages (from httpx->gradio) (2022.12.7)
Collecting httpcore<0.18.0,>=0.15.0
Downloading httpcore-0.17.0-py3-none-any.whl (70 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 70.6/70.6 kB 10.7 MB/s eta 0:00:00
Requirement already satisfied: idna in /usr/local/lib/python3.9/dist-packages (from httpx->gradio) (3.4)
Requirement already satisfied: sniffio in /usr/local/lib/python3.9/dist-packages (from httpx->gradio) (1.3.0)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.9/dist-packages (from matplotlib->gradio) (1.0.7)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.9/dist-packages (from matplotlib->gradio) (3.0.9)
Requirement already satisfied: importlib-resources>=3.2.0 in /usr/local/lib/python3.9/dist-packages (from matplotlib->gradio) (5.12.0)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.9/dist-packages (from matplotlib->gradio) (1.4.4)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.9/dist-packages (from matplotlib->gradio) (4.39.3)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.9/dist-packages (from matplotlib->gradio) (0.11.0)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->gradio) (1.26.15)
Collecting h11>=0.8
Downloading h11-0.14.0-py3-none-any.whl (58 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 58.3/58.3 kB 6.6 MB/s eta 0:00:00
Requirement already satisfied: click>=7.0 in /usr/local/lib/python3.9/dist-packages (from uvicorn->gradio) (8.1.3)
Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.9/dist-packages (from httpcore<0.18.0,>=0.15.0->httpx->gradio) (3.6.2)
Requirement already satisfied: zipp>=3.1.0 in /usr/local/lib/python3.9/dist-packages (from importlib-resources>=3.2.0->matplotlib->gradio) (3.15.0)
Requirement already satisfied: pyrsistent!=0.17.0,!=0.17.1,!=0.17.2,>=0.14.0 in /usr/local/lib/python3.9/dist-packages (from jsonschema>=3.0->altair>=4.2.0->gradio) (0.19.3)
Collecting uc-micro-py
Downloading uc_micro_py-1.0.1-py3-none-any.whl (6.2 kB)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/dist-packages (from python-dateutil>=2.8.1->pandas->gradio) (1.16.0)
Building wheels for collected packages: ffmpy
Building wheel for ffmpy (setup.py) ... done
Created wheel for ffmpy: filename=ffmpy-0.3.0-py3-none-any.whl size=4707 sha256=841e4b93092c15d1f561b9dc0216ed5503350c6b1aa1578b9e12d84d6960b428
Stored in directory: /root/.cache/pip/wheels/91/e2/96/f676aa08bfd789328c6576cd0f1fde4a3d686703bb0c247697
Successfully built ffmpy
Installing collected packages: pydub, ffmpy, websockets, uc-micro-py, semantic-version, python-multipart, orjson, h11, aiofiles, uvicorn, starlette, mdit-py-plugins, linkify-it-py, httpcore, httpx, fastapi, gradio-client, gradio
Successfully installed aiofiles-23.1.0 fastapi-0.95.1 ffmpy-0.3.0 gradio-3.27.0 gradio-client-0.1.3 h11-0.14.0 httpcore-0.17.0 httpx-0.24.0 linkify-it-py-2.0.0 mdit-py-plugins-0.3.3 orjson-3.8.10 pydub-0.25.1 python-multipart-0.0.6 semantic-version-2.10.0 starlette-0.26.1 uc-micro-py-1.0.1 uvicorn-0.21.1 websockets-11.0.2
In [4]:
# download data git repository
!GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/datasets/QingyiSi/Alpaca-CoT data
# pull specify data and move it，change <alpaca/> to your preference
!cd /workspace/data && git config core.sparsecheckout true && git config lfs.fetchinclude alpaca/
!cd /workspace/data && git lfs pull
!cp /workspace/data/alpaca/*.json /workspace/code/data/
!ls -lh /workspace/code/data/
Cloning into 'data'... remote: Enumerating objects: 2195, done. remote: Counting objects: 100% (2172/2172), done. remote: Compressing objects: 100% (2115/2115), done. remote: Total 2195 (delta 156), reused 1617 (delta 0), pack-reused 23 Receiving objects: 100% (2195/2195), 21.86 MiB | 5.91 MiB/s, done. Resolving deltas: 100% (162/162), done. total 44M -rw-r--r-- 1 root root 22M Apr 19 13:13 alpaca_data_cleaned.json -rw-r--r-- 1 root root 22M Apr 19 13:13 alpaca_data.json drwxr-xr-x 2 root root 4.0K Apr 19 13:11 formatted_cot_data drwxr-xr-x 2 root root 4.0K Apr 19 13:11 origin_cot_data
In [7]:
!cd /workspace && git clone https://github.com/utensil/llm-playground.git
!python3 /workspace/llm-playground/helper/upload.py
Cloning into 'llm-playground'... remote: Enumerating objects: 202, done. remote: Counting objects: 100% (202/202), done. remote: Compressing objects: 100% (134/134), done. remote: Total 202 (delta 117), reused 129 (delta 55), pack-reused 0 Receiving objects: 100% (202/202), 2.31 MiB | 4.47 MiB/s, done. Resolving deltas: 100% (117/117), done. Working directory changed to: /workspace/llm-playground/helper/.. Cloning https://huggingface.co/datasets/utensil/storage into local empty directory. Nothing to upload, exiting...
In [8]:
!pip install wandb
Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting wandb
Downloading wandb-0.14.2-py3-none-any.whl (2.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.0/2.0 MB 56.0 MB/s eta 0:00:00
Collecting docker-pycreds>=0.4.0
Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)
Requirement already satisfied: requests<3,>=2.0.0 in /usr/local/lib/python3.9/dist-packages (from wandb) (2.27.1)
Collecting pathtools
Downloading pathtools-0.1.2.tar.gz (11 kB)
Preparing metadata (setup.py) ... done
Requirement already satisfied: appdirs>=1.4.3 in /usr/local/lib/python3.9/dist-packages (from wandb) (1.4.4)
Collecting setproctitle
Downloading setproctitle-1.3.2-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30 kB)
Requirement already satisfied: PyYAML in /usr/local/lib/python3.9/dist-packages (from wandb) (6.0)
Requirement already satisfied: typing-extensions in /usr/local/lib/python3.9/dist-packages (from wandb) (4.5.0)
Requirement already satisfied: psutil>=5.0.0 in /usr/local/lib/python3.9/dist-packages (from wandb) (5.9.4)
Requirement already satisfied: protobuf!=4.21.0,<5,>=3.15.0 in /usr/local/lib/python3.9/dist-packages (from wandb) (3.20.3)
Collecting GitPython!=3.1.29,>=1.0.0
Downloading GitPython-3.1.31-py3-none-any.whl (184 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 184.3/184.3 kB 26.7 MB/s eta 0:00:00
Requirement already satisfied: setuptools in /usr/local/lib/python3.9/dist-packages (from wandb) (67.6.1)
Requirement already satisfied: Click!=8.0.0,>=7.0 in /usr/local/lib/python3.9/dist-packages (from wandb) (8.1.3)
Collecting sentry-sdk>=1.0.0
Downloading sentry_sdk-1.20.0-py2.py3-none-any.whl (198 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 198.8/198.8 kB 30.7 MB/s eta 0:00:00
Requirement already satisfied: six>=1.4.0 in /usr/local/lib/python3.9/dist-packages (from docker-pycreds>=0.4.0->wandb) (1.16.0)
Collecting gitdb<5,>=4.0.1
Downloading gitdb-4.0.10-py3-none-any.whl (62 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 62.7/62.7 kB 9.3 MB/s eta 0:00:00
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2.0.0->wandb) (2022.12.7)
Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2.0.0->wandb) (1.26.15)
Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2.0.0->wandb) (2.0.12)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests<3,>=2.0.0->wandb) (3.4)
Collecting smmap<6,>=3.0.1
Downloading smmap-5.0.0-py3-none-any.whl (24 kB)
Building wheels for collected packages: pathtools
Building wheel for pathtools (setup.py) ... done
Created wheel for pathtools: filename=pathtools-0.1.2-py3-none-any.whl size=8807 sha256=a713831c9274c7e437c14f02c6bf158ab92d85ae7c7fead0f4e770114a567a10
Stored in directory: /root/.cache/pip/wheels/b7/0a/67/ada2a22079218c75a88361c0782855cc72aebc4d18d0289d05
Successfully built pathtools
Installing collected packages: pathtools, smmap, setproctitle, sentry-sdk, docker-pycreds, gitdb, GitPython, wandb
Successfully installed GitPython-3.1.31 docker-pycreds-0.4.0 gitdb-4.0.10 pathtools-0.1.2 sentry-sdk-1.20.0 setproctitle-1.3.2 smmap-5.0.0 wandb-0.14.2
In [12]:
!wandb login
wandb: Logging into wandb.ai. (Learn how to deploy a W&B server locally: https://wandb.me/wandb-server) wandb: You can find your API key in your browser here: https://wandb.ai/authorize wandb: Paste an API key from your profile and hit enter, or press ctrl+c to quit: wandb: Appending key for api.wandb.ai to your netrc file: /root/.netrc
In [20]:
!cd /workspace/llm-playground/storage/ && git lfs pull
In [21]:
!cp -r /workspace/llm-playground/storage/saved_models /workspace/code/
In [22]:
!rm -rf /workspace/code/saved_models/llama-7b-hf_alpaca/llama-7b-hf_alpaca
In [23]:
!ls -lhta /workspace/code/saved_models/llama-7b-hf_alpaca/checkpoint-780
total 49M drwxr-xr-x 7 root root 4.0K Apr 19 13:35 .. drwxr-xr-x 2 root root 4.0K Apr 19 13:34 . -rw-r--r-- 1 root root 8.9K Apr 19 13:34 trainer_state.json -rw-r--r-- 1 root root 3.6K Apr 19 13:34 training_args.bin -rw-r--r-- 1 root root 15K Apr 19 13:34 rng_state.pth -rw-r--r-- 1 root root 557 Apr 19 13:34 scaler.pt -rw-r--r-- 1 root root 627 Apr 19 13:34 scheduler.pt -rw-r--r-- 1 root root 17M Apr 19 13:34 pytorch_model.bin -rw-r--r-- 1 root root 33M Apr 19 13:34 optimizer.pt
In [ ]:
# instruction finetuning: trigger model download, output cleaned
!cd /workspace/code && python uniform_finetune.py --model_type llama --model_name_or_path decapoda-research/llama-7b-hf --data alpaca --lora_target_modules q_proj v_proj --per_gpu_train_batch_size 4 --learning_rate 3e-4 --epochs 1 --report_to wandb
In [16]:
# instruction finetuning: from scratch
!cd /workspace/code && python uniform_finetune.py --model_type llama --model_name_or_path decapoda-research/llama-7b-hf --data alpaca --lora_target_modules q_proj v_proj --per_gpu_train_batch_size 4 --learning_rate 3e-4 --epochs 1 --report_to wandb
===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please run
python -m bitsandbytes
and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
================================================================================
bin /usr/local/lib/python3.9/dist-packages/bitsandbytes/libbitsandbytes_cuda118.so
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: /usr/lib64-nvidia did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/sys/fs/cgroup/memory.events /var/colab/cgroup/jupyter-children/memory.events')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('8013'), PosixPath('//172.28.0.1'), PosixPath('http')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('--listen_host=172.28.0.12 --target_host=172.28.0.12 --tunnel_background_save_url=https'), PosixPath('//colab.research.google.com/tun/m/cc48301118ce562b961b3c22d803539adc1e0c19/gpu-t4-s-32k5i5k8yhbau --tunnel_background_save_delay=10s --tunnel_periodic_background_save_frequency=30m0s --enable_output_coalescing=true --output_coalescing_required=true')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/env/python')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//ipykernel.pylab.backend_inline'), PosixPath('module')}
warn(msg)
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: Found duplicate ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] files: {PosixPath('/usr/local/cuda/lib64/libcudart.so.11.0'), PosixPath('/usr/local/cuda/lib64/libcudart.so')}.. We'll flip a coin and try one of these, in order to fail forward.
