{ "cells": [ { "cell_type": "markdown", "source": [ "**종속성 설치**" ], "metadata": { "id": "QGv6ld9q1XHv" }, "id": "QGv6ld9q1XHv" }, { "cell_type": "code", "execution_count": 1, "metadata": { "id": "nDZe_wqKU6J3", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "5213a3aa-dcf4-47af-b508-dcb224a701d1" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.35.2)\n", "Collecting peft\n", " Downloading peft-0.7.0-py3-none-any.whl (168 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m168.3/168.3 kB\u001b[0m \u001b[31m4.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting accelerate\n", " Downloading accelerate-0.25.0-py3-none-any.whl (265 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m265.7/265.7 kB\u001b[0m \u001b[31m21.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting optimum\n", " Downloading optimum-1.15.0-py3-none-any.whl (400 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m400.9/400.9 kB\u001b[0m \u001b[31m43.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting bitsandbytes\n", " Downloading bitsandbytes-0.41.3-py3-none-any.whl (92.6 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m92.6/92.6 MB\u001b[0m \u001b[31m10.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting trl\n", " Downloading trl-0.7.4-py3-none-any.whl (133 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m133.9/133.9 kB\u001b[0m \u001b[31m18.1 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 (2.1 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m74.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting einops\n", " Downloading 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[31m6.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.13.1)\n", "Requirement already satisfied: huggingface-hub<1.0,>=0.16.4 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.19.4)\n", "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.23.5)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.2)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.6.3)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n", "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.0)\n", "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.1)\n", "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.1)\n", "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from peft) (5.9.5)\n", "Requirement already satisfied: torch>=1.13.0 in /usr/local/lib/python3.10/dist-packages (from peft) (2.1.0+cu118)\n", "Collecting coloredlogs (from optimum)\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[31m5.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from optimum) (1.12)\n", "Collecting datasets (from optimum)\n", " Downloading datasets-2.15.0-py3-none-any.whl (521 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m521.2/521.2 kB\u001b[0m \u001b[31m52.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting tyro>=0.5.11 (from trl)\n", " Downloading tyro-0.6.0-py3-none-any.whl (100 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m100.9/100.9 kB\u001b[0m \u001b[31m13.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: Click!=8.0.0,>=7.1 in /usr/local/lib/python3.10/dist-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 (190 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m190.6/190.6 kB\u001b[0m \u001b[31m24.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting sentry-sdk>=1.0.0 (from wandb)\n", " Downloading sentry_sdk-1.38.0-py2.py3-none-any.whl (252 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m252.8/252.8 kB\u001b[0m \u001b[31m29.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting 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 (30 kB)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from wandb) (67.7.2)\n", "Requirement already satisfied: appdirs>=1.4.3 in /usr/local/lib/python3.10/dist-packages (from wandb) (1.4.4)\n", "Requirement already satisfied: protobuf!