# Check if GPU is available I used 4x NVIDIA GeForce RTX 3090 (rented 2.1.2-cuda12.1-cudnn8-devel)
import torch
print('GPU available?', torch.cuda.is_available())
print('BF16 is supported?', torch.cuda.is_bf16_supported())GPU available? True
BF16 is supported? TrueCollecting huggingface_hub
Downloading huggingface_hub-0.20.1-py3-none-any.whl.metadata (12 kB)
Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (3.9.0)
Requirement already satisfied: fsspec>=2023.5.0 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (2023.10.0)
Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (2.31.0)
Requirement already satisfied: tqdm>=4.42.1 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (4.65.0)
Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (6.0.1)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (4.7.1)
Requirement already satisfied: packaging>=20.9 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (23.1)
Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (1.26.18)
Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (2023.7.22)
Downloading huggingface_hub-0.20.1-py3-none-any.whl (330 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 330.1/330.1 kB 8.8 MB/s eta 0:00:00:00:01
Installing collected packages: huggingface_hub
Successfully installed huggingface_hub-0.20.1
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv#Login to huggingface so you can push the model to hub later
import sys
stdout = sys.stdout
notebook_login()Cloning into 'axolotl'...
remote: Enumerating objects: 235, done.
remote: Counting objects: 100% (235/235), done.
remote: Compressing objects: 100% (207/207), done.
remote: Total 235 (delta 48), reused 123 (delta 13), pack-reused 0
Receiving objects: 100% (235/235), 1.46 MiB | 11.65 MiB/s, done.
Resolving deltas: 100% (48/48), done.#instaling what is needed inside axolotl file
!pip install packaging
!pip install -e '.[flash-attn,deepspeed]'
!pip install -U git+https://github.com/huggingface/peft.gitRequirement already satisfied: packaging in /opt/conda/lib/python3.10/site-packages (23.1)
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv
Obtaining file:///axolotl
Preparing metadata (setup.py) ... done
Collecting auto-gptq==0.5.1
Downloading auto_gptq-0.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (20 kB)
Requirement already satisfied: packaging in /opt/conda/lib/python3.10/site-packages (23.1)
Collecting peft==0.6.0
Downloading peft-0.6.0-py3-none-any.whl.metadata (23 kB)
Collecting transformers==4.36.2
Downloading transformers-4.36.2-py3-none-any.whl.metadata (126 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 126.8/126.8 kB 9.1 MB/s eta 0:00:00
Collecting tokenizers==0.15.0
Downloading tokenizers-0.15.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)
Collecting bitsandbytes>=0.41.1
Downloading bitsandbytes-0.41.3.post2-py3-none-any.whl.metadata (9.8 kB)
Collecting accelerate==0.24.1
Downloading accelerate-0.24.1-py3-none-any.whl.metadata (18 kB)
Collecting addict
Downloading addict-2.4.0-py3-none-any.whl (3.8 kB)
Collecting fire
Downloading fire-0.5.0.tar.gz (88 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 88.3/88.3 kB 28.4 MB/s eta 0:00:00
Preparing metadata (setup.py) ... done
Requirement already satisfied: PyYAML>=6.0 in /opt/conda/lib/python3.10/site-packages (6.0.1)
Collecting datasets>=2.15.0
Downloading datasets-2.16.0-py3-none-any.whl.metadata (20 kB)
Collecting sentencepiece
Downloading sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 47.9 MB/s eta 0:00:00
Collecting wandb
Downloading wandb-0.16.1-py3-none-any.whl.metadata (9.8 kB)
Collecting einops
Downloading einops-0.7.0-py3-none-any.whl.metadata (13 kB)
Collecting optimum==1.13.2
Downloading optimum-1.13.2.tar.gz (300 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 301.0/301.0 kB 72.3 MB/s eta 0:00:00
Installing build dependencies ... done
Getting requirements to build wheel ... done
Preparing metadata (pyproject.toml) ... done
Collecting hf_transfer
Downloading hf_transfer-0.1.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.5 kB)
Collecting colorama
Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)
Collecting numba
Downloading numba-0.58.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (2.7 kB)
Requirement already satisfied: numpy>=1.24.4 in /opt/conda/lib/python3.10/site-packages (1.26.0)
Collecting bert-score==0.3.13
Downloading bert_score-0.3.13-py3-none-any.whl (61 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 61.1/61.1 kB 20.1 MB/s eta 0:00:00
Collecting evaluate==0.4.0
Downloading evaluate-0.4.0-py3-none-any.whl (81 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 81.4/81.4 kB 26.0 MB/s eta 0:00:00
Collecting rouge-score==0.1.2
Downloading rouge_score-0.1.2.tar.gz (17 kB)
Preparing metadata (setup.py) ... done
Collecting scipy
Downloading scipy-1.11.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 60.4/60.4 kB 17.3 MB/s eta 0:00:00
Collecting scikit-learn==1.2.2
Downloading scikit_learn-1.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 9.6/9.6 MB 83.2 MB/s eta 0:00:0000:0100:01m
Collecting pynvml
Downloading pynvml-11.5.0-py3-none-any.whl (53 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 53.1/53.1 kB 13.6 MB/s eta 0:00:00
Collecting art
Downloading art-6.1-py3-none-any.whl.metadata (69 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 69.9/69.9 kB 21.5 MB/s eta 0:00:00
Collecting fschat==0.2.34
Downloading fschat-0.2.34-py3-none-any.whl.metadata (20 kB)
Collecting gradio==3.50.2
Downloading gradio-3.50.2-py3-none-any.whl.metadata (17 kB)
Collecting tensorboard
Downloading tensorboard-2.15.1-py3-none-any.whl.metadata (1.7 kB)
Collecting s3fs
Downloading s3fs-2023.12.2-py3-none-any.whl.metadata (1.6 kB)
Collecting gcsfs
Downloading gcsfs-2023.12.2.post1-py2.py3-none-any.whl.metadata (1.6 kB)
Collecting xformers==0.0.23
Downloading xformers-0.0.23-cp310-cp310-manylinux2014_x86_64.whl.metadata (1.0 kB)
Collecting deepspeed
Downloading deepspeed-0.12.6.tar.gz (1.2 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 109.7 MB/s eta 0:00:00
Preparing metadata (setup.py) ... done
Collecting flash-attn==2.3.3
Downloading flash_attn-2.3.3.tar.gz (2.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.3/2.3 MB 111.5 MB/s eta 0:00:00
Preparing metadata (setup.py) ... done
Requirement already satisfied: psutil in /opt/conda/lib/python3.10/site-packages (from accelerate==0.24.1) (5.9.0)
Requirement already satisfied: torch>=1.10.0 in /opt/conda/lib/python3.10/site-packages (from accelerate==0.24.1) (2.1.1)
Requirement already satisfied: huggingface-hub in /opt/conda/lib/python3.10/site-packages (from accelerate==0.24.1) (0.20.1)
Collecting rouge (from auto-gptq==0.5.1)
Downloading rouge-1.0.1-py3-none-any.whl (13 kB)
Collecting gekko (from auto-gptq==0.5.1)
Downloading gekko-1.0.6-py3-none-any.whl (12.2 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 12.2/12.2 MB 77.9 MB/s eta 0:00:0000:010:01
Collecting safetensors (from auto-gptq==0.5.1)
Downloading safetensors-0.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)
Requirement already satisfied: tqdm in /opt/conda/lib/python3.10/site-packages (from auto-gptq==0.5.1) (4.65.0)
Collecting pandas>=1.0.1 (from bert-score==0.3.13)
Downloading pandas-2.1.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (18 kB)
Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from bert-score==0.3.13) (2.31.0)
Collecting matplotlib (from bert-score==0.3.13)
Downloading matplotlib-3.8.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.8 kB)
Collecting dill (from evaluate==0.4.0)
Downloading dill-0.3.7-py3-none-any.whl.metadata (9.9 kB)
Collecting xxhash (from evaluate==0.4.0)
Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)
Collecting multiprocess (from evaluate==0.4.0)
Downloading multiprocess-0.70.15-py310-none-any.whl.metadata (7.2 kB)
Requirement already satisfied: fsspec>=2021.05.0 in /opt/conda/lib/python3.10/site-packages (from fsspec[http]>=2021.05.0->evaluate==0.4.0) (2023.10.0)
Collecting responses<0.19 (from evaluate==0.4.0)
Downloading responses-0.18.0-py3-none-any.whl (38 kB)
Collecting ninja (from flash-attn==2.3.3)
Downloading ninja-1.11.1.1-py2.py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl.metadata (5.3 kB)
Collecting aiohttp (from fschat==0.2.34)
Downloading aiohttp-3.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.4 kB)
Collecting fastapi (from fschat==0.2.34)
Downloading fastapi-0.108.0-py3-none-any.whl.metadata (24 kB)
Collecting httpx (from fschat==0.2.34)
Downloading httpx-0.26.0-py3-none-any.whl.metadata (7.6 kB)
Collecting markdown2[all] (from fschat==0.2.34)
Downloading markdown2-2.4.12-py2.py3-none-any.whl.metadata (2.0 kB)
Collecting nh3 (from fschat==0.2.34)
Downloading nh3-0.2.15-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.7 kB)
Requirement already satisfied: prompt-toolkit>=3.0.0 in /opt/conda/lib/python3.10/site-packages (from fschat==0.2.34) (3.0.36)
Collecting pydantic<2,>=1 (from fschat==0.2.34)
Downloading pydantic-1.10.13-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (149 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 149.6/149.6 kB 42.3 MB/s eta 0:00:00
Collecting rich>=10.0.0 (from fschat==0.2.34)
Downloading rich-13.7.0-py3-none-any.whl.metadata (18 kB)
Collecting shortuuid (from fschat==0.2.34)
Downloading shortuuid-1.0.11-py3-none-any.whl (10 kB)
Collecting tiktoken (from fschat==0.2.34)
Downloading tiktoken-0.5.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.6 kB)
Collecting uvicorn (from fschat==0.2.34)
Downloading uvicorn-0.25.0-py3-none-any.whl.metadata (6.4 kB)
Collecting aiofiles<24.0,>=22.0 (from gradio==3.50.2)
Downloading aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 kB)
Collecting altair<6.0,>=4.2.0 (from gradio==3.50.2)
Downloading altair-5.2.0-py3-none-any.whl.metadata (8.7 kB)
Collecting ffmpy (from gradio==3.50.2)
Downloading ffmpy-0.3.1.tar.gz (5.5 kB)
Preparing metadata (setup.py) ... done
Collecting gradio-client==0.6.1 (from gradio==3.50.2)
Downloading gradio_client-0.6.1-py3-none-any.whl.metadata (7.1 kB)
Collecting importlib-resources<7.0,>=1.3 (from gradio==3.50.2)
Downloading importlib_resources-6.1.1-py3-none-any.whl.metadata (4.1 kB)
Requirement already satisfied: jinja2<4.0 in /opt/conda/lib/python3.10/site-packages (from gradio==3.50.2) (3.1.2)
Requirement already satisfied: markupsafe~=2.0 in /opt/conda/lib/python3.10/site-packages (from gradio==3.50.2) (2.1.1)
Collecting orjson~=3.0 (from gradio==3.50.2)
Downloading orjson-3.9.10-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (49 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 49.3/49.3 kB 14.0 MB/s eta 0:00:00
Requirement already satisfied: pillow<11.0,>=8.0 in /opt/conda/lib/python3.10/site-packages (from gradio==3.50.2) (10.0.1)
Collecting pydub (from gradio==3.50.2)
Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)
Collecting python-multipart (from gradio==3.50.2)
Downloading python_multipart-0.0.6-py3-none-any.whl (45 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 45.7/45.7 kB 13.5 MB/s eta 0:00:00
Collecting semantic-version~=2.0 (from gradio==3.50.2)
Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)
Requirement already satisfied: typing-extensions~=4.0 in /opt/conda/lib/python3.10/site-packages (from gradio==3.50.2) (4.7.1)
Collecting websockets<12.0,>=10.0 (from gradio==3.50.2)
Downloading websockets-11.0.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (129 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 129.9/129.9 kB 30.8 MB/s eta 0:00:00
Collecting coloredlogs (from optimum==1.13.2)
Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 46.0/46.0 kB 11.6 MB/s eta 0:00:00
Requirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from optimum==1.13.2) (1.11.1)
Collecting absl-py (from rouge-score==0.1.2)
Downloading absl_py-2.0.0-py3-none-any.whl.metadata (2.3 kB)
Collecting nltk (from rouge-score==0.1.2)
Downloading nltk-3.8.1-py3-none-any.whl (1.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.5/1.5 MB 90.4 MB/s eta 0:00:00
Requirement already satisfied: six>=1.14.0 in /opt/conda/lib/python3.10/site-packages (from rouge-score==0.1.2) (1.16.0)
Collecting joblib>=1.1.1 (from scikit-learn==1.2.2)
Downloading joblib-1.3.2-py3-none-any.whl.metadata (5.4 kB)
Collecting threadpoolctl>=2.0.0 (from scikit-learn==1.2.2)
Downloading threadpoolctl-3.2.0-py3-none-any.whl.metadata (10.0 kB)
Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from transformers==4.36.2) (3.9.0)
Collecting regex!=2019.12.17 (from transformers==4.36.2)
Downloading regex-2023.12.25-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 40.9/40.9 kB 12.0 MB/s eta 0:00:00
Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch>=1.10.0->accelerate==0.24.1) (3.1)
Collecting pyarrow>=8.0.0 (from datasets>=2.15.0)
Downloading pyarrow-14.0.2-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.0 kB)
Collecting pyarrow-hotfix (from datasets>=2.15.0)
Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)
Collecting hjson (from deepspeed)
Downloading hjson-3.1.0-py3-none-any.whl (54 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 54.0/54.0 kB 19.4 MB/s eta 0:00:00
Collecting py-cpuinfo (from deepspeed)
Downloading py_cpuinfo-9.0.0-py3-none-any.whl (22 kB)
Collecting termcolor (from fire)
Downloading termcolor-2.4.0-py3-none-any.whl.metadata (6.1 kB)
Requirement already satisfied: decorator>4.1.2 in /opt/conda/lib/python3.10/site-packages (from gcsfs) (5.1.1)
INFO: pip is looking at multiple versions of gcsfs to determine which version is compatible with other requirements. This could take a while.
Collecting gcsfs
Downloading gcsfs-2023.12.1-py2.py3-none-any.whl.metadata (1.6 kB)
Downloading gcsfs-2023.12.0-py2.py3-none-any.whl.metadata (1.6 kB)
Downloading gcsfs-2023.10.0-py2.py3-none-any.whl.metadata (1.6 kB)
Collecting google-auth>=1.2 (from gcsfs)
Downloading google_auth-2.25.2-py2.py3-none-any.whl.metadata (4.7 kB)
Collecting google-auth-oauthlib (from gcsfs)
Downloading google_auth_oauthlib-1.2.0-py2.py3-none-any.whl.metadata (2.7 kB)
Collecting google-cloud-storage (from gcsfs)
Downloading google_cloud_storage-2.14.0-py2.py3-none-any.whl.metadata (6.1 kB)
Collecting llvmlite<0.42,>=0.41.0dev0 (from numba)
Downloading llvmlite-0.41.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.8 kB)
Collecting aiobotocore<3.0.0,>=2.5.4 (from s3fs)
Downloading aiobotocore-2.9.0-py3-none-any.whl.metadata (20 kB)
INFO: pip is looking at multiple versions of s3fs to determine which version is compatible with other requirements. This could take a while.