Either way, this might cause trouble in the future:
If you get `CUDA error: invalid device function` errors, the above might be the cause and the solution is to make sure only one ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] in the paths that we search based on your env.
warn(msg)
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so.11.0
CUDA SETUP: Highest compute capability among GPUs detected: 7.5
CUDA SETUP: Detected CUDA version 118
CUDA SETUP: Loading binary /usr/local/lib/python3.9/dist-packages/bitsandbytes/libbitsandbytes_cuda118.so...
2023-04-19 13:24:00.464215: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Namespace(size=None, data='alpaca', local_rank=-1, model_type='llama', model_name_or_path='decapoda-research/llama-7b-hf', per_gpu_train_batch_size=4, gradient_accumulation_steps=32, epochs=1, learning_rate=0.0003, cutoff_len=512, lora_r=8, lora_alpha=16, lora_dropout=0.05, val_set_size=2000, lora_target_modules=['q_proj', 'v_proj'], resume_from_checkpoint=None)
Found cached dataset json (/root/.cache/huggingface/datasets/json/default-9abf0eaf9929841c/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e)
100% 1/1 [00:00<00:00, 310.39it/s]
DatasetDict({
train: Dataset({
features: ['instruction', 'input', 'output'],
num_rows: 51942
})
})
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in mixed int8. Either pass torch_dtype=torch.float16 or don't pass this argument at all to remove this warning.
Loading checkpoint shards: 100% 33/33 [01:03<00:00, 1.92s/it]
The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'LLaMATokenizer'.
The class this function is called from is 'LlamaTokenizer'.
trainable params: 4194304 || all params: 6742609920 || trainable%: 0.06220594176090199
Loading cached split indices for dataset at /root/.cache/huggingface/datasets/json/default-9abf0eaf9929841c/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e/cache-7396bb661538563c.arrow and /root/.cache/huggingface/datasets/json/default-9abf0eaf9929841c/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e/cache-e0ee9ca563d38c5a.arrow
***** Running training *****
Num Epochs = 1
Instantaneous batch size per GPU = 4
Gradient Accumulation steps = 32
Total train batch size (w. parallel, distributed & accumulation) = 128
Total optimization steps = 390
Saving steps = 39
/usr/local/lib/python3.9/dist-packages/transformers/optimization.py:391: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
warnings.warn(
wandb: Currently logged in as: utensil. Use `wandb login --relogin` to force relogin
wandb: Tracking run with wandb version 0.14.2
wandb: Run data is saved locally in /content/code/wandb/run-20230419_132646-ha3psr8a
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run proud-morning-1
wandb: ⭐️ View project at https://wandb.ai/utensil/huggingface
wandb: 🚀 View run at https://wandb.ai/utensil/huggingface/runs/ha3psr8a
0% 1/390 [01:27<9:27:53, 87.59s/it]Traceback (most recent call last):
File "/content/code/uniform_finetune.py", line 353, in <module>
train(args)
File "/content/code/uniform_finetune.py", line 321, in train
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)
File "/usr/local/lib/python3.9/dist-packages/transformers/trainer.py", line 1661, in train
return inner_training_loop(
File "/usr/local/lib/python3.9/dist-packages/transformers/trainer.py", line 1928, in _inner_training_loop
tr_loss_step = self.training_step(model, inputs)
File "/usr/local/lib/python3.9/dist-packages/transformers/trainer.py", line 2708, in training_step
self.scaler.scale(loss).backward()
File "/usr/local/lib/python3.9/dist-packages/torch/_tensor.py", line 487, in backward
torch.autograd.backward(
File "/usr/local/lib/python3.9/dist-packages/torch/autograd/__init__.py", line 200, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
KeyboardInterrupt
╭───────────────────── Traceback (most recent call last) ──────────────────────╮
│ /content/code/uniform_finetune.py:353 in <module> │
│ │
│ 350 │ args, _ = parser.parse_known_args() │
│ 351 │ print(args) │
│ 352 │ │
│ ❱ 353 │ train(args) │
│ 354 │
│ │
│ /content/code/uniform_finetune.py:321 in train │
│ │
│ 318 │ if torch.__version__ >= "2" and sys.platform != "win32": │
│ 319 │ │ model = torch.compile(model) │
│ 320 │ │
│ ❱ 321 │ trainer.train(resume_from_checkpoint=args.resume_from_checkpoint) │
│ 322 │ │
│ 323 │ model.save_pretrained(output_dir) │
│ 324 │
│ │
│ /usr/local/lib/python3.9/dist-packages/transformers/trainer.py:1661 in train │
│ │
│ 1658 │ │ inner_training_loop = find_executable_batch_size( │
│ 1659 │ │ │ self._inner_training_loop, self._train_batch_size, args.a │
│ 1660 │ │ ) │
│ ❱ 1661 │ │ return inner_training_loop( │
│ 1662 │ │ │ args=args, │
│ 1663 │ │ │ resume_from_checkpoint=resume_from_checkpoint, │
│ 1664 │ │ │ trial=trial, │
│ │
│ /usr/local/lib/python3.9/dist-packages/transformers/trainer.py:1928 in │
│ _inner_training_loop │
│ │
│ 1925 │ │ │ │ │ with model.no_sync(): │
│ 1926 │ │ │ │ │ │ tr_loss_step = self.training_step(model, inpu │
│ 1927 │ │ │ │ else: │
│ ❱ 1928 │ │ │ │ │ tr_loss_step = self.training_step(model, inputs) │
│ 1929 │ │ │ │ │
│ 1930 │ │ │ │ if ( │
│ 1931 │ │ │ │ │ args.logging_nan_inf_filter │
│ │
│ /usr/local/lib/python3.9/dist-packages/transformers/trainer.py:2708 in │
│ training_step │
│ │
│ 2705 │ │ │ loss = loss / self.args.gradient_accumulation_steps │
│ 2706 │ │ │
│ 2707 │ │ if self.do_grad_scaling: │
│ ❱ 2708 │ │ │ self.scaler.scale(loss).backward() │
│ 2709 │ │ elif self.use_apex: │
│ 2710 │ │ │ with amp.scale_loss(loss, self.optimizer) as scaled_loss: │
│ 2711 │ │ │ │ scaled_loss.backward() │
│ │
│ /usr/local/lib/python3.9/dist-packages/torch/_tensor.py:487 in backward │
│ │
│ 484 │ │ │ │ create_graph=create_graph, │
│ 485 │ │ │ │ inputs=inputs, │
│ 486 │ │ │ ) │
│ ❱ 487 │ │ torch.autograd.backward( │
│ 488 │ │ │ self, gradient, retain_graph, create_graph, inputs=inputs │
│ 489 │ │ ) │
│ 490 │
│ │
│ /usr/local/lib/python3.9/dist-packages/torch/autograd/__init__.py:200 in │
│ backward │
│ │
│ 197 │ # The reason we repeat same the comment below is that │
│ 198 │ # some Python versions print out the first line of a multi-line fu │
│ 199 │ # calls in the traceback and some print out the last line │
│ ❱ 200 │ Variable._execution_engine.run_backward( # Calls into the C++ eng │
│ 201 │ │ tensors, grad_tensors_, retain_graph, create_graph, inputs, │
│ 202 │ │ allow_unreachable=True, accumulate_grad=True) # Calls into th │
│ 203 │
╰──────────────────────────────────────────────────────────────────────────────╯
KeyboardInterrupt
wandb: Waiting for W&B process to finish... (failed 255). Press Control-C to abort syncing.
wandb: 🚀 View run proud-morning-1 at: https://wandb.ai/utensil/huggingface/runs/ha3psr8a
wandb: Synced 5 W&B file(s), 0 media file(s), 2 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20230419_132646-ha3psr8a/logs
^C
In [24]:
# instruction finetuning: from the latest checkpoint
!cd /workspace/code && python uniform_finetune.py --model_type llama --model_name_or_path decapoda-research/llama-7b-hf --data alpaca --lora_target_modules q_proj v_proj --per_gpu_train_batch_size 4 --learning_rate 3e-4 --epochs 3 --report_to wandb --resume_from_checkpoint
===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please run
python -m bitsandbytes
and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
================================================================================
bin /usr/local/lib/python3.9/dist-packages/bitsandbytes/libbitsandbytes_cuda118.so
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: /usr/lib64-nvidia did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/sys/fs/cgroup/memory.events /var/colab/cgroup/jupyter-children/memory.events')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//172.28.0.1'), PosixPath('8013'), PosixPath('http')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//colab.research.google.com/tun/m/cc48301118ce562b961b3c22d803539adc1e0c19/gpu-t4-s-32k5i5k8yhbau --tunnel_background_save_delay=10s --tunnel_periodic_background_save_frequency=30m0s --enable_output_coalescing=true --output_coalescing_required=true'), PosixPath('--listen_host=172.28.0.12 --target_host=172.28.0.12 --tunnel_background_save_url=https')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/env/python')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//ipykernel.pylab.backend_inline')}
warn(msg)
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: Found duplicate ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] files: {PosixPath('/usr/local/cuda/lib64/libcudart.so'), PosixPath('/usr/local/cuda/lib64/libcudart.so.11.0')}.. We'll flip a coin and try one of these, in order to fail forward.
