tocmo0nlord/axolotl
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

Fine-Tuning Mistral-7b for Real-World Chatbot Applications Using Axolotl (Lora used) (#1155)

Browse Source 
* Mistral-7b finetune example using axolotl with code,config,data

* Corrected the path for huggingface dataset

* Update data.jsonl

* chore: lint

---------

Co-authored-by: twenty8th <twenty8th@users.noreply.github.com>
Co-authored-by: Wing Lian <wing.lian@gmail.com>
This commit is contained in:
Tilemachos Chatzipapas
2024-01-23 14:32:21 +02:00
committed by GitHub
parent 9135b9e2aa
commit cc250391a0
5 changed files with 1070 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
README.md
View File

@@ -1,3 +1,6 @@
## What's New
- Added `Mistral-7b-example`: A comprehensive example for fine-tuning Mistral-7b model. [Check it out here](https://github.com/Tilemachoc/axolotl/tree/mistral-7b-example/examples/mistral/Mistral-7b-example).
# Axolotl
Axolotl is a tool designed to streamline the fine-tuning of various AI models, offering support for multiple configurations and architectures.

12
examples/mistral/Mistral-7b-example/README.md Normal file
View File

@@ -0,0 +1,12 @@
# Description
This repository presents an in-depth guide for fine-tuning Mistral-7b or any other compatible model using Axolotl, tailored specifically for chatbot development. It streamlines the process of fine-tuning and uploading the enhanced model to HuggingFace 🤗, thereby serving as an invaluable tool for developers in the AI and chatbot domain.
**What’s Inside:**
Beginner-Friendly Instructions: Comprehensive steps to guide you through fine-tuning your chosen model, including details on the data structure (jsonl), configuration, and the code itself.
Hardware Utilized: For reference, the fine-tuning in this guide was performed using 4x NVIDIA GeForce RTX 3090 (rented 2.1.2-cuda12.1-cudnn8-devel).
**Uploading to HuggingFace 🤗:**
To upload your fine-tuned model to Hugging Face, include the following files:
![Screenshot 2024-01-19 213932](https://github.com/OpenAccess-AI-Collective/axolotl/assets/138583191/d660eb84-2d76-46a1-9846-cf0aeb3006d9)