Collecting s3fs
Downloading s3fs-2023.12.1-py3-none-any.whl.metadata (1.6 kB)
Downloading s3fs-2023.10.0-py3-none-any.whl.metadata (1.6 kB)
Collecting aiobotocore~=2.7.0 (from s3fs)
Downloading aiobotocore-2.7.0-py3-none-any.whl.metadata (20 kB)
Collecting grpcio>=1.48.2 (from tensorboard)
Downloading grpcio-1.60.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.0 kB)
Collecting markdown>=2.6.8 (from tensorboard)
Downloading Markdown-3.5.1-py3-none-any.whl.metadata (7.1 kB)
Collecting protobuf<4.24,>=3.19.6 (from tensorboard)
Downloading protobuf-4.23.4-cp37-abi3-manylinux2014_x86_64.whl.metadata (540 bytes)
Requirement already satisfied: setuptools>=41.0.0 in /opt/conda/lib/python3.10/site-packages (from tensorboard) (68.0.0)
Collecting tensorboard-data-server<0.8.0,>=0.7.0 (from tensorboard)
Downloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl.metadata (1.1 kB)
Collecting werkzeug>=1.0.1 (from tensorboard)
Downloading werkzeug-3.0.1-py3-none-any.whl.metadata (4.1 kB)
Requirement already satisfied: Click!=8.0.0,>=7.1 in /opt/conda/lib/python3.10/site-packages (from wandb) (8.1.7)
Collecting GitPython!=3.1.29,>=1.0.0 (from wandb)
Downloading GitPython-3.1.40-py3-none-any.whl.metadata (12 kB)
Collecting sentry-sdk>=1.0.0 (from wandb)
Downloading sentry_sdk-1.39.1-py2.py3-none-any.whl.metadata (9.7 kB)
Collecting docker-pycreds>=0.4.0 (from wandb)
Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)
Collecting setproctitle (from wandb)
Downloading setproctitle-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (9.9 kB)
Collecting appdirs>=1.4.3 (from wandb)
Downloading appdirs-1.4.4-py2.py3-none-any.whl (9.6 kB)
Collecting botocore<1.31.65,>=1.31.16 (from aiobotocore~=2.7.0->s3fs)
Downloading botocore-1.31.64-py3-none-any.whl.metadata (6.1 kB)
Collecting wrapt<2.0.0,>=1.10.10 (from aiobotocore~=2.7.0->s3fs)
Downloading wrapt-1.16.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.6 kB)
Collecting aioitertools<1.0.0,>=0.5.1 (from aiobotocore~=2.7.0->s3fs)
Downloading aioitertools-0.11.0-py3-none-any.whl (23 kB)
Requirement already satisfied: attrs>=17.3.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->fschat==0.2.34) (23.1.0)
Collecting multidict<7.0,>=4.5 (from aiohttp->fschat==0.2.34)
Downloading multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 114.5/114.5 kB 37.1 MB/s eta 0:00:00
Collecting yarl<2.0,>=1.0 (from aiohttp->fschat==0.2.34)
Downloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (31 kB)
Collecting frozenlist>=1.1.1 (from aiohttp->fschat==0.2.34)
Downloading frozenlist-1.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)
Collecting aiosignal>=1.1.2 (from aiohttp->fschat==0.2.34)
Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)
Collecting async-timeout<5.0,>=4.0 (from aiohttp->fschat==0.2.34)
Downloading async_timeout-4.0.3-py3-none-any.whl.metadata (4.2 kB)
Requirement already satisfied: jsonschema>=3.0 in /opt/conda/lib/python3.10/site-packages (from altair<6.0,>=4.2.0->gradio==3.50.2) (4.20.0)
Requirement already satisfied: toolz in /opt/conda/lib/python3.10/site-packages (from altair<6.0,>=4.2.0->gradio==3.50.2) (0.12.0)
Collecting gitdb<5,>=4.0.1 (from GitPython!=3.1.29,>=1.0.0->wandb)
Downloading gitdb-4.0.11-py3-none-any.whl.metadata (1.2 kB)
Collecting cachetools<6.0,>=2.0.0 (from google-auth>=1.2->gcsfs)
Downloading cachetools-5.3.2-py3-none-any.whl.metadata (5.2 kB)
Collecting pyasn1-modules>=0.2.1 (from google-auth>=1.2->gcsfs)
Downloading pyasn1_modules-0.3.0-py2.py3-none-any.whl (181 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 181.3/181.3 kB 59.8 MB/s eta 0:00:00
Collecting rsa<5,>=3.1.4 (from google-auth>=1.2->gcsfs)
Downloading rsa-4.9-py3-none-any.whl (34 kB)
Collecting requests-oauthlib>=0.7.0 (from google-auth-oauthlib->gcsfs)
Downloading requests_oauthlib-1.3.1-py2.py3-none-any.whl (23 kB)
Collecting contourpy>=1.0.1 (from matplotlib->bert-score==0.3.13)
Downloading contourpy-1.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.8 kB)
Collecting cycler>=0.10 (from matplotlib->bert-score==0.3.13)
Downloading cycler-0.12.1-py3-none-any.whl.metadata (3.8 kB)
Collecting fonttools>=4.22.0 (from matplotlib->bert-score==0.3.13)
Downloading fonttools-4.47.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (157 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 157.2/157.2 kB 41.3 MB/s eta 0:00:00
Collecting kiwisolver>=1.3.1 (from matplotlib->bert-score==0.3.13)
Downloading kiwisolver-1.4.5-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl.metadata (6.4 kB)
Collecting pyparsing>=2.3.1 (from matplotlib->bert-score==0.3.13)
Downloading pyparsing-3.1.1-py3-none-any.whl.metadata (5.1 kB)
Requirement already satisfied: python-dateutil>=2.7 in /opt/conda/lib/python3.10/site-packages (from matplotlib->bert-score==0.3.13) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.10/site-packages (from pandas>=1.0.1->bert-score==0.3.13) (2023.3.post1)
Collecting tzdata>=2022.1 (from pandas>=1.0.1->bert-score==0.3.13)
Downloading tzdata-2023.3-py2.py3-none-any.whl (341 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 341.8/341.8 kB 72.5 MB/s eta 0:00:00
Requirement already satisfied: wcwidth in /opt/conda/lib/python3.10/site-packages (from prompt-toolkit>=3.0.0->fschat==0.2.34) (0.2.5)
Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->bert-score==0.3.13) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->bert-score==0.3.13) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->bert-score==0.3.13) (1.26.18)
Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->bert-score==0.3.13) (2023.7.22)
Collecting markdown-it-py>=2.2.0 (from rich>=10.0.0->fschat==0.2.34)
Downloading markdown_it_py-3.0.0-py3-none-any.whl.metadata (6.9 kB)
Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /opt/conda/lib/python3.10/site-packages (from rich>=10.0.0->fschat==0.2.34) (2.15.1)
Collecting h11>=0.8 (from uvicorn->fschat==0.2.34)
Downloading h11-0.14.0-py3-none-any.whl (58 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 58.3/58.3 kB 21.6 MB/s eta 0:00:00
Collecting humanfriendly>=9.1 (from coloredlogs->optimum==1.13.2)
Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 86.8/86.8 kB 27.2 MB/s eta 0:00:00
Collecting starlette<0.33.0,>=0.29.0 (from fastapi->fschat==0.2.34)
Downloading starlette-0.32.0.post1-py3-none-any.whl.metadata (5.8 kB)
Collecting typing-extensions~=4.0 (from gradio==3.50.2)
Downloading typing_extensions-4.9.0-py3-none-any.whl.metadata (3.0 kB)
Collecting google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5 (from google-cloud-storage->gcsfs)
Downloading google_api_core-2.15.0-py3-none-any.whl.metadata (2.7 kB)
Collecting google-cloud-core<3.0dev,>=2.3.0 (from google-cloud-storage->gcsfs)
Downloading google_cloud_core-2.4.1-py2.py3-none-any.whl.metadata (2.7 kB)
Collecting google-resumable-media>=2.6.0 (from google-cloud-storage->gcsfs)
Downloading google_resumable_media-2.7.0-py2.py3-none-any.whl.metadata (2.2 kB)
Collecting google-crc32c<2.0dev,>=1.0 (from google-cloud-storage->gcsfs)
Downloading google_crc32c-1.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (32 kB)
Requirement already satisfied: anyio in /opt/conda/lib/python3.10/site-packages (from httpx->fschat==0.2.34) (4.2.0)
Collecting httpcore==1.* (from httpx->fschat==0.2.34)
Downloading httpcore-1.0.2-py3-none-any.whl.metadata (20 kB)
Requirement already satisfied: sniffio in /opt/conda/lib/python3.10/site-packages (from httpx->fschat==0.2.34) (1.3.0)
Collecting wavedrom (from markdown2[all]->fschat==0.2.34)
Downloading wavedrom-2.0.3.post3.tar.gz (137 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 137.7/137.7 kB 47.1 MB/s eta 0:00:00
Preparing metadata (setup.py) ... done
Requirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->optimum==1.13.2) (1.3.0)
Collecting jmespath<2.0.0,>=0.7.1 (from botocore<1.31.65,>=1.31.16->aiobotocore~=2.7.0->s3fs)
Downloading jmespath-1.0.1-py3-none-any.whl (20 kB)
Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->GitPython!=3.1.29,>=1.0.0->wandb)
Downloading smmap-5.0.1-py3-none-any.whl.metadata (4.3 kB)
Collecting googleapis-common-protos<2.0.dev0,>=1.56.2 (from google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5->google-cloud-storage->gcsfs)
Downloading googleapis_common_protos-1.62.0-py2.py3-none-any.whl.metadata (1.5 kB)
Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /opt/conda/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2) (2023.12.1)
Requirement already satisfied: referencing>=0.28.4 in /opt/conda/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2) (0.32.0)