Either way, this might cause trouble in the future:
If you get `CUDA error: invalid device function` errors, the above might be the cause and the solution is to make sure only one ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] in the paths that we search based on your env.
warn(msg)
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so
CUDA SETUP: Highest compute capability among GPUs detected: 7.5
CUDA SETUP: Detected CUDA version 118
CUDA SETUP: Loading binary /usr/local/lib/python3.9/dist-packages/bitsandbytes/libbitsandbytes_cuda118.so...
2023-04-19 13:36:23.802857: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Namespace(size=None, data='alpaca', local_rank=-1, model_type='llama', model_name_or_path='decapoda-research/llama-7b-hf', per_gpu_train_batch_size=4, gradient_accumulation_steps=32, epochs=3, learning_rate=0.0003, cutoff_len=512, lora_r=8, lora_alpha=16, lora_dropout=0.05, val_set_size=2000, lora_target_modules=['q_proj', 'v_proj'], resume_from_checkpoint=True)
Found cached dataset json (/root/.cache/huggingface/datasets/json/default-9abf0eaf9929841c/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e)
100% 1/1 [00:00<00:00, 461.06it/s]
DatasetDict({
train: Dataset({
features: ['instruction', 'input', 'output'],
num_rows: 51942
})
})
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in mixed int8. Either pass torch_dtype=torch.float16 or don't pass this argument at all to remove this warning.
Loading checkpoint shards: 100% 33/33 [01:03<00:00, 1.92s/it]
The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'LLaMATokenizer'.
The class this function is called from is 'LlamaTokenizer'.
trainable params: 4194304 || all params: 6742609920 || trainable%: 0.06220594176090199
Loading cached split indices for dataset at /root/.cache/huggingface/datasets/json/default-9abf0eaf9929841c/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e/cache-7396bb661538563c.arrow and /root/.cache/huggingface/datasets/json/default-9abf0eaf9929841c/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e/cache-e0ee9ca563d38c5a.arrow
***** Running training *****
Num Epochs = 3
Instantaneous batch size per GPU = 4
Gradient Accumulation steps = 32
Total train batch size (w. parallel, distributed & accumulation) = 128
Total optimization steps = 390
Saving steps = 39
There were missing keys in the checkpoint model loaded: ['base_model.model.model.embed_tokens.weight', 'base_model.model.model.layers.0.self_attn.q_proj.weight', 'base_model.model.model.layers.0.self_attn.k_proj.weight', 'base_model.model.model.layers.0.self_attn.v_proj.weight', 'base_model.model.model.layers.0.self_attn.o_proj.weight', 'base_model.model.model.layers.0.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.0.mlp.gate_proj.weight', 'base_model.model.model.layers.0.mlp.down_proj.weight', 'base_model.model.model.layers.0.mlp.up_proj.weight', 'base_model.model.model.layers.0.input_layernorm.weight', 'base_model.model.model.layers.0.post_attention_layernorm.weight', 'base_model.model.model.layers.1.self_attn.q_proj.weight', 'base_model.model.model.layers.1.self_attn.k_proj.weight', 'base_model.model.model.layers.1.self_attn.v_proj.weight', 'base_model.model.model.layers.1.self_attn.o_proj.weight', 'base_model.model.model.layers.1.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.1.mlp.gate_proj.weight', 'base_model.model.model.layers.1.mlp.down_proj.weight', 'base_model.model.model.layers.1.mlp.up_proj.weight', 'base_model.model.model.layers.1.input_layernorm.weight', 'base_model.model.model.layers.1.post_attention_layernorm.weight', 'base_model.model.model.layers.2.self_attn.q_proj.weight', 'base_model.model.model.layers.2.self_attn.k_proj.weight', 'base_model.model.model.layers.2.self_attn.v_proj.weight', 'base_model.model.model.layers.2.self_attn.o_proj.weight', 'base_model.model.model.layers.2.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.2.mlp.gate_proj.weight', 'base_model.model.model.layers.2.mlp.down_proj.weight', 'base_model.model.model.layers.2.mlp.up_proj.weight', 'base_model.model.model.layers.2.input_layernorm.weight', 'base_model.model.model.layers.2.post_attention_layernorm.weight', 'base_model.model.model.layers.3.self_attn.q_proj.weight', 'base_model.model.model.layers.3.self_attn.k_proj.weight', 'base_model.model.model.layers.3.self_attn.v_proj.weight', 'base_model.model.model.layers.3.self_attn.o_proj.weight', 'base_model.model.model.layers.3.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.3.mlp.gate_proj.weight', 'base_model.model.model.layers.3.mlp.down_proj.weight', 'base_model.model.model.layers.3.mlp.up_proj.weight', 'base_model.model.model.layers.3.input_layernorm.weight', 'base_model.model.model.layers.3.post_attention_layernorm.weight', 'base_model.model.model.layers.4.self_attn.q_proj.weight', 'base_model.model.model.layers.4.self_attn.k_proj.weight', 'base_model.model.model.layers.4.self_attn.v_proj.weight', 'base_model.model.model.layers.4.self_attn.o_proj.weight', 'base_model.model.model.layers.4.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.4.mlp.gate_proj.weight', 'base_model.model.model.layers.4.mlp.down_proj.weight', 'base_model.model.model.layers.4.mlp.up_proj.weight', 'base_model.model.model.layers.4.input_layernorm.weight', 'base_model.model.model.layers.4.post_attention_layernorm.weight', 'base_model.model.model.layers.5.self_attn.q_proj.weight', 'base_model.model.model.layers.5.self_attn.k_proj.weight', 'base_model.model.model.layers.5.self_attn.v_proj.weight', 'base_model.model.model.layers.5.self_attn.o_proj.weight', 'base_model.model.model.layers.5.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.5.mlp.gate_proj.weight', 'base_model.model.model.layers.5.mlp.down_proj.weight', 'base_model.model.model.layers.5.mlp.up_proj.weight', 'base_model.model.model.layers.5.input_layernorm.weight', 'base_model.model.model.layers.5.post_attention_layernorm.weight', 'base_model.model.model.layers.6.self_attn.q_proj.weight', 'base_model.model.model.layers.6.self_attn.k_proj.weight', 'base_model.model.model.layers.6.self_attn.v_proj.weight', 'base_model.model.model.layers.6.self_attn.o_proj.weight', 'base_model.model.model.layers.6.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.6.mlp.gate_proj.weight', 'base_model.model.model.layers.6.mlp.down_proj.weight', 'base_model.model.model.layers.6.mlp.up_proj.weight', 'base_model.model.model.layers.6.input_layernorm.weight', 'base_model.model.model.layers.6.post_attention_layernorm.weight', 'base_model.model.model.layers.7.self_attn.q_proj.weight', 'base_model.model.model.layers.7.self_attn.k_proj.weight', 'base_model.model.model.layers.7.self_attn.v_proj.weight', 'base_model.model.model.layers.7.self_attn.o_proj.weight', 'base_model.model.model.layers.7.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.7.mlp.gate_proj.weight', 'base_model.model.model.layers.7.mlp.down_proj.weight', 'base_model.model.model.layers.7.mlp.up_proj.weight', 'base_model.model.model.layers.7.input_layernorm.weight', 'base_model.model.model.layers.7.post_attention_layernorm.weight', 'base_model.model.model.layers.8.self_attn.q_proj.weight', 'base_model.model.model.layers.8.self_attn.k_proj.weight', 'base_model.model.model.layers.8.self_attn.v_proj.weight', 'base_model.model.model.layers.8.self_attn.o_proj.weight', 'base_model.model.model.layers.8.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.8.mlp.gate_proj.weight', 'base_model.model.model.layers.8.mlp.down_proj.weight', 'base_model.model.model.layers.8.mlp.up_proj.weight', 'base_model.model.model.layers.8.input_layernorm.weight', 'base_model.model.model.layers.8.post_attention_layernorm.weight', 'base_model.model.model.layers.9.self_attn.q_proj.weight', 'base_model.model.model.layers.9.self_attn.k_proj.weight', 'base_model.model.model.layers.9.self_attn.v_proj.weight', 'base_model.model.model.layers.9.self_attn.o_proj.weight', 'base_model.model.model.layers.9.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.9.mlp.gate_proj.weight', 'base_model.model.model.layers.9.mlp.down_proj.weight', 'base_model.model.model.layers.9.mlp.up_proj.weight', 'base_model.model.model.layers.9.input_layernorm.weight', 'base_model.model.model.layers.9.post_attention_layernorm.weight', 'base_model.model.model.layers.10.self_attn.q_proj.weight', 'base_model.model.model.layers.10.self_attn.k_proj.weight', 'base_model.model.model.layers.10.self_attn.v_proj.weight', 'base_model.model.model.layers.10.self_attn.o_proj.weight', 'base_model.model.model.layers.10.