=4.21.0,<5,>=3.19.0 in /usr/local/lib/python3.10/dist-packages (from wandb) (3.20.3)\n", "Requirement already satisfied: six>=1.4.0 in /usr/local/lib/python3.10/dist-packages (from docker-pycreds>=0.4.0->wandb) (1.16.0)\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 (62 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m5.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.16.4->transformers) (2023.6.0)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.16.4->transformers) (4.5.0)\n", "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.6)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2023.11.17)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft) (3.2.1)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft) (3.1.2)\n", "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.13.0->peft) (2.1.0)\n", "Collecting sentencepiece!=0.1.92,>=0.1.91 (from transformers)\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[31m47.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting docstring-parser>=0.14.1 (from tyro>=0.5.11->trl)\n", " Downloading docstring_parser-0.15-py3-none-any.whl (36 kB)\n", "Requirement already satisfied: rich>=11.1.0 in /usr/local/lib/python3.10/dist-packages (from tyro>=0.5.11->trl) (13.7.0)\n", "Collecting shtab>=1.5.6 (from tyro>=0.5.11->trl)\n", " Downloading shtab-1.6.5-py3-none-any.whl (13 kB)\n", "Collecting humanfriendly>=9.1 (from coloredlogs->optimum)\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[31m9.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (9.0.0)\n", "Collecting pyarrow-hotfix (from datasets->optimum)\n", " Downloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n", "Collecting dill<0.3.8,>=0.3.0 (from datasets->optimum)\n", " Downloading 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[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (1.5.3)\n", "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (3.4.1)\n", "Collecting multiprocess (from datasets->optimum)\n", " Downloading 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[31m4.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets->optimum) (3.9.1)\n", "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->optimum) (1.3.0)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (23.1.0)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (6.0.4)\n", "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (1.9.3)\n", "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (1.4.0)\n", "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (1.3.1)\n", "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets->optimum) (4.0.3)\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 (24 kB)\n", "Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=11.1.0->tyro>=0.5.11->trl) (3.0.0)\n", "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=11.1.0->tyro>=0.5.11->trl) (2.16.1)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.13.0->peft) (2.1.3)\n", "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets->optimum) (2.8.2)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets->optimum) (2023.3.post1)\n", "Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=11.1.0->tyro>=0.5.11->trl) (0.1.2)\n", "Installing collected packages: sentencepiece, bitsandbytes, smmap, shtab, setproctitle, sentry-sdk, pyarrow-hotfix, humanfriendly, einops, docstring-parser, docker-pycreds, dill, multiprocess, gitdb, coloredlogs, tyro, GitPython, accelerate, wandb, datasets, trl, peft, optimum\n", "Successfully installed GitPython-3.1.40 accelerate-0.25.0 bitsandbytes-0.41.3 coloredlogs-15.0.1 datasets-2.15.0 dill-0.3.7 docker-pycreds-0.4.0 docstring-parser-0.15 einops-0.7.0 gitdb-4.0.11 humanfriendly-10.0 multiprocess-0.70.15 optimum-1.15.0 peft-0.7.0 pyarrow-hotfix-0.6 sentencepiece-0.1.99 sentry-sdk-1.38.0 setproctitle-1.3.3 shtab-1.6.5 smmap-5.0.1 trl-0.7.4 tyro-0.6.0 wandb-0.16.1\n" ] } ], "source": [ "pip install transformers peft accelerate optimum bitsandbytes trl wandb einops" ], "id": "nDZe_wqKU6J3" }, { "cell_type": "markdown", "source": [ "라이브러리 및 모듈 임포트" ], "metadata": { "id": "hNUtFKCYBGm4" }, "id": "hNUtFKCYBGm4" }, { "cell_type": "code", "execution_count": 2, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "51eb00d7-2928-41ad-9ae9-7f0da7d64d6d", "outputId": "ed07918d-f1c3-4772-bcf5-f8b0926025a1" }, "outputs": [ { "output_type": "stream", "name": "stderr", "text": [ "/usr/local/lib/python3.10/dist-packages/trl/trainer/ppo_config.py:141: UserWarning: The `optimize_cuda_cache` arguement will be deprecated soon, please use `optimize_device_cache` instead.