Requirement already satisfied: rpds-py>=0.7.1 in /opt/conda/lib/python3.10/site-packages (from jsonschema>=3.0->altair<6.0,>=4.2.0->gradio==3.50.2) (0.15.2)
Collecting mdurl~=0.1 (from markdown-it-py>=2.2.0->rich>=10.0.0->fschat==0.2.34)
Downloading mdurl-0.1.2-py3-none-any.whl (10.0 kB)
Collecting pyasn1<0.6.0,>=0.4.6 (from pyasn1-modules>=0.2.1->google-auth>=1.2->gcsfs)
Downloading pyasn1-0.5.1-py2.py3-none-any.whl.metadata (8.6 kB)
Collecting oauthlib>=3.0.0 (from requests-oauthlib>=0.7.0->google-auth-oauthlib->gcsfs)
Downloading oauthlib-3.2.2-py3-none-any.whl (151 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 151.7/151.7 kB 50.3 MB/s eta 0:00:00
Requirement already satisfied: exceptiongroup>=1.0.2 in /opt/conda/lib/python3.10/site-packages (from anyio->httpx->fschat==0.2.34) (1.0.4)
Collecting svgwrite (from wavedrom->markdown2[all]->fschat==0.2.34)
Downloading svgwrite-1.4.3-py3-none-any.whl (67 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 67.1/67.1 kB 21.8 MB/s eta 0:00:00
Downloading accelerate-0.24.1-py3-none-any.whl (261 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 261.4/261.4 kB 53.4 MB/s eta 0:00:00
Downloading auto_gptq-0.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.8 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.8/4.8 MB 89.9 MB/s eta 0:00:00ta 0:00:01
Downloading fschat-0.2.34-py3-none-any.whl (220 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 220.1/220.1 kB 63.9 MB/s eta 0:00:00
Downloading gradio-3.50.2-py3-none-any.whl (20.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 20.3/20.3 MB 82.8 MB/s eta 0:00:00:00:0100:01
Downloading peft-0.6.0-py3-none-any.whl (134 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 134.9/134.9 kB 40.0 MB/s eta 0:00:00
Downloading tokenizers-0.15.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.8 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.8/3.8 MB 87.1 MB/s eta 0:00:00ta 0:00:01
Downloading transformers-4.36.2-py3-none-any.whl (8.2 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 8.2/8.2 MB 90.1 MB/s eta 0:00:00ta 0:00:01
Downloading xformers-0.0.23-cp310-cp310-manylinux2014_x86_64.whl (213.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 213.0/213.0 MB 36.6 MB/s eta 0:00:0000:0100:01
Downloading gradio_client-0.6.1-py3-none-any.whl (299 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 299.2/299.2 kB 64.9 MB/s eta 0:00:00
Downloading bitsandbytes-0.41.3.post2-py3-none-any.whl (92.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 92.6/92.6 MB 56.6 MB/s eta 0:00:00:00:0100:01
Downloading datasets-2.16.0-py3-none-any.whl (507 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 507.1/507.1 kB 87.3 MB/s eta 0:00:00
Downloading scipy-1.11.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (36.4 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 36.4/36.4 MB 77.4 MB/s eta 0:00:00:00:0100:01
Downloading art-6.1-py3-none-any.whl (599 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 599.8/599.8 kB 96.0 MB/s eta 0:00:00
Downloading einops-0.7.0-py3-none-any.whl (44 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 44.6/44.6 kB 13.3 MB/s eta 0:00:00
Downloading gcsfs-2023.10.0-py2.py3-none-any.whl (33 kB)
Downloading hf_transfer-0.1.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.9 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.9/3.9 MB 99.7 MB/s eta 0:00:00:00:01
Downloading numba-0.58.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (3.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.6/3.6 MB 100.1 MB/s eta 0:00:0000:01
Downloading s3fs-2023.10.0-py3-none-any.whl (28 kB)
Downloading tensorboard-2.15.1-py3-none-any.whl (5.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 5.5/5.5 MB 96.9 MB/s eta 0:00:00ta 0:00:01
Downloading wandb-0.16.1-py3-none-any.whl (2.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.1/2.1 MB 99.4 MB/s eta 0:00:00
Downloading absl_py-2.0.0-py3-none-any.whl (130 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 130.2/130.2 kB 36.6 MB/s eta 0:00:00
Downloading aiobotocore-2.7.0-py3-none-any.whl (73 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 73.5/73.5 kB 25.1 MB/s eta 0:00:00
Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)
Downloading aiohttp-3.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.2/1.2 MB 99.6 MB/s eta 0:00:00
Downloading altair-5.2.0-py3-none-any.whl (996 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 996.9/996.9 kB 110.4 MB/s eta 0:00:00
Downloading dill-0.3.7-py3-none-any.whl (115 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 115.3/115.3 kB 34.9 MB/s eta 0:00:00
Downloading GitPython-3.1.40-py3-none-any.whl (190 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 190.6/190.6 kB 47.0 MB/s eta 0:00:00
Downloading google_auth-2.25.2-py2.py3-none-any.whl (184 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 184.2/184.2 kB 44.9 MB/s eta 0:00:00
Downloading google_auth_oauthlib-1.2.0-py2.py3-none-any.whl (24 kB)
Downloading grpcio-1.60.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.4 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 5.4/5.4 MB 102.4 MB/s eta 0:00:00a 0:00:01
Downloading importlib_resources-6.1.1-py3-none-any.whl (33 kB)
Downloading joblib-1.3.2-py3-none-any.whl (302 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 302.2/302.2 kB 64.0 MB/s eta 0:00:00
Downloading llvmlite-0.41.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (43.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 43.6/43.6 MB 74.3 MB/s eta 0:00:00:00:0100:01
Downloading Markdown-3.5.1-py3-none-any.whl (102 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 102.2/102.2 kB 34.4 MB/s eta 0:00:00
Downloading matplotlib-3.8.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.6/11.6 MB 99.9 MB/s eta 0:00:00:00:010:01
Downloading orjson-3.9.10-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (138 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 138.7/138.7 kB 38.8 MB/s eta 0:00:00
Downloading pandas-2.1.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 12.3/12.3 MB 96.4 MB/s eta 0:00:00:00:010:01
Downloading protobuf-4.23.4-cp37-abi3-manylinux2014_x86_64.whl (304 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 304.5/304.5 kB 68.5 MB/s eta 0:00:00
Downloading pyarrow-14.0.2-cp310-cp310-manylinux_2_28_x86_64.whl (38.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 38.0/38.0 MB 78.5 MB/s eta 0:00:00:00:0100:01
Downloading pydantic-1.10.13-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 3.1/3.1 MB 95.6 MB/s eta 0:00:00
Downloading regex-2023.12.25-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (773 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 774.0/774.0 kB 116.8 MB/s eta 0:00:00
Downloading rich-13.7.0-py3-none-any.whl (240 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 240.6/240.6 kB 59.9 MB/s eta 0:00:00
Downloading safetensors-0.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.3/1.3 MB 102.1 MB/s eta 0:00:00
Downloading sentry_sdk-1.39.1-py2.py3-none-any.whl (254 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 254.1/254.1 kB 71.9 MB/s eta 0:00:00
Downloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl (6.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 6.6/6.6 MB 104.2 MB/s eta 0:00:00a 0:00:01
Downloading threadpoolctl-3.2.0-py3-none-any.whl (15 kB)
Downloading uvicorn-0.25.0-py3-none-any.whl (60 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 60.3/60.3 kB 19.1 MB/s eta 0:00:00
Downloading werkzeug-3.0.1-py3-none-any.whl (226 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 226.7/226.7 kB 67.5 MB/s eta 0:00:00
Downloading fastapi-0.108.0-py3-none-any.whl (92 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 92.0/92.0 kB 33.8 MB/s eta 0:00:00
Downloading typing_extensions-4.9.0-py3-none-any.whl (32 kB)
Downloading google_cloud_storage-2.14.0-py2.py3-none-any.whl (121 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 121.6/121.6 kB 36.9 MB/s eta 0:00:00
Downloading httpx-0.26.0-py3-none-any.whl (75 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 75.9/75.9 kB 24.7 MB/s eta 0:00:00
Downloading httpcore-1.0.2-py3-none-any.whl (76 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 76.9/76.9 kB 28.4 MB/s eta 0:00:00
Downloading multiprocess-0.70.15-py310-none-any.whl (134 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 134.8/134.8 kB 48.7 MB/s eta 0:00:00
Downloading nh3-0.2.15-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.7 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.7/1.7 MB 108.1 MB/s eta 0:00:00
Downloading ninja-1.11.1.1-py2.py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl (307 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 307.2/307.2 kB 66.5 MB/s eta 0:00:00
Downloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)
Downloading setproctitle-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30 kB)
Downloading termcolor-2.4.0-py3-none-any.whl (7.7 kB)
Downloading tiktoken-0.5.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.0 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 2.0/2.0 MB 101.9 MB/s eta 0:00:00
Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 194.1/194.1 kB 44.4 MB/s eta 0:00:00
Downloading async_timeout-4.0.3-py3-none-any.whl (5.7 kB)
Downloading botocore-1.31.64-py3-none-any.whl (11.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 11.3/11.3 MB 98.8 MB/s eta 0:00:00:00:010:01
Downloading cachetools-5.3.2-py3-none-any.whl (9.3 kB)
Downloading contourpy-1.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (310 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 310.7/310.7 kB 69.7 MB/s eta 0:00:00
Downloading cycler-0.12.1-py3-none-any.whl (8.3 kB)
Downloading fonttools-4.47.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 4.6/4.6 MB 102.7 MB/s eta 0:00:00a 0:00:01
Downloading frozenlist-1.4.1-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (239 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 239.5/239.5 kB 71.4 MB/s eta 0:00:00
Downloading gitdb-4.0.11-py3-none-any.whl (62 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 62.7/62.7 kB 23.3 MB/s eta 0:00:00
Downloading google_api_core-2.15.0-py3-none-any.whl (121 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 122.0/122.0 kB 32.4 MB/s eta 0:00:00
Downloading google_cloud_core-2.4.1-py2.py3-none-any.whl (29 kB)
Downloading google_resumable_media-2.7.0-py2.py3-none-any.whl (80 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 80.6/80.6 kB 22.5 MB/s eta 0:00:00
Downloading kiwisolver-1.4.5-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.6 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.6/1.6 MB 102.0 MB/s eta 0:00:00
Downloading markdown_it_py-3.0.0-py3-none-any.whl (87 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 87.5/87.5 kB 25.0 MB/s eta 0:00:00
Downloading pyparsing-3.1.1-py3-none-any.whl (103 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 103.1/103.1 kB 32.7 MB/s eta 0:00:00
Downloading starlette-0.32.0.post1-py3-none-any.whl (70 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 70.0/70.0 kB 19.1 MB/s eta 0:00:00
Downloading wrapt-1.16.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (80 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 80.3/80.3 kB 30.3 MB/s eta 0:00:00
Downloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (301 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 301.6/301.6 kB 80.7 MB/s eta 0:00:00
Downloading markdown2-2.4.12-py2.py3-none-any.whl (41 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 41.2/41.2 kB 12.5 MB/s eta 0:00:00
Downloading googleapis_common_protos-1.62.0-py2.py3-none-any.whl (228 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 228.7/228.7 kB 57.7 MB/s eta 0:00:00
Downloading pyasn1-0.5.1-py2.py3-none-any.whl (84 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 84.9/84.9 kB 30.5 MB/s eta 0:00:00
Downloading smmap-5.0.1-py3-none-any.whl (24 kB)
Building wheels for collected packages: flash-attn, optimum, rouge-score, deepspeed, fire, ffmpy, wavedrom
Building wheel for flash-attn (setup.py) ... done
Created wheel for flash-attn: filename=flash_attn-2.3.3-cp310-cp310-linux_x86_64.whl size=57042553 sha256=b1df92cb5bd7657d38b789dd48e907aa3e0bd2715c817eb85f3c4320bb11fb3f
Stored in directory: /root/.cache/pip/wheels/e5/e6/fa/941802ec61d1afd320d27160ab1db98e6dba65381f84b76d4a
Building wheel for optimum (pyproject.toml) ... done
Created wheel for optimum: filename=optimum-1.13.2-py3-none-any.whl size=395599 sha256=ff3a73120e1b6eeeda28f76e3fc8cd4cd826e5d66c869b7848ba150e7af79c62
Stored in directory: /root/.cache/pip/wheels/6e/b7/2c/79405d98f0943373d8546daeae25a3d377f7659ca0cbe48699
Building wheel for rouge-score (setup.py) ... done
Created wheel for rouge-score: filename=rouge_score-0.1.2-py3-none-any.whl size=24932 sha256=8118ecbbcd3529085e794c803f0ddb182fc6c6d3e8a494103b49a94abf1bec37
Stored in directory: /root/.cache/pip/wheels/5f/dd/89/461065a73be61a532ff8599a28e9beef17985c9e9c31e541b4
Building wheel for deepspeed (setup.py) ... done
Created wheel for deepspeed: filename=deepspeed-0.12.6-py3-none-any.whl size=1306729 sha256=35c46b6f0275b0d3063522e0af4f3cbd9ec1c310114d8917d87cbe2bf43346e2
Stored in directory: /root/.cache/pip/wheels/a3/dc/a2/f585faaed4dec84108916dcc8e8a7c129a216df8202ca32984
Building wheel for fire (setup.py) ... done
Created wheel for fire: filename=fire-0.5.0-py2.py3-none-any.whl size=116934 sha256=e76d5185f237f34ec69bb8aa657497bef07408978e4f7efdaef48663bb8cd4ef
Stored in directory: /root/.cache/pip/wheels/90/d4/f7/9404e5db0116bd4d43e5666eaa3e70ab53723e1e3ea40c9a95
Building wheel for ffmpy (setup.py) ... done
Created wheel for ffmpy: filename=ffmpy-0.3.1-py3-none-any.whl size=5579 sha256=da3b54dc0ac1a825a1a233315970ac80b8b4c53ebd9cb2a2cfdeab118f453a64
Stored in directory: /root/.cache/pip/wheels/01/a6/d1/1c0828c304a4283b2c1639a09ad86f83d7c487ef34c6b4a1bf
Building wheel for wavedrom (setup.py) ... done
Created wheel for wavedrom: filename=wavedrom-2.0.3.post3-py2.py3-none-any.whl size=30052 sha256=7f0cbd15d63ee9c120190bac122ab51bbbfc91ee374bc3c046fadb320816c17e
Stored in directory: /root/.cache/pip/wheels/9c/52/8c/38b454b42f712f325e26f633287484c7dc1ad469e1580c5954
Successfully built flash-attn optimum rouge-score deepspeed fire ffmpy wavedrom
Installing collected packages: sentencepiece, pydub, py-cpuinfo, ninja, nh3, hjson, ffmpy, bitsandbytes, appdirs, addict, xxhash, wrapt, werkzeug, websockets, tzdata, typing-extensions, threadpoolctl, termcolor, tensorboard-data-server, svgwrite, smmap, shortuuid, setproctitle, sentry-sdk, semantic-version, scipy, safetensors, rouge, regex, python-multipart, pyparsing, pynvml, pyasn1, pyarrow-hotfix, pyarrow, protobuf, orjson, oauthlib, multidict, mdurl, markdown2, markdown, llvmlite, kiwisolver, joblib, jmespath, importlib-resources, humanfriendly, hf_transfer, h11, grpcio, google-crc32c, gekko, frozenlist, fonttools, einops, docker-pycreds, dill, cycler, contourpy, colorama, cachetools, async-timeout, art, aioitertools, aiofiles, absl-py, yarl, wavedrom, uvicorn, tiktoken, scikit-learn, rsa, responses, requests-oauthlib, pydantic, pyasn1-modules, pandas, numba, nltk, multiprocess, matplotlib, markdown-it-py, httpcore, googleapis-common-protos, google-resumable-media, gitdb, fire, coloredlogs, botocore, aiosignal, xformers, tokenizers, starlette, rouge-score, rich, httpx, google-auth, GitPython, flash-attn, deepspeed, aiohttp, accelerate, wandb, transformers, gradio-client, google-auth-oauthlib, google-api-core, fastapi, altair, aiobotocore, tensorboard, s3fs, peft, gradio, google-cloud-core, fschat, datasets, bert-score, optimum, google-cloud-storage, evaluate, auto-gptq, gcsfs, axolotl
Attempting uninstall: typing-extensions
Found existing installation: typing_extensions 4.7.1
Uninstalling typing_extensions-4.7.1:
Successfully uninstalled typing_extensions-4.7.1
Running setup.py develop for axolotl
Successfully installed GitPython-3.1.40 absl-py-2.0.0 accelerate-0.24.1 addict-2.4.0 aiobotocore-2.7.0 aiofiles-23.2.1 aiohttp-3.9.1 aioitertools-0.11.0 aiosignal-1.3.1 altair-5.2.0 appdirs-1.4.4 art-6.1 async-timeout-4.0.3 auto-gptq-0.5.1 axolotl-0.3.0 bert-score-0.3.13 bitsandbytes-0.41.3.post2 botocore-1.31.64 cachetools-5.3.2 colorama-0.4.6 coloredlogs-15.0.1 contourpy-1.2.0 cycler-0.12.1 datasets-2.16.0 deepspeed-0.12.6 dill-0.3.7 docker-pycreds-0.4.0 einops-0.7.0 evaluate-0.4.0 fastapi-0.108.0 ffmpy-0.3.1 fire-0.5.0 flash-attn-2.3.3 fonttools-4.47.0 frozenlist-1.4.1 fschat-0.2.34 gcsfs-2023.10.0 gekko-1.0.6 gitdb-4.0.11 google-api-core-2.15.0 google-auth-2.25.2 google-auth-oauthlib-1.2.0 google-cloud-core-2.4.1 google-cloud-storage-2.14.0 google-crc32c-1.5.0 google-resumable-media-2.7.0 googleapis-common-protos-1.62.0 gradio-3.50.2 gradio-client-0.6.1 grpcio-1.60.0 h11-0.14.0 hf_transfer-0.1.4 hjson-3.1.0 httpcore-1.0.2 httpx-0.26.0 humanfriendly-10.0 importlib-resources-6.1.1 jmespath-1.0.1 joblib-1.3.2 kiwisolver-1.4.5 llvmlite-0.41.1 markdown-3.5.1 markdown-it-py-3.0.0 markdown2-2.4.12 matplotlib-3.8.2 mdurl-0.1.2 multidict-6.0.4 multiprocess-0.70.15 nh3-0.2.15 ninja-1.11.1.1 nltk-3.8.1 numba-0.58.1 oauthlib-3.2.2 optimum-1.13.2 orjson-3.9.10 pandas-2.1.4 peft-0.6.0 protobuf-4.23.4 py-cpuinfo-9.0.0 pyarrow-14.0.2 pyarrow-hotfix-0.6 pyasn1-0.5.1 pyasn1-modules-0.3.0 pydantic-1.10.13 pydub-0.25.1 pynvml-11.5.0 pyparsing-3.1.1 python-multipart-0.0.6 regex-2023.12.25 requests-oauthlib-1.3.1 responses-0.18.0 rich-13.7.0 rouge-1.0.1 rouge-score-0.1.2 rsa-4.9 s3fs-2023.10.0 safetensors-0.4.1 scikit-learn-1.2.2 scipy-1.11.4 semantic-version-2.10.0 sentencepiece-0.1.99 sentry-sdk-1.39.1 setproctitle-1.3.3 shortuuid-1.0.11 smmap-5.0.1 starlette-0.32.0.post1 svgwrite-1.4.3 tensorboard-2.15.1 tensorboard-data-server-0.7.2 termcolor-2.4.0 threadpoolctl-3.2.0 tiktoken-0.5.2 tokenizers-0.15.0 transformers-4.36.2 typing-extensions-4.8.0 tzdata-2023.3 uvicorn-0.25.0 wandb-0.16.1 wavedrom-2.0.3.post3 websockets-11.0.3 werkzeug-3.0.1 wrapt-1.16.0 xformers-0.0.23 xxhash-3.4.1 yarl-1.9.4
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv
Collecting git+https://github.com/huggingface/peft.git
Cloning https://github.com/huggingface/peft.git to /tmp/pip-req-build-hka8xgk2
Running command git clone --filter=blob:none --quiet https://github.com/huggingface/peft.git /tmp/pip-req-build-hka8xgk2
Resolved https://github.com/huggingface/peft.git to commit cf04d0353f0343cbf66627228c4495f51669af34
Installing build dependencies ... done
Getting requirements to build wheel ... done
Preparing metadata (pyproject.toml) ... done
Requirement already satisfied: numpy>=1.17 in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (1.26.0)
Requirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (23.1)
Requirement already satisfied: psutil in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (5.9.0)
Requirement already satisfied: pyyaml in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (6.0.1)
Requirement already satisfied: torch>=1.13.0 in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (2.1.1)
Requirement already satisfied: transformers in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (4.36.2)
Requirement already satisfied: tqdm in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (4.65.0)
Requirement already satisfied: accelerate>=0.21.0 in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (0.24.1)
Requirement already satisfied: safetensors in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (0.4.1)
Requirement already satisfied: huggingface-hub>=0.17.0 in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (0.20.1)
Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.17.0->peft==0.7.2.dev0) (3.9.0)
Requirement already satisfied: fsspec>=2023.5.0 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.17.0->peft==0.7.2.dev0) (2023.10.0)
Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.17.0->peft==0.7.2.dev0) (2.31.0)
Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.17.0->peft==0.7.2.dev0) (4.8.0)
Requirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from torch>=1.13.0->peft==0.7.2.dev0) (1.11.1)
Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch>=1.13.0->peft==0.7.2.dev0) (3.1)
Requirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch>=1.13.0->peft==0.7.2.dev0) (3.1.2)
Requirement already satisfied: regex!=2019.12.17 in /opt/conda/lib/python3.10/site-packages (from transformers->peft==0.7.2.dev0) (2023.12.25)
Requirement already satisfied: tokenizers<0.19,>=0.14 in /opt/conda/lib/python3.10/site-packages (from transformers->peft==0.7.2.dev0) (0.15.0)
Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch>=1.13.0->peft==0.7.2.dev0) (2.1.1)
Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.17.0->peft==0.7.2.dev0) (2.0.4)
Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.17.0->peft==0.7.2.dev0) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.17.0->peft==0.7.2.dev0) (1.26.18)
Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface-hub>=0.17.0->peft==0.7.2.dev0) (2023.7.22)
Requirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->torch>=1.13.0->peft==0.7.2.dev0) (1.3.0)
Building wheels for collected packages: peft
Building wheel for peft (pyproject.toml) ... done
Created wheel for peft: filename=peft-0.7.2.dev0-py3-none-any.whl size=169456 sha256=4c70d23e759fa6abb3827fb2f3a8683be3b24d78777d0f403bbc2c0548e5dd4b
Stored in directory: /tmp/pip-ephem-wheel-cache-my5ncou6/wheels/d7/c7/de/1368fac8590e1b103ddc2ec2a28ad51d83aded1a3830e8a087
Successfully built peft
Installing collected packages: peft
Attempting uninstall: peft
Found existing installation: peft 0.6.0
Uninstalling peft-0.6.0:
Successfully uninstalled peft-0.6.0
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
axolotl 0.3.0 requires peft==0.6.0, but you have peft 0.7.2.dev0 which is incompatible.
Successfully installed peft-0.7.2.dev0
WARNING: Running pip as the 'root' user can result in broken permissions and conflicting behaviour with the system package manager. It is recommended to use a virtual environment instead: https://pip.pypa.io/warnings/venv"""
Training using the config.yml file and using deepspeed:zero3_bf16 the most aggressive optimization out of zero1,zero2,zero3 stages which partitions
not only optimizer states but also gradients and parameters across GPUs. The bf16 indicate mixed precision training using bfloat16.
For more information read axolotl's readme
"""
!accelerate launch -m axolotl.cli.train /folder/config.yml --deepspeed deepspeed_configs/zero3_bf16.jsonThe following values were not passed to `accelerate launch` and had defaults used instead:
`--num_processes` was set to a value of `3`
More than one GPU was found, enabling multi-GPU training.
If this was unintended please pass in `--num_processes=1`.
`--num_machines` was set to a value of `1`
`--mixed_precision` was set to a value of `'no'`
`--dynamo_backend` was set to a value of `'no'`
To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.
/opt/conda/lib/python3.10/site-packages/transformers/deepspeed.py:23: FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations
warnings.warn(
[2023-12-28 15:44:09,979] [INFO] [datasets.<module>:58] [PID:2814] PyTorch version 2.1.1 available.
/opt/conda/lib/python3.10/site-packages/transformers/deepspeed.py:23: FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations
warnings.warn(
/opt/conda/lib/python3.10/site-packages/transformers/deepspeed.py:23: FutureWarning: transformers.deepspeed module is deprecated and will be removed in a future version. Please import deepspeed modules directly from transformers.integrations
warnings.warn(
[2023-12-28 15:44:10,011] [INFO] [datasets.<module>:58] [PID:2812] PyTorch version 2.1.1 available.
[2023-12-28 15:44:10,013] [INFO] [datasets.<module>:58] [PID:2813] PyTorch version 2.1.1 available.
[2023-12-28 15:44:10,805] [INFO] [axolotl.normalize_config:150] [PID:2814] [RANK:2] GPU memory usage baseline: 0.000GB (+0.317GB misc)
[2023-12-28 15:44:10,830] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2023-12-28 15:44:10,842] [INFO] [axolotl.normalize_config:150] [PID:2813] [RANK:1] GPU memory usage baseline: 0.000GB (+0.317GB misc)
[2023-12-28 15:44:10,865] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2023-12-28 15:44:10,869] [INFO] [axolotl.normalize_config:150] [PID:2812] [RANK:0] GPU memory usage baseline: 0.000GB (+0.351GB misc)
[2023-12-28 15:44:10,887] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)
[2023-12-28 15:44:10,961] [INFO] [comm.py:637:init_distributed] cdb=None
[2023-12-28 15:44:10,994] [INFO] [comm.py:637:init_distributed] cdb=None
[2023-12-28 15:44:11,015] [INFO] [comm.py:637:init_distributed] cdb=None
[2023-12-28 15:44:11,015] [INFO] [comm.py:668:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl
dP dP dP
88 88 88
.d8888b. dP. .dP .d8888b. 88 .d8888b. d8888P 88
88' `88 `8bd8' 88' `88 88 88' `88 88 88
88. .88 .d88b. 88. .88 88 88. .88 88 88
`88888P8 dP' `dP `88888P' dP `88888P' dP dP
[2023-12-28 15:44:11,412] [DEBUG] [axolotl.load_tokenizer:184] [PID:2812] [RANK:0] EOS: 2 / </s>
[2023-12-28 15:44:11,412] [DEBUG] [axolotl.load_tokenizer:185] [PID:2812] [RANK:0] BOS: 1 / <s>
[2023-12-28 15:44:11,412] [DEBUG] [axolotl.load_tokenizer:186] [PID:2812] [RANK:0] PAD: 2 / </s>
[2023-12-28 15:44:11,412] [DEBUG] [axolotl.load_tokenizer:187] [PID:2812] [RANK:0] UNK: 0 / <unk>
[2023-12-28 15:44:11,413] [INFO] [axolotl.load_tokenized_prepared_datasets:143] [PID:2812] [RANK:0] Loading prepared dataset from disk at tilemachos/GF_new.json/1adc45d2edc1e98ce657814412c6593c...