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.10.mlp.gate_proj.weight', 'base_model.model.model.layers.10.mlp.down_proj.weight', 'base_model.model.model.layers.10.mlp.up_proj.weight', 'base_model.model.model.layers.10.input_layernorm.weight', 'base_model.model.model.layers.10.post_attention_layernorm.weight', 'base_model.model.model.layers.11.self_attn.q_proj.weight', 'base_model.model.model.layers.11.self_attn.k_proj.weight', 'base_model.model.model.layers.11.self_attn.v_proj.weight', 'base_model.model.model.layers.11.self_attn.o_proj.weight', 'base_model.model.model.layers.11.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.11.mlp.gate_proj.weight', 'base_model.model.model.layers.11.mlp.down_proj.weight', 'base_model.model.model.layers.11.mlp.up_proj.weight', 'base_model.model.model.layers.11.input_layernorm.weight', 'base_model.model.model.layers.11.post_attention_layernorm.weight', 'base_model.model.model.layers.12.self_attn.q_proj.weight', 'base_model.model.model.layers.12.self_attn.k_proj.weight', 'base_model.model.model.layers.12.self_attn.v_proj.weight', 'base_model.model.model.layers.12.self_attn.o_proj.weight', 'base_model.model.model.layers.12.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.12.mlp.gate_proj.weight', 'base_model.model.model.layers.12.mlp.down_proj.weight', 'base_model.model.model.layers.12.mlp.up_proj.weight', 'base_model.model.model.layers.12.input_layernorm.weight', 'base_model.model.model.layers.12.post_attention_layernorm.weight', 'base_model.model.model.layers.13.self_attn.q_proj.weight', 'base_model.model.model.layers.13.self_attn.k_proj.weight', 'base_model.model.model.layers.13.self_attn.v_proj.weight', 'base_model.model.model.layers.13.self_attn.o_proj.weight', 'base_model.model.model.layers.13.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.13.mlp.gate_proj.weight', 'base_model.model.model.layers.13.mlp.down_proj.weight', 'base_model.model.model.layers.13.mlp.up_proj.weight', 'base_model.model.model.layers.13.input_layernorm.weight', 'base_model.model.model.layers.13.post_attention_layernorm.weight', 'base_model.model.model.layers.14.self_attn.q_proj.weight', 'base_model.model.model.layers.14.self_attn.k_proj.weight', 'base_model.model.model.layers.14.self_attn.v_proj.weight', 'base_model.model.model.layers.14.self_attn.o_proj.weight', 'base_model.model.model.layers.14.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.14.mlp.gate_proj.weight', 'base_model.model.model.layers.14.mlp.down_proj.weight', 'base_model.model.model.layers.14.mlp.up_proj.weight', 'base_model.model.model.layers.14.input_layernorm.weight', 'base_model.model.model.layers.14.post_attention_layernorm.weight', 'base_model.model.model.layers.15.self_attn.q_proj.weight', 'base_model.model.model.layers.15.self_attn.k_proj.weight', 'base_model.model.model.layers.15.self_attn.v_proj.weight', 'base_model.model.model.layers.15.self_attn.o_proj.weight', 'base_model.model.model.layers.15.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.15.mlp.gate_proj.weight', 'base_model.model.model.layers.15.mlp.down_proj.weight', 'base_model.model.model.layers.15.mlp.up_proj.weight', 'base_model.model.model.layers.15.input_layernorm.weight', 'base_model.model.model.layers.15.post_attention_layernorm.weight', 'base_model.model.model.layers.16.self_attn.q_proj.weight', 'base_model.model.model.layers.16.self_attn.k_proj.weight', 'base_model.model.model.layers.16.self_attn.v_proj.weight', 'base_model.model.model.layers.16.self_attn.o_proj.weight', 'base_model.model.model.layers.16.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.16.mlp.gate_proj.weight', 'base_model.model.model.layers.16.mlp.down_proj.weight', 'base_model.model.model.layers.16.mlp.up_proj.weight', 'base_model.model.model.layers.16.input_layernorm.weight', 'base_model.model.model.layers.16.post_attention_layernorm.weight', 'base_model.model.model.layers.17.self_attn.q_proj.weight', 'base_model.model.model.layers.17.self_attn.k_proj.weight', 'base_model.model.model.layers.17.self_attn.v_proj.weight', 'base_model.model.model.layers.17.self_attn.o_proj.weight', 'base_model.model.model.layers.17.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.17.mlp.gate_proj.weight', 'base_model.model.model.layers.17.mlp.down_proj.weight', 'base_model.model.model.layers.17.mlp.up_proj.weight', 'base_model.model.model.layers.17.input_layernorm.weight', 'base_model.model.model.layers.17.post_attention_layernorm.weight', 'base_model.model.model.layers.18.self_attn.q_proj.weight', 'base_model.model.model.layers.18.self_attn.k_proj.weight', 'base_model.model.model.layers.18.self_attn.v_proj.weight', 'base_model.model.model.layers.18.self_attn.o_proj.weight', 'base_model.model.model.layers.18.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.18.mlp.gate_proj.weight', 'base_model.model.model.layers.18.mlp.down_proj.weight', 'base_model.model.model.layers.18.mlp.up_proj.weight', 'base_model.model.model.layers.18.input_layernorm.weight', 'base_model.model.model.layers.18.post_attention_layernorm.weight', 'base_model.model.model.layers.19.self_attn.q_proj.weight', 'base_model.model.model.layers.19.self_attn.k_proj.weight', 'base_model.model.model.layers.19.self_attn.v_proj.weight', 'base_model.model.model.layers.19.self_attn.o_proj.weight', 'base_model.model.model.layers.19.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.19.mlp.gate_proj.weight', 'base_model.model.model.layers.19.mlp.down_proj.weight', 'base_model.model.model.layers.19.mlp.up_proj.weight', 'base_model.model.model.layers.19.input_layernorm.weight', 'base_model.model.model.layers.19.post_attention_layernorm.weight', 'base_model.model.model.layers.20.self_attn.q_proj.weight', 'base_model.model.model.layers.20.self_attn.k_proj.weight', 'base_model.model.model.layers.20.self_attn.v_proj.weight', 'base_model.model.model.layers.20.self_attn.o_proj.weight', 'base_model.model.model.layers.20.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.20.mlp.gate_proj.weight', 'base_model.model.model.layers.20.mlp.down_proj.weight', 'base_model.model.model.layers.20.mlp.up_proj.weight', 'base_model.model.model.layers.20.input_layernorm.weight', 'base_model.model.model.layers.20.post_attention_layernorm.weight', 'base_model.model.model.layers.21.self_attn.q_proj.weight', 'base_model.model.model.layers.21.self_attn.k_proj.weight', 'base_model.model.model.layers.21.self_attn.v_proj.weight', 'base_model.model.model.layers.21.self_attn.o_proj.weight', 'base_model.model.model.layers.21.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.21.mlp.gate_proj.weight', 'base_model.model.model.layers.21.mlp.down_proj.weight', 'base_model.model.model.layers.21.mlp.up_proj.weight', 'base_model.model.model.layers.21.input_layernorm.weight', 'base_model.model.model.layers.21.post_attention_layernorm.weight', 'base_model.model.model.layers.22.self_attn.q_proj.weight', 'base_model.model.model.layers.22.self_attn.k_proj.weight', 'base_model.model.model.layers.22.self_attn.v_proj.weight', 'base_model.model.model.layers.22.self_attn.o_proj.weight', 'base_model.model.model.layers.22.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.22.mlp.gate_proj.weight', 'base_model.model.model.layers.22.mlp.down_proj.weight', 'base_model.model.model.layers.22.mlp.up_proj.weight', 'base_model.model.model.layers.22.input_layernorm.weight', 'base_model.model.model.layers.22.post_attention_layernorm.weight', 'base_model.model.model.layers.23.self_attn.q_proj.weight', 'base_model.model.model.layers.23.self_attn.k_proj.weight', 'base_model.model.model.layers.23.self_attn.v_proj.weight', 'base_model.model.model.layers.23.self_attn.o_proj.weight', 'base_model.model.model.layers.23.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.23.mlp.gate_proj.weight', 'base_model.model.model.layers.23.mlp.down_proj.weight', 'base_model.model.model.layers.23.mlp.up_proj.weight', 'base_model.model.model.layers.23.input_layernorm.weight', 'base_model.model.model.layers.23.post_attention_layernorm.weight', 'base_model.model.model.layers.24.self_attn.q_proj.weight', 'base_model.model.model.layers.24.self_attn.k_proj.weight', 'base_model.model.model.layers.24.self_attn.v_proj.weight', 'base_model.model.model.layers.24.self_attn.o_proj.weight', 'base_model.model.model.layers.24.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.24.mlp.gate_proj.weight', 'base_model.model.model.layers.24.mlp.down_proj.weight', 'base_model.model.model.layers.24.mlp.up_proj.weight', 'base_model.model.model.layers.24.input_layernorm.weight', 'base_model.model.model.layers.24.post_attention_layernorm.weight', 'base_model.model.model.layers.25.self_attn.q_proj.weight', 'base_model.model.model.layers.25.self_attn.k_proj.weight', 'base_model.model.model.layers.25.self_attn.v_proj.weight', 'base_model.model.model.layers.25.self_attn.o_proj.weight', 'base_model.model.model.layers.25.