\n", " warnings.warn(\n" ] } ], "source": [ "import os\n", "from dataclasses import dataclass, field\n", "from typing import Optional\n", "import re\n", "\n", "import torch\n", "import tyro\n", "from accelerate import Accelerator\n", "from datasets import load_dataset, Dataset\n", "from peft import AutoPeftModelForCausalLM, LoraConfig\n", "from tqdm import tqdm\n", "from transformers import (\n", " AutoModelForCausalLM,\n", " AutoTokenizer,\n", " BitsAndBytesConfig,\n", " TrainingArguments,\n", ")\n", "\n", "from trl import SFTTrainer\n", "\n", "from trl.trainer import ConstantLengthDataset" ], "id": "51eb00d7-2928-41ad-9ae9-7f0da7d64d6d" }, { "cell_type": "code", "execution_count": 2, "metadata": { "colab": { "base_uri": "https://localhost:8080/", "height": 158, "referenced_widgets": [ "0f44dbac37424152ac0bdef0e16e4771", "eec756ae16fa497aa0c5fd9670a2862c", "897a4815dd0b447480a212ff81cf1069", "c56feaeacd2d4c858cf12370155c90d9", "b1fdb55628ef4deab74333414838e8a1", "c2cf32bbc86e47558b643061ee259207", "5a4e42f28fd541b2b93fa85476f23935", "19a4a603811e4c12a8b71e7ab57367ef", "dd8044969f52407ab3951771a536487d", "e3c3bf1e8ce64b61a317968f40b7b98c", "54880464a6974f5ba683407cf3d99faf", "50bfb0ff6a1044d78696e23f21326dc4", "18918393a100494c98772f5221404a1f", "c0a16708a5bb40a49704f603c870de5b", "a4463f0298f443d38d6f06cdd3f95f8c", "5922efe9dbff464393ed1e76685093bf", "e29e2fd443574c69af022dfef253d587", "e9f8a2f3e5434244afdd164f07e79a53", "698acc9f74574f6b9d8f22b3b41b7392", "436b45f7309944acb95fad6e5ce0bf13", "f9e3abef808446c388b2a8132121dcdb", "5259d666361641e09449aa903361124a", "301e40018b4c4262a1b9d3948e95afeb", "30140a0a2746420280dd754b9acde5e2", "34da297abe3c4e938686423e8825e1bf", "305f83d3aa624b909e76ddbd9425636c", "5aa6ad99fd754f259da4754502680baf", "d0e8087a02154e3c954d38cb2136810c", "06c4d7ca241e4a0e8fe67a631781c4d7", "ccdbd1df3467489094425677f51c0325", "e923319ff4ec4556b543f78d84f865f4", "97e0a8143f484c0d8d34a59535f818b0" ] }, "id": "tX7gYxZaVhYL", "outputId": "15f8a967-15ea-45fe-ecb9-91382c6fd9bb" }, "outputs": [ { "output_type": "display_data", "data": { "text/plain": [ "VBox(children=(HTML(value='
/content/wandb/run-20231210_131434-p3xsnu5x
"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"Step | \n", "Training Loss | \n", "
---|---|
50 | \n", "1.922300 | \n", "
100 | \n", "1.110100 | \n", "
150 | \n", "1.057100 | \n", "
200 | \n", "1.045300 | \n", "
250 | \n", "1.053800 | \n", "
300 | \n", "1.049200 | \n", "
350 | \n", "1.065100 | \n", "
400 | \n", "1.053200 | \n", "
450 | \n", "1.058000 | \n", "
500 | \n", "1.034800 | \n", "
550 | \n", "1.064300 | \n", "
600 | \n", "0.976800 | \n", "
650 | \n", "0.995700 | \n", "
700 | \n", "0.987800 | \n", "
750 | \n", "1.003000 | \n", "
800 | \n", "1.010500 | \n", "
"
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/trl/trainer/utils.py:570: UserWarning: The dataset reached end and the iterator is reset to the start.\n",
" warnings.warn(\"The dataset reached end and the iterator is reset to the start.\")\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"TrainOutput(global_step=800, training_loss=1.0929430866241454, metrics={'train_runtime': 2003.4806, 'train_samples_per_second': 0.799, 'train_steps_per_second': 0.399, 'total_flos': 1.65609039986688e+16, 'train_loss': 1.0929430866241454, 'epoch': 0.32})"
]
},
"metadata": {},
"execution_count": 30
}
],
"source": [
"trainer.train()"
],
"id": "14019fa9-0c6f-4729-ac99-0d407af375b8"
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {
"id": "3Y4FQSyRghQt",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 35
},
"outputId": "9b8595ae-cb07-4961-8e08-0c8093adebeb"
},
"outputs": [
{
"output_type": "execute_result",
"data": {
"text/plain": [
"'/gdrive/MyDrive/nlp/lora-midm-7b-nsmc-v1.2'"
],
"application/vnd.google.colaboratory.intrinsic+json": {
"type": "string"
}
},
"metadata": {},
"execution_count": 31
}
],
"source": [
"script_args.training_args.output_dir"
],
"id": "3Y4FQSyRghQt"
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {
"id": "49f05450-da2a-4edd-9db2-63836a0ec73a"
},
"outputs": [],
"source": [
"trainer.save_model(script_args.training_args.output_dir)"
],
"id": "49f05450-da2a-4edd-9db2-63836a0ec73a"
},
{
"cell_type": "markdown",
"metadata": {
"id": "652f307e-e1d7-43ae-b083-dba2d94c2296"
},
"source": [
"# 추론 테스트"
],
"id": "652f307e-e1d7-43ae-b083-dba2d94c2296"
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {
"id": "ea8a1fea-7499-4386-9dea-0509110f61af"
},
"outputs": [],
"source": [
"from transformers import pipeline, TextStreamer"
],
"id": "ea8a1fea-7499-4386-9dea-0509110f61af"
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {
"id": "52626888-1f6e-46b6-a8dd-836622149ff5"
},
"outputs": [],
"source": [
"instruction_prompt_template = \"\"\"###System;다음은 네이버 영화 리뷰들을 모아놓은 문장이다. 이를 분석하여 사용자가 작성한 영화 리뷰의 감정을 긍정 또는 부정으로 예측하라.\n",
"\n",
"### 리뷰 내용: {0} ### 분석 결과:\n",
"\"\"\"\n",
"\n",
"prompt_template = \"\"\"###System;{System}\n",
"###User;{User}\n",
"###Midm;\"\"\"\n",
"\n",
"default_system_msg = (\n",
" \"너는 먼저 사용자가 작성한 영화 리뷰의 감정을 분석하는 에이전트이다. 이로부터 주어진 영화 리뷰에 대한 긍정 또는 부정을 추출해야 한다.\"\n",
")"
],
"id": "52626888-1f6e-46b6-a8dd-836622149ff5"
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {
"id": "1919cf1f-482e-4185-9d06-e3cea1918416"
},
"outputs": [],
"source": [
"def wrapper_generate(model, input_prompt, do_stream=False):\n",
" data = tokenizer(input_prompt, return_tensors=\"pt\")\n",
" streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)\n",
" input_ids = data.input_ids[..., :-1]\n",
" with torch.no_grad():\n",
" pred = model.generate(\n",
" #input_ids=input_ids.cuda(),\n",
" input_ids = input_ids.to('cuda'),\n",
" streamer=streamer if do_stream else None,\n",
" use_cache=True,\n",
" max_new_tokens=float('inf'),\n",
" do_sample=False\n",
" )\n",
" decoded_text = tokenizer.batch_decode(pred, skip_special_tokens=True)\n",
" decoded_text = decoded_text[0].replace(\"<[!newline]>\", \"\\n\")\n",
" return (decoded_text[len(input_prompt):])"
],
"id": "1919cf1f-482e-4185-9d06-e3cea1918416"
},
{
"cell_type": "code",
"source": [
"eval_dic = {i:wrapper_generate(model=base_model, input_prompt=prompt_template.format(System=default_system_msg, User=evaluation_queries[i]))for i, query in enumerate(evaluation_queries)}"
],
"metadata": {
"id": "aO5N5XX4BjFr"
},
"id": "aO5N5XX4BjFr",
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"미세튜닝된 모델 테스트"
],
"metadata": {
"id": "DKeAPc9NAs4F"
},
"id": "DKeAPc9NAs4F"
},
{
"cell_type": "code",
"source": [
"from transformers import pipeline, TextStreamer"
],
"metadata": {
"id": "XMU2ydLG2k3Z"
},
"id": "XMU2ydLG2k3Z",
"execution_count": 38,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"프롬프트 정의"
],
"metadata": {
"id": "e-SkE9mf2sWx"
},
"id": "e-SkE9mf2sWx"
},
{
"cell_type": "code",
"source": [
"instruction_prompt_template = \"\"\"###System;다음은 네이버 영화 리뷰들을 모아놓은 문장이다. 이를 분석하여 사용자가 작성한 영화 리뷰의 감정을 긍정 또는 부정으로 예측하라.\n",
"\n",
"### 리뷰 내용: {0} ### 분석 결과:\n",
"\"\"\"\n",
"\n",
"prompt_template = \"\"\"###System;{System}\n",
"###User;{User}\n",
"###Midm;\"\"\"\n",
"\n",
"default_system_msg = (\n",
" \"너는 사용자가 작성한 리뷰의 긍정 또는 부정을 판단해야 한다.\"\n",
")"
],
"metadata": {
"id": "XUvbhk6t2pXs"
},
"id": "XUvbhk6t2pXs",
"execution_count": 39,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"사용자 영화 리뷰에 대한 입력 프롬프트 생성"
],
"metadata": {
"id": "p4J4p1b62yAM"
},
"id": "p4J4p1b62yAM"
},
{
"cell_type": "code",
"source": [
"def wrapper_generate(model, input_prompt, do_stream=False):\n",
" data = tokenizer(input_prompt, return_tensors=\"pt\")\n",
" streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)\n",
" input_ids = data.input_ids[..., :-1]\n",
" with torch.no_grad():\n",
" pred = model.generate(\n",
" input_ids=input_ids.cuda(),\n",
" streamer=streamer if do_stream else None,\n",
" use_cache=True,\n",
" max_new_tokens=float('inf'),\n",
" do_sample=False\n",
" )\n",
" decoded_text = tokenizer.batch_decode(pred, skip_special_tokens=True)\n",
" decoded_text = decoded_text[0].replace(\"<[!newline]>\", \"\\n\")\n",
" return (decoded_text[len(input_prompt):])"
],
"metadata": {
"id": "iov1rlPJ21K-"
},
"id": "iov1rlPJ21K-",
"execution_count": 40,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"양자화 설정: 4비트로 양자화함"
],
"metadata": {
"id": "Vs2CLd2D24ha"
},
"id": "Vs2CLd2D24ha"
},
{
"cell_type": "code",
"execution_count": 41,
"metadata": {
"id": "a43bdd07-7555-42b2-9888-a614afec892f"
},
"outputs": [],
"source": [
"bnb_config = BitsAndBytesConfig(\n",
" load_in_4bit=True,\n",
" bnb_4bit_quant_type=\"nf4\",\n",
" bnb_4bit_compute_dtype=torch.bfloat16,\n",
")"
],
"id": "a43bdd07-7555-42b2-9888-a614afec892f"
},
{
"cell_type": "markdown",
"source": [
"미세튜닝된 모델을 4비트로 양자화함"
],
"metadata": {
"id": "q6n3Tr4L27kR"
},
"id": "q6n3Tr4L27kR"
},
{
"cell_type": "code",
"execution_count": 42,
"metadata": {
"id": "39db2ee4-23c8-471f-89b2-bca34964bf81",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 576
},
"outputId": "92593767-43aa-4670-9358-6b71c456365f"
},
"outputs": [
{
"output_type": "error",
"ename": "ValueError",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 12\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 13\u001b[0;31m \u001b[0mtrained_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpad_token_id\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpad_token_id\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 14\u001b[0m \u001b[0mtrained_model\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconfig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbos_token_id\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtokenizer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbos_token_id\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mNameError\u001b[0m: name 'trained_model' is not defined"
]
}
],
"source": [
"tokenizer = AutoTokenizer.from_pretrained(\n",
" script_args.model_name,\n",
" trust_remote_code=True,\n",
" cache_dir=script_args.cache_dir,\n",
")\n",
"\n",
"if getattr(tokenizer, \"pad_token\", None) is None:\n",
" tokenizer.pad_token = tokenizer.eos_token\n",
"tokenizer.padding_side = \"right\" # Fix weird overflow issue with fp16 training\n",
"\n",
"tokenizer.add_special_tokens(dict(bos_token=''))\n",
"\n",
"trained_model.config.pad_token_id = tokenizer.pad_token_id\n",
"trained_model.config.bos_token_id = tokenizer.bos_token_id"
],
"id": "b0b75ca4-730d-4bde-88bb-a86462a76d52"
},
{
"cell_type": "markdown",
"source": [
"데이터셋 생성"
],
"metadata": {
"id": "SIHMdQmKADor"
},
"id": "SIHMdQmKADor"
},
{
"cell_type": "code",
"source": [
"valid_dataset = create_valid_datasets(tokenizer, script_args)"
],
"metadata": {
"id": "a_uxsZ4U3EHP"
},
"id": "a_uxsZ4U3EHP",
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "e374555b-9f8a-4617-8ea7-c1e6ee1b2999"
},
"outputs": [],
"source": [
"eval_dic = {i: wrapper_generate(model=trained_model, input_prompt=prompt_template.format(System=default_system_msg, User=example[\"document\"]))for i, example in enumerate(valid_dataset)}"
],
"id": "e374555b-9f8a-4617-8ea7-c1e6ee1b2999"
},
{
"cell_type": "markdown",
"source": [
"모델 결과"
],
"metadata": {
"id": "O50xByhv3RoQ"
},
"id": "O50xByhv3RoQ"
},
{
"cell_type": "code",
"source": [
"import seaborn as sns\n",
"import matplotlib.pyplot as plt\n",
"import pandas as pd\n",
"from sklearn.metrics import accuracy_score, confusion_matrix, precision_score, recall_score, f1_score, classification_report\n",
"\n",
"true_labels = [example[\"label\"] for example in valid_dataset]\n",
"\n",
"predicted_labels = [1 if \"긍정\" in eval_dic[i] else 0 for i in range(len(valid_dataset))]\n",
"\n",
"conf_matrix = confusion_matrix(true_labels, predicted_labels)\n",
"\n",
"accuracy = accuracy_score(true_labels, predicted_labels)\n",
"\n",
"precision = precision_score(true_labels, predicted_labels)\n",
"recall = recall_score(true_labels, predicted_labels)\n",
"f1 = f1_score(true_labels, predicted_labels)\n",
"\n",
"print(\"Precision:\", precision)\n",
"print(\"Recall:\", recall)\n",
"print(\"F1 Score:\", f1, \"\\n\")\n",
"\n",
"# 분류 리포트 출력\n",
"class_report = classification_report(true_labels, predicted_labels, target_names=['Negative', 'Positive'])\n",
"print(\"Classification Report:\\n\", class_report)"
],
"metadata": {
"id": "TL7zOjZD3T14"
},
"id": "TL7zOjZD3T14",
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"![image.png](data:image/png;base64,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)"
],
"metadata": {
"id": "9MH1yeHHB6Ly"
},
"id": "9MH1yeHHB6Ly"
},
{
"cell_type": "markdown",
"source": [
"![image.png](data:image/png;base64,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)"
],
"metadata": {
"id": "xQd8rk9VBM3L"
},
"id": "xQd8rk9VBM3L"
},
{
"cell_type": "code",
"source": [
"!pip install --upgrade huggingface_hub\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "E5cdHlN0DBZ7",
"outputId": "d1dd4e38-84ab-4c56-fe0b-080edffb9ca6"
},
"id": "E5cdHlN0DBZ7",
"execution_count": 4,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: huggingface_hub in /usr/local/lib/python3.10/dist-packages (0.19.4)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (3.13.1)\n",
"Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2023.6.0)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (2.31.0)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.66.1)\n",
"Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (6.0.1)\n",
"Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (4.5.0)\n",
"Requirement already satisfied: packaging>=20.9 in /usr/local/lib/python3.10/dist-packages (from huggingface_hub) (23.2)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (3.6)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface_hub) (2023.11.17)\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"from huggingface_hub import Repository\n",
"import os\n",
"\n",
"notebook_file = \"okdol/hw-midm-7B-nsmc.ipynb\"\n",
"repo_name = \"okdol/hw-midm-7B-nsmc\"\n",
"repo_url = f\"https://huggingface.co/okdol/hw-midm-7B-nsmc\"\n",
"\n",
"\n",
"# 로컬에 리포지토리 디렉토리 생성\n",
"os.makedirs(repo_name, exist_ok=True)\n",
"\n",
"# 리포지토리 초기화\n",
"repo = Repository(local_dir=repo_name, clone_from=repo_url)\n",
"\n",
"# 노트북 파일을 리포지토리 디렉토리로 복사\n",
"notebook_path_in_repo = os.path.join(repo_name, os.path.basename(notebook_file))\n",
"os.replace(notebook_file, notebook_path_in_repo)\n",
"\n",
"# Hugging Face Hub에 푸시\n",
"repo.push_to_hub()\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 388
},
"id": "UC-Ymv8pCaEr",
"outputId": "a6aaaa63-e5d4-45dd-e5cd-03d1fb031d11"
},
"id": "UC-Ymv8pCaEr",
"execution_count": 7,
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_deprecation.py:127: FutureWarning: 'Repository' (from 'huggingface_hub.repository') is deprecated and will be removed from version '1.0'. Please prefer the http-based alternatives instead. Given its large adoption in legacy code, the complete removal is only planned on next major release.\n",
"For more details, please read https://huggingface.co/docs/huggingface_hub/concepts/git_vs_http.\n",
" warnings.warn(warning_message, FutureWarning)\n",
"/content/okdol/hw-midm-7B-nsmc is already a clone of https://huggingface.co/okdol/hw-midm-7B-nsmc. Make sure you pull the latest changes with `repo.git_pull()`.\n",
"WARNING:huggingface_hub.repository:/content/okdol/hw-midm-7B-nsmc is already a clone of https://huggingface.co/okdol/hw-midm-7B-nsmc. Make sure you pull the latest changes with `repo.git_pull()`.\n"
]
},
{
"output_type": "error",
"ename": "FileNotFoundError",
"evalue": "ignored",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mFileNotFoundError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m
Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.