[2023-12-28 15:44:11,415] [INFO] [axolotl.load_tokenized_prepared_datasets:145] [PID:2812] [RANK:0] Prepared dataset loaded from disk...
[2023-12-28 15:44:11,432] [DEBUG] [axolotl.load_tokenizer:184] [PID:2814] [RANK:2] EOS: 2 / </s>
[2023-12-28 15:44:11,432] [DEBUG] [axolotl.load_tokenizer:185] [PID:2814] [RANK:2] BOS: 1 / <s>
[2023-12-28 15:44:11,432] [DEBUG] [axolotl.load_tokenizer:186] [PID:2814] [RANK:2] PAD: 2 / </s>
[2023-12-28 15:44:11,432] [DEBUG] [axolotl.load_tokenizer:187] [PID:2814] [RANK:2] UNK: 0 / <unk>
[2023-12-28 15:44:11,530] [DEBUG] [axolotl.load_tokenizer:184] [PID:2813] [RANK:1] EOS: 2 / </s>
[2023-12-28 15:44:11,531] [DEBUG] [axolotl.load_tokenizer:185] [PID:2813] [RANK:1] BOS: 1 / <s>
[2023-12-28 15:44:11,531] [DEBUG] [axolotl.load_tokenizer:186] [PID:2813] [RANK:1] PAD: 2 / </s>
[2023-12-28 15:44:11,531] [DEBUG] [axolotl.load_tokenizer:187] [PID:2813] [RANK:1] UNK: 0 / <unk>
[2023-12-28 15:44:12,158] [INFO] [axolotl.load_tokenized_prepared_datasets:143] [PID:2813] [RANK:1] Loading prepared dataset from disk at tilemachos/GF_new.json/1adc45d2edc1e98ce657814412c6593c...
[2023-12-28 15:44:12,158] [INFO] [axolotl.load_tokenized_prepared_datasets:143] [PID:2814] [RANK:2] Loading prepared dataset from disk at tilemachos/GF_new.json/1adc45d2edc1e98ce657814412c6593c...
[2023-12-28 15:44:12,160] [INFO] [axolotl.load_tokenized_prepared_datasets:145] [PID:2813] [RANK:1] Prepared dataset loaded from disk...
[2023-12-28 15:44:12,161] [INFO] [axolotl.load_tokenized_prepared_datasets:145] [PID:2814] [RANK:2] Prepared dataset loaded from disk...
[2023-12-28 15:44:12,236] [DEBUG] [axolotl.log:60] [PID:2812] [RANK:0] total_num_tokens: 28120
[2023-12-28 15:44:12,238] [DEBUG] [axolotl.log:60] [PID:2812] [RANK:0] `total_supervised_tokens: 7990`
[2023-12-28 15:44:12,238] [DEBUG] [axolotl.log:60] [PID:2812] [RANK:0] total_num_steps: 6
[2023-12-28 15:44:12,242] [DEBUG] [axolotl.train.log:60] [PID:2812] [RANK:0] loading tokenizer... mistralai/Mistral-7B-v0.1
[2023-12-28 15:44:12,518] [DEBUG] [axolotl.load_tokenizer:184] [PID:2812] [RANK:0] EOS: 2 / </s>
[2023-12-28 15:44:12,518] [DEBUG] [axolotl.load_tokenizer:185] [PID:2812] [RANK:0] BOS: 1 / <s>
[2023-12-28 15:44:12,518] [DEBUG] [axolotl.load_tokenizer:186] [PID:2812] [RANK:0] PAD: 2 / </s>
[2023-12-28 15:44:12,518] [DEBUG] [axolotl.load_tokenizer:187] [PID:2812] [RANK:0] UNK: 0 / <unk>
[2023-12-28 15:44:12,518] [DEBUG] [axolotl.train.log:60] [PID:2812] [RANK:0] loading model and peft_config...
[2023-12-28 15:44:12,589] [DEBUG] [axolotl.load_tokenizer:184] [PID:2814] [RANK:2] EOS: 2 / </s>
[2023-12-28 15:44:12,589] [DEBUG] [axolotl.load_tokenizer:185] [PID:2814] [RANK:2] BOS: 1 / <s>
[2023-12-28 15:44:12,589] [DEBUG] [axolotl.load_tokenizer:186] [PID:2814] [RANK:2] PAD: 2 / </s>
[2023-12-28 15:44:12,589] [DEBUG] [axolotl.load_tokenizer:187] [PID:2814] [RANK:2] UNK: 0 / <unk>
[2023-12-28 15:44:12,599] [DEBUG] [axolotl.load_tokenizer:184] [PID:2813] [RANK:1] EOS: 2 / </s>
[2023-12-28 15:44:12,599] [DEBUG] [axolotl.load_tokenizer:185] [PID:2813] [RANK:1] BOS: 1 / <s>
[2023-12-28 15:44:12,599] [DEBUG] [axolotl.load_tokenizer:186] [PID:2813] [RANK:1] PAD: 2 / </s>
[2023-12-28 15:44:12,599] [DEBUG] [axolotl.load_tokenizer:187] [PID:2813] [RANK:1] UNK: 0 / <unk>
[2023-12-28 15:44:13,049] [INFO] [partition_parameters.py:348:__exit__] finished initializing model - num_params = 291, num_elems = 7.24B
Loading checkpoint shards: 100%|██████████████████| 2/2 [00:11<00:00, 5.81s/it]
Loading checkpoint shards: 100%|██████████████████| 2/2 [00:11<00:00, 5.98s/it]
[2023-12-28 15:44:25,395] [INFO] [axolotl.load_model:503] [PID:2813] [RANK:1] GPU memory usage after model load: 7.576GB (+0.524GB cache, +0.708GB misc)
[2023-12-28 15:44:25,399] [INFO] [axolotl.load_model:526] [PID:2813] [RANK:1] converting PEFT model w/ prepare_model_for_kbit_training
[2023-12-28 15:44:25,403] [INFO] [axolotl.load_model:538] [PID:2813] [RANK:1] converting modules to torch.bfloat16 for flash attention
trainable params: 3,407,872 || all params: 7,245,139,968 || trainable%: 0.04703666202518836
[2023-12-28 15:44:25,480] [INFO] [axolotl.load_model:568] [PID:2813] [RANK:1] GPU memory usage after adapters: 7.589GB (+1.501GB cache, +0.708GB misc)
[2023-12-28 15:44:25,572] [INFO] [axolotl.load_model:503] [PID:2814] [RANK:2] GPU memory usage after model load: 7.576GB (+0.410GB cache, +0.708GB misc)
[2023-12-28 15:44:25,576] [INFO] [axolotl.load_model:526] [PID:2814] [RANK:2] converting PEFT model w/ prepare_model_for_kbit_training
[2023-12-28 15:44:25,580] [INFO] [axolotl.load_model:538] [PID:2814] [RANK:2] converting modules to torch.bfloat16 for flash attention
trainable params: 3,407,872 || all params: 7,245,139,968 || trainable%: 0.04703666202518836
[2023-12-28 15:44:25,660] [INFO] [axolotl.load_model:568] [PID:2814] [RANK:2] GPU memory usage after adapters: 7.589GB (+1.388GB cache, +0.708GB misc)
Loading checkpoint shards: 100%|██████████████████| 2/2 [00:12<00:00, 6.30s/it]
[2023-12-28 15:44:26,170] [INFO] [axolotl.load_model:503] [PID:2812] [RANK:0] GPU memory usage after model load: 7.576GB (+0.776GB cache, +0.741GB misc)
[2023-12-28 15:44:26,177] [INFO] [axolotl.load_model:526] [PID:2812] [RANK:0] converting PEFT model w/ prepare_model_for_kbit_training
[2023-12-28 15:44:26,181] [INFO] [axolotl.load_model:538] [PID:2812] [RANK:0] converting modules to torch.bfloat16 for flash attention
trainable params: 3,407,872 || all params: 7,245,139,968 || trainable%: 0.04703666202518836
[2023-12-28 15:44:26,259] [INFO] [axolotl.load_model:568] [PID:2812] [RANK:0] GPU memory usage after adapters: 7.589GB (+1.753GB cache, +0.741GB misc)
[2023-12-28 15:44:26,293] [INFO] [axolotl.train.log:60] [PID:2812] [RANK:0] Pre-saving adapter config to ./out
[2023-12-28 15:44:26,296] [INFO] [axolotl.train.log:60] [PID:2812] [RANK:0] Starting trainer...
Using /root/.cache/torch_extensions/py310_cu121 as PyTorch extensions root...
Using /root/.cache/torch_extensions/py310_cu121 as PyTorch extensions root...
Using /root/.cache/torch_extensions/py310_cu121 as PyTorch extensions root...
Detected CUDA files, patching ldflags
Emitting ninja build file /root/.cache/torch_extensions/py310_cu121/fused_adam/build.ninja...
Building extension module fused_adam...
Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)
ninja: no work to do.
Loading extension module fused_adam...
Time to load fused_adam op: 0.05891108512878418 seconds
Loading extension module fused_adam...
Time to load fused_adam op: 0.10173463821411133 seconds
Loading extension module fused_adam...
Time to load fused_adam op: 0.10152459144592285 seconds
/opt/conda/lib/python3.10/site-packages/deepspeed/ops/adam/fused_adam.py:96: UserWarning: The torch.cuda.*DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=*, device='cuda') to create tensors. (Triggered internally at /opt/conda/conda-bld/pytorch_1699449201336/work/torch/csrc/tensor/python_tensor.cpp:83.)
self._dummy_overflow_buf = get_accelerator().IntTensor([0])
/opt/conda/lib/python3.10/site-packages/deepspeed/ops/adam/fused_adam.py:96: UserWarning: The torch.cuda.*DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=*, device='cuda') to create tensors. (Triggered internally at /opt/conda/conda-bld/pytorch_1699449201336/work/torch/csrc/tensor/python_tensor.cpp:83.)
self._dummy_overflow_buf = get_accelerator().IntTensor([0])
/opt/conda/lib/python3.10/site-packages/deepspeed/ops/adam/fused_adam.py:96: UserWarning: The torch.cuda.*DtypeTensor constructors are no longer recommended. It's best to use methods such as torch.tensor(data, dtype=*, device='cuda') to create tensors. (Triggered internally at /opt/conda/conda-bld/pytorch_1699449201336/work/torch/csrc/tensor/python_tensor.cpp:83.)
self._dummy_overflow_buf = get_accelerator().IntTensor([0])
Parameter Offload: Total persistent parameters: 3674112 in 193 params
0%| | 0/17 [00:00<?, ?it/s]/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
/opt/conda/lib/python3.10/site-packages/torch/utils/checkpoint.py:429: UserWarning: torch.utils.checkpoint: please pass in use_reentrant=True or use_reentrant=False explicitly. The default value of use_reentrant will be updated to be False in the future. To maintain current behavior, pass use_reentrant=True. It is recommended that you use use_reentrant=False. Refer to docs for more details on the differences between the two variants.
warnings.warn(
/opt/conda/lib/python3.10/site-packages/bitsandbytes/autograd/_functions.py:322: UserWarning: MatMul8bitLt: inputs will be cast from torch.bfloat16 to float16 during quantization
warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization")
/opt/conda/lib/python3.10/site-packages/bitsandbytes/autograd/_functions.py:322: UserWarning: MatMul8bitLt: inputs will be cast from torch.bfloat16 to float16 during quantization
warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization")
/opt/conda/lib/python3.10/site-packages/bitsandbytes/autograd/_functions.py:322: UserWarning: MatMul8bitLt: inputs will be cast from torch.bfloat16 to float16 during quantization
warnings.warn(f"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization")
{'loss': 2.0448, 'learning_rate': 2e-05, 'epoch': 0.06}
6%|██▌ | 1/17 [00:28<07:32, 28.30s/it]
0%| | 0/3 [00:00<?, ?it/s]
67%|██████████████████████████████ | 2/3 [00:03<00:01, 1.85s/it]
{'eval_loss': 1.9694719314575195, 'eval_runtime': 11.391, 'eval_samples_per_second': 1.492, 'eval_steps_per_second': 0.263, 'epoch': 0.06}
6%|██▌ | 1/17 [00:39<07:32, 28.30s/it]
100%|█████████████████████████████████████████████| 3/3 [00:07<00:00, 2.65s/it]
[2023-12-28 15:45:35,358] [INFO] [axolotl.callbacks.on_step_end:122] [PID:2812] [RANK:0] GPU memory usage while training: 12.210GB (+4.259GB cache, +0.776GB misc)
12%|█████▏ | 2/17 [01:04<08:18, 33.20s/it][2023-12-28 15:45:35,358] [INFO] [axolotl.callbacks.on_step_end:122] [PID:2814] [RANK:2] GPU memory usage while training: 12.269GB (+4.522GB cache, +0.743GB misc)
[2023-12-28 15:45:35,358] [INFO] [axolotl.callbacks.on_step_end:122] [PID:2813] [RANK:1] GPU memory usage while training: 12.283GB (+4.493GB cache, +0.743GB misc)
{'loss': 2.0022, 'learning_rate': 4e-05, 'epoch': 0.12}
{'loss': 2.1054, 'learning_rate': 6e-05, 'epoch': 0.17}
{'loss': 1.9004, 'learning_rate': 8e-05, 'epoch': 0.23}
{'loss': 1.8794, 'learning_rate': 0.0001, 'epoch': 0.29}
29%|████████████▉ | 5/17 [02:20<05:23, 26.92s/it]
0%| | 0/3 [00:00<?, ?it/s]
67%|██████████████████████████████ | 2/3 [00:03<00:01, 1.88s/it]
{'eval_loss': 1.7912336587905884, 'eval_runtime': 11.3106, 'eval_samples_per_second': 1.503, 'eval_steps_per_second': 0.265, 'epoch': 0.29}
29%|████████████▉ | 5/17 [02:32<05:23, 26.92s/it]
100%|█████████████████████████████████████████████| 3/3 [00:07<00:00, 2.67s/it]
{'loss': 1.7871, 'learning_rate': 0.00012, 'epoch': 0.35}
{'loss': 1.7758, 'learning_rate': 0.00014, 'epoch': 0.4}
{'loss': 1.4645, 'learning_rate': 0.00016, 'epoch': 0.46}
{'loss': 1.4009, 'learning_rate': 0.00018, 'epoch': 0.52}
{'loss': 1.3927, 'learning_rate': 0.0002, 'epoch': 0.58}
59%|█████████████████████████▎ | 10/17 [04:38<03:04, 26.33s/it]
0%| | 0/3 [00:00<?, ?it/s]
67%|██████████████████████████████ | 2/3 [00:03<00:01, 1.89s/it]
{'eval_loss': 1.1426481008529663, 'eval_runtime': 11.3344, 'eval_samples_per_second': 1.5, 'eval_steps_per_second': 0.265, 'epoch': 0.58}
59%|█████████████████████████▎ | 10/17 [04:49<03:04, 26.33s/it]
100%|█████████████████████████████████████████████| 3/3 [00:07<00:00, 2.68s/it]
{'loss': 1.0122, 'learning_rate': 0.0001900968867902419, 'epoch': 0.63}
{'loss': 1.0019, 'learning_rate': 0.00016234898018587337, 'epoch': 0.69}
{'loss': 0.8976, 'learning_rate': 0.00012225209339563145, 'epoch': 0.75}
{'loss': 0.9301, 'learning_rate': 7.774790660436858e-05, 'epoch': 0.81}
{'loss': 0.8595, 'learning_rate': 3.7651019814126654e-05, 'epoch': 0.87}
88%|█████████████████████████████████████▉ | 15/17 [06:55<00:52, 26.17s/it]
0%| | 0/3 [00:00<?, ?it/s]
67%|██████████████████████████████ | 2/3 [00:03<00:01, 1.88s/it]
{'eval_loss': 0.8175248503684998, 'eval_runtime': 11.2932, 'eval_samples_per_second': 1.505, 'eval_steps_per_second': 0.266, 'epoch': 0.87}
88%|█████████████████████████████████████▉ | 15/17 [07:06<00:52, 26.17s/it]
100%|█████████████████████████████████████████████| 3/3 [00:07<00:00, 2.67s/it]
{'loss': 0.7931, 'learning_rate': 9.903113209758096e-06, 'epoch': 0.92}
{'loss': 0.6909, 'learning_rate': 0.0, 'epoch': 0.98}
100%|███████████████████████████████████████████| 17/17 [07:56<00:00, 28.03s/it]/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1879: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
warnings.warn(
/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1879: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
warnings.warn(
/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py:1879: UserWarning: Positional args are being deprecated, use kwargs instead. Refer to https://pytorch.org/docs/master/generated/torch.nn.Module.html#torch.nn.Module.state_dict for details.
warnings.warn(
{'train_runtime': 489.0649, 'train_samples_per_second': 0.63, 'train_steps_per_second': 0.035, 'train_loss': 1.408153467318591, 'epoch': 0.98}
100%|███████████████████████████████████████████| 17/17 [08:09<00:00, 28.77s/it]
[2023-12-28 15:52:39,488] [INFO] [axolotl.train.log:60] [PID:2812] [RANK:0] Training Completed!!! Saving pre-trained model to ./out