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.25.mlp.gate_proj.weight', 'base_model.model.model.layers.25.mlp.down_proj.weight', 'base_model.model.model.layers.25.mlp.up_proj.weight', 'base_model.model.model.layers.25.input_layernorm.weight', 'base_model.model.model.layers.25.post_attention_layernorm.weight', 'base_model.model.model.layers.26.self_attn.q_proj.weight', 'base_model.model.model.layers.26.self_attn.k_proj.weight', 'base_model.model.model.layers.26.self_attn.v_proj.weight', 'base_model.model.model.layers.26.self_attn.o_proj.weight', 'base_model.model.model.layers.26.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.26.mlp.gate_proj.weight', 'base_model.model.model.layers.26.mlp.down_proj.weight', 'base_model.model.model.layers.26.mlp.up_proj.weight', 'base_model.model.model.layers.26.input_layernorm.weight', 'base_model.model.model.layers.26.post_attention_layernorm.weight', 'base_model.model.model.layers.27.self_attn.q_proj.weight', 'base_model.model.model.layers.27.self_attn.k_proj.weight', 'base_model.model.model.layers.27.self_attn.v_proj.weight', 'base_model.model.model.layers.27.self_attn.o_proj.weight', 'base_model.model.model.layers.27.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.27.mlp.gate_proj.weight', 'base_model.model.model.layers.27.mlp.down_proj.weight', 'base_model.model.model.layers.27.mlp.up_proj.weight', 'base_model.model.model.layers.27.input_layernorm.weight', 'base_model.model.model.layers.27.post_attention_layernorm.weight', 'base_model.model.model.layers.28.self_attn.q_proj.weight', 'base_model.model.model.layers.28.self_attn.k_proj.weight', 'base_model.model.model.layers.28.self_attn.v_proj.weight', 'base_model.model.model.layers.28.self_attn.o_proj.weight', 'base_model.model.model.layers.28.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.28.mlp.gate_proj.weight', 'base_model.model.model.layers.28.mlp.down_proj.weight', 'base_model.model.model.layers.28.mlp.up_proj.weight', 'base_model.model.model.layers.28.input_layernorm.weight', 'base_model.model.model.layers.28.post_attention_layernorm.weight', 'base_model.model.model.layers.29.self_attn.q_proj.weight', 'base_model.model.model.layers.29.self_attn.k_proj.weight', 'base_model.model.model.layers.29.self_attn.v_proj.weight', 'base_model.model.model.layers.29.self_attn.o_proj.weight', 'base_model.model.model.layers.29.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.29.mlp.gate_proj.weight', 'base_model.model.model.layers.29.mlp.down_proj.weight', 'base_model.model.model.layers.29.mlp.up_proj.weight', 'base_model.model.model.layers.29.input_layernorm.weight', 'base_model.model.model.layers.29.post_attention_layernorm.weight', 'base_model.model.model.layers.30.self_attn.q_proj.weight', 'base_model.model.model.layers.30.self_attn.k_proj.weight', 'base_model.model.model.layers.30.self_attn.v_proj.weight', 'base_model.model.model.layers.30.self_attn.o_proj.weight', 'base_model.model.model.layers.30.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.30.mlp.gate_proj.weight', 'base_model.model.model.layers.30.mlp.down_proj.weight', 'base_model.model.model.layers.30.mlp.up_proj.weight', 'base_model.model.model.layers.30.input_layernorm.weight', 'base_model.model.model.layers.30.post_attention_layernorm.weight', 'base_model.model.model.layers.31.self_attn.q_proj.weight', 'base_model.model.model.layers.31.self_attn.k_proj.weight', 'base_model.model.model.layers.31.self_attn.v_proj.weight', 'base_model.model.model.layers.31.self_attn.o_proj.weight', 'base_model.model.model.layers.31.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.31.mlp.gate_proj.weight', 'base_model.model.model.layers.31.mlp.down_proj.weight', 'base_model.model.model.layers.31.mlp.up_proj.weight', 'base_model.model.model.layers.31.input_layernorm.weight', 'base_model.model.model.layers.31.post_attention_layernorm.weight', 'base_model.model.model.norm.weight', 'base_model.model.lm_head.0.weight'].
/usr/local/lib/python3.9/dist-packages/transformers/optimization.py:391: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
warnings.warn(
wandb: Currently logged in as: utensil. Use `wandb login --relogin` to force relogin
wandb: Tracking run with wandb version 0.14.2
wandb: Run data is saved locally in /content/code/wandb/run-20230419_133905-qwu7ug1n
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run restful-wood-2
wandb: ⭐️ View project at https://wandb.ai/utensil/huggingface
wandb: 🚀 View run at https://wandb.ai/utensil/huggingface/runs/qwu7ug1n
67% 781/1170 [01:21<00:40, 9.59it/s]Traceback (most recent call last):
File "/content/code/uniform_finetune.py", line 353, in <module>
train(args)
File "/content/code/uniform_finetune.py", line 321, in train
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)
File "/usr/local/lib/python3.9/dist-packages/transformers/trainer.py", line 1661, in train
return inner_training_loop(
File "/usr/local/lib/python3.9/dist-packages/transformers/trainer.py", line 1928, in _inner_training_loop
tr_loss_step = self.training_step(model, inputs)
File "/usr/local/lib/python3.9/dist-packages/transformers/trainer.py", line 2708, in training_step
self.scaler.scale(loss).backward()
File "/usr/local/lib/python3.9/dist-packages/torch/_tensor.py", line 487, in backward
torch.autograd.backward(
File "/usr/local/lib/python3.9/dist-packages/torch/autograd/__init__.py", line 200, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
KeyboardInterrupt
╭───────────────────── Traceback (most recent call last) ──────────────────────╮
│ /content/code/uniform_finetune.py:353 in <module> │
│ │
│ 350 │ args, _ = parser.parse_known_args() │
│ 351 │ print(args) │
│ 352 │ │
│ ❱ 353 │ train(args) │
│ 354 │
│ │
│ /content/code/uniform_finetune.py:321 in train │
│ │
│ 318 │ if torch.__version__ >= "2" and sys.platform != "win32": │
│ 319 │ │ model = torch.compile(model) │
│ 320 │ │
│ ❱ 321 │ trainer.train(resume_from_checkpoint=args.resume_from_checkpoint) │
│ 322 │ │
│ 323 │ model.save_pretrained(output_dir) │
│ 324 │
│ │
│ /usr/local/lib/python3.9/dist-packages/transformers/trainer.py:1661 in train │
│ │
│ 1658 │ │ inner_training_loop = find_executable_batch_size( │
│ 1659 │ │ │ self._inner_training_loop, self._train_batch_size, args.a │
│ 1660 │ │ ) │
│ ❱ 1661 │ │ return inner_training_loop( │
│ 1662 │ │ │ args=args, │
│ 1663 │ │ │ resume_from_checkpoint=resume_from_checkpoint, │
│ 1664 │ │ │ trial=trial, │
│ │
│ /usr/local/lib/python3.9/dist-packages/transformers/trainer.py:1928 in │
│ _inner_training_loop │
│ │
│ 1925 │ │ │ │ │ with model.no_sync(): │
│ 1926 │ │ │ │ │ │ tr_loss_step = self.training_step(model, inpu │
│ 1927 │ │ │ │ else: │
│ ❱ 1928 │ │ │ │ │ tr_loss_step = self.training_step(model, inputs) │
│ 1929 │ │ │ │ │
│ 1930 │ │ │ │ if ( │
│ 1931 │ │ │ │ │ args.logging_nan_inf_filter │
│ │
│ /usr/local/lib/python3.9/dist-packages/transformers/trainer.py:2708 in │
│ training_step │
│ │
│ 2705 │ │ │ loss = loss / self.args.gradient_accumulation_steps │
│ 2706 │ │ │
│ 2707 │ │ if self.do_grad_scaling: │
│ ❱ 2708 │ │ │ self.scaler.scale(loss).backward() │
│ 2709 │ │ elif self.use_apex: │
│ 2710 │ │ │ with amp.scale_loss(loss, self.optimizer) as scaled_loss: │
│ 2711 │ │ │ │ scaled_loss.backward() │
│ │
│ /usr/local/lib/python3.9/dist-packages/torch/_tensor.py:487 in backward │
│ │
│ 484 │ │ │ │ create_graph=create_graph, │
│ 485 │ │ │ │ inputs=inputs, │
│ 486 │ │ │ ) │
│ ❱ 487 │ │ torch.autograd.backward( │
│ 488 │ │ │ self, gradient, retain_graph, create_graph, inputs=inputs │
│ 489 │ │ ) │
│ 490 │
│ │
│ /usr/local/lib/python3.9/dist-packages/torch/autograd/__init__.py:200 in │
│ backward │
│ │
│ 197 │ # The reason we repeat same the comment below is that │
│ 198 │ # some Python versions print out the first line of a multi-line fu │
│ 199 │ # calls in the traceback and some print out the last line │
│ ❱ 200 │ Variable._execution_engine.run_backward( # Calls into the C++ eng │
│ 201 │ │ tensors, grad_tensors_, retain_graph, create_graph, inputs, │
│ 202 │ │ allow_unreachable=True, accumulate_grad=True) # Calls into th │
│ 203 │
╰──────────────────────────────────────────────────────────────────────────────╯
KeyboardInterrupt
wandb: Waiting for W&B process to finish... (failed 255). Press Control-C to abort syncing.
wandb: 🚀 View run restful-wood-2 at: https://wandb.ai/utensil/huggingface/runs/qwu7ug1n
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20230419_133905-qwu7ug1n/logs
^C
In [25]:
!ls -lhta /workspace/code/saved_models/llama-7b-hf_alpaca/checkpoint-351
total 49M drwxr-xr-x 7 root root 4.0K Apr 19 13:35 .. -rw-r--r-- 1 root root 4.2K Apr 19 13:34 trainer_state.json -rw-r--r-- 1 root root 3.5K Apr 19 13:34 training_args.bin -rw-r--r-- 1 root root 557 Apr 19 13:34 scaler.pt -rw-r--r-- 1 root root 627 Apr 19 13:34 scheduler.pt -rw-r--r-- 1 root root 15K Apr 19 13:34 rng_state.pth -rw-r--r-- 1 root root 17M Apr 19 13:34 pytorch_model.bin -rw-r--r-- 1 root root 33M Apr 19 13:34 optimizer.pt drwxr-xr-x 2 root root 4.0K Apr 19 13:17 .