970
examples/mistral/Mistral-7b-example/code.ipynb Normal file
View File

@@ -0,0 +1,970 @@
{
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"id": "3fe31229-8f6b-48bc-a86d-af8e5466d11c",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"GPU available? True\n",
"BF16 is supported? True\n"
]
}
],
"source": [
"# Check if GPU is available I used 4x NVIDIA GeForce RTX 3090 (rented 2.1.2-cuda12.1-cudnn8-devel)\n",
"import torch\n",
"print('GPU available?', torch.cuda.is_available())\n",
"print('BF16 is supported?', torch.cuda.is_bf16_supported())"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "1dee845b-f3cb-4b1e-bdd9-1a918eac140b",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Collecting huggingface_hub\n",
" Downloading huggingface_hub-0.20.1-py3-none-any.whl.metadata (12 kB)\n",
"Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (3.9.0)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (2023.10.0)\n",
"Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (2.31.0)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (4.65.0)\n",
"Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (6.0.1)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (4.7.1)\n",
"Requirement already satisfied: packaging>=20.9 in /opt/conda/lib/python3.10/site-packages (from huggingface_hub) (23.1)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (2.0.4)\n",
"Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (3.4)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (1.26.18)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests->huggingface_hub) (2023.7.22)\n",
"Downloading huggingface_hub-0.20.1-py3-none-any.whl (330 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m330.1/330.1 kB\u001b[0m \u001b[31m8.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n",
"\u001b[?25hInstalling collected packages: huggingface_hub\n",
"Successfully installed huggingface_hub-0.20.1\n",
"\u001b[33mWARNING: 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\u001b[0m\u001b[33m\n",
"\u001b[0m"
]
}
],
"source": [
"!pip install huggingface_hub"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "88731672-9050-4034-8266-11aaace2a44e",
"metadata": {},
"outputs": [],
"source": [
"from huggingface_hub import notebook_login"
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "6b5aa7d7-3b18-4c14-afd4-043c2c545259",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "60df98d7b0294289aad8b6c8cd023c3b",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"#Login to huggingface so you can push the model to hub later\n",
"import sys\n",
"stdout = sys.stdout\n",
"notebook_login()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "b74d0635-5033-4494-b7bd-ff6822103d93",
"metadata": {},
"outputs": [],
"source": [
"#I noticed that when you use notebook_login() nothing gets printed after so we use sys \n",
"sys.stdout = stdout"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "e3c3b088-45e7-484b-ae39-66beabc48da8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Cloning into 'axolotl'...\n",
"remote: Enumerating objects: 235, done.\u001b[K\n",
"remote: Counting objects: 100% (235/235), done.\u001b[K\n",
"remote: Compressing objects: 100% (207/207), done.\u001b[K\n",
"remote: Total 235 (delta 48), reused 123 (delta 13), pack-reused 0\u001b[K\n",
"Receiving objects: 100% (235/235), 1.46 MiB | 11.65 MiB/s, done.\n",
"Resolving deltas: 100% (48/48), done.\n"
]
}
],
"source": [
"#axolotl\n",
"!git clone -b main --depth 1 https://github.com/OpenAccess-AI-Collective/axolotl"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "66927751-4fd6-4477-97fc-6ab08c9d9a74",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"/axolotl\n"
]
}
],
"source": [
"cd axolotl"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "fcccf8da-353b-4d70-8f55-5cfe08c7e6b9",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: packaging in /opt/conda/lib/python3.10/site-packages (23.1)\n",
"\u001b[33mWARNING: 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\u001b[0m\u001b[33m\n",
"\u001b[0mObtaining file:///axolotl\n",
" Preparing metadata (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25hCollecting auto-gptq==0.5.1\n",
" Downloading auto_gptq-0.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (20 kB)\n",
"Requirement already satisfied: packaging in /opt/conda/lib/python3.10/site-packages (23.1)\n",
"Collecting peft==0.6.0\n",
" Downloading peft-0.6.0-py3-none-any.whl.metadata (23 kB)\n",
"Collecting transformers==4.36.2\n",
" Downloading transformers-4.36.2-py3-none-any.whl.metadata (126 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m126.8/126.8 kB\u001b[0m \u001b[31m9.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting tokenizers==0.15.0\n",
" Downloading tokenizers-0.15.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.7 kB)\n",
"Collecting bitsandbytes>=0.41.1\n",
" Downloading bitsandbytes-0.41.3.post2-py3-none-any.whl.metadata (9.8 kB)\n",
"Collecting accelerate==0.24.1\n",
" Downloading accelerate-0.24.1-py3-none-any.whl.metadata (18 kB)\n",
"Collecting addict\n",
" Downloading addict-2.4.0-py3-none-any.whl (3.8 kB)\n",
"Collecting fire\n",
" Downloading fire-0.5.0.tar.gz (88 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m88.3/88.3 kB\u001b[0m \u001b[31m28.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25hRequirement already satisfied: PyYAML>=6.0 in /opt/conda/lib/python3.10/site-packages (6.0.1)\n",
"Collecting datasets>=2.15.0\n",
" Downloading datasets-2.16.0-py3-none-any.whl.metadata (20 kB)\n",
"Collecting sentencepiece\n",
" Downloading sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m47.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting wandb\n",
" Downloading wandb-0.16.1-py3-none-any.whl.metadata (9.8 kB)\n",
"Collecting einops\n",
" Downloading einops-0.7.0-py3-none-any.whl.metadata (13 kB)\n",
"Collecting optimum==1.13.2\n",
" Downloading optimum-1.13.2.tar.gz (300 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m301.0/301.0 kB\u001b[0m \u001b[31m72.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Installing build dependencies ... \u001b[?25ldone\n",
"\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
"\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
"\u001b[?25hCollecting hf_transfer\n",
" Downloading hf_transfer-0.1.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.5 kB)\n",
"Collecting colorama\n",
" Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n",
"Collecting numba\n",
" Downloading numba-0.58.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl.metadata (2.7 kB)\n",
"Requirement already satisfied: numpy>=1.24.4 in /opt/conda/lib/python3.10/site-packages (1.26.0)\n",
"Collecting bert-score==0.3.13\n",
" Downloading bert_score-0.3.13-py3-none-any.whl (61 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m61.1/61.1 kB\u001b[0m \u001b[31m20.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting evaluate==0.4.0\n",
" Downloading evaluate-0.4.0-py3-none-any.whl (81 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.4/81.4 kB\u001b[0m \u001b[31m26.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting rouge-score==0.1.2\n",
" Downloading rouge_score-0.1.2.tar.gz (17 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25hCollecting scipy\n",
" Downloading scipy-1.11.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (60 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.4/60.4 kB\u001b[0m \u001b[31m17.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting scikit-learn==1.2.2\n",
" Downloading scikit_learn-1.2.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (9.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.6/9.6 MB\u001b[0m \u001b[31m83.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0mm\n",
"\u001b[?25hCollecting pynvml\n",
" Downloading pynvml-11.5.0-py3-none-any.whl (53 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.1/53.1 kB\u001b[0m \u001b[31m13.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting art\n",
" Downloading art-6.1-py3-none-any.whl.metadata (69 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m69.9/69.9 kB\u001b[0m \u001b[31m21.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting fschat==0.2.34\n",
" Downloading fschat-0.2.34-py3-none-any.whl.metadata (20 kB)\n",
"Collecting gradio==3.50.2\n",
" Downloading gradio-3.50.2-py3-none-any.whl.metadata (17 kB)\n",
"Collecting tensorboard\n",
" Downloading tensorboard-2.15.1-py3-none-any.whl.metadata (1.7 kB)\n",
"Collecting s3fs\n",
" Downloading s3fs-2023.12.2-py3-none-any.whl.metadata (1.6 kB)\n",
"Collecting gcsfs\n",
" Downloading gcsfs-2023.12.2.post1-py2.py3-none-any.whl.metadata (1.6 kB)\n",
"Collecting xformers==0.0.23\n",
" Downloading xformers-0.0.23-cp310-cp310-manylinux2014_x86_64.whl.metadata (1.0 kB)\n",
"Collecting deepspeed\n",
" Downloading deepspeed-0.12.6.tar.gz (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m109.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25hCollecting flash-attn==2.3.3\n",
" Downloading flash_attn-2.3.3.tar.gz (2.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.3/2.3 MB\u001b[0m \u001b[31m111.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25hRequirement already satisfied: psutil in /opt/conda/lib/python3.10/site-packages (from accelerate==0.24.1) (5.9.0)\n",
"Requirement already satisfied: torch>=1.10.0 in /opt/conda/lib/python3.10/site-packages (from accelerate==0.24.1) (2.1.1)\n",
"Requirement already satisfied: huggingface-hub in /opt/conda/lib/python3.10/site-packages (from accelerate==0.24.1) (0.20.1)\n",
"Collecting rouge (from auto-gptq==0.5.1)\n",
" Downloading rouge-1.0.1-py3-none-any.whl (13 kB)\n",
"Collecting gekko (from auto-gptq==0.5.1)\n",
" Downloading gekko-1.0.6-py3-none-any.whl (12.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.2/12.2 MB\u001b[0m \u001b[31m77.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m0:01\u001b[0m\n",
"\u001b[?25hCollecting safetensors (from auto-gptq==0.5.1)\n",
" Downloading safetensors-0.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (3.8 kB)\n",
"Requirement already satisfied: tqdm in /opt/conda/lib/python3.10/site-packages (from auto-gptq==0.5.1) (4.65.0)\n",
"Collecting pandas>=1.0.1 (from bert-score==0.3.13)\n",
" Downloading pandas-2.1.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (18 kB)\n",
"Requirement already satisfied: requests in /opt/conda/lib/python3.10/site-packages (from bert-score==0.3.13) (2.31.0)\n",
"Collecting matplotlib (from bert-score==0.3.13)\n",
" Downloading matplotlib-3.8.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.8 kB)\n",
"Collecting dill (from evaluate==0.4.0)\n",
" Downloading dill-0.3.7-py3-none-any.whl.metadata (9.9 kB)\n",
"Collecting xxhash (from evaluate==0.4.0)\n",
" Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n",
"Collecting multiprocess (from evaluate==0.4.0)\n",
" Downloading multiprocess-0.70.15-py310-none-any.whl.metadata (7.2 kB)\n",
"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)\n",
"Collecting responses<0.19 (from evaluate==0.4.0)\n",
" Downloading responses-0.18.0-py3-none-any.whl (38 kB)\n",
"Collecting ninja (from flash-attn==2.3.3)\n",
" Downloading ninja-1.11.1.1-py2.py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl.metadata (5.3 kB)\n",
"Collecting aiohttp (from fschat==0.2.34)\n",
" Downloading aiohttp-3.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (7.4 kB)\n",
"Collecting fastapi (from fschat==0.2.34)\n",
" Downloading fastapi-0.108.0-py3-none-any.whl.metadata (24 kB)\n",
"Collecting httpx (from fschat==0.2.34)\n",
" Downloading httpx-0.26.0-py3-none-any.whl.metadata (7.6 kB)\n",
"Collecting markdown2[all] (from fschat==0.2.34)\n",
" Downloading markdown2-2.4.12-py2.py3-none-any.whl.metadata (2.0 kB)\n",
"Collecting nh3 (from fschat==0.2.34)\n",
" Downloading nh3-0.2.15-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (1.7 kB)\n",
"Requirement already satisfied: prompt-toolkit>=3.0.0 in /opt/conda/lib/python3.10/site-packages (from fschat==0.2.34) (3.0.36)\n",
"Collecting pydantic<2,>=1 (from fschat==0.2.34)\n",
" Downloading pydantic-1.10.13-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (149 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m149.6/149.6 kB\u001b[0m \u001b[31m42.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting rich>=10.0.0 (from fschat==0.2.34)\n",
" Downloading rich-13.7.0-py3-none-any.whl.metadata (18 kB)\n",
"Collecting shortuuid (from fschat==0.2.34)\n",
" Downloading shortuuid-1.0.11-py3-none-any.whl (10 kB)\n",
"Collecting tiktoken (from fschat==0.2.34)\n",
" Downloading tiktoken-0.5.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (6.6 kB)\n",
"Collecting uvicorn (from fschat==0.2.34)\n",
" Downloading uvicorn-0.25.0-py3-none-any.whl.metadata (6.4 kB)\n",
"Collecting aiofiles<24.0,>=22.0 (from gradio==3.50.2)\n",
" Downloading aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 kB)\n",
"Collecting altair<6.0,>=4.2.0 (from gradio==3.50.2)\n",
" Downloading altair-5.2.0-py3-none-any.whl.metadata (8.7 kB)\n",
"Collecting ffmpy (from gradio==3.50.2)\n",
" Downloading ffmpy-0.3.1.tar.gz (5.5 kB)\n",
" Preparing metadata (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25hCollecting gradio-client==0.6.1 (from gradio==3.50.2)\n",
" Downloading gradio_client-0.6.1-py3-none-any.whl.metadata (7.1 kB)\n",
"Collecting importlib-resources<7.0,>=1.3 (from gradio==3.50.2)\n",
" Downloading importlib_resources-6.1.1-py3-none-any.whl.metadata (4.1 kB)\n",
"Requirement already satisfied: jinja2<4.0 in /opt/conda/lib/python3.10/site-packages (from gradio==3.50.2) (3.1.2)\n",
"Requirement already satisfied: markupsafe~=2.0 in /opt/conda/lib/python3.10/site-packages (from gradio==3.50.2) (2.1.1)\n",
"Collecting orjson~=3.0 (from gradio==3.50.2)\n",
" Downloading orjson-3.9.10-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (49 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m49.3/49.3 kB\u001b[0m \u001b[31m14.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: pillow<11.0,>=8.0 in /opt/conda/lib/python3.10/site-packages (from gradio==3.50.2) (10.0.1)\n",
"Collecting pydub (from gradio==3.50.2)\n",
" Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
"Collecting python-multipart (from gradio==3.50.2)\n",
" Downloading python_multipart-0.0.6-py3-none-any.whl (45 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m45.7/45.7 kB\u001b[0m \u001b[31m13.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting semantic-version~=2.0 (from gradio==3.50.2)\n",
" Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
"Requirement already satisfied: typing-extensions~=4.0 in /opt/conda/lib/python3.10/site-packages (from gradio==3.50.2) (4.7.1)\n",
"Collecting websockets<12.0,>=10.0 (from gradio==3.50.2)\n",
" 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)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m129.9/129.9 kB\u001b[0m \u001b[31m30.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting coloredlogs (from optimum==1.13.2)\n",
" Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m11.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from optimum==1.13.2) (1.11.1)\n",
"Collecting absl-py (from rouge-score==0.1.2)\n",
" Downloading absl_py-2.0.0-py3-none-any.whl.metadata (2.3 kB)\n",
"Collecting nltk (from rouge-score==0.1.2)\n",
" Downloading nltk-3.8.1-py3-none-any.whl (1.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.5/1.5 MB\u001b[0m \u001b[31m90.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: six>=1.14.0 in /opt/conda/lib/python3.10/site-packages (from rouge-score==0.1.2) (1.16.0)\n",
"Collecting joblib>=1.1.1 (from scikit-learn==1.2.2)\n",
" Downloading joblib-1.3.2-py3-none-any.whl.metadata (5.4 kB)\n",
"Collecting threadpoolctl>=2.0.0 (from scikit-learn==1.2.2)\n",
" Downloading threadpoolctl-3.2.0-py3-none-any.whl.metadata (10.0 kB)\n",
"Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from transformers==4.36.2) (3.9.0)\n",
"Collecting regex!=2019.12.17 (from transformers==4.36.2)\n",
" Downloading regex-2023.12.25-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (40 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.9/40.9 kB\u001b[0m \u001b[31m12.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch>=1.10.0->accelerate==0.24.1) (3.1)\n",
"Collecting pyarrow>=8.0.0 (from datasets>=2.15.0)\n",
" Downloading pyarrow-14.0.2-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.0 kB)\n",
"Collecting pyarrow-hotfix (from datasets>=2.15.0)\n",
" Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\n",
"Collecting hjson (from deepspeed)\n",
" Downloading hjson-3.1.0-py3-none-any.whl (54 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m54.0/54.0 kB\u001b[0m \u001b[31m19.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting py-cpuinfo (from deepspeed)\n",
" Downloading py_cpuinfo-9.0.0-py3-none-any.whl (22 kB)\n",
"Collecting termcolor (from fire)\n",
" Downloading termcolor-2.4.0-py3-none-any.whl.metadata (6.1 kB)\n",
"Requirement already satisfied: decorator>4.1.2 in /opt/conda/lib/python3.10/site-packages (from gcsfs) (5.1.1)\n",
"INFO: pip is looking at multiple versions of gcsfs to determine which version is compatible with other requirements. This could take a while.\n",
"Collecting gcsfs\n",
" Downloading gcsfs-2023.12.1-py2.py3-none-any.whl.metadata (1.6 kB)\n",
" Downloading gcsfs-2023.12.0-py2.py3-none-any.whl.metadata (1.6 kB)\n",
" Downloading gcsfs-2023.10.0-py2.py3-none-any.whl.metadata (1.6 kB)\n",
"Collecting google-auth>=1.2 (from gcsfs)\n",
" Downloading google_auth-2.25.2-py2.py3-none-any.whl.metadata (4.7 kB)\n",
"Collecting google-auth-oauthlib (from gcsfs)\n",
" Downloading google_auth_oauthlib-1.2.0-py2.py3-none-any.whl.metadata (2.7 kB)\n",
"Collecting google-cloud-storage (from gcsfs)\n",
" Downloading google_cloud_storage-2.14.0-py2.py3-none-any.whl.metadata (6.1 kB)\n",
"Collecting llvmlite<0.42,>=0.41.0dev0 (from numba)\n",
" Downloading llvmlite-0.41.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.8 kB)\n",
"Collecting aiobotocore<3.0.0,>=2.5.4 (from s3fs)\n",
" Downloading aiobotocore-2.9.0-py3-none-any.whl.metadata (20 kB)\n",
"INFO: pip is looking at multiple versions of s3fs to determine which version is compatible with other requirements. This could take a while.\n",
"Collecting s3fs\n",
" Downloading s3fs-2023.12.1-py3-none-any.whl.metadata (1.6 kB)\n",
" Downloading s3fs-2023.10.0-py3-none-any.whl.metadata (1.6 kB)\n",
"Collecting aiobotocore~=2.7.0 (from s3fs)\n",
" Downloading aiobotocore-2.7.0-py3-none-any.whl.metadata (20 kB)\n",
"Collecting grpcio>=1.48.2 (from tensorboard)\n",
" Downloading grpcio-1.60.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (4.0 kB)\n",
"Collecting markdown>=2.6.8 (from tensorboard)\n",
" Downloading Markdown-3.5.1-py3-none-any.whl.metadata (7.1 kB)\n",
"Collecting protobuf<4.24,>=3.19.6 (from tensorboard)\n",
" Downloading protobuf-4.23.4-cp37-abi3-manylinux2014_x86_64.whl.metadata (540 bytes)\n",
"Requirement already satisfied: setuptools>=41.0.0 in /opt/conda/lib/python3.10/site-packages (from tensorboard) (68.0.0)\n",
"Collecting tensorboard-data-server<0.8.0,>=0.7.0 (from tensorboard)\n",
" Downloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl.metadata (1.1 kB)\n",
"Collecting werkzeug>=1.0.1 (from tensorboard)\n",
" Downloading werkzeug-3.0.1-py3-none-any.whl.metadata (4.1 kB)\n",
"Requirement already satisfied: Click!=8.0.0,>=7.1 in /opt/conda/lib/python3.10/site-packages (from wandb) (8.1.7)\n",
"Collecting GitPython!=3.1.29,>=1.0.0 (from wandb)\n",
" Downloading GitPython-3.1.40-py3-none-any.whl.metadata (12 kB)\n",
"Collecting sentry-sdk>=1.0.0 (from wandb)\n",
" Downloading sentry_sdk-1.39.1-py2.py3-none-any.whl.metadata (9.7 kB)\n",
"Collecting docker-pycreds>=0.4.0 (from wandb)\n",
" Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)\n",
"Collecting setproctitle (from wandb)\n",
" 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)\n",
"Collecting appdirs>=1.4.3 (from wandb)\n",
" Downloading appdirs-1.4.4-py2.py3-none-any.whl (9.6 kB)\n",
"Collecting botocore<1.31.65,>=1.31.16 (from aiobotocore~=2.7.0->s3fs)\n",
" Downloading botocore-1.31.64-py3-none-any.whl.metadata (6.1 kB)\n",
"Collecting wrapt<2.0.0,>=1.10.10 (from aiobotocore~=2.7.0->s3fs)\n",
" 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)\n",
"Collecting aioitertools<1.0.0,>=0.5.1 (from aiobotocore~=2.7.0->s3fs)\n",
" Downloading aioitertools-0.11.0-py3-none-any.whl (23 kB)\n",
"Requirement already satisfied: attrs>=17.3.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->fschat==0.2.34) (23.1.0)\n",
"Collecting multidict<7.0,>=4.5 (from aiohttp->fschat==0.2.34)\n",
" Downloading multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.5/114.5 kB\u001b[0m \u001b[31m37.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting yarl<2.0,>=1.0 (from aiohttp->fschat==0.2.34)\n",
" Downloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (31 kB)\n",
"Collecting frozenlist>=1.1.1 (from aiohttp->fschat==0.2.34)\n",
" 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)\n",
"Collecting aiosignal>=1.1.2 (from aiohttp->fschat==0.2.34)\n",
" Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n",
"Collecting async-timeout<5.0,>=4.0 (from aiohttp->fschat==0.2.34)\n",
" Downloading async_timeout-4.0.3-py3-none-any.whl.metadata (4.2 kB)\n",
"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)\n",
"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)\n",
"Collecting gitdb<5,>=4.0.1 (from GitPython!=3.1.29,>=1.0.0->wandb)\n",
" Downloading gitdb-4.0.11-py3-none-any.whl.metadata (1.2 kB)\n",
"Collecting cachetools<6.0,>=2.0.0 (from google-auth>=1.2->gcsfs)\n",
" Downloading cachetools-5.3.2-py3-none-any.whl.metadata (5.2 kB)\n",
"Collecting pyasn1-modules>=0.2.1 (from google-auth>=1.2->gcsfs)\n",
" Downloading pyasn1_modules-0.3.0-py2.py3-none-any.whl (181 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m181.3/181.3 kB\u001b[0m \u001b[31m59.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting rsa<5,>=3.1.4 (from google-auth>=1.2->gcsfs)\n",
" Downloading rsa-4.9-py3-none-any.whl (34 kB)\n",
"Collecting requests-oauthlib>=0.7.0 (from google-auth-oauthlib->gcsfs)\n",
" Downloading requests_oauthlib-1.3.1-py2.py3-none-any.whl (23 kB)\n",
"Collecting contourpy>=1.0.1 (from matplotlib->bert-score==0.3.13)\n",
" Downloading contourpy-1.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (5.8 kB)\n",
"Collecting cycler>=0.10 (from matplotlib->bert-score==0.3.13)\n",
" Downloading cycler-0.12.1-py3-none-any.whl.metadata (3.8 kB)\n",
"Collecting fonttools>=4.22.0 (from matplotlib->bert-score==0.3.13)\n",
" Downloading fonttools-4.47.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (157 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m157.2/157.2 kB\u001b[0m \u001b[31m41.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting kiwisolver>=1.3.1 (from matplotlib->bert-score==0.3.13)\n",
" Downloading kiwisolver-1.4.5-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl.metadata (6.4 kB)\n",
"Collecting pyparsing>=2.3.1 (from matplotlib->bert-score==0.3.13)\n",
" Downloading pyparsing-3.1.1-py3-none-any.whl.metadata (5.1 kB)\n",
"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)\n",
"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)\n",
"Collecting tzdata>=2022.1 (from pandas>=1.0.1->bert-score==0.3.13)\n",
" Downloading tzdata-2023.3-py2.py3-none-any.whl (341 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m341.8/341.8 kB\u001b[0m \u001b[31m72.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: wcwidth in /opt/conda/lib/python3.10/site-packages (from prompt-toolkit>=3.0.0->fschat==0.2.34) (0.2.5)\n",
"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)\n",
"Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests->bert-score==0.3.13) (3.4)\n",
"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)\n",
"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)\n",
"Collecting markdown-it-py>=2.2.0 (from rich>=10.0.0->fschat==0.2.34)\n",
" Downloading markdown_it_py-3.0.0-py3-none-any.whl.metadata (6.9 kB)\n",
"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)\n",
"Collecting h11>=0.8 (from uvicorn->fschat==0.2.34)\n",
" Downloading h11-0.14.0-py3-none-any.whl (58 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m58.3/58.3 kB\u001b[0m \u001b[31m21.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting humanfriendly>=9.1 (from coloredlogs->optimum==1.13.2)\n",
" Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m27.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting starlette<0.33.0,>=0.29.0 (from fastapi->fschat==0.2.34)\n",
" Downloading starlette-0.32.0.post1-py3-none-any.whl.metadata (5.8 kB)\n",
"Collecting typing-extensions~=4.0 (from gradio==3.50.2)\n",
" Downloading typing_extensions-4.9.0-py3-none-any.whl.metadata (3.0 kB)\n",
"Collecting google-api-core!=2.0.*,!=2.1.*,!=2.2.*,!=2.3.0,<3.0.0dev,>=1.31.5 (from google-cloud-storage->gcsfs)\n",
" Downloading google_api_core-2.15.0-py3-none-any.whl.metadata (2.7 kB)\n",
"Collecting google-cloud-core<3.0dev,>=2.3.0 (from google-cloud-storage->gcsfs)\n",
" Downloading google_cloud_core-2.4.1-py2.py3-none-any.whl.metadata (2.7 kB)\n",
"Collecting google-resumable-media>=2.6.0 (from google-cloud-storage->gcsfs)\n",
" Downloading google_resumable_media-2.7.0-py2.py3-none-any.whl.metadata (2.2 kB)\n",
"Collecting google-crc32c<2.0dev,>=1.0 (from google-cloud-storage->gcsfs)\n",
" Downloading google_crc32c-1.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (32 kB)\n",
"Requirement already satisfied: anyio in /opt/conda/lib/python3.10/site-packages (from httpx->fschat==0.2.34) (4.2.0)\n",
"Collecting httpcore==1.* (from httpx->fschat==0.2.34)\n",
" Downloading httpcore-1.0.2-py3-none-any.whl.metadata (20 kB)\n",
"Requirement already satisfied: sniffio in /opt/conda/lib/python3.10/site-packages (from httpx->fschat==0.2.34) (1.3.0)\n",
"Collecting wavedrom (from markdown2[all]->fschat==0.2.34)\n",
" Downloading wavedrom-2.0.3.post3.tar.gz (137 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m137.7/137.7 kB\u001b[0m \u001b[31m47.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25hRequirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->optimum==1.13.2) (1.3.0)\n",
"Collecting jmespath<2.0.0,>=0.7.1 (from botocore<1.31.65,>=1.31.16->aiobotocore~=2.7.0->s3fs)\n",
" Downloading jmespath-1.0.1-py3-none-any.whl (20 kB)\n",
"Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->GitPython!=3.1.29,>=1.0.0->wandb)\n",
" Downloading smmap-5.0.1-py3-none-any.whl.metadata (4.3 kB)\n",
"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)\n",
" Downloading googleapis_common_protos-1.62.0-py2.py3-none-any.whl.metadata (1.5 kB)\n",
"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)\n",
"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)\n",
"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)\n",
"Collecting mdurl~=0.1 (from markdown-it-py>=2.2.0->rich>=10.0.0->fschat==0.2.34)\n",
" Downloading mdurl-0.1.2-py3-none-any.whl (10.0 kB)\n",
"Collecting pyasn1<0.6.0,>=0.4.6 (from pyasn1-modules>=0.2.1->google-auth>=1.2->gcsfs)\n",
" Downloading pyasn1-0.5.1-py2.py3-none-any.whl.metadata (8.6 kB)\n",
"Collecting oauthlib>=3.0.0 (from requests-oauthlib>=0.7.0->google-auth-oauthlib->gcsfs)\n",
" Downloading oauthlib-3.2.2-py3-none-any.whl (151 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m151.7/151.7 kB\u001b[0m \u001b[31m50.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: exceptiongroup>=1.0.2 in /opt/conda/lib/python3.10/site-packages (from anyio->httpx->fschat==0.2.34) (1.0.4)\n",
"Collecting svgwrite (from wavedrom->markdown2[all]->fschat==0.2.34)\n",
" Downloading svgwrite-1.4.3-py3-none-any.whl (67 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.1/67.1 kB\u001b[0m \u001b[31m21.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading accelerate-0.24.1-py3-none-any.whl (261 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m261.4/261.4 kB\u001b[0m \u001b[31m53.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading auto_gptq-0.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.8/4.8 MB\u001b[0m \u001b[31m89.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading fschat-0.2.34-py3-none-any.whl (220 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m220.1/220.1 kB\u001b[0m \u001b[31m63.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading gradio-3.50.2-py3-none-any.whl (20.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m20.3/20.3 MB\u001b[0m \u001b[31m82.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading peft-0.6.0-py3-none-any.whl (134 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.9/134.9 kB\u001b[0m \u001b[31m40.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading tokenizers-0.15.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.8 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.8/3.8 MB\u001b[0m \u001b[31m87.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading transformers-4.36.2-py3-none-any.whl (8.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m8.2/8.2 MB\u001b[0m \u001b[31m90.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading xformers-0.0.23-cp310-cp310-manylinux2014_x86_64.whl (213.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m213.0/213.0 MB\u001b[0m \u001b[31m36.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading gradio_client-0.6.1-py3-none-any.whl (299 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m299.2/299.2 kB\u001b[0m \u001b[31m64.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading bitsandbytes-0.41.3.post2-py3-none-any.whl (92.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.6/92.6 MB\u001b[0m \u001b[31m56.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading datasets-2.16.0-py3-none-any.whl (507 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m507.1/507.1 kB\u001b[0m \u001b[31m87.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading scipy-1.11.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (36.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m36.4/36.4 MB\u001b[0m \u001b[31m77.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading art-6.1-py3-none-any.whl (599 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m599.8/599.8 kB\u001b[0m \u001b[31m96.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading einops-0.7.0-py3-none-any.whl (44 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading gcsfs-2023.10.0-py2.py3-none-any.whl (33 kB)\n",
"Downloading hf_transfer-0.1.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.9 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.9/3.9 MB\u001b[0m \u001b[31m99.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m\n",
"\u001b[?25hDownloading numba-0.58.1-cp310-cp310-manylinux2014_x86_64.manylinux_2_17_x86_64.whl (3.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m100.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading s3fs-2023.10.0-py3-none-any.whl (28 kB)\n",
"Downloading tensorboard-2.15.1-py3-none-any.whl (5.5 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.5/5.5 MB\u001b[0m \u001b[31m96.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0mta \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading wandb-0.16.1-py3-none-any.whl (2.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m99.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading absl_py-2.0.0-py3-none-any.whl (130 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m130.2/130.2 kB\u001b[0m \u001b[31m36.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading aiobotocore-2.7.0-py3-none-any.whl (73 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m73.5/73.5 kB\u001b[0m \u001b[31m25.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
"Downloading aiohttp-3.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.2 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.2/1.2 MB\u001b[0m \u001b[31m99.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading altair-5.2.0-py3-none-any.whl (996 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m996.9/996.9 kB\u001b[0m \u001b[31m110.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading dill-0.3.7-py3-none-any.whl (115 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m34.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading GitPython-3.1.40-py3-none-any.whl (190 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m190.6/190.6 kB\u001b[0m \u001b[31m47.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading google_auth-2.25.2-py2.py3-none-any.whl (184 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m184.2/184.2 kB\u001b[0m \u001b[31m44.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading google_auth_oauthlib-1.2.0-py2.py3-none-any.whl (24 kB)\n",
"Downloading grpcio-1.60.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (5.4 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m5.4/5.4 MB\u001b[0m \u001b[31m102.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading importlib_resources-6.1.1-py3-none-any.whl (33 kB)\n",
"Downloading joblib-1.3.2-py3-none-any.whl (302 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.2/302.2 kB\u001b[0m \u001b[31m64.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading llvmlite-0.41.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (43.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.6/43.6 MB\u001b[0m \u001b[31m74.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading Markdown-3.5.1-py3-none-any.whl (102 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m102.2/102.2 kB\u001b[0m \u001b[31m34.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading matplotlib-3.8.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (11.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.6/11.6 MB\u001b[0m \u001b[31m99.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m0:01\u001b[0m\n",
"\u001b[?25hDownloading orjson-3.9.10-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (138 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m138.7/138.7 kB\u001b[0m \u001b[31m38.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pandas-2.1.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (12.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m12.3/12.3 MB\u001b[0m \u001b[31m96.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m0:01\u001b[0m\n",
"\u001b[?25hDownloading protobuf-4.23.4-cp37-abi3-manylinux2014_x86_64.whl (304 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m304.5/304.5 kB\u001b[0m \u001b[31m68.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyarrow-14.0.2-cp310-cp310-manylinux_2_28_x86_64.whl (38.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.0/38.0 MB\u001b[0m \u001b[31m78.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m00:01\u001b[0m\n",
"\u001b[?25hDownloading pydantic-1.10.13-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m95.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading regex-2023.12.25-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (773 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m774.0/774.0 kB\u001b[0m \u001b[31m116.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading rich-13.7.0-py3-none-any.whl (240 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m240.6/240.6 kB\u001b[0m \u001b[31m59.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading safetensors-0.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m102.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading sentry_sdk-1.39.1-py2.py3-none-any.whl (254 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m254.1/254.1 kB\u001b[0m \u001b[31m71.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading tensorboard_data_server-0.7.2-py3-none-manylinux_2_31_x86_64.whl (6.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.6/6.6 MB\u001b[0m \u001b[31m104.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading threadpoolctl-3.2.0-py3-none-any.whl (15 kB)\n",
"Downloading uvicorn-0.25.0-py3-none-any.whl (60 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.3/60.3 kB\u001b[0m \u001b[31m19.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading werkzeug-3.0.1-py3-none-any.whl (226 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m226.7/226.7 kB\u001b[0m \u001b[31m67.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading fastapi-0.108.0-py3-none-any.whl (92 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.0/92.0 kB\u001b[0m \u001b[31m33.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading typing_extensions-4.9.0-py3-none-any.whl (32 kB)\n",
"Downloading google_cloud_storage-2.14.0-py2.py3-none-any.whl (121 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.6/121.6 kB\u001b[0m \u001b[31m36.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading httpx-0.26.0-py3-none-any.whl (75 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m75.9/75.9 kB\u001b[0m \u001b[31m24.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading httpcore-1.0.2-py3-none-any.whl (76 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m76.9/76.9 kB\u001b[0m \u001b[31m28.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading multiprocess-0.70.15-py310-none-any.whl (134 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m48.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading nh3-0.2.15-cp37-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.7 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.7/1.7 MB\u001b[0m \u001b[31m108.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading ninja-1.11.1.1-py2.py3-none-manylinux1_x86_64.manylinux_2_5_x86_64.whl (307 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m307.2/307.2 kB\u001b[0m \u001b[31m66.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n",
"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)\n",
"Downloading termcolor-2.4.0-py3-none-any.whl (7.7 kB)\n",
"Downloading tiktoken-0.5.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m101.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m44.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading async_timeout-4.0.3-py3-none-any.whl (5.7 kB)\n",
"Downloading botocore-1.31.64-py3-none-any.whl (11.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m11.3/11.3 MB\u001b[0m \u001b[31m98.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m:00:01\u001b[0m0:01\u001b[0m\n",
"\u001b[?25hDownloading cachetools-5.3.2-py3-none-any.whl (9.3 kB)\n",
"Downloading contourpy-1.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (310 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m310.7/310.7 kB\u001b[0m \u001b[31m69.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading cycler-0.12.1-py3-none-any.whl (8.3 kB)\n",
"Downloading fonttools-4.47.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (4.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m4.6/4.6 MB\u001b[0m \u001b[31m102.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0ma \u001b[36m0:00:01\u001b[0m\n",
"\u001b[?25hDownloading 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)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m239.5/239.5 kB\u001b[0m \u001b[31m71.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading gitdb-4.0.11-py3-none-any.whl (62 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m23.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading google_api_core-2.15.0-py3-none-any.whl (121 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m122.0/122.0 kB\u001b[0m \u001b[31m32.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading google_cloud_core-2.4.1-py2.py3-none-any.whl (29 kB)\n",
"Downloading google_resumable_media-2.7.0-py2.py3-none-any.whl (80 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m80.6/80.6 kB\u001b[0m \u001b[31m22.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading kiwisolver-1.4.5-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl (1.6 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m102.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading markdown_it_py-3.0.0-py3-none-any.whl (87 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m87.5/87.5 kB\u001b[0m \u001b[31m25.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyparsing-3.1.1-py3-none-any.whl (103 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m103.1/103.1 kB\u001b[0m \u001b[31m32.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading starlette-0.32.0.post1-py3-none-any.whl (70 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m70.0/70.0 kB\u001b[0m \u001b[31m19.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading 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)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m80.3/80.3 kB\u001b[0m \u001b[31m30.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading yarl-1.9.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (301 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m301.6/301.6 kB\u001b[0m \u001b[31m80.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading markdown2-2.4.12-py2.py3-none-any.whl (41 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m41.2/41.2 kB\u001b[0m \u001b[31m12.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading googleapis_common_protos-1.62.0-py2.py3-none-any.whl (228 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m228.7/228.7 kB\u001b[0m \u001b[31m57.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading pyasn1-0.5.1-py2.py3-none-any.whl (84 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.9/84.9 kB\u001b[0m \u001b[31m30.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hDownloading smmap-5.0.1-py3-none-any.whl (24 kB)\n",
"Building wheels for collected packages: flash-attn, optimum, rouge-score, deepspeed, fire, ffmpy, wavedrom\n",
" Building wheel for flash-attn (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for flash-attn: filename=flash_attn-2.3.3-cp310-cp310-linux_x86_64.whl size=57042553 sha256=b1df92cb5bd7657d38b789dd48e907aa3e0bd2715c817eb85f3c4320bb11fb3f\n",
" Stored in directory: /root/.cache/pip/wheels/e5/e6/fa/941802ec61d1afd320d27160ab1db98e6dba65381f84b76d4a\n",
" Building wheel for optimum (pyproject.toml) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for optimum: filename=optimum-1.13.2-py3-none-any.whl size=395599 sha256=ff3a73120e1b6eeeda28f76e3fc8cd4cd826e5d66c869b7848ba150e7af79c62\n",
" Stored in directory: /root/.cache/pip/wheels/6e/b7/2c/79405d98f0943373d8546daeae25a3d377f7659ca0cbe48699\n",
" Building wheel for rouge-score (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for rouge-score: filename=rouge_score-0.1.2-py3-none-any.whl size=24932 sha256=8118ecbbcd3529085e794c803f0ddb182fc6c6d3e8a494103b49a94abf1bec37\n",
" Stored in directory: /root/.cache/pip/wheels/5f/dd/89/461065a73be61a532ff8599a28e9beef17985c9e9c31e541b4\n",
" Building wheel for deepspeed (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for deepspeed: filename=deepspeed-0.12.6-py3-none-any.whl size=1306729 sha256=35c46b6f0275b0d3063522e0af4f3cbd9ec1c310114d8917d87cbe2bf43346e2\n",
" Stored in directory: /root/.cache/pip/wheels/a3/dc/a2/f585faaed4dec84108916dcc8e8a7c129a216df8202ca32984\n",
" Building wheel for fire (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for fire: filename=fire-0.5.0-py2.py3-none-any.whl size=116934 sha256=e76d5185f237f34ec69bb8aa657497bef07408978e4f7efdaef48663bb8cd4ef\n",
" Stored in directory: /root/.cache/pip/wheels/90/d4/f7/9404e5db0116bd4d43e5666eaa3e70ab53723e1e3ea40c9a95\n",
" Building wheel for ffmpy (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for ffmpy: filename=ffmpy-0.3.1-py3-none-any.whl size=5579 sha256=da3b54dc0ac1a825a1a233315970ac80b8b4c53ebd9cb2a2cfdeab118f453a64\n",
" Stored in directory: /root/.cache/pip/wheels/01/a6/d1/1c0828c304a4283b2c1639a09ad86f83d7c487ef34c6b4a1bf\n",
" Building wheel for wavedrom (setup.py) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for wavedrom: filename=wavedrom-2.0.3.post3-py2.py3-none-any.whl size=30052 sha256=7f0cbd15d63ee9c120190bac122ab51bbbfc91ee374bc3c046fadb320816c17e\n",
" Stored in directory: /root/.cache/pip/wheels/9c/52/8c/38b454b42f712f325e26f633287484c7dc1ad469e1580c5954\n",
"Successfully built flash-attn optimum rouge-score deepspeed fire ffmpy wavedrom\n",
"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\n",
" Attempting uninstall: typing-extensions\n",
" Found existing installation: typing_extensions 4.7.1\n",
" Uninstalling typing_extensions-4.7.1:\n",
" Successfully uninstalled typing_extensions-4.7.1\n",
" Running setup.py develop for axolotl\n",
"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\n",
"\u001b[33mWARNING: 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\u001b[0m\u001b[33m\n",
"\u001b[0mCollecting git+https://github.com/huggingface/peft.git\n",
" Cloning https://github.com/huggingface/peft.git to /tmp/pip-req-build-hka8xgk2\n",
" Running command git clone --filter=blob:none --quiet https://github.com/huggingface/peft.git /tmp/pip-req-build-hka8xgk2\n",
" Resolved https://github.com/huggingface/peft.git to commit cf04d0353f0343cbf66627228c4495f51669af34\n",
" Installing build dependencies ... \u001b[?25ldone\n",
"\u001b[?25h Getting requirements to build wheel ... \u001b[?25ldone\n",
"\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25ldone\n",
"\u001b[?25hRequirement already satisfied: numpy>=1.17 in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (1.26.0)\n",
"Requirement already satisfied: packaging>=20.0 in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (23.1)\n",
"Requirement already satisfied: psutil in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (5.9.0)\n",
"Requirement already satisfied: pyyaml in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (6.0.1)\n",
"Requirement already satisfied: torch>=1.13.0 in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (2.1.1)\n",
"Requirement already satisfied: transformers in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (4.36.2)\n",
"Requirement already satisfied: tqdm in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (4.65.0)\n",
"Requirement already satisfied: accelerate>=0.21.0 in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (0.24.1)\n",
"Requirement already satisfied: safetensors in /opt/conda/lib/python3.10/site-packages (from peft==0.7.2.dev0) (0.4.1)\n",
"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)\n",
"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)\n",
"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)\n",
"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)\n",
"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)\n",
"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)\n",
"Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch>=1.13.0->peft==0.7.2.dev0) (3.1)\n",
"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)\n",
"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)\n",
"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)\n",
"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)\n",
"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)\n",
"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)\n",
"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)\n",
"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)\n",
"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)\n",
"Building wheels for collected packages: peft\n",
" Building wheel for peft (pyproject.toml) ... \u001b[?25ldone\n",
"\u001b[?25h Created wheel for peft: filename=peft-0.7.2.dev0-py3-none-any.whl size=169456 sha256=4c70d23e759fa6abb3827fb2f3a8683be3b24d78777d0f403bbc2c0548e5dd4b\n",
" Stored in directory: /tmp/pip-ephem-wheel-cache-my5ncou6/wheels/d7/c7/de/1368fac8590e1b103ddc2ec2a28ad51d83aded1a3830e8a087\n",
"Successfully built peft\n",
"Installing collected packages: peft\n",
" Attempting uninstall: peft\n",
" Found existing installation: peft 0.6.0\n",
" Uninstalling peft-0.6.0:\n",
" Successfully uninstalled peft-0.6.0\n",
"\u001b[31mERROR: 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.\n",
"axolotl 0.3.0 requires peft==0.6.0, but you have peft 0.7.2.dev0 which is incompatible.\u001b[0m\u001b[31m\n",
"\u001b[0mSuccessfully installed peft-0.7.2.dev0\n",
"\u001b[33mWARNING: 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\u001b[0m\u001b[33m\n",
"\u001b[0m"
]
}
],
"source": [
"#instaling what is needed inside axolotl file\n",
"!pip install packaging\n",
"!pip install -e '.[flash-attn,deepspeed]'\n",
"!pip install -U git+https://github.com/huggingface/peft.git"
]
},
{
"cell_type": "code",
"execution_count": 16,
"id": "82d1a380-1e87-48fe-89fe-25331326014d",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"The following values were not passed to `accelerate launch` and had defaults used instead:\n",
"\t`--num_processes` was set to a value of `3`\n",
"\t\tMore than one GPU was found, enabling multi-GPU training.\n",
"\t\tIf this was unintended please pass in `--num_processes=1`.\n",
"\t`--num_machines` was set to a value of `1`\n",
"\t`--mixed_precision` was set to a value of `'no'`\n",
"\t`--dynamo_backend` was set to a value of `'no'`\n",
"To avoid this warning pass in values for each of the problematic parameters or run `accelerate config`.\n",
"/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\n",
" warnings.warn(\n",
"[2023-12-28 15:44:09,979] [INFO] [datasets.<module>:58] [PID:2814] PyTorch version 2.1.1 available.\n",
"/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\n",
" warnings.warn(\n",
"/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\n",
" warnings.warn(\n",
"[2023-12-28 15:44:10,011] [INFO] [datasets.<module>:58] [PID:2812] PyTorch version 2.1.1 available.\n",
"[2023-12-28 15:44:10,013] [INFO] [datasets.<module>:58] [PID:2813] PyTorch version 2.1.1 available.\n",
"[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)\u001b[39m\n",
"[2023-12-28 15:44:10,830] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)\n",
"[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)\u001b[39m\n",
"[2023-12-28 15:44:10,865] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)\n",
"[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)\u001b[39m\n",
"[2023-12-28 15:44:10,887] [INFO] [real_accelerator.py:161:get_accelerator] Setting ds_accelerator to cuda (auto detect)\n",
"[2023-12-28 15:44:10,961] [INFO] [comm.py:637:init_distributed] cdb=None\n",
"[2023-12-28 15:44:10,994] [INFO] [comm.py:637:init_distributed] cdb=None\n",
"[2023-12-28 15:44:11,015] [INFO] [comm.py:637:init_distributed] cdb=None\n",
"[2023-12-28 15:44:11,015] [INFO] [comm.py:668:init_distributed] Initializing TorchBackend in DeepSpeed with backend nccl\n",
" dP dP dP \n",
" 88 88 88 \n",
" .d8888b. dP. .dP .d8888b. 88 .d8888b. d8888P 88 \n",
" 88' `88 `8bd8' 88' `88 88 88' `88 88 88 \n",
" 88. .88 .d88b. 88. .88 88 88. .88 88 88 \n",
" `88888P8 dP' `dP `88888P' dP `88888P' dP dP \n",
" \n",
" \n",
"\n",
"[2023-12-28 15:44:11,412] [DEBUG] [axolotl.load_tokenizer:184] [PID:2812] [RANK:0] EOS: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:11,412] [DEBUG] [axolotl.load_tokenizer:185] [PID:2812] [RANK:0] BOS: 1 / <s>\u001b[39m\n",
"[2023-12-28 15:44:11,412] [DEBUG] [axolotl.load_tokenizer:186] [PID:2812] [RANK:0] PAD: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:11,412] [DEBUG] [axolotl.load_tokenizer:187] [PID:2812] [RANK:0] UNK: 0 / <unk>\u001b[39m\n",
"[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...\u001b[39m\n",
"[2023-12-28 15:44:11,415] [INFO] [axolotl.load_tokenized_prepared_datasets:145] [PID:2812] [RANK:0] Prepared dataset loaded from disk...\u001b[39m\n",
"[2023-12-28 15:44:11,432] [DEBUG] [axolotl.load_tokenizer:184] [PID:2814] [RANK:2] EOS: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:11,432] [DEBUG] [axolotl.load_tokenizer:185] [PID:2814] [RANK:2] BOS: 1 / <s>\u001b[39m\n",
"[2023-12-28 15:44:11,432] [DEBUG] [axolotl.load_tokenizer:186] [PID:2814] [RANK:2] PAD: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:11,432] [DEBUG] [axolotl.load_tokenizer:187] [PID:2814] [RANK:2] UNK: 0 / <unk>\u001b[39m\n",
"[2023-12-28 15:44:11,530] [DEBUG] [axolotl.load_tokenizer:184] [PID:2813] [RANK:1] EOS: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:11,531] [DEBUG] [axolotl.load_tokenizer:185] [PID:2813] [RANK:1] BOS: 1 / <s>\u001b[39m\n",
"[2023-12-28 15:44:11,531] [DEBUG] [axolotl.load_tokenizer:186] [PID:2813] [RANK:1] PAD: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:11,531] [DEBUG] [axolotl.load_tokenizer:187] [PID:2813] [RANK:1] UNK: 0 / <unk>\u001b[39m\n",
"[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...\u001b[39m\n",
"[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...\u001b[39m\n",
"[2023-12-28 15:44:12,160] [INFO] [axolotl.load_tokenized_prepared_datasets:145] [PID:2813] [RANK:1] Prepared dataset loaded from disk...\u001b[39m\n",
"[2023-12-28 15:44:12,161] [INFO] [axolotl.load_tokenized_prepared_datasets:145] [PID:2814] [RANK:2] Prepared dataset loaded from disk...\u001b[39m\n",
"[2023-12-28 15:44:12,236] [DEBUG] [axolotl.log:60] [PID:2812] [RANK:0] total_num_tokens: 28120\u001b[39m\n",
"[2023-12-28 15:44:12,238] [DEBUG] [axolotl.log:60] [PID:2812] [RANK:0] `total_supervised_tokens: 7990`\u001b[39m\n",
"[2023-12-28 15:44:12,238] [DEBUG] [axolotl.log:60] [PID:2812] [RANK:0] total_num_steps: 6\u001b[39m\n",
"[2023-12-28 15:44:12,242] [DEBUG] [axolotl.train.log:60] [PID:2812] [RANK:0] loading tokenizer... mistralai/Mistral-7B-v0.1\u001b[39m\n",
"[2023-12-28 15:44:12,518] [DEBUG] [axolotl.load_tokenizer:184] [PID:2812] [RANK:0] EOS: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:12,518] [DEBUG] [axolotl.load_tokenizer:185] [PID:2812] [RANK:0] BOS: 1 / <s>\u001b[39m\n",
"[2023-12-28 15:44:12,518] [DEBUG] [axolotl.load_tokenizer:186] [PID:2812] [RANK:0] PAD: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:12,518] [DEBUG] [axolotl.load_tokenizer:187] [PID:2812] [RANK:0] UNK: 0 / <unk>\u001b[39m\n",
"[2023-12-28 15:44:12,518] [DEBUG] [axolotl.train.log:60] [PID:2812] [RANK:0] loading model and peft_config...\u001b[39m\n",
"[2023-12-28 15:44:12,589] [DEBUG] [axolotl.load_tokenizer:184] [PID:2814] [RANK:2] EOS: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:12,589] [DEBUG] [axolotl.load_tokenizer:185] [PID:2814] [RANK:2] BOS: 1 / <s>\u001b[39m\n",
"[2023-12-28 15:44:12,589] [DEBUG] [axolotl.load_tokenizer:186] [PID:2814] [RANK:2] PAD: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:12,589] [DEBUG] [axolotl.load_tokenizer:187] [PID:2814] [RANK:2] UNK: 0 / <unk>\u001b[39m\n",
"[2023-12-28 15:44:12,599] [DEBUG] [axolotl.load_tokenizer:184] [PID:2813] [RANK:1] EOS: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:12,599] [DEBUG] [axolotl.load_tokenizer:185] [PID:2813] [RANK:1] BOS: 1 / <s>\u001b[39m\n",
"[2023-12-28 15:44:12,599] [DEBUG] [axolotl.load_tokenizer:186] [PID:2813] [RANK:1] PAD: 2 / </s>\u001b[39m\n",
"[2023-12-28 15:44:12,599] [DEBUG] [axolotl.load_tokenizer:187] [PID:2813] [RANK:1] UNK: 0 / <unk>\u001b[39m\n",
"[2023-12-28 15:44:13,049] [INFO] [partition_parameters.py:348:__exit__] finished initializing model - num_params = 291, num_elems = 7.24B\n",
"Loading checkpoint shards: 100%|██████████████████| 2/2 [00:11<00:00, 5.81s/it]\n",
"Loading checkpoint shards: 100%|██████████████████| 2/2 [00:11<00:00, 5.98s/it]\n",
"[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)\u001b[39m\n",
"[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\u001b[39m\n",
"[2023-12-28 15:44:25,403] [INFO] [axolotl.load_model:538] [PID:2813] [RANK:1] converting modules to torch.bfloat16 for flash attention\u001b[39m\n",
"trainable params: 3,407,872 || all params: 7,245,139,968 || trainable%: 0.04703666202518836\n",
"[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)\u001b[39m\n",
"[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)\u001b[39m\n",
"[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\u001b[39m\n",
"[2023-12-28 15:44:25,580] [INFO] [axolotl.load_model:538] [PID:2814] [RANK:2] converting modules to torch.bfloat16 for flash attention\u001b[39m\n",
"trainable params: 3,407,872 || all params: 7,245,139,968 || trainable%: 0.04703666202518836\n",
"[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)\u001b[39m\n",
"Loading checkpoint shards: 100%|██████████████████| 2/2 [00:12<00:00, 6.30s/it]\n",
"[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)\u001b[39m\n",
"[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\u001b[39m\n",
"[2023-12-28 15:44:26,181] [INFO] [axolotl.load_model:538] [PID:2812] [RANK:0] converting modules to torch.bfloat16 for flash attention\u001b[39m\n",
"trainable params: 3,407,872 || all params: 7,245,139,968 || trainable%: 0.04703666202518836\n",
"[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)\u001b[39m\n",
"[2023-12-28 15:44:26,293] [INFO] [axolotl.train.log:60] [PID:2812] [RANK:0] Pre-saving adapter config to ./out\u001b[39m\n",
"[2023-12-28 15:44:26,296] [INFO] [axolotl.train.log:60] [PID:2812] [RANK:0] Starting trainer...\u001b[39m\n",
"Using /root/.cache/torch_extensions/py310_cu121 as PyTorch extensions root...\n",
"Using /root/.cache/torch_extensions/py310_cu121 as PyTorch extensions root...\n",
"Using /root/.cache/torch_extensions/py310_cu121 as PyTorch extensions root...\n",
"Detected CUDA files, patching ldflags\n",
"Emitting ninja build file /root/.cache/torch_extensions/py310_cu121/fused_adam/build.ninja...\n",
"Building extension module fused_adam...\n",
"Allowing ninja to set a default number of workers... (overridable by setting the environment variable MAX_JOBS=N)\n",
"ninja: no work to do.\n",
"Loading extension module fused_adam...\n",
"Time to load fused_adam op: 0.05891108512878418 seconds\n",
"Loading extension module fused_adam...\n",
"Time to load fused_adam op: 0.10173463821411133 seconds\n",
"Loading extension module fused_adam...\n",
"Time to load fused_adam op: 0.10152459144592285 seconds\n",
"/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.)\n",
" self._dummy_overflow_buf = get_accelerator().IntTensor([0])\n",
"/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.)\n",
" self._dummy_overflow_buf = get_accelerator().IntTensor([0])\n",
"/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.)\n",
" self._dummy_overflow_buf = get_accelerator().IntTensor([0])\n",
"Parameter Offload: Total persistent parameters: 3674112 in 193 params\n",
" 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.\n",
" warnings.warn(\n",
"/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.\n",
" warnings.warn(\n",
"/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.\n",
" warnings.warn(\n",
"/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\n",
" warnings.warn(f\"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization\")\n",
"/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\n",
" warnings.warn(f\"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization\")\n",
"/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\n",
" warnings.warn(f\"MatMul8bitLt: inputs will be cast from {A.dtype} to float16 during quantization\")\n",
"{'loss': 2.0448, 'learning_rate': 2e-05, 'epoch': 0.06} \n",
" 6%|██▌ | 1/17 [00:28<07:32, 28.30s/it]\n",
" 0%| | 0/3 [00:00<?, ?it/s]\u001b[A\n",
" 67%|██████████████████████████████ | 2/3 [00:03<00:01, 1.85s/it]\u001b[A\n",
" \u001b[A\n",
"\u001b[A{'eval_loss': 1.9694719314575195, 'eval_runtime': 11.391, 'eval_samples_per_second': 1.492, 'eval_steps_per_second': 0.263, 'epoch': 0.06}\n",
" 6%|██▌ | 1/17 [00:39<07:32, 28.30s/it]\n",
"100%|█████████████████████████████████████████████| 3/3 [00:07<00:00, 2.65s/it]\u001b[A\n",
" \u001b[A[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)\u001b[39m\n",
" 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)\u001b[39m\n",
"[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)\u001b[39m\n",
"{'loss': 2.0022, 'learning_rate': 4e-05, 'epoch': 0.12} \n",
"{'loss': 2.1054, 'learning_rate': 6e-05, 'epoch': 0.17} \n",
"{'loss': 1.9004, 'learning_rate': 8e-05, 'epoch': 0.23} \n",
"{'loss': 1.8794, 'learning_rate': 0.0001, 'epoch': 0.29} \n",
" 29%|████████████▉ | 5/17 [02:20<05:23, 26.92s/it]\n",
" 0%| | 0/3 [00:00<?, ?it/s]\u001b[A\n",
" 67%|██████████████████████████████ | 2/3 [00:03<00:01, 1.88s/it]\u001b[A\n",
" \u001b[A\n",
"\u001b[A{'eval_loss': 1.7912336587905884, 'eval_runtime': 11.3106, 'eval_samples_per_second': 1.503, 'eval_steps_per_second': 0.265, 'epoch': 0.29}\n",
" 29%|████████████▉ | 5/17 [02:32<05:23, 26.92s/it]\n",
"100%|█████████████████████████████████████████████| 3/3 [00:07<00:00, 2.67s/it]\u001b[A\n",
"{'loss': 1.7871, 'learning_rate': 0.00012, 'epoch': 0.35} \u001b[A\n",
"{'loss': 1.7758, 'learning_rate': 0.00014, 'epoch': 0.4} \n",
"{'loss': 1.4645, 'learning_rate': 0.00016, 'epoch': 0.46} \n",
"{'loss': 1.4009, 'learning_rate': 0.00018, 'epoch': 0.52} \n",
"{'loss': 1.3927, 'learning_rate': 0.0002, 'epoch': 0.58} \n",
" 59%|█████████████████████████▎ | 10/17 [04:38<03:04, 26.33s/it]\n",
" 0%| | 0/3 [00:00<?, ?it/s]\u001b[A\n",
" 67%|██████████████████████████████ | 2/3 [00:03<00:01, 1.89s/it]\u001b[A\n",
" \u001b[A\n",
"\u001b[A{'eval_loss': 1.1426481008529663, 'eval_runtime': 11.3344, 'eval_samples_per_second': 1.5, 'eval_steps_per_second': 0.265, 'epoch': 0.58}\n",
" 59%|█████████████████████████▎ | 10/17 [04:49<03:04, 26.33s/it]\n",
"100%|█████████████████████████████████████████████| 3/3 [00:07<00:00, 2.68s/it]\u001b[A\n",
"{'loss': 1.0122, 'learning_rate': 0.0001900968867902419, 'epoch': 0.63} \u001b[A\n",
"{'loss': 1.0019, 'learning_rate': 0.00016234898018587337, 'epoch': 0.69} \n",
"{'loss': 0.8976, 'learning_rate': 0.00012225209339563145, 'epoch': 0.75} \n",
"{'loss': 0.9301, 'learning_rate': 7.774790660436858e-05, 'epoch': 0.81} \n",
"{'loss': 0.8595, 'learning_rate': 3.7651019814126654e-05, 'epoch': 0.87} \n",
" 88%|█████████████████████████████████████▉ | 15/17 [06:55<00:52, 26.17s/it]\n",
" 0%| | 0/3 [00:00<?, ?it/s]\u001b[A\n",
" 67%|██████████████████████████████ | 2/3 [00:03<00:01, 1.88s/it]\u001b[A\n",
" \u001b[A\n",
"\u001b[A{'eval_loss': 0.8175248503684998, 'eval_runtime': 11.2932, 'eval_samples_per_second': 1.505, 'eval_steps_per_second': 0.266, 'epoch': 0.87}\n",
" 88%|█████████████████████████████████████▉ | 15/17 [07:06<00:52, 26.17s/it]\n",
"100%|█████████████████████████████████████████████| 3/3 [00:07<00:00, 2.67s/it]\u001b[A\n",
"{'loss': 0.7931, 'learning_rate': 9.903113209758096e-06, 'epoch': 0.92} \u001b[A\n",
"{'loss': 0.6909, 'learning_rate': 0.0, 'epoch': 0.98} \n",
"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.\n",
" warnings.warn(\n",
"/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.\n",
" warnings.warn(\n",
"/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.\n",
" warnings.warn(\n",
"{'train_runtime': 489.0649, 'train_samples_per_second': 0.63, 'train_steps_per_second': 0.035, 'train_loss': 1.408153467318591, 'epoch': 0.98}\n",
"100%|███████████████████████████████████████████| 17/17 [08:09<00:00, 28.77s/it]\n",
"[2023-12-28 15:52:39,488] [INFO] [axolotl.train.log:60] [PID:2812] [RANK:0] Training Completed!!! Saving pre-trained model to ./out\u001b[39m\n",
"\u001b[0m\u001b[0m\u001b[0m"
]
}
],
"source": [
"\"\"\"\n",
"Training using the config.yml file and using deepspeed:zero3_bf16 the most aggressive optimization out of zero1,zero2,zero3 stages which partitions \n",
"not only optimizer states but also gradients and parameters across GPUs. The bf16 indicate mixed precision training using bfloat16.\n",
"For more information read axolotl's readme\n",
"\"\"\"\n",
"!accelerate launch -m axolotl.cli.train /folder/config.yml --deepspeed deepspeed/zero3_bf16.json"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.13"
}
},
"nbformat": 4,
"nbformat_minor": 5
}

75
examples/mistral/Mistral-7b-example/config.yml Normal file
View File

@@ -0,0 +1,75 @@
#Mistral-7b
base_model: mistralai/Mistral-7B-v0.1
model_type: MistralForCausalLM
tokenizer_type: LlamaTokenizer
is_mistral_derived_model: true
load_in_8bit: true
load_in_4bit: false
strict: false
datasets:
- path: tilemachos/Demo-Dataset #Path to json dataset file in huggingface
#for type,conversation arguments read axolotl readme and pick what is suited for your project, I wanted a chatbot and put sharegpt and chatml
type: sharegpt
conversation: chatml
dataset_prepared_path: tilemachos/Demo-Dataset #Path to json dataset file in huggingface
val_set_size: 0.05
output_dir: ./out
#using lora for lower cost
adapter: lora
lora_r: 8
lora_alpha: 16
lora_dropout: 0.05
lora_target_modules:
- q_proj
- v_proj
sequence_len: 512
sample_packing: false
pad_to_sequence_len: true
wandb_project:
wandb_entity:
wandb_watch:
wandb_name:
wandb_log_model:
#only 2 epochs because of small dataset
gradient_accumulation_steps: 3
micro_batch_size: 2
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0002
train_on_inputs: false
group_by_length: false
bf16: true
fp16: false
tf32: false
gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true
warmup_steps: 10
evals_per_epoch: 4
eval_table_size:
eval_table_max_new_tokens: 128
saves_per_epoch: 1
debug:
#default deepspeed, can use more aggresive if needed like zero2, zero3
deepspeed: deepspeed/zero1.json
weight_decay: 0.0
fsdp:
fsdp_config:
special_tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"

10
examples/mistral/Mistral-7b-example/data.jsonl Normal file
View File

@@ -0,0 +1,10 @@
{"conversations": [{"from": "Customer", "value": "\"<Customer>: Who is the Founder of Apple\""}, {"from": "gpt", "value": "\"<Chatbot>: The founder of Apple is Steve Jobs\""}]}
{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the capital of France?\""}, {"from": "gpt", "value": "\"<Chatbot>: The capital of France is Paris.\""}]}
{"conversations": [{"from": "Customer", "value": "\"<Customer>: How far is the Moon from Earth?\""}, {"from": "gpt", "value": "\"<Chatbot>: The Moon is approximately 384,400 kilometers from Earth.\""}]}
{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the tallest mountain in the world?\""}, {"from": "gpt", "value": "\"<Chatbot>: The tallest mountain in the world is Mount Everest.\""}]}
{"conversations": [{"from": "Customer", "value": "\"<Customer>: Who wrote Romeo and Juliet?\""}, {"from": "gpt", "value": "\"<Chatbot>: Romeo and Juliet was written by William Shakespeare.\""}]}
{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the boiling point of water?\""}, {"from": "gpt", "value": "\"<Chatbot>: The boiling point of water is 100 degrees Celsius.\""}]}
{"conversations": [{"from": "Customer", "value": "\"<Customer>: When was the first man on the moon?\""}, {"from": "gpt", "value": "\"<Chatbot>: The first man landed on the moon in 1969.\""}]}
{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the largest ocean?\""}, {"from": "gpt", "value": "\"<Chatbot>: The largest ocean is the Pacific Ocean.\""}]}
{"conversations": [{"from": "Customer", "value": "\"<Customer>: Who invented the telephone?\""}, {"from": "gpt", "value": "\"<Chatbot>: The telephone was invented by Alexander Graham Bell.\""}]}
{"conversations": [{"from": "Customer", "value": "\"<Customer>: What is the formula for water?\""}, {"from": "gpt", "value": "\"<Chatbot>: The chemical formula for water is H2O.\""}]}