In [26]:
# instruction finetuning: from the specified checkpoint
!cd /workspace/code && python uniform_finetune.py --model_type llama --model_name_or_path decapoda-research/llama-7b-hf --data alpaca --lora_target_modules q_proj v_proj --per_gpu_train_batch_size 4 --learning_rate 3e-4 --epochs 2 --report_to wandb --resume_from_checkpoint /workspace/code/saved_models/llama-7b-hf_alpaca/checkpoint-351
===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please run
python -m bitsandbytes
and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
================================================================================
bin /usr/local/lib/python3.9/dist-packages/bitsandbytes/libbitsandbytes_cuda118.so
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: /usr/lib64-nvidia did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/sys/fs/cgroup/memory.events /var/colab/cgroup/jupyter-children/memory.events')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('8013'), PosixPath('//172.28.0.1'), PosixPath('http')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('//colab.research.google.com/tun/m/cc48301118ce562b961b3c22d803539adc1e0c19/gpu-t4-s-32k5i5k8yhbau --tunnel_background_save_delay=10s --tunnel_periodic_background_save_frequency=30m0s --enable_output_coalescing=true --output_coalescing_required=true'), PosixPath('--listen_host=172.28.0.12 --target_host=172.28.0.12 --tunnel_background_save_url=https')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/env/python')}
warn(msg)
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//ipykernel.pylab.backend_inline')}
warn(msg)
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching in backup paths...
/usr/local/lib/python3.9/dist-packages/bitsandbytes/cuda_setup/main.py:145: UserWarning: Found duplicate ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] files: {PosixPath('/usr/local/cuda/lib64/libcudart.so.11.0'), PosixPath('/usr/local/cuda/lib64/libcudart.so')}.. We'll flip a coin and try one of these, in order to fail forward.
Either way, this might cause trouble in the future:
If you get `CUDA error: invalid device function` errors, the above might be the cause and the solution is to make sure only one ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] in the paths that we search based on your env.
warn(msg)
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so.11.0
CUDA SETUP: Highest compute capability among GPUs detected: 7.5
CUDA SETUP: Detected CUDA version 118
CUDA SETUP: Loading binary /usr/local/lib/python3.9/dist-packages/bitsandbytes/libbitsandbytes_cuda118.so...
2023-04-19 13:41:34.276398: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT
Namespace(size=None, data='alpaca', local_rank=-1, model_type='llama', model_name_or_path='decapoda-research/llama-7b-hf', per_gpu_train_batch_size=4, gradient_accumulation_steps=32, epochs=2, learning_rate=0.0003, cutoff_len=512, lora_r=8, lora_alpha=16, lora_dropout=0.05, val_set_size=2000, lora_target_modules=['q_proj', 'v_proj'], resume_from_checkpoint='/workspace/code/saved_models/llama-7b-hf_alpaca/checkpoint-351')
Found cached dataset json (/root/.cache/huggingface/datasets/json/default-9abf0eaf9929841c/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e)
100% 1/1 [00:00<00:00, 467.80it/s]
DatasetDict({
train: Dataset({
features: ['instruction', 'input', 'output'],
num_rows: 51942
})
})
Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in mixed int8. Either pass torch_dtype=torch.float16 or don't pass this argument at all to remove this warning.
Loading checkpoint shards: 100% 33/33 [01:04<00:00, 1.94s/it]
The tokenizer class you load from this checkpoint is not the same type as the class this function is called from. It may result in unexpected tokenization.
The tokenizer class you load from this checkpoint is 'LLaMATokenizer'.
The class this function is called from is 'LlamaTokenizer'.
trainable params: 4194304 || all params: 6742609920 || trainable%: 0.06220594176090199
Loading cached split indices for dataset at /root/.cache/huggingface/datasets/json/default-9abf0eaf9929841c/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e/cache-7396bb661538563c.arrow and /root/.cache/huggingface/datasets/json/default-9abf0eaf9929841c/0.0.0/fe5dd6ea2639a6df622901539cb550cf8797e5a6b2dd7af1cf934bed8e233e6e/cache-e0ee9ca563d38c5a.arrow
***** Running training *****
Num Epochs = 2
Instantaneous batch size per GPU = 4
Gradient Accumulation steps = 32
Total train batch size (w. parallel, distributed & accumulation) = 128
Total optimization steps = 390
Saving steps = 39
There were missing keys in the checkpoint model loaded: ['base_model.model.model.embed_tokens.weight', 'base_model.model.model.layers.0.self_attn.q_proj.weight', 'base_model.model.model.layers.0.self_attn.k_proj.weight', 'base_model.model.model.layers.0.self_attn.v_proj.weight', 'base_model.model.model.layers.0.self_attn.o_proj.weight', 'base_model.model.model.layers.0.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.0.mlp.gate_proj.weight', 'base_model.model.model.layers.0.mlp.down_proj.weight', 'base_model.model.model.layers.0.mlp.up_proj.weight', 'base_model.model.model.layers.0.input_layernorm.weight', 'base_model.model.model.layers.0.post_attention_layernorm.weight', 'base_model.model.model.layers.1.self_attn.q_proj.weight', 'base_model.model.model.layers.1.self_attn.k_proj.weight', 'base_model.model.model.layers.1.self_attn.v_proj.weight', 'base_model.model.model.layers.1.self_attn.o_proj.weight', 'base_model.model.model.layers.1.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.1.mlp.gate_proj.weight', 'base_model.model.model.layers.1.mlp.down_proj.weight', 'base_model.model.model.layers.1.mlp.up_proj.weight', 'base_model.model.model.layers.1.input_layernorm.weight', 'base_model.model.model.layers.1.post_attention_layernorm.weight', 'base_model.model.model.layers.2.self_attn.q_proj.weight', 'base_model.model.model.layers.2.self_attn.k_proj.weight', 'base_model.model.model.layers.2.self_attn.v_proj.weight', 'base_model.model.model.layers.2.self_attn.o_proj.weight', 'base_model.model.model.layers.2.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.2.mlp.gate_proj.weight', 'base_model.model.model.layers.2.mlp.down_proj.weight', 'base_model.model.model.layers.2.mlp.up_proj.weight', 'base_model.model.model.layers.2.input_layernorm.weight', 'base_model.model.model.layers.2.post_attention_layernorm.weight', 'base_model.model.model.layers.3.self_attn.q_proj.weight', 'base_model.model.model.layers.3.self_attn.k_proj.weight', 'base_model.model.model.layers.3.self_attn.v_proj.weight', 'base_model.model.model.layers.3.self_attn.o_proj.weight', 'base_model.model.model.layers.3.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.3.mlp.gate_proj.weight', 'base_model.model.model.layers.3.mlp.down_proj.weight', 'base_model.model.model.layers.3.mlp.up_proj.weight', 'base_model.model.model.layers.3.input_layernorm.weight', 'base_model.model.model.layers.3.post_attention_layernorm.weight', 'base_model.model.model.layers.4.self_attn.q_proj.weight', 'base_model.model.model.layers.4.self_attn.k_proj.weight', 'base_model.model.model.layers.4.self_attn.v_proj.weight', 'base_model.model.model.layers.4.self_attn.o_proj.weight', 'base_model.model.model.layers.4.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.4.mlp.gate_proj.weight', 'base_model.model.model.layers.4.mlp.down_proj.weight', 'base_model.model.model.layers.4.mlp.up_proj.weight', 'base_model.model.model.layers.4.input_layernorm.weight', 'base_model.model.model.layers.4.post_attention_layernorm.weight', 'base_model.model.model.layers.5.self_attn.q_proj.weight', 'base_model.model.model.layers.5.self_attn.k_proj.weight', 'base_model.model.model.layers.5.self_attn.v_proj.weight', 'base_model.model.model.layers.5.self_attn.o_proj.weight', 'base_model.model.model.layers.5.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.5.mlp.gate_proj.weight', 'base_model.model.model.layers.5.mlp.down_proj.weight', 'base_model.model.model.layers.5.mlp.up_proj.weight', 'base_model.model.model.layers.5.input_layernorm.weight', 'base_model.model.model.layers.5.post_attention_layernorm.weight', 'base_model.model.model.layers.6.self_attn.q_proj.weight', 'base_model.model.model.layers.6.self_attn.k_proj.weight', 'base_model.model.model.layers.6.self_attn.v_proj.weight', 'base_model.model.model.layers.6.self_attn.o_proj.weight', 'base_model.model.model.layers.6.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.6.mlp.gate_proj.weight', 'base_model.model.model.layers.6.mlp.down_proj.weight', 'base_model.model.model.layers.6.mlp.up_proj.weight', 'base_model.model.model.layers.6.input_layernorm.weight', 'base_model.model.model.layers.6.post_attention_layernorm.weight', 'base_model.model.model.layers.7.self_attn.q_proj.weight', 'base_model.model.model.layers.7.self_attn.k_proj.weight', 'base_model.model.model.layers.7.self_attn.v_proj.weight', 'base_model.model.model.layers.7.self_attn.o_proj.weight', 'base_model.model.model.layers.7.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.7.mlp.gate_proj.weight', 'base_model.model.model.layers.7.mlp.down_proj.weight', 'base_model.model.model.layers.7.mlp.up_proj.weight', 'base_model.model.model.layers.7.input_layernorm.weight', 'base_model.model.model.layers.7.post_attention_layernorm.weight', 'base_model.model.model.layers.8.self_attn.q_proj.weight', 'base_model.model.model.layers.8.self_attn.k_proj.weight', 'base_model.model.model.layers.8.self_attn.v_proj.weight', 'base_model.model.model.layers.8.self_attn.o_proj.weight', 'base_model.model.model.layers.8.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.8.mlp.gate_proj.weight', 'base_model.model.model.layers.8.mlp.down_proj.weight', 'base_model.model.model.layers.8.mlp.up_proj.weight', 'base_model.model.model.layers.8.input_layernorm.weight', 'base_model.model.model.layers.8.post_attention_layernorm.weight', 'base_model.model.model.layers.9.self_attn.q_proj.weight', 'base_model.model.model.layers.9.self_attn.k_proj.weight', 'base_model.model.model.layers.9.self_attn.v_proj.weight', 'base_model.model.model.layers.9.self_attn.o_proj.weight', 'base_model.model.model.layers.9.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.9.mlp.gate_proj.weight', 'base_model.model.model.layers.9.mlp.down_proj.weight', 'base_model.model.model.layers.9.mlp.up_proj.weight', 'base_model.model.model.layers.9.input_layernorm.weight', 'base_model.model.model.layers.9.post_attention_layernorm.weight', 'base_model.model.model.layers.10.self_attn.q_proj.weight', 'base_model.model.model.layers.10.self_attn.k_proj.weight', 'base_model.model.model.layers.10.self_attn.v_proj.weight', 'base_model.model.model.layers.10.self_attn.o_proj.weight', 'base_model.model.model.layers.10.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.10.mlp.gate_proj.weight', 'base_model.model.model.layers.10.mlp.down_proj.weight', 'base_model.model.model.layers.10.mlp.up_proj.weight', 'base_model.model.model.layers.10.input_layernorm.weight', 'base_model.model.model.layers.10.post_attention_layernorm.weight', 'base_model.model.model.layers.11.self_attn.q_proj.weight', 'base_model.model.model.layers.11.self_attn.k_proj.weight', 'base_model.model.model.layers.11.self_attn.v_proj.weight', 'base_model.model.model.layers.11.self_attn.o_proj.weight', 'base_model.model.model.layers.11.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.11.mlp.gate_proj.weight', 'base_model.model.model.layers.11.mlp.down_proj.weight', 'base_model.model.model.layers.11.mlp.up_proj.weight', 'base_model.model.model.layers.11.input_layernorm.weight', 'base_model.model.model.layers.11.post_attention_layernorm.weight', 'base_model.model.model.layers.12.self_attn.q_proj.weight', 'base_model.model.model.layers.12.self_attn.k_proj.weight', 'base_model.model.model.layers.12.self_attn.v_proj.weight', 'base_model.model.model.layers.12.self_attn.o_proj.weight', 'base_model.model.model.layers.12.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.12.mlp.gate_proj.weight', 'base_model.model.model.layers.12.mlp.down_proj.weight', 'base_model.model.model.layers.12.mlp.up_proj.weight', 'base_model.model.model.layers.12.input_layernorm.weight', 'base_model.model.model.layers.12.post_attention_layernorm.weight', 'base_model.model.model.layers.13.self_attn.q_proj.weight', 'base_model.model.model.layers.13.self_attn.k_proj.weight', 'base_model.model.model.layers.13.self_attn.v_proj.weight', 'base_model.model.model.layers.13.self_attn.o_proj.weight', 'base_model.model.model.layers.13.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.13.mlp.gate_proj.weight', 'base_model.model.model.layers.13.mlp.down_proj.weight', 'base_model.model.model.layers.13.mlp.up_proj.weight', 'base_model.model.model.layers.13.input_layernorm.weight', 'base_model.model.model.layers.13.post_attention_layernorm.weight', 'base_model.model.model.layers.14.self_attn.q_proj.weight', 'base_model.model.model.layers.14.self_attn.k_proj.weight', 'base_model.model.model.layers.14.self_attn.v_proj.weight', 'base_model.model.model.layers.14.self_attn.o_proj.weight', 'base_model.model.model.layers.14.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.14.mlp.gate_proj.weight', 'base_model.model.model.layers.14.mlp.down_proj.weight', 'base_model.model.model.layers.14.mlp.up_proj.weight', 'base_model.model.model.layers.14.input_layernorm.weight', 'base_model.model.model.layers.14.post_attention_layernorm.weight', 'base_model.model.model.layers.15.self_attn.q_proj.weight', 'base_model.model.model.layers.15.self_attn.k_proj.weight', 'base_model.model.model.layers.15.self_attn.v_proj.weight', 'base_model.model.model.layers.15.self_attn.o_proj.weight', 'base_model.model.model.layers.15.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.15.mlp.gate_proj.weight', 'base_model.model.model.layers.15.mlp.down_proj.weight', 'base_model.model.model.layers.15.mlp.up_proj.weight', 'base_model.model.model.layers.15.input_layernorm.weight', 'base_model.model.model.layers.15.post_attention_layernorm.weight', 'base_model.model.model.layers.16.self_attn.q_proj.weight', 'base_model.model.model.layers.16.self_attn.k_proj.weight', 'base_model.model.model.layers.16.self_attn.v_proj.weight', 'base_model.model.model.layers.16.self_attn.o_proj.weight', 'base_model.model.model.layers.16.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.16.mlp.gate_proj.weight', 'base_model.model.model.layers.16.mlp.down_proj.weight', 'base_model.model.model.layers.16.mlp.up_proj.weight', 'base_model.model.model.layers.16.input_layernorm.weight', 'base_model.model.model.layers.16.post_attention_layernorm.weight', 'base_model.model.model.layers.17.self_attn.q_proj.weight', 'base_model.model.model.layers.17.self_attn.k_proj.weight', 'base_model.model.model.layers.17.self_attn.v_proj.weight', 'base_model.model.model.layers.17.self_attn.o_proj.weight', 'base_model.model.model.layers.17.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.17.mlp.gate_proj.weight', 'base_model.model.model.layers.17.mlp.down_proj.weight', 'base_model.model.model.layers.17.mlp.up_proj.weight', 'base_model.model.model.layers.17.input_layernorm.weight', 'base_model.model.model.layers.17.post_attention_layernorm.weight', 'base_model.model.model.layers.18.self_attn.q_proj.weight', 'base_model.model.model.layers.18.self_attn.k_proj.weight', 'base_model.model.model.layers.18.self_attn.v_proj.weight', 'base_model.model.model.layers.18.self_attn.o_proj.weight', 'base_model.model.model.layers.18.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.18.mlp.gate_proj.weight', 'base_model.model.model.layers.18.mlp.down_proj.weight', 'base_model.model.model.layers.18.mlp.up_proj.weight', 'base_model.model.model.layers.18.input_layernorm.weight', 'base_model.model.model.layers.18.post_attention_layernorm.weight', 'base_model.model.model.layers.19.self_attn.q_proj.weight', 'base_model.model.model.layers.19.self_attn.k_proj.weight', 'base_model.model.model.layers.19.self_attn.v_proj.weight', 'base_model.model.model.layers.19.self_attn.o_proj.weight', 'base_model.model.model.layers.19.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.19.mlp.gate_proj.weight', 'base_model.model.model.layers.19.mlp.down_proj.weight', 'base_model.model.model.layers.19.mlp.up_proj.weight', 'base_model.model.model.layers.19.input_layernorm.weight', 'base_model.model.model.layers.19.post_attention_layernorm.weight', 'base_model.model.model.layers.20.self_attn.q_proj.weight', 'base_model.model.model.layers.20.self_attn.k_proj.weight', 'base_model.model.model.layers.20.self_attn.v_proj.weight', 'base_model.model.model.layers.20.self_attn.o_proj.weight', 'base_model.model.model.layers.20.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.20.mlp.gate_proj.weight', 'base_model.model.model.layers.20.mlp.down_proj.weight', 'base_model.model.model.layers.20.mlp.up_proj.weight', 'base_model.model.model.layers.20.input_layernorm.weight', 'base_model.model.model.layers.20.post_attention_layernorm.weight', 'base_model.model.model.layers.21.self_attn.q_proj.weight', 'base_model.model.model.layers.21.self_attn.k_proj.weight', 'base_model.model.model.layers.21.self_attn.v_proj.weight', 'base_model.model.model.layers.21.self_attn.o_proj.weight', 'base_model.model.model.layers.21.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.21.mlp.gate_proj.weight', 'base_model.model.model.layers.21.mlp.down_proj.weight', 'base_model.model.model.layers.21.mlp.up_proj.weight', 'base_model.model.model.layers.21.input_layernorm.weight', 'base_model.model.model.layers.21.post_attention_layernorm.weight', 'base_model.model.model.layers.22.self_attn.q_proj.weight', 'base_model.model.model.layers.22.self_attn.k_proj.weight', 'base_model.model.model.layers.22.self_attn.v_proj.weight', 'base_model.model.model.layers.22.self_attn.o_proj.weight', 'base_model.model.model.layers.22.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.22.mlp.gate_proj.weight', 'base_model.model.model.layers.22.mlp.down_proj.weight', 'base_model.model.model.layers.22.mlp.up_proj.weight', 'base_model.model.model.layers.22.input_layernorm.weight', 'base_model.model.model.layers.22.post_attention_layernorm.weight', 'base_model.model.model.layers.23.self_attn.q_proj.weight', 'base_model.model.model.layers.23.self_attn.k_proj.weight', 'base_model.model.model.layers.23.self_attn.v_proj.weight', 'base_model.model.model.layers.23.self_attn.o_proj.weight', 'base_model.model.model.layers.23.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.23.mlp.gate_proj.weight', 'base_model.model.model.layers.23.mlp.down_proj.weight', 'base_model.model.model.layers.23.mlp.up_proj.weight', 'base_model.model.model.layers.23.input_layernorm.weight', 'base_model.model.model.layers.23.post_attention_layernorm.weight', 'base_model.model.model.layers.24.self_attn.q_proj.weight', 'base_model.model.model.layers.24.self_attn.k_proj.weight', 'base_model.model.model.layers.24.self_attn.v_proj.weight', 'base_model.model.model.layers.24.self_attn.o_proj.weight', 'base_model.model.model.layers.24.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.24.mlp.gate_proj.weight', 'base_model.model.model.layers.24.mlp.down_proj.weight', 'base_model.model.model.layers.24.mlp.up_proj.weight', 'base_model.model.model.layers.24.input_layernorm.weight', 'base_model.model.model.layers.24.post_attention_layernorm.weight', 'base_model.model.model.layers.25.self_attn.q_proj.weight', 'base_model.model.model.layers.25.self_attn.k_proj.weight', 'base_model.model.model.layers.25.self_attn.v_proj.weight', 'base_model.model.model.layers.25.self_attn.o_proj.weight', 'base_model.model.model.layers.25.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.25.mlp.gate_proj.weight', 'base_model.model.model.layers.25.mlp.down_proj.weight', 'base_model.model.model.layers.25.mlp.up_proj.weight', 'base_model.model.model.layers.25.input_layernorm.weight', 'base_model.model.model.layers.25.post_attention_layernorm.weight', 'base_model.model.model.layers.26.self_attn.q_proj.weight', 'base_model.model.model.layers.26.self_attn.k_proj.weight', 'base_model.model.model.layers.26.self_attn.v_proj.weight', 'base_model.model.model.layers.26.self_attn.o_proj.weight', 'base_model.model.model.layers.26.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.26.mlp.gate_proj.weight', 'base_model.model.model.layers.26.mlp.down_proj.weight', 'base_model.model.model.layers.26.mlp.up_proj.weight', 'base_model.model.model.layers.26.input_layernorm.weight', 'base_model.model.model.layers.26.post_attention_layernorm.weight', 'base_model.model.model.layers.27.self_attn.q_proj.weight', 'base_model.model.model.layers.27.self_attn.k_proj.weight', 'base_model.model.model.layers.27.self_attn.v_proj.weight', 'base_model.model.model.layers.27.self_attn.o_proj.weight', 'base_model.model.model.layers.27.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.27.mlp.gate_proj.weight', 'base_model.model.model.layers.27.mlp.down_proj.weight', 'base_model.model.model.layers.27.mlp.up_proj.weight', 'base_model.model.model.layers.27.input_layernorm.weight', 'base_model.model.model.layers.27.post_attention_layernorm.weight', 'base_model.model.model.layers.28.self_attn.q_proj.weight', 'base_model.model.model.layers.28.self_attn.k_proj.weight', 'base_model.model.model.layers.28.self_attn.v_proj.weight', 'base_model.model.model.layers.28.self_attn.o_proj.weight', 'base_model.model.model.layers.28.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.28.mlp.gate_proj.weight', 'base_model.model.model.layers.28.mlp.down_proj.weight', 'base_model.model.model.layers.28.mlp.up_proj.weight', 'base_model.model.model.layers.28.input_layernorm.weight', 'base_model.model.model.layers.28.post_attention_layernorm.weight', 'base_model.model.model.layers.29.self_attn.q_proj.weight', 'base_model.model.model.layers.29.self_attn.k_proj.weight', 'base_model.model.model.layers.29.self_attn.v_proj.weight', 'base_model.model.model.layers.29.self_attn.o_proj.weight', 'base_model.model.model.layers.29.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.29.mlp.gate_proj.weight', 'base_model.model.model.layers.29.mlp.down_proj.weight', 'base_model.model.model.layers.29.mlp.up_proj.weight', 'base_model.model.model.layers.29.input_layernorm.weight', 'base_model.model.model.layers.29.post_attention_layernorm.weight', 'base_model.model.model.layers.30.self_attn.q_proj.weight', 'base_model.model.model.layers.30.self_attn.k_proj.weight', 'base_model.model.model.layers.30.self_attn.v_proj.weight', 'base_model.model.model.layers.30.self_attn.o_proj.weight', 'base_model.model.model.layers.30.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.30.mlp.gate_proj.weight', 'base_model.model.model.layers.30.mlp.down_proj.weight', 'base_model.model.model.layers.30.mlp.up_proj.weight', 'base_model.model.model.layers.30.input_layernorm.weight', 'base_model.model.model.layers.30.post_attention_layernorm.weight', 'base_model.model.model.layers.31.self_attn.q_proj.weight', 'base_model.model.model.layers.31.self_attn.k_proj.weight', 'base_model.model.model.layers.31.self_attn.v_proj.weight', 'base_model.model.model.layers.31.self_attn.o_proj.weight', 'base_model.model.model.layers.31.self_attn.rotary_emb.inv_freq', 'base_model.model.model.layers.31.mlp.gate_proj.weight', 'base_model.model.model.layers.31.mlp.down_proj.weight', 'base_model.model.model.layers.31.mlp.up_proj.weight', 'base_model.model.model.layers.31.input_layernorm.weight', 'base_model.model.model.layers.31.post_attention_layernorm.weight', 'base_model.model.model.norm.weight', 'base_model.model.lm_head.0.weight'].
/usr/local/lib/python3.9/dist-packages/transformers/optimization.py:391: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning
warnings.warn(
wandb: Currently logged in as: utensil. Use `wandb login --relogin` to force relogin
wandb: Tracking run with wandb version 0.14.2
wandb: Run data is saved locally in /content/code/wandb/run-20230419_134415-xyekygze
wandb: Run `wandb offline` to turn off syncing.
wandb: Syncing run earnest-music-3
wandb: ⭐️ View project at https://wandb.ai/utensil/huggingface
wandb: 🚀 View run at https://wandb.ai/utensil/huggingface/runs/xyekygze
45% 352/780 [01:22<01:40, 4.28it/s]Traceback (most recent call last):
File "/content/code/uniform_finetune.py", line 353, in <module>
train(args)
File "/content/code/uniform_finetune.py", line 321, in train
trainer.train(resume_from_checkpoint=args.resume_from_checkpoint)
File "/usr/local/lib/python3.9/dist-packages/transformers/trainer.py", line 1661, in train
return inner_training_loop(
File "/usr/local/lib/python3.9/dist-packages/transformers/trainer.py", line 1928, in _inner_training_loop
tr_loss_step = self.training_step(model, inputs)
File "/usr/local/lib/python3.9/dist-packages/transformers/trainer.py", line 2708, in training_step
self.scaler.scale(loss).backward()
File "/usr/local/lib/python3.9/dist-packages/torch/_tensor.py", line 487, in backward
torch.autograd.backward(
File "/usr/local/lib/python3.9/dist-packages/torch/autograd/__init__.py", line 200, in backward
Variable._execution_engine.run_backward( # Calls into the C++ engine to run the backward pass
KeyboardInterrupt
╭───────────────────── Traceback (most recent call last) ──────────────────────╮
│ /content/code/uniform_finetune.py:353 in <module> │
│ │
│ 350 │ args, _ = parser.parse_known_args() │
│ 351 │ print(args) │
│ 352 │ │
│ ❱ 353 │ train(args) │
│ 354 │
│ │
│ /content/code/uniform_finetune.py:321 in train │
│ │
│ 318 │ if torch.__version__ >= "2" and sys.platform != "win32": │
│ 319 │ │ model = torch.compile(model) │
│ 320 │ │
│ ❱ 321 │ trainer.train(resume_from_checkpoint=args.resume_from_checkpoint) │
│ 322 │ │
│ 323 │ model.save_pretrained(output_dir) │
│ 324 │
│ │
│ /usr/local/lib/python3.9/dist-packages/transformers/trainer.py:1661 in train │
│ │
│ 1658 │ │ inner_training_loop = find_executable_batch_size( │
│ 1659 │ │ │ self._inner_training_loop, self._train_batch_size, args.a │
│ 1660 │ │ ) │
│ ❱ 1661 │ │ return inner_training_loop( │
│ 1662 │ │ │ args=args, │
│ 1663 │ │ │ resume_from_checkpoint=resume_from_checkpoint, │
│ 1664 │ │ │ trial=trial, │
│ │
│ /usr/local/lib/python3.9/dist-packages/transformers/trainer.py:1928 in │
│ _inner_training_loop │
│ │
│ 1925 │ │ │ │ │ with model.no_sync(): │
│ 1926 │ │ │ │ │ │ tr_loss_step = self.training_step(model, inpu │
│ 1927 │ │ │ │ else: │
│ ❱ 1928 │ │ │ │ │ tr_loss_step = self.training_step(model, inputs) │
│ 1929 │ │ │ │ │
│ 1930 │ │ │ │ if ( │
│ 1931 │ │ │ │ │ args.logging_nan_inf_filter │
│ │
│ /usr/local/lib/python3.9/dist-packages/transformers/trainer.py:2708 in │
│ training_step │
│ │
│ 2705 │ │ │ loss = loss / self.args.gradient_accumulation_steps │
│ 2706 │ │ │
│ 2707 │ │ if self.do_grad_scaling: │
│ ❱ 2708 │ │ │ self.scaler.scale(loss).backward() │
│ 2709 │ │ elif self.use_apex: │
│ 2710 │ │ │ with amp.scale_loss(loss, self.optimizer) as scaled_loss: │
│ 2711 │ │ │ │ scaled_loss.backward() │
│ │
│ /usr/local/lib/python3.9/dist-packages/torch/_tensor.py:487 in backward │
│ │
│ 484 │ │ │ │ create_graph=create_graph, │
│ 485 │ │ │ │ inputs=inputs, │
│ 486 │ │ │ ) │
│ ❱ 487 │ │ torch.autograd.backward( │
│ 488 │ │ │ self, gradient, retain_graph, create_graph, inputs=inputs │
│ 489 │ │ ) │
│ 490 │
│ │
│ /usr/local/lib/python3.9/dist-packages/torch/autograd/__init__.py:200 in │
│ backward │
│ │
│ 197 │ # The reason we repeat same the comment below is that │
│ 198 │ # some Python versions print out the first line of a multi-line fu │
│ 199 │ # calls in the traceback and some print out the last line │
│ ❱ 200 │ Variable._execution_engine.run_backward( # Calls into the C++ eng │
│ 201 │ │ tensors, grad_tensors_, retain_graph, create_graph, inputs, │
│ 202 │ │ allow_unreachable=True, accumulate_grad=True) # Calls into th │
│ 203 │
╰──────────────────────────────────────────────────────────────────────────────╯
KeyboardInterrupt
wandb: Waiting for W&B process to finish... (failed 255). Press Control-C to abort syncing.
wandb: 🚀 View run earnest-music-3 at: https://wandb.ai/utensil/huggingface/runs/xyekygze
wandb: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)
wandb: Find logs at: ./wandb/run-20230419_134415-xyekygze/logs
^C
In [ ]: