{ "cells": [ { "cell_type": "markdown", "id": "f9f8a4ee", "metadata": { "id": "IqM-T1RTzY6C", "papermill": { "duration": 0.038159, "end_time": "2024-03-28T00:08:52.505173", "exception": false, "start_time": "2024-03-28T00:08:52.467014", "status": "completed" }, "tags": [] }, "source": [ "To run this, press \"*Runtime*\" and press \"*Run all*\" on a **free** Tesla T4 Google Colab instance!\n", "
\n", " \n", " \n", " Join Discord if you need help + support us if you can!\n", "
\n", "\n", "To install Unsloth on your own computer, follow the installation instructions on our Github page [here](https://github.com/unslothai/unsloth#installation-instructions---conda).\n", "\n", "You will learn how to do [data prep](#Data), how to [train](#Train), how to [run the model](#Inference), & [how to save it](#Save) (eg for Llama.cpp).\n", "\n", "This notebook uses the `ChatML` format for conversation style finetunes. We use [Open Assistant conversations](https://huggingface.co/datasets/philschmid/guanaco-sharegpt-style) in ShareGPT style." ] }, { "cell_type": "code", "execution_count": 1, "id": "4c970fa0", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T00:08:52.578683Z", "iopub.status.busy": "2024-03-28T00:08:52.577956Z", "iopub.status.idle": "2024-03-28T00:12:44.149130Z", "shell.execute_reply": "2024-03-28T00:12:44.147764Z" }, "id": "2eSvM9zX_2d3", "papermill": { "duration": 231.609576, "end_time": "2024-03-28T00:12:44.151750", "exception": false, "start_time": "2024-03-28T00:08:52.542174", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Looking in indexes: https://download.pytorch.org/whl/cu121\r\n", "Collecting xformers\r\n", " Downloading https://download.pytorch.org/whl/cu121/xformers-0.0.25-cp310-cp310-manylinux2014_x86_64.whl (222.5 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m222.5/222.5 MB\u001b[0m \u001b[31m7.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hRequirement already satisfied: numpy in /opt/conda/lib/python3.10/site-packages (from xformers) (1.26.4)\r\n", "Collecting torch==2.2.1 (from xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/torch-2.2.1%2Bcu121-cp310-cp310-linux_x86_64.whl (757.3 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m757.3/757.3 MB\u001b[0m \u001b[31m2.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hRequirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from torch==2.2.1->xformers) (3.13.1)\r\n", "Requirement already satisfied: typing-extensions>=4.8.0 in /opt/conda/lib/python3.10/site-packages (from torch==2.2.1->xformers) (4.9.0)\r\n", "Requirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from torch==2.2.1->xformers) (1.12)\r\n", "Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch==2.2.1->xformers) (3.2.1)\r\n", "Requirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch==2.2.1->xformers) (3.1.2)\r\n", "Requirement already satisfied: fsspec in /opt/conda/lib/python3.10/site-packages (from torch==2.2.1->xformers) (2024.3.0)\r\n", "Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.7/23.7 MB\u001b[0m \u001b[31m26.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-cuda-runtime-cu12==12.1.105 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.6/823.6 kB\u001b[0m \u001b[31m40.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-cuda-cupti-cu12==12.1.105 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m84.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-cudnn-cu12==8.9.2.26 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m731.7/731.7 MB\u001b[0m \u001b[31m2.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-cublas-cu12==12.1.3.1 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.6/410.6 MB\u001b[0m \u001b[31m1.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-cufft-cu12==11.0.2.54 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.6/121.6 MB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-curand-cu12==10.3.2.106 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.5/56.5 MB\u001b[0m \u001b[31m28.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-cusolver-cu12==11.4.5.107 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.2/124.2 MB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-cusparse-cu12==12.1.0.106 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.0/196.0 MB\u001b[0m \u001b[31m8.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-nccl-cu12==2.19.3 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.0/166.0 MB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-nvtx-cu12==12.1.105 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.1/99.1 kB\u001b[0m \u001b[31m6.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting triton==2.2.0 (from torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/triton-2.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (167.9 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m167.9/167.9 MB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hCollecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch==2.2.1->xformers)\r\n", " Downloading https://download.pytorch.org/whl/cu121/nvidia_nvjitlink_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (19.8 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m19.8/19.8 MB\u001b[0m \u001b[31m46.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hRequirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch==2.2.1->xformers) (2.1.3)\r\n", "Requirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->torch==2.2.1->xformers) (1.3.0)\r\n", "Installing collected packages: triton, nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, torch, xformers\r\n", " Attempting uninstall: torch\r\n", " Found existing installation: torch 2.1.2\r\n", " Uninstalling torch-2.1.2:\r\n", " Successfully uninstalled torch-2.1.2\r\n", "Successfully installed nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.1.105 nvidia-nvtx-cu12-12.1.105 torch-2.2.1+cu121 triton-2.2.0 xformers-0.0.25\r\n", "Collecting unsloth@ git+https://github.com/unslothai/unsloth.git (from unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git)\r\n", " Cloning https://github.com/unslothai/unsloth.git to /tmp/pip-install-yfpl0t85/unsloth_63990d9a4b8e4d6ca74bbfccdc6198cb\r\n", " Running command git clone --filter=blob:none --quiet https://github.com/unslothai/unsloth.git /tmp/pip-install-yfpl0t85/unsloth_63990d9a4b8e4d6ca74bbfccdc6198cb\r\n", " Resolved https://github.com/unslothai/unsloth.git to commit a68aebc1fa17755ffbcdafc9239e7ca37ab21657\r\n", " Installing build dependencies ... \u001b[?25l-\b \b\\\b \b|\b \b/\b \b-\b \b\\\b \b|\b \b/\b \b-\b \bdone\r\n", "\u001b[?25h Getting requirements to build wheel ... \u001b[?25l-\b \b\\\b \bdone\r\n", "\u001b[?25h Installing backend dependencies ... \u001b[?25l-\b \b\\\b \b|\b \b/\b \bdone\r\n", "\u001b[?25h Preparing metadata (pyproject.toml) ... \u001b[?25l-\b \b\\\b \bdone\r\n", "\u001b[?25hRequirement already satisfied: triton in /opt/conda/lib/python3.10/site-packages (2.2.0)\r\n", "Collecting datasets==2.17.1\r\n", " Downloading datasets-2.17.1-py3-none-any.whl.metadata (20 kB)\r\n", "Requirement already satisfied: filelock in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (3.13.1)\r\n", "Requirement already satisfied: numpy>=1.17 in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (1.26.4)\r\n", "Collecting pyarrow>=12.0.0 (from datasets==2.17.1)\r\n", " Downloading pyarrow-15.0.2-cp310-cp310-manylinux_2_28_x86_64.whl.metadata (3.0 kB)\r\n", "Collecting pyarrow-hotfix (from datasets==2.17.1)\r\n", " Downloading pyarrow_hotfix-0.6-py3-none-any.whl.metadata (3.6 kB)\r\n", "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (0.3.8)\r\n", "Requirement already satisfied: pandas in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (2.1.4)\r\n", "Requirement already satisfied: requests>=2.19.0 in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (2.31.0)\r\n", "Requirement already satisfied: tqdm>=4.62.1 in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (4.66.1)\r\n", "Requirement already satisfied: xxhash in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (3.4.1)\r\n", "Requirement already satisfied: multiprocess in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (0.70.16)\r\n", "Collecting fsspec<=2023.10.0,>=2023.1.0 (from fsspec[http]<=2023.10.0,>=2023.1.0->datasets==2.17.1)\r\n", " Downloading fsspec-2023.10.0-py3-none-any.whl.metadata (6.8 kB)\r\n", "Requirement already satisfied: aiohttp in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (3.9.1)\r\n", "Requirement already satisfied: huggingface-hub>=0.19.4 in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (0.21.4)\r\n", "Requirement already satisfied: packaging in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (21.3)\r\n", "Requirement already satisfied: pyyaml>=5.1 in /opt/conda/lib/python3.10/site-packages (from datasets==2.17.1) (6.0.1)\r\n", "Collecting bitsandbytes (from unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git)\r\n", " Downloading bitsandbytes-0.43.0-py3-none-manylinux_2_24_x86_64.whl.metadata (1.8 kB)\r\n", "Requirement already satisfied: attrs>=17.3.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets==2.17.1) (23.2.0)\r\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets==2.17.1) (6.0.4)\r\n", "Requirement already satisfied: yarl<2.0,>=1.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets==2.17.1) (1.9.3)\r\n", "Requirement already satisfied: frozenlist>=1.1.1 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets==2.17.1) (1.4.1)\r\n", "Requirement already satisfied: aiosignal>=1.1.2 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets==2.17.1) (1.3.1)\r\n", "Requirement already satisfied: async-timeout<5.0,>=4.0 in /opt/conda/lib/python3.10/site-packages (from aiohttp->datasets==2.17.1) (4.0.3)\r\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /opt/conda/lib/python3.10/site-packages (from huggingface-hub>=0.19.4->datasets==2.17.1) (4.9.0)\r\n", "Requirement already satisfied: pyparsing!=3.0.5,>=2.0.2 in /opt/conda/lib/python3.10/site-packages (from packaging->datasets==2.17.1) (3.1.1)\r\n", "Requirement already satisfied: charset-normalizer<4,>=2 in /opt/conda/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.17.1) (3.3.2)\r\n", "Requirement already satisfied: idna<4,>=2.5 in /opt/conda/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.17.1) (3.6)\r\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /opt/conda/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.17.1) (1.26.18)\r\n", "Requirement already satisfied: certifi>=2017.4.17 in /opt/conda/lib/python3.10/site-packages (from requests>=2.19.0->datasets==2.17.1) (2024.2.2)\r\n", "Requirement already satisfied: torch in /opt/conda/lib/python3.10/site-packages (from bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (2.2.1+cu121)\r\n", "Requirement already satisfied: python-dateutil>=2.8.2 in /opt/conda/lib/python3.10/site-packages (from pandas->datasets==2.17.1) (2.9.0.post0)\r\n", "Requirement already satisfied: pytz>=2020.1 in /opt/conda/lib/python3.10/site-packages (from pandas->datasets==2.17.1) (2023.3.post1)\r\n", "Requirement already satisfied: tzdata>=2022.1 in /opt/conda/lib/python3.10/site-packages (from pandas->datasets==2.17.1) (2023.4)\r\n", "Collecting tyro (from unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git)\r\n", " Downloading tyro-0.7.3-py3-none-any.whl.metadata (7.7 kB)\r\n", "Requirement already satisfied: transformers>=4.38.2 in /opt/conda/lib/python3.10/site-packages (from unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (4.38.2)\r\n", "Requirement already satisfied: sentencepiece in /opt/conda/lib/python3.10/site-packages (from unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (0.2.0)\r\n", "Requirement already satisfied: psutil in /opt/conda/lib/python3.10/site-packages (from unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (5.9.3)\r\n", "Requirement already satisfied: wheel>=0.42.0 in /opt/conda/lib/python3.10/site-packages (from unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (0.42.0)\r\n", "Requirement already satisfied: accelerate>=0.26.1 in /opt/conda/lib/python3.10/site-packages (from unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (0.28.0)\r\n", "Collecting trl>=0.7.9 (from unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git)\r\n", " Downloading trl-0.8.1-py3-none-any.whl.metadata (11 kB)\r\n", "Collecting peft>=0.7.1 (from unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git)\r\n", " Downloading peft-0.10.0-py3-none-any.whl.metadata (13 kB)\r\n", "Requirement already satisfied: safetensors>=0.3.1 in /opt/conda/lib/python3.10/site-packages (from accelerate>=0.26.1->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (0.4.2)\r\n", "Requirement already satisfied: six>=1.5 in /opt/conda/lib/python3.10/site-packages (from python-dateutil>=2.8.2->pandas->datasets==2.17.1) (1.16.0)\r\n", "Requirement already satisfied: sympy in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (1.12)\r\n", "Requirement already satisfied: networkx in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (3.2.1)\r\n", "Requirement already satisfied: jinja2 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (3.1.2)\r\n", "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (12.1.105)\r\n", "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (12.1.105)\r\n", "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (12.1.105)\r\n", "Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (8.9.2.26)\r\n", "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (12.1.3.1)\r\n", "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (11.0.2.54)\r\n", "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (10.3.2.106)\r\n", "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (11.4.5.107)\r\n", "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (12.1.0.106)\r\n", "Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (2.19.3)\r\n", "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /opt/conda/lib/python3.10/site-packages (from torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (12.1.105)\r\n", "Requirement already satisfied: nvidia-nvjitlink-cu12 in /opt/conda/lib/python3.10/site-packages (from nvidia-cusolver-cu12==11.4.5.107->torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (12.1.105)\r\n", "Requirement already satisfied: regex!=2019.12.17 in /opt/conda/lib/python3.10/site-packages (from transformers>=4.38.2->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (2023.12.25)\r\n", "Requirement already satisfied: tokenizers<0.19,>=0.14 in /opt/conda/lib/python3.10/site-packages (from transformers>=4.38.2->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (0.15.2)\r\n", "Requirement already satisfied: docstring-parser>=0.14.1 in /opt/conda/lib/python3.10/site-packages (from tyro->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (0.15)\r\n", "Requirement already satisfied: rich>=11.1.0 in /opt/conda/lib/python3.10/site-packages (from tyro->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (13.7.0)\r\n", "Collecting shtab>=1.5.6 (from tyro->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git)\r\n", " Downloading shtab-1.7.1-py3-none-any.whl.metadata (7.3 kB)\r\n", "Requirement already satisfied: markdown-it-py>=2.2.0 in /opt/conda/lib/python3.10/site-packages (from rich>=11.1.0->tyro->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (3.0.0)\r\n", "Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /opt/conda/lib/python3.10/site-packages (from rich>=11.1.0->tyro->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (2.17.2)\r\n", "Requirement already satisfied: MarkupSafe>=2.0 in /opt/conda/lib/python3.10/site-packages (from jinja2->torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (2.1.3)\r\n", "Requirement already satisfied: mpmath>=0.19 in /opt/conda/lib/python3.10/site-packages (from sympy->torch->bitsandbytes->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (1.3.0)\r\n", "Requirement already satisfied: mdurl~=0.1 in /opt/conda/lib/python3.10/site-packages (from markdown-it-py>=2.2.0->rich>=11.1.0->tyro->unsloth@ git+https://github.com/unslothai/unsloth.git->unsloth[kaggle-new]@ git+https://github.com/unslothai/unsloth.git) (0.1.2)\r\n", "Downloading datasets-2.17.1-py3-none-any.whl (536 kB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m536.7/536.7 kB\u001b[0m \u001b[31m4.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hDownloading fsspec-2023.10.0-py3-none-any.whl (166 kB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m166.4/166.4 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hDownloading pyarrow-15.0.2-cp310-cp310-manylinux_2_28_x86_64.whl (38.3 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m38.3/38.3 MB\u001b[0m \u001b[31m36.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hDownloading bitsandbytes-0.43.0-py3-none-manylinux_2_24_x86_64.whl (102.2 MB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m102.2/102.2 MB\u001b[0m \u001b[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hDownloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\r\n", "Downloading peft-0.10.0-py3-none-any.whl (199 kB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m199.1/199.1 kB\u001b[0m \u001b[31m14.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hDownloading trl-0.8.1-py3-none-any.whl (225 kB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m225.0/225.0 kB\u001b[0m \u001b[31m11.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hDownloading tyro-0.7.3-py3-none-any.whl (79 kB)\r\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.8/79.8 kB\u001b[0m \u001b[31m5.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\r\n", "\u001b[?25hDownloading shtab-1.7.1-py3-none-any.whl (14 kB)\r\n", "Building wheels for collected packages: unsloth\r\n", " Building wheel for unsloth (pyproject.toml) ... \u001b[?25l-\b \b\\\b \b|\b \bdone\r\n", "\u001b[?25h Created wheel for unsloth: filename=unsloth-2024.3-py3-none-any.whl size=93934 sha256=34861411793a48098b4d9e04f35bc2ce841bfae25a980dd6ce151eecc1321a1a\r\n", " Stored in directory: /tmp/pip-ephem-wheel-cache-6kf3ks_c/wheels/ed/d4/e9/76fb290ee3df0a5fc21ce5c2c788e29e9607a2353d8342fd0d\r\n", "Successfully built unsloth\r\n", "Installing collected packages: unsloth, shtab, pyarrow-hotfix, pyarrow, fsspec, tyro, datasets, bitsandbytes, trl, peft\r\n", " Attempting uninstall: pyarrow\r\n", " Found existing installation: pyarrow 11.0.0\r\n", " Uninstalling pyarrow-11.0.0:\r\n", " Successfully uninstalled pyarrow-11.0.0\r\n", " Attempting uninstall: fsspec\r\n", " Found existing installation: fsspec 2024.3.0\r\n", " Uninstalling fsspec-2024.3.0:\r\n", " Successfully uninstalled fsspec-2024.3.0\r\n", " Attempting uninstall: datasets\r\n", " Found existing installation: datasets 2.1.0\r\n", " Uninstalling datasets-2.1.0:\r\n", " Successfully uninstalled datasets-2.1.0\r\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.\r\n", "cudf 23.8.0 requires cubinlinker, which is not installed.\r\n", "cudf 23.8.0 requires cupy-cuda11x>=12.0.0, which is not installed.\r\n", "cudf 23.8.0 requires ptxcompiler, which is not installed.\r\n", "cuml 23.8.0 requires cupy-cuda11x>=12.0.0, which is not installed.\r\n", "dask-cudf 23.8.0 requires cupy-cuda11x>=12.0.0, which is not installed.\r\n", "apache-beam 2.46.0 requires dill<0.3.2,>=0.3.1.1, but you have dill 0.3.8 which is incompatible.\r\n", "apache-beam 2.46.0 requires numpy<1.25.0,>=1.14.3, but you have numpy 1.26.4 which is incompatible.\r\n", "apache-beam 2.46.0 requires pyarrow<10.0.0,>=3.0.0, but you have pyarrow 15.0.2 which is incompatible.\r\n", "beatrix-jupyterlab 2023.128.151533 requires jupyterlab~=3.6.0, but you have jupyterlab 4.1.5 which is incompatible.\r\n", "cudf 23.8.0 requires cuda-python<12.0a0,>=11.7.1, but you have cuda-python 12.4.0 which is incompatible.\r\n", "cudf 23.8.0 requires pandas<1.6.0dev0,>=1.3, but you have pandas 2.1.4 which is incompatible.\r\n", "cudf 23.8.0 requires protobuf<5,>=4.21, but you have protobuf 3.20.3 which is incompatible.\r\n", "cudf 23.8.0 requires pyarrow==11.*, but you have pyarrow 15.0.2 which is incompatible.\r\n", "cuml 23.8.0 requires dask==2023.7.1, but you have dask 2024.3.1 which is incompatible.\r\n", "dask-cuda 23.8.0 requires dask==2023.7.1, but you have dask 2024.3.1 which is incompatible.\r\n", "dask-cuda 23.8.0 requires pandas<1.6.0dev0,>=1.3, but you have pandas 2.1.4 which is incompatible.\r\n", "dask-cudf 23.8.0 requires dask==2023.7.1, but you have dask 2024.3.1 which is incompatible.\r\n", "dask-cudf 23.8.0 requires pandas<1.6.0dev0,>=1.3, but you have pandas 2.1.4 which is incompatible.\r\n", "distributed 2023.7.1 requires dask==2023.7.1, but you have dask 2024.3.1 which is incompatible.\r\n", "gcsfs 2023.12.2.post1 requires fsspec==2023.12.2, but you have fsspec 2023.10.0 which is incompatible.\r\n", "raft-dask 23.8.0 requires dask==2023.7.1, but you have dask 2024.3.1 which is incompatible.\r\n", "s3fs 2024.3.0 requires fsspec==2024.3.0, but you have fsspec 2023.10.0 which is incompatible.\u001b[0m\u001b[31m\r\n", "\u001b[0mSuccessfully installed bitsandbytes-0.43.0 datasets-2.17.1 fsspec-2023.10.0 peft-0.10.0 pyarrow-15.0.2 pyarrow-hotfix-0.6 shtab-1.7.1 trl-0.8.1 tyro-0.7.3 unsloth-2024.3\r\n" ] } ], "source": [ "#%%capture\n", "#import torch\n", "#major_version, minor_version = torch.cuda.get_device_capability()\n", "\n", "!pip install -U xformers --index-url https://download.pytorch.org/whl/cu121\n", "!pip install \"unsloth[kaggle-new] @ git+https://github.com/unslothai/unsloth.git\" triton datasets==2.17.1\n", "#if major_version >= 8:\n", "# # Use this for new GPUs like Ampere, Hopper GPUs (RTX 30xx, RTX 40xx, A100, H100, L40)\n", "# !pip install --no-deps packaging ninja einops flash-attn xformers trl peft accelerate bitsandbytes\n", "#else:\n", "# # Use this for older GPUs (V100, Tesla T4, RTX 20xx)\n", "# !pip install --no-deps xformers trl peft accelerate bitsandbytes\n", "\n", "import os\n", "os.environ[\"WANDB_DISABLED\"] = \"true\"" ] }, { "cell_type": "markdown", "id": "c963a9d2", "metadata": { "id": "r2v_X2fA0Df5", "papermill": { "duration": 0.123192, "end_time": "2024-03-28T00:12:44.398766", "exception": false, "start_time": "2024-03-28T00:12:44.275574", "status": "completed" }, "tags": [] }, "source": [ "* We support Llama, Mistral, CodeLlama, TinyLlama, Vicuna, Open Hermes etc\n", "* And Yi, Qwen ([llamafied](https://huggingface.co/models?sort=trending&search=qwen+llama)), Deepseek, all Llama, Mistral derived archs.\n", "* We support 16bit LoRA or 4bit QLoRA. Both 2x faster.\n", "* `max_seq_length` can be set to anything, since we do automatic RoPE Scaling via [kaiokendev's](https://kaiokendev.github.io/til) method.\n", "* With [PR 26037](https://github.com/huggingface/transformers/pull/26037), we support downloading 4bit models **4x faster**! [Our repo](https://huggingface.co/unsloth) has Llama, Mistral 4bit models.\n", "* [**NEW**] We make Gemma 6 trillion tokens **2.5x faster**! See our [Gemma notebook](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing)" ] }, { "cell_type": "code", "execution_count": 2, "id": "88a40779", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T00:12:44.654372Z", "iopub.status.busy": "2024-03-28T00:12:44.653667Z", "iopub.status.idle": "2024-03-28T00:13:38.483179Z", "shell.execute_reply": "2024-03-28T00:13:38.482338Z" }, "id": "QmUBVEnvCDJv", "outputId": "40383ec5-b379-4fcd-ba5c-b5656b0ff129", "papermill": { "duration": 53.95967, "end_time": "2024-03-28T00:13:38.485764", "exception": false, "start_time": "2024-03-28T00:12:44.526094", "status": "completed" }, "tags": [] }, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "58648d0ab785418089b24914c46df7a4", "version_major": 2, "version_minor": 0 }, "text/plain": [ "config.json: 0%| | 0.00/1.05k [00:00 0 ! Suggested 8, 16, 32, 64, 128\n", " target_modules = [\"q_proj\", \"k_proj\", \"v_proj\", \"o_proj\",\n", " \"gate_proj\", \"up_proj\", \"down_proj\",],\n", " lora_alpha = 16,\n", " lora_dropout = 0, # Supports any, but = 0 is optimized\n", " bias = \"none\", # Supports any, but = \"none\" is optimized\n", " use_gradient_checkpointing = True,\n", " random_state = 3407,\n", " use_rslora = False, # We support rank stabilized LoRA\n", " loftq_config = None, # And LoftQ\n", ")" ] }, { "cell_type": "markdown", "id": "0b7c4848", "metadata": { "id": "vITh0KVJ10qX", "papermill": { "duration": 0.124172, "end_time": "2024-03-28T00:13:40.129776", "exception": false, "start_time": "2024-03-28T00:13:40.005604", "status": "completed" }, "tags": [] }, "source": [ "\n", "### Data Prep\n", "We now use the `ChatML` format for conversation style finetunes. We use [Open Assistant conversations](https://huggingface.co/datasets/philschmid/guanaco-sharegpt-style) in ShareGPT style. ChatML renders multi turn conversations like below:\n", "\n", "```\n", "<|im_start|>system\n", "You are a helpful assistant.<|im_end|>\n", "<|im_start|>user\n", "What's the capital of France?<|im_end|>\n", "<|im_start|>assistant\n", "Paris.\n", "```\n", "\n", "**[NOTE]** To train only on completions (ignoring the user's input) read TRL's docs [here](https://huggingface.co/docs/trl/sft_trainer#train-on-completions-only).\n", "\n", "We use our `get_chat_template` function to get the correct chat template. We support `zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old` and our own optimized `unsloth` template.\n", "\n", "Normally one has to train `<|im_start|>` and `<|im_end|>`. We instead map `<|im_end|>` to be the EOS token, and leave `<|im_start|>` as is. This requires no additional training of additional tokens.\n", "\n", "Note ShareGPT uses `{\"from\": \"human\", \"value\" : \"Hi\"}` and not `{\"role\": \"user\", \"content\" : \"Hi\"}`, so we use `mapping` to map it.\n", "\n", "For text completions like novel writing, try this [notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing)." ] }, { "cell_type": "code", "execution_count": 4, "id": "0d33d99d", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T00:13:40.375057Z", "iopub.status.busy": "2024-03-28T00:13:40.374718Z", "iopub.status.idle": "2024-03-28T00:13:41.633504Z", "shell.execute_reply": "2024-03-28T00:13:41.632366Z" }, "id": "LjY75GoYUCB8", "outputId": "50c7b539-b750-4964-fa4a-45a99d5923f1", "papermill": { "duration": 1.382761, "end_time": "2024-03-28T00:13:41.635817", "exception": false, "start_time": "2024-03-28T00:13:40.253056", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Unsloth: Will map <|im_end|> to EOS = .\n" ] } ], "source": [ "from datasets import load_dataset\n", "import json\n", "from unsloth.chat_templates import get_chat_template\n", "\n", "tokenizer = get_chat_template(\n", " tokenizer,\n", " chat_template = \"chatml\", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth\n", " #mapping = {\"role\" : \"from\", \"content\" : \"value\", \"user\" : \"human\", \"assistant\" : \"gpt\"}, # ShareGPT style\n", " map_eos_token = True, # Maps <|im_end|> to instead\n", ")\n", "\n", "def formatting_prompts_func(convos):\n", " texts = [tokenizer.apply_chat_template(convo, tokenize = False, add_generation_prompt = False) for convo in convos]\n", " return { \"text\" : texts, }\n", "\n", "with open(\"/kaggle/input/the-group-chat/output-10k-c.json\") as chatfile:\n", " convos = [json.loads(j) for j in chatfile.readlines()]\n", "\n", "dataset = formatting_prompts_func(convos)" ] }, { "cell_type": "markdown", "id": "f75a3f33", "metadata": { "id": "cHiVoToneynS", "papermill": { "duration": 0.127199, "end_time": "2024-03-28T00:13:41.890438", "exception": false, "start_time": "2024-03-28T00:13:41.763239", "status": "completed" }, "tags": [] }, "source": [ "Let's see how the `ChatML` format works by printing the 5th element" ] }, { "cell_type": "code", "execution_count": 5, "id": "08ef098f", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T00:13:42.144988Z", "iopub.status.busy": "2024-03-28T00:13:42.144281Z", "iopub.status.idle": "2024-03-28T00:13:42.148878Z", "shell.execute_reply": "2024-03-28T00:13:42.147833Z" }, "id": "U5iEWrUkevpE", "outputId": "e28b6889-29f9-400f-a08c-5fc7d5cbc5db", "papermill": { "duration": 0.133687, "end_time": "2024-03-28T00:13:42.150735", "exception": false, "start_time": "2024-03-28T00:13:42.017048", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "#dataset[5][\"conversations\"]\n", "#print(dataset[\"text\"])" ] }, { "cell_type": "markdown", "id": "a77a6d20", "metadata": { "id": "GuKOAUDpUeDL", "papermill": { "duration": 0.121878, "end_time": "2024-03-28T00:13:42.399195", "exception": false, "start_time": "2024-03-28T00:13:42.277317", "status": "completed" }, "tags": [] }, "source": [ "If you're looking to make your own chat template, that also is possible! You must use the Jinja templating regime. We provide our own stripped down version of the `Unsloth template` which we find to be more efficient, and leverages ChatML, Zephyr and Alpaca styles.\n", "\n", "More info on chat templates on [our wiki page!](https://github.com/unslothai/unsloth/wiki#chat-templates)" ] }, { "cell_type": "code", "execution_count": 6, "id": "cdd24991", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T00:13:42.653294Z", "iopub.status.busy": "2024-03-28T00:13:42.652894Z", "iopub.status.idle": "2024-03-28T00:13:42.658835Z", "shell.execute_reply": "2024-03-28T00:13:42.657902Z" }, "id": "p31Z-S6FUieB", "papermill": { "duration": 0.136303, "end_time": "2024-03-28T00:13:42.660931", "exception": false, "start_time": "2024-03-28T00:13:42.524628", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "unsloth_template = \\\n", " \"{{ bos_token }}\"\\\n", " \"{{ 'You are a helpful assistant to the user\\n' }}\"\\\n", " \"{% endif %}\"\\\n", " \"{% for message in messages %}\"\\\n", " \"{% if message['role'] == 'user' %}\"\\\n", " \"{{ '>>> User: ' + message['content'] + '\\n' }}\"\\\n", " \"{% elif message['role'] == 'assistant' %}\"\\\n", " \"{{ '>>> Assistant: ' + message['content'] + eos_token + '\\n' }}\"\\\n", " \"{% endif %}\"\\\n", " \"{% endfor %}\"\\\n", " \"{% if add_generation_prompt %}\"\\\n", " \"{{ '>>> Assistant: ' }}\"\\\n", " \"{% endif %}\"\n", "unsloth_eos_token = \"eos_token\"\n", "\n", "if False:\n", " tokenizer = get_chat_template(\n", " tokenizer,\n", " chat_template = (unsloth_template, unsloth_eos_token,), # You must provide a template and EOS token\n", " mapping = {\"role\" : \"from\", \"content\" : \"value\", \"user\" : \"human\", \"assistant\" : \"gpt\"}, # ShareGPT style\n", " map_eos_token = True, # Maps <|im_end|> to instead\n", " )" ] }, { "cell_type": "markdown", "id": "44e5c271", "metadata": { "id": "idAEIeSQ3xdS", "papermill": { "duration": 0.127599, "end_time": "2024-03-28T00:13:42.915115", "exception": false, "start_time": "2024-03-28T00:13:42.787516", "status": "completed" }, "tags": [] }, "source": [ "\n", "### Train the model\n", "Now let's use Huggingface TRL's `SFTTrainer`! More docs here: [TRL SFT docs](https://huggingface.co/docs/trl/sft_trainer). We do 60 steps to speed things up, but you can set `num_train_epochs=1` for a full run, and turn off `max_steps=None`. We also support TRL's `DPOTrainer`!" ] }, { "cell_type": "code", "execution_count": 7, "id": "84d94e51", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T00:13:43.163495Z", "iopub.status.busy": "2024-03-28T00:13:43.162623Z", "iopub.status.idle": "2024-03-28T00:13:43.243458Z", "shell.execute_reply": "2024-03-28T00:13:43.242622Z" }, "papermill": { "duration": 0.20747, "end_time": "2024-03-28T00:13:43.245965", "exception": false, "start_time": "2024-03-28T00:13:43.038495", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "from datasets import Dataset\n", "dataset = Dataset.from_dict(dataset)" ] }, { "cell_type": "code", "execution_count": 8, "id": "099afa9e", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T00:13:43.492984Z", "iopub.status.busy": "2024-03-28T00:13:43.492622Z", "iopub.status.idle": "2024-03-28T00:13:48.324291Z", "shell.execute_reply": "2024-03-28T00:13:48.323307Z" }, "id": "95_Nn-89DhsL", "outputId": "c13d3e90-5342-4535-9541-98f9120dfe2b", "papermill": { "duration": 4.95752, "end_time": "2024-03-28T00:13:48.326701", "exception": false, "start_time": "2024-03-28T00:13:43.369181", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Using the `WANDB_DISABLED` environment variable is deprecated and will be removed in v5. Use the --report_to flag to control the integrations used for logging result (for instance --report_to none).\n" ] }, { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "e363d483a5134f5d873c11f936d2d9f5", "version_major": 2, "version_minor": 0 }, "text/plain": [ "Map (num_proc=2): 0%| | 0/10000 [00:00\n", " \n", " \n", " [1250/1250 3:38:46, Epoch 1/1]\n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", " \n", "
StepTraining Loss
12.415600
22.560600
32.358100
42.018800
51.869800
61.859900
71.855700
81.985000
91.739100
101.857900
111.858300
121.574900
131.680000
141.615100
151.720000
161.731600
171.727100
181.587100
191.579300
201.642300
211.487200
221.585400
231.611900
241.598700
251.617600
261.511700
271.805500
281.569000
291.652700
301.421700
311.666500
321.633400
331.630900
341.744100
351.577500
361.665400
371.569500
381.597500
391.703800
401.556500
411.451800
421.629500
431.538500
441.508600
451.439400
461.590000
471.568200
481.554900
491.486900
501.617100
511.695700
521.470600
531.680400
541.605500
551.472900
561.636600
571.527600
581.579300
591.551700
601.503900
611.364500
621.575300
631.516700
641.632000
651.430900
661.542000
671.609800
681.647700
691.478100
701.328200
711.725000
721.522400
731.557200
741.670000
751.648900
761.670400
771.615300
781.541800
791.549200
801.544500
811.423300
821.300900
831.626600
841.585000
851.444500
861.598200
871.541000
881.429500
891.517300
901.539100
911.604200
921.504300
931.520200
941.459000
951.619900
961.629000
971.507000
981.455300
991.461700
1001.513500
1011.521500
1021.658100
1031.579500
1041.430100
1051.591500
1061.620900
1071.681300
1081.662900
1091.717200
1101.656000
1111.545400
1121.434400
1131.665900
1141.483000
1151.411300
1161.549000
1171.627200
1181.608600
1191.549700
1201.560800
1211.581400
1221.586100
1231.442700
1241.666800
1251.563900
1261.550300
1271.475600
1281.470400
1291.605000
1301.546100
1311.552900
1321.562300
1331.468900
1341.368200
1351.545800
1361.519900
1371.646300
1381.588800
1391.550300
1401.484800
1411.581600
1421.623200
1431.664700
1441.538800
1451.662800
1461.593500
1471.419500
1481.656200
1491.479400
1501.512500
1511.528800
1521.500800
1531.597800
1541.548600
1551.626200
1561.633400
1571.536100
1581.535300
1591.571300
1601.461200
1611.516200
1621.465500
1631.563900
1641.599900
1651.494400
1661.550500
1671.382100
1681.550800
1691.554000
1701.499200
1711.619500
1721.571800
1731.552700
1741.360500
1751.457600
1761.528500
1771.450600
1781.497100
1791.415400
1801.549900
1811.459800
1821.653100
1831.255300
1841.511100
1851.487700
1861.678500
1871.566400
1881.479300
1891.503900
1901.493700
1911.468400
1921.499400
1931.462300
1941.606200
1951.726000
1961.424700
1971.560500
1981.572200
1991.694600
2001.508900
2011.465600
2021.533500
2031.531400
2041.543200
2051.546500
2061.568600
2071.437200
2081.524100
2091.644300
2101.412500
2111.604700
2121.538300
2131.552600
2141.654100
2151.632300
2161.634200
2171.562400
2181.528000
2191.444400
2201.449800
2211.561900
2221.565400
2231.526800
2241.422900
2251.514200
2261.663700
2271.402100
2281.536400
2291.411200
2301.582300
2311.489300
2321.531800
2331.509500
2341.514100
2351.503800
2361.558800
2371.433500
2381.593100
2391.442500
2401.458900
2411.609300
2421.368500
2431.488500
2441.495500
2451.587800
2461.597700
2471.337800
2481.527200
2491.343900
2501.376000
2511.506100
2521.415800
2531.528500
2541.499300
2551.605400
2561.471000
2571.507400
2581.471800
2591.460100
2601.623500
2611.470000
2621.317300
2631.381800
2641.381500
2651.475200
2661.511700
2671.524100
2681.487300
2691.331600
2701.479500
2711.474400
2721.530400
2731.520800
2741.613700
2751.543800
2761.588600
2771.462600
2781.433200
2791.508600
2801.401300
2811.486700
2821.590800
2831.455800
2841.442800
2851.660000
2861.642900
2871.431400
2881.575100
2891.557800
2901.553200
2911.541500
2921.531600
2931.489800
2941.561100
2951.524400
2961.421400
2971.466800
2981.526200
2991.411400
3001.428100
3011.464500
3021.460000
3031.522700
3041.533100
3051.464400
3061.545100
3071.506800
3081.508500
3091.576900
3101.587500
3111.397800
3121.478100
3131.484200
3141.428500
3151.520700
3161.464100
3171.412200
3181.493000
3191.514200
3201.538200
3211.537100
3221.470500
3231.361800
3241.540100
3251.583800
3261.411400
3271.585000
3281.561200
3291.441400
3301.443100
3311.487900
3321.441400
3331.502100
3341.680100
3351.718200
3361.613200
3371.428600
3381.659800
3391.550100
3401.479900
3411.512500
3421.371900
3431.418200
3441.605200
3451.455900
3461.413300
3471.463400
3481.459700
3491.473400
3501.467900
3511.424800
3521.607200
3531.697500
3541.510900
3551.606700
3561.639400
3571.460200
3581.456100
3591.393600
3601.477500
3611.438100
3621.412900
3631.564800
3641.423000
3651.517000
3661.378000
3671.541300
3681.426400
3691.512400
3701.470800
3711.514200
3721.480300
3731.489100
3741.546200
3751.481200
3761.476000
3771.385400
3781.613200
3791.245500
3801.312100
3811.396700
3821.501400
3831.405100
3841.481700
3851.520400
3861.596300
3871.585500
3881.557700
3891.432000
3901.627200
3911.498900
3921.583700
3931.411800
3941.454600
3951.532200
3961.443000
3971.358000
3981.400200
3991.493300
4001.387900
4011.430900
4021.485400
4031.757100
4041.606100
4051.570100
4061.600700
4071.489300
4081.570900
4091.442300
4101.504900
4111.406900
4121.600600
4131.362500
4141.527700
4151.509400
4161.619800
4171.367200
4181.440800
4191.523200
4201.507500
4211.473100
4221.406900
4231.417000
4241.462700
4251.536800
4261.545300
4271.457400
4281.471200
4291.470500
4301.550000
4311.517700
4321.552500
4331.564900
4341.662400
4351.484900
4361.381200
4371.505900
4381.439100
4391.343900
4401.508700
4411.525400
4421.434000
4431.470400
4441.544200
4451.380300
4461.475500
4471.653600
4481.636300
4491.525200
4501.500500
4511.438000
4521.488800
4531.396300
4541.440200
4551.482000
4561.461400
4571.471400
4581.315300
4591.587200
4601.452000
4611.718700
4621.414400
4631.514500
4641.492100
4651.581400
4661.425000
4671.476900
4681.403700
4691.438700
4701.563300
4711.475600
4721.610700
4731.348700
4741.470000
4751.615400
4761.446700
4771.394500
4781.470600
4791.397700
4801.377500
4811.504900
4821.485500
4831.461600
4841.520600
4851.532300
4861.627200
4871.509800
4881.387400
4891.438900
4901.440700
4911.527900
4921.478900
4931.461900
4941.624800
4951.521600
4961.406800
4971.480600
4981.602300
4991.590400
5001.622000
5011.582400
5021.548000
5031.439800
5041.406300
5051.499700
5061.389400
5071.591000
5081.453000
5091.532200
5101.482900
5111.428800
5121.575800
5131.460300
5141.530200
5151.447100
5161.621300
5171.525500
5181.528700
5191.466200
5201.488700
5211.449400
5221.537600
5231.398400
5241.316700
5251.386100
5261.603900
5271.353800
5281.306700
5291.401600
5301.380400
5311.394900
5321.498300
5331.462200
5341.458100
5351.515000
5361.483900
5371.508600
5381.612800
5391.443400
5401.455600
5411.568900
5421.547600
5431.432400
5441.583800
5451.365600
5461.596500
5471.450600
5481.485400
5491.457700
5501.390200
5511.399700
5521.417600
5531.579800
5541.472400
5551.386100
5561.439000
5571.418300
5581.444300
5591.516500
5601.550100
5611.410800
5621.560600
5631.523800
5641.489200
5651.423400
5661.436900
5671.546700
5681.393200
5691.556600
5701.446700
5711.380600
5721.340500
5731.477000
5741.367000
5751.643500
5761.448600
5771.419600
5781.568400
5791.473300
5801.650400
5811.572000
5821.499300
5831.613200
5841.566500
5851.477800
5861.507300
5871.374800
5881.480100
5891.357000
5901.328300
5911.343400
5921.470600
5931.524700
5941.420600
5951.398400
5961.498600
5971.530700
5981.520700
5991.579800
6001.559300
6011.400800
6021.489000
6031.532900
6041.507300
6051.447400
6061.527100
6071.433700
6081.533300
6091.469300
6101.504100
6111.416300
6121.601600
6131.526500
6141.491200
6151.605900
6161.561700
6171.384500
6181.561900
6191.416700
6201.484600
6211.558600
6221.449400
6231.477200
6241.557600
6251.550600
6261.575000
6271.376900
6281.557200
6291.466200
6301.390700
6311.441400
6321.526600
6331.455400
6341.310500
6351.445300
6361.431300
6371.596800
6381.520600
6391.554900
6401.456100
6411.566200
6421.507100
6431.522700
6441.482700
6451.525900
6461.327800
6471.441400
6481.412400
6491.338100
6501.466900
6511.592100
6521.473300
6531.526600
6541.484900
6551.537900
6561.368500
6571.332000
6581.545500
6591.425000
6601.487300
6611.499200
6621.461900
6631.495800
6641.432700
6651.480300
6661.452000
6671.516700
6681.465200
6691.455800
6701.402400
6711.377000
6721.540900
6731.436500
6741.597800
6751.432400
6761.417700
6771.305100
6781.543400
6791.629200
6801.404100
6811.544200
6821.552600
6831.422000
6841.477900
6851.293200
6861.411200
6871.480900
6881.486800
6891.316400
6901.466900
6911.376700
6921.440000
6931.594300
6941.482100
6951.537500
6961.543200
6971.458800
6981.493900
6991.517100
7001.408600
7011.488700
7021.363300
7031.300900
7041.488000
7051.377400
7061.526500
7071.392900
7081.536000
7091.349900
7101.447300
7111.349600
7121.548100
7131.441000
7141.418200
7151.434100
7161.387700
7171.293200
7181.396800
7191.430700
7201.363800
7211.471500
7221.502400
7231.394000
7241.339500
7251.478800
7261.554500
7271.355800
7281.422100
7291.487600
7301.425300
7311.429600
7321.440100
7331.484700
7341.588300
7351.428800
7361.510200
7371.418300
7381.461400
7391.455600
7401.377100
7411.382400
7421.520200
7431.383200
7441.494000
7451.567400
7461.437000
7471.458000
7481.483100
7491.473700
7501.644300
7511.348900
7521.442800
7531.616400
7541.459600
7551.478100
7561.469500
7571.510300
7581.402400
7591.477400
7601.597400
7611.470700
7621.586600
7631.316800
7641.298600
7651.482500
7661.544300
7671.396300
7681.321000
7691.424400
7701.449300
7711.479900
7721.451300
7731.567600
7741.257600
7751.649800
7761.516400
7771.461400
7781.494800
7791.621100
7801.571900
7811.331500
7821.575500
7831.439000
7841.347600
7851.522800
7861.584100
7871.419300
7881.385400
7891.435000
7901.483800
7911.452200
7921.587100
7931.495600
7941.485100
7951.444100
7961.534800
7971.436100
7981.366400
7991.603100
8001.505600
8011.484300
8021.353700
8031.462300
8041.497700
8051.448300
8061.388900
8071.440900
8081.437100
8091.527300
8101.497200
8111.482200
8121.361200
8131.435700
8141.463700
8151.478700
8161.523100
8171.560500
8181.457100
8191.477400
8201.558200
8211.424400
8221.578200
8231.465400
8241.343500
8251.405000
8261.476500
8271.458900
8281.458300
8291.497900
8301.436900
8311.575000
8321.531200
8331.490700
8341.556900
8351.620300
8361.563400
8371.436300
8381.465600
8391.412700
8401.487900
8411.506800
8421.427100
8431.376300
8441.500300
8451.573100
8461.443300
8471.476400
8481.497100
8491.310600
8501.404200
8511.575800
8521.506100
8531.424900
8541.522100
8551.376900
8561.476000
8571.339700
8581.440300
8591.518100
8601.411400
8611.394900
8621.522100
8631.436000
8641.585100
8651.490100
8661.472400
8671.299200
8681.422200
8691.487800
8701.623900
8711.605000
8721.580400
8731.275400
8741.452700
8751.400200
8761.473500
8771.359500
8781.495800
8791.451500
8801.420400
8811.528400
8821.397800
8831.597900
8841.509000
8851.568300
8861.473000
8871.553900
8881.588500
8891.442500
8901.415100
8911.357400
8921.311900
8931.405100
8941.464700
8951.495000
8961.488900
8971.584100
8981.444000
8991.414800
9001.465800
9011.523400
9021.518300
9031.488800
9041.305900
9051.549500
9061.580100
9071.603000
9081.450600
9091.503000
9101.450300
9111.382200
9121.439700
9131.561000
9141.443600
9151.487600
9161.322300
9171.318500
9181.387300
9191.441600
9201.519100
9211.453000
9221.407000
9231.422700
9241.352900
9251.494900
9261.434600
9271.465200
9281.417500
9291.342500
9301.547600
9311.545800
9321.496000
9331.398800
9341.327900
9351.587400
9361.347300
9371.543000
9381.418500
9391.396600
9401.364200
9411.439700
9421.523800
9431.385000
9441.491100
9451.528500
9461.536600
9471.292600
9481.522600
9491.438900
9501.423500
9511.468600
9521.486000
9531.542800
9541.571000
9551.455500
9561.434000
9571.442600
9581.448800
9591.342500
9601.431400
9611.475000
9621.483500
9631.493600
9641.417400
9651.352000
9661.603600
9671.465300
9681.454300
9691.563800
9701.572700
9711.428400
9721.561200
9731.404200
9741.628700
9751.593300
9761.670900
9771.438500
9781.325400
9791.479200
9801.411100
9811.362000
9821.348000
9831.381000
9841.415500
9851.583300
9861.465600
9871.495200
9881.499300
9891.455300
9901.452700
9911.296100
9921.356300
9931.505300
9941.429800
9951.423700
9961.547100
9971.512000
9981.458500
9991.445100
10001.381500
10011.508700
10021.457800
10031.508300
10041.370400
10051.487900
10061.517900
10071.492000
10081.462700
10091.397000
10101.522600
10111.492100
10121.318800
10131.501300
10141.491900
10151.413900
10161.453600
10171.459800
10181.492700
10191.471900
10201.328900
10211.552300
10221.300600
10231.366600
10241.365000
10251.420200
10261.392600
10271.492400
10281.524600
10291.371600
10301.431100
10311.471200
10321.534200
10331.417100
10341.394700
10351.455900
10361.536200
10371.626100
10381.588400
10391.538200
10401.375200
10411.589300
10421.557200
10431.526000
10441.349600
10451.420000
10461.444700
10471.411600
10481.444600
10491.591000
10501.384300
10511.470500
10521.380200
10531.278600
10541.276000
10551.363100
10561.487500
10571.583300
10581.470100
10591.450300
10601.449600
10611.509500
10621.436600
10631.538900
10641.336300
10651.403300
10661.440900
10671.482600
10681.482000
10691.474700
10701.539600
10711.492200
10721.409400
10731.445600
10741.339800
10751.505300
10761.513600
10771.508100
10781.592900
10791.465400
10801.285500
10811.412400
10821.588400
10831.369300
10841.412800
10851.517000
10861.518100
10871.453300
10881.358200
10891.441300
10901.573100
10911.470400
10921.446200
10931.404700
10941.325000
10951.493900
10961.340800
10971.408600
10981.440300
10991.479400
11001.390100
11011.433100
11021.412200
11031.382300
11041.555300
11051.388700
11061.450600
11071.552400
11081.364400
11091.338100
11101.367700
11111.418500
11121.449400
11131.381700
11141.358700
11151.406300
11161.406500
11171.363200
11181.523900
11191.433600
11201.452200
11211.544300
11221.465900
11231.377600
11241.440300
11251.302200
11261.468200
11271.378600
11281.435300
11291.479000
11301.382800
11311.424500
11321.428200
11331.469500
11341.468200
11351.444400
11361.544500
11371.431600
11381.442000
11391.537700
11401.396300
11411.410400
11421.438300
11431.270800
11441.449900
11451.492000
11461.487600
11471.369300
11481.365100
11491.491000
11501.413800
11511.563000
11521.507800
11531.301600
11541.511200
11551.538100
11561.301700
11571.379500
11581.603100
11591.453100
11601.422200
11611.597700
11621.541900
11631.456500
11641.467500
11651.303300
11661.495300
11671.454000
11681.562400
11691.406800
11701.247900
11711.631900
11721.394800
11731.493100
11741.379300
11751.334400
11761.499200
11771.505100
11781.415100
11791.453500
11801.368400
11811.459900
11821.544000
11831.549300
11841.580900
11851.456400
11861.465700
11871.457900
11881.497100
11891.600700
11901.438900
11911.406400
11921.415300
11931.442900
11941.488600
11951.457500
11961.484800
11971.455100
11981.467500
11991.568700
12001.466500
12011.495300
12021.496600
12031.500400
12041.571200
12051.448100
12061.405400
12071.510100
12081.400100
12091.461100
12101.368100
12111.474400
12121.363600
12131.564700
12141.553300
12151.326500
12161.338000
12171.407600
12181.584600
12191.384300
12201.461900
12211.384800
12221.406000
12231.500400
12241.351400
12251.399500
12261.415000
12271.287200
12281.417100
12291.372600
12301.329200
12311.547300
12321.395000
12331.321300
12341.296700
12351.414100
12361.383600
12371.384600
12381.401000
12391.403600
12401.572300
12411.422600
12421.386300
12431.365200
12441.430600
12451.573700
12461.518800
12471.399000
12481.408100
12491.542400
12501.504800

" ], "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "trainer_stats = trainer.train()" ] }, { "cell_type": "code", "execution_count": 11, "id": "f70aca8b", "metadata": { "cellView": "form", "execution": { "iopub.execute_input": "2024-03-28T03:52:49.697610Z", "iopub.status.busy": "2024-03-28T03:52:49.696564Z", "iopub.status.idle": "2024-03-28T03:52:49.704999Z", "shell.execute_reply": "2024-03-28T03:52:49.703738Z" }, "id": "pCqnaKmlO1U9", "outputId": "e34545d2-808b-44b3-80d5-c21ca7a2da16", "papermill": { "duration": 0.146166, "end_time": "2024-03-28T03:52:49.707144", "exception": false, "start_time": "2024-03-28T03:52:49.560978", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "13140.0413 seconds used for training.\n", "219.0 minutes used for training.\n", "Peak reserved memory = 7.268 GB.\n", "Peak reserved memory for training = 2.768 GB.\n", "Peak reserved memory % of max memory = 49.281 %.\n", "Peak reserved memory for training % of max memory = 18.769 %.\n" ] } ], "source": [ "#@title Show final memory and time stats\n", "used_memory = round(torch.cuda.max_memory_reserved() / 1024 / 1024 / 1024, 3)\n", "used_memory_for_lora = round(used_memory - start_gpu_memory, 3)\n", "used_percentage = round(used_memory /max_memory*100, 3)\n", "lora_percentage = round(used_memory_for_lora/max_memory*100, 3)\n", "print(f\"{trainer_stats.metrics['train_runtime']} seconds used for training.\")\n", "print(f\"{round(trainer_stats.metrics['train_runtime']/60, 2)} minutes used for training.\")\n", "print(f\"Peak reserved memory = {used_memory} GB.\")\n", "print(f\"Peak reserved memory for training = {used_memory_for_lora} GB.\")\n", "print(f\"Peak reserved memory % of max memory = {used_percentage} %.\")\n", "print(f\"Peak reserved memory for training % of max memory = {lora_percentage} %.\")" ] }, { "cell_type": "markdown", "id": "8d5dff6e", "metadata": { "id": "ekOmTR1hSNcr", "papermill": { "duration": 0.139123, "end_time": "2024-03-28T03:52:49.982166", "exception": false, "start_time": "2024-03-28T03:52:49.843043", "status": "completed" }, "tags": [] }, "source": [ "\n", "### Inference\n", "Let's run the model! Since we're using `ChatML`, use `apply_chat_template` with `add_generation_prompt` set to `True` for inference." ] }, { "cell_type": "code", "execution_count": 12, "id": "bebbdda7", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T03:52:50.245764Z", "iopub.status.busy": "2024-03-28T03:52:50.244849Z", "iopub.status.idle": "2024-03-28T03:52:52.425841Z", "shell.execute_reply": "2024-03-28T03:52:52.424679Z" }, "id": "kR3gIAX-SM2q", "outputId": "d1b13317-4781-4078-90bf-0de74d93f6e4", "papermill": { "duration": 2.314189, "end_time": "2024-03-28T03:52:52.428079", "exception": false, "start_time": "2024-03-28T03:52:50.113890", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "Unsloth: Will map <|im_end|> to EOS = <|im_end|>.\n", "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n", "Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n" ] }, { "data": { "text/plain": [ "['<|im_start|>user\\nContinue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,<|im_end|> \\n<|im_start|>assistant\\n13<|im_end|>']" ] }, "execution_count": 12, "metadata": {}, "output_type": "execute_result" } ], "source": [ "from unsloth.chat_templates import get_chat_template\n", "\n", "tokenizer = get_chat_template(\n", " tokenizer,\n", " chat_template = \"chatml\", # Supports zephyr, chatml, mistral, llama, alpaca, vicuna, vicuna_old, unsloth\n", " mapping = {\"role\" : \"from\", \"content\" : \"value\", \"user\" : \"human\", \"assistant\" : \"gpt\"}, # ShareGPT style\n", " map_eos_token = True, # Maps <|im_end|> to instead\n", ")\n", "\n", "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", "\n", "messages = [\n", " {\"from\": \"human\", \"value\": \"Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,\"},\n", "]\n", "inputs = tokenizer.apply_chat_template(\n", " messages,\n", " tokenize = True,\n", " add_generation_prompt = True, # Must add for generation\n", " return_tensors = \"pt\",\n", ").to(\"cuda\")\n", "\n", "outputs = model.generate(input_ids = inputs, max_new_tokens = 64, use_cache = True)\n", "tokenizer.batch_decode(outputs)" ] }, { "cell_type": "markdown", "id": "6c7afa6f", "metadata": { "id": "CrSvZObor0lY", "papermill": { "duration": 0.138692, "end_time": "2024-03-28T03:52:52.712525", "exception": false, "start_time": "2024-03-28T03:52:52.573833", "status": "completed" }, "tags": [] }, "source": [ " You can also use a `TextStreamer` for continuous inference - so you can see the generation token by token, instead of waiting the whole time!" ] }, { "cell_type": "code", "execution_count": 13, "id": "5cf2ad38", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T03:52:52.996612Z", "iopub.status.busy": "2024-03-28T03:52:52.996171Z", "iopub.status.idle": "2024-03-28T03:52:53.413691Z", "shell.execute_reply": "2024-03-28T03:52:53.412641Z" }, "id": "e2pEuRb1r2Vg", "outputId": "3b7b291c-8237-4473-c3db-8bc5ebbf07f9", "papermill": { "duration": 0.561247, "end_time": "2024-03-28T03:52:53.415994", "exception": false, "start_time": "2024-03-28T03:52:52.854747", "status": "completed" }, "tags": [] }, "outputs": [ { "name": "stderr", "output_type": "stream", "text": [ "The attention mask and the pad token id were not set. As a consequence, you may observe unexpected behavior. Please pass your input's `attention_mask` to obtain reliable results.\n", "Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.\n" ] }, { "name": "stdout", "output_type": "stream", "text": [ "<|im_start|>user\n", "Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,<|im_end|> \n", "<|im_start|>assistant\n", "13<|im_end|>\n" ] } ], "source": [ "FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", "\n", "messages = [\n", " {\"from\": \"human\", \"value\": \"Continue the fibonnaci sequence: 1, 1, 2, 3, 5, 8,\"},\n", "]\n", "inputs = tokenizer.apply_chat_template(\n", " messages,\n", " tokenize = True,\n", " add_generation_prompt = True, # Must add for generation\n", " return_tensors = \"pt\",\n", ").to(\"cuda\")\n", "\n", "from transformers import TextStreamer\n", "text_streamer = TextStreamer(tokenizer)\n", "_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 128, use_cache = True)" ] }, { "cell_type": "markdown", "id": "92f1fa55", "metadata": { "id": "uMuVrWbjAzhc", "papermill": { "duration": 0.129027, "end_time": "2024-03-28T03:52:53.687793", "exception": false, "start_time": "2024-03-28T03:52:53.558766", "status": "completed" }, "tags": [] }, "source": [ "\n", "### Saving, loading finetuned models\n", "To save the final model as LoRA adapters, either use Huggingface's `push_to_hub` for an online save or `save_pretrained` for a local save.\n", "\n", "**[NOTE]** This ONLY saves the LoRA adapters, and not the full model. To save to 16bit or GGUF, scroll down!" ] }, { "cell_type": "code", "execution_count": 14, "id": "ab909818", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T03:52:53.959109Z", "iopub.status.busy": "2024-03-28T03:52:53.958163Z", "iopub.status.idle": "2024-03-28T03:53:02.098759Z", "shell.execute_reply": "2024-03-28T03:53:02.097480Z" }, "id": "upcOlWe7A1vc", "papermill": { "duration": 8.274548, "end_time": "2024-03-28T03:53:02.101048", "exception": false, "start_time": "2024-03-28T03:52:53.826500", "status": "completed" }, "tags": [] }, "outputs": [ { "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "50b8d4fbd7064930bbdf338796e9f09b", "version_major": 2, "version_minor": 0 }, "text/plain": [ "README.md: 0%| | 0.00/579 [00:00user\n", "What is a famous tall tower in Paris?<|im_end|> \n", "<|im_start|>assistant\n", "Eiffel tower<|im_end|>\n" ] } ], "source": [ "if False:\n", " from unsloth import FastLanguageModel\n", " model, tokenizer = FastLanguageModel.from_pretrained(\n", " model_name = \"lora_model\", # YOUR MODEL YOU USED FOR TRAINING\n", " max_seq_length = max_seq_length,\n", " dtype = dtype,\n", " load_in_4bit = load_in_4bit,\n", " )\n", " FastLanguageModel.for_inference(model) # Enable native 2x faster inference\n", "\n", "messages = [\n", " {\"from\": \"human\", \"value\": \"What is a famous tall tower in Paris?\"},\n", "]\n", "inputs = tokenizer.apply_chat_template(\n", " messages,\n", " tokenize = True,\n", " add_generation_prompt = True, # Must add for generation\n", " return_tensors = \"pt\",\n", ").to(\"cuda\")\n", "\n", "from transformers import TextStreamer\n", "text_streamer = TextStreamer(tokenizer)\n", "_ = model.generate(input_ids = inputs, streamer = text_streamer, max_new_tokens = 128, use_cache = True)" ] }, { "cell_type": "markdown", "id": "9ada1c2a", "metadata": { "id": "QQMjaNrjsU5_", "papermill": { "duration": 0.126538, "end_time": "2024-03-28T03:53:03.522957", "exception": false, "start_time": "2024-03-28T03:53:03.396419", "status": "completed" }, "tags": [] }, "source": [ "You can also use Hugging Face's `AutoModelForPeftCausalLM`. Only use this if you do not have `unsloth` installed. It can be hopelessly slow, since `4bit` model downloading is not supported, and Unsloth's **inference is 2x faster**." ] }, { "cell_type": "code", "execution_count": 16, "id": "3c9e54cd", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T03:53:03.788897Z", "iopub.status.busy": "2024-03-28T03:53:03.788477Z", "iopub.status.idle": "2024-03-28T03:53:03.793816Z", "shell.execute_reply": "2024-03-28T03:53:03.792849Z" }, "id": "yFfaXG0WsQuE", "papermill": { "duration": 0.139822, "end_time": "2024-03-28T03:53:03.795815", "exception": false, "start_time": "2024-03-28T03:53:03.655993", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "if False:\n", " # I highly do NOT suggest - use Unsloth if possible\n", " from peft import AutoModelForPeftCausalLM\n", " from transformers import AutoTokenizer\n", " model = AutoModelForPeftCausalLM.from_pretrained(\n", " \"lora_model\", # YOUR MODEL YOU USED FOR TRAINING\n", " load_in_4bit = load_in_4bit,\n", " )\n", " tokenizer = AutoTokenizer.from_pretrained(\"lora_model\")" ] }, { "cell_type": "markdown", "id": "ae8b6865", "metadata": { "id": "f422JgM9sdVT", "papermill": { "duration": 0.133177, "end_time": "2024-03-28T03:53:04.058229", "exception": false, "start_time": "2024-03-28T03:53:03.925052", "status": "completed" }, "tags": [] }, "source": [ "### Saving to float16 for VLLM\n", "\n", "We also support saving to `float16` directly. Select `merged_16bit` for float16 or `merged_4bit` for int4. We also allow `lora` adapters as a fallback. Use `push_to_hub_merged` to upload to your Hugging Face account! You can go to https://huggingface.co/settings/tokens for your personal tokens." ] }, { "cell_type": "code", "execution_count": 17, "id": "73bff174", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T03:53:04.324460Z", "iopub.status.busy": "2024-03-28T03:53:04.324036Z", "iopub.status.idle": "2024-03-28T03:53:04.331159Z", "shell.execute_reply": "2024-03-28T03:53:04.330165Z" }, "id": "iHjt_SMYsd3P", "papermill": { "duration": 0.140814, "end_time": "2024-03-28T03:53:04.333322", "exception": false, "start_time": "2024-03-28T03:53:04.192508", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "# Merge to 16bit\n", "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_16bit\",)\n", "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_16bit\", token = \"\")\n", "\n", "# Merge to 4bit\n", "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"merged_4bit\",)\n", "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"merged_4bit\", token = \"\")\n", "\n", "# Just LoRA adapters\n", "if False: model.save_pretrained_merged(\"model\", tokenizer, save_method = \"lora\",)\n", "if False: model.push_to_hub_merged(\"hf/model\", tokenizer, save_method = \"lora\", token = \"\")" ] }, { "cell_type": "markdown", "id": "96270533", "metadata": { "id": "TCv4vXHd61i7", "papermill": { "duration": 0.141816, "end_time": "2024-03-28T03:53:04.663103", "exception": false, "start_time": "2024-03-28T03:53:04.521287", "status": "completed" }, "tags": [] }, "source": [ "### GGUF / llama.cpp Conversion\n", "To save to `GGUF` / `llama.cpp`, we support it natively now! We clone `llama.cpp` and we default save it to `q8_0`. We allow all methods like `q4_k_m`. Use `save_pretrained_gguf` for local saving and `push_to_hub_gguf` for uploading to HF.\n", "\n", "Some supported quant methods (full list on our [Wiki page](https://github.com/unslothai/unsloth/wiki#gguf-quantization-options)):\n", "* `q8_0` - Fast conversion. High resource use, but generally acceptable.\n", "* `q4_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q4_K.\n", "* `q5_k_m` - Recommended. Uses Q6_K for half of the attention.wv and feed_forward.w2 tensors, else Q5_K." ] }, { "cell_type": "code", "execution_count": 18, "id": "cd67a84a", "metadata": { "execution": { "iopub.execute_input": "2024-03-28T03:53:04.940718Z", "iopub.status.busy": "2024-03-28T03:53:04.939798Z", "iopub.status.idle": "2024-03-28T03:53:04.948324Z", "shell.execute_reply": "2024-03-28T03:53:04.947106Z" }, "id": "FqfebeAdT073", "papermill": { "duration": 0.147412, "end_time": "2024-03-28T03:53:04.951208", "exception": false, "start_time": "2024-03-28T03:53:04.803796", "status": "completed" }, "tags": [] }, "outputs": [], "source": [ "# Save to 8bit Q8_0\n", "if False: model.save_pretrained_gguf(\"model\", tokenizer,)\n", "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, token = \"\")\n", "\n", "# Save to 16bit GGUF\n", "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"f16\")\n", "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"f16\", token = \"\")\n", "\n", "# Save to q4_k_m GGUF\n", "if False: model.save_pretrained_gguf(\"model\", tokenizer, quantization_method = \"q4_k_m\")\n", "if False: model.push_to_hub_gguf(\"hf/model\", tokenizer, quantization_method = \"q4_k_m\", token = \"\")" ] }, { "cell_type": "markdown", "id": "974bde3a", "metadata": { "id": "bDp0zNpwe6U_", "papermill": { "duration": 0.159571, "end_time": "2024-03-28T03:53:05.263051", "exception": false, "start_time": "2024-03-28T03:53:05.103480", "status": "completed" }, "tags": [] }, "source": [ "Now, use the `model-unsloth.gguf` file or `model-unsloth-Q4_K_M.gguf` file in `llama.cpp` or a UI based system like `GPT4All`. You can install GPT4All by going [here](https://gpt4all.io/index.html)." ] }, { "cell_type": "markdown", "id": "c25b0c14", "metadata": { "id": "Zt9CHJqO6p30", "papermill": { "duration": 0.126368, "end_time": "2024-03-28T03:53:05.527719", "exception": false, "start_time": "2024-03-28T03:53:05.401351", "status": "completed" }, "tags": [] }, "source": [ "And we're done! If you have any questions on Unsloth, we have a [Discord](https://discord.gg/u54VK8m8tk) channel! If you find any bugs or want to keep updated with the latest LLM stuff, or need help, join projects etc, feel free to join our Discord!\n", "\n", "Some other links:\n", "1. Zephyr DPO 2x faster [free Colab](https://colab.research.google.com/drive/15vttTpzzVXv_tJwEk-hIcQ0S9FcEWvwP?usp=sharing)\n", "2. Llama 7b 2x faster [free Colab](https://colab.research.google.com/drive/1lBzz5KeZJKXjvivbYvmGarix9Ao6Wxe5?usp=sharing)\n", "3. TinyLlama 4x faster full Alpaca 52K in 1 hour [free Colab](https://colab.research.google.com/drive/1AZghoNBQaMDgWJpi4RbffGM1h6raLUj9?usp=sharing)\n", "4. CodeLlama 34b 2x faster [A100 on Colab](https://colab.research.google.com/drive/1y7A0AxE3y8gdj4AVkl2aZX47Xu3P1wJT?usp=sharing)\n", "5. Mistral 7b [free Kaggle version](https://www.kaggle.com/code/danielhanchen/kaggle-mistral-7b-unsloth-notebook)\n", "6. We also did a [blog](https://huggingface.co/blog/unsloth-trl) with 🤗 HuggingFace, and we're in the TRL [docs](https://huggingface.co/docs/trl/main/en/sft_trainer#accelerate-fine-tuning-2x-using-unsloth)!\n", "7. Text completions like novel writing [notebook](https://colab.research.google.com/drive/1ef-tab5bhkvWmBOObepl1WgJvfvSzn5Q?usp=sharing)\n", "9. Gemma 6 trillion tokens is 2.5x faster! [free Colab](https://colab.research.google.com/drive/10NbwlsRChbma1v55m8LAPYG15uQv6HLo?usp=sharing)\n", "\n", "

\n", " \n", " \n", " Support our work if you can! Thanks!\n", "
" ] } ], "metadata": { "accelerator": "GPU", "colab": { "gpuType": "T4", "provenance": [] }, "kaggle": { "accelerator": "nvidiaTeslaT4", "dataSources": [ { "databundleVersionId": 8069943, "datasetId": 4675483, "sourceId": 7960221, "sourceType": "datasetVersion" } ], "dockerImageVersionId": 30674, "isGpuEnabled": true, "isInternetEnabled": true, "language": "python", "sourceType": "notebook" }, "kernelspec": { "display_name": "Python 3", "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" }, "papermill": { "default_parameters": {}, "duration": 13460.036096, "end_time": "2024-03-28T03:53:09.311636", "environment_variables": {}, "exception": null, "input_path": "__notebook__.ipynb", "output_path": "__notebook__.ipynb", "parameters": {}, "start_time": "2024-03-28T00:08:49.275540", "version": "2.5.0" }, "widgets": { "application/vnd.jupyter.widget-state+json": { "state": { "0115b7fb1d69489db936630116a2fd95": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "0291f4d1f4734954946a71afef1e1519": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_158f6c4ac7424b11b5c52e11c44b7048", "IPY_MODEL_a3f2617affcc4004a6c90a0aff265efa", "IPY_MODEL_32872e40c0614d86b196c45a6daf6f0f" ], "layout": "IPY_MODEL_d181e166c5624b939f1e52ea36f0b501" } }, "07b887a58fa24b6bbac72e1912ce6f2d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c923307d2ec34dcbb6ffc9c72d6bd907", "placeholder": "​", "style": "IPY_MODEL_3fea601e40ad410e9fcbd3f8746e0114", "value": " 493k/493k [00:00<00:00, 32.6MB/s]" } }, "0ae97a9e92204ba3adeda272690ca00a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_dfc5e79bc6df4103862801033bf223c4", "max": 10000, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_80730c77f59f4d77a7309968c3565eff", "value": 10000 } }, "0aea08bb4b424c028157fc47920880ba": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e8060f5acdc44fb4b08b9031cda127be", "placeholder": "​", "style": "IPY_MODEL_83892ec619ff46d69a90e59fb1a31699", "value": " 438/438 [00:00<00:00, 36.5kB/s]" } }, "0b7256cbb0df4612892401684edf4c6b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "0c08cdcc7686498f9dfca58fd546aa81": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "0d0bc50934304ebbbd5767774c1bba6c": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "107e30bda0f7447ba2cae4b4b8e439d8": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1173bc14f32e46e99dc6860367629ed0": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1334bfd9e02f46baaced48e306753b61": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_5e3a5f9429134ac5bae37c33e20141f4", "max": 493443, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_645835ede2a64a698f3e7ae720ebb524", "value": 493443 } }, "1430fff1572a43fbadecedb54630c004": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "158f6c4ac7424b11b5c52e11c44b7048": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_cfdedb4f201c4a1d82c6dd2c19d66eab", "placeholder": "​", "style": "IPY_MODEL_1d2abbae10d5489ca31f2923e3608ce5", "value": "model.safetensors: 100%" } }, "1990a051263f4ecba55c2d190b89d18a": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "1a6305f14afe472c911c243151a7d754": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_f5610eccab294c99ab9004d5cd496185", "placeholder": "​", "style": "IPY_MODEL_5971293c1eb243e9835079846e57e888", "value": "tokenizer.model: 100%" } }, "1d2abbae10d5489ca31f2923e3608ce5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "22ac3169e6a74ef59352c9c1a633940a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_3524bea482354033a8867f5d8808e2bf", "placeholder": "​", "style": "IPY_MODEL_ca92331767b848c5af22af298c030b7d", "value": " 579/579 [00:00<00:00, 34.5kB/s]" } }, "235497034e5c4a3293591576999865e8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_d368cc755f8142f7852135fcac43007b", "placeholder": "​", "style": "IPY_MODEL_53494ae85aea477c9daac23b952ebd01", "value": "Map (num_proc=2): 100%" } }, "2543f037a9b048b6a49d074fac474e7a": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "32872e40c0614d86b196c45a6daf6f0f": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e5601c035def4d1ab1e146370d3c0dc9", "placeholder": "​", "style": "IPY_MODEL_e8d7de2bb23a4d67b5f9e8b72e8b6e86", "value": " 4.13G/4.13G [00:23<00:00, 207MB/s]" } }, "3524bea482354033a8867f5d8808e2bf": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "374a7e4da1474ba1b4827d867f1a49ad": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "3fea601e40ad410e9fcbd3f8746e0114": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "430e25b60ae544ca932139c6232e8580": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_8eb0d1b9b2e54c5f8515768af89677aa", "placeholder": "​", "style": "IPY_MODEL_6867905d03624962a4b4ebcf818ea218", "value": "generation_config.json: 100%" } }, "4646579350cb4e44b075a18f9eee2d33": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "46660e1d775d4280b3d942b03d1bb54e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "4728bc10d9e64cee99025ee07689a449": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "48d009073a83434f946f292e830a371d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "50b8d4fbd7064930bbdf338796e9f09b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_5177a503e53a4fb38db35b3f13400ef6", "IPY_MODEL_c858048f53f94de2a1b0a1982834c358", "IPY_MODEL_22ac3169e6a74ef59352c9c1a633940a" ], "layout": "IPY_MODEL_ab97cbd99a3c4013a9ad37fabbb1cc9f" } }, "5177a503e53a4fb38db35b3f13400ef6": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_1990a051263f4ecba55c2d190b89d18a", "placeholder": "​", "style": "IPY_MODEL_a7298a133c0c4735afb22c3622b47124", "value": "README.md: 100%" } }, "528c2302fc7a480895a850916b8efaba": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "533ef0f3916b423cbc151d4b1929030e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "53494ae85aea477c9daac23b952ebd01": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "54a9cc9d3fea4b2f84a90d9540654950": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "58648d0ab785418089b24914c46df7a4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_e9db2da5e7604322a8ef642e23eb9e3d", "IPY_MODEL_f2786dfcd82a4e14b70e5bae4a78fe51", "IPY_MODEL_5e3e1df5ad73479cb78e29820aba2f93" ], "layout": "IPY_MODEL_528c2302fc7a480895a850916b8efaba" } }, "59233cb5bb5849d0800cde9d3c129184": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_eeef8455b81547249bff4b71af02f6b1", "IPY_MODEL_5f2c77ad6e1f4c1091016b86703586e9", "IPY_MODEL_0aea08bb4b424c028157fc47920880ba" ], "layout": "IPY_MODEL_d8e77b14b649416bbe4f177d7c3013ed" } }, "5971293c1eb243e9835079846e57e888": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "5e3a5f9429134ac5bae37c33e20141f4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "5e3e1df5ad73479cb78e29820aba2f93": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_bf88208e773c423b904ce0f8820f85bc", "placeholder": "​", "style": "IPY_MODEL_54a9cc9d3fea4b2f84a90d9540654950", "value": " 1.05k/1.05k [00:00<00:00, 81.7kB/s]" } }, "5f2c77ad6e1f4c1091016b86703586e9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_ff7a5292b7d649e3a089c5efa790122e", "max": 438, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_e1cfa28343e844c1ae94eb516a91c2b4", "value": 438 } }, "637ccbae2ae14930be31fd9484a86b52": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b0496f143171468fa45614691e9a47f8", "max": 116, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_c03125a200e1408fbb7fa0a20abebda0", "value": 116 } }, "645835ede2a64a698f3e7ae720ebb524": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "6867905d03624962a4b4ebcf818ea218": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "6d4015e9a13b4ce99d5d1b2b1aa86ded": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "71c42de5a7fd4df1a85295b07c33c1e6": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "720036ee71e346ce909dfd8c5e3a7e29": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_1173bc14f32e46e99dc6860367629ed0", "max": 167832240, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_a27d39bbfd7642269fa34a53496bf3c9", "value": 167832240 } }, "776a339dd3044e83b7a34444ddc008e2": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "77abdec067904f0081dfd825b2521ec4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_1430fff1572a43fbadecedb54630c004", "placeholder": "​", "style": "IPY_MODEL_0b7256cbb0df4612892401684edf4c6b", "value": "tokenizer.json: 100%" } }, "792a56bc40ea4529886d964473d96954": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "7963938987694831aedd24fd6061a8df": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_dd636d310bfe41d7a22230b10918ffe3", "placeholder": "​", "style": "IPY_MODEL_f364f4bbb7f847f780ffc157ab872703", "value": " 116/116 [00:00<00:00, 8.89kB/s]" } }, "80730c77f59f4d77a7309968c3565eff": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "83892ec619ff46d69a90e59fb1a31699": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "83fd232b47314e42bbe7526e0ab7aecf": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "84af480c5f6c4ad490074ef103af5628": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_77abdec067904f0081dfd825b2521ec4", "IPY_MODEL_d3995c4222f9481b81dd057d8177afd8", "IPY_MODEL_b1040d0671624ccd965ea5f99adbd0d3" ], "layout": "IPY_MODEL_776a339dd3044e83b7a34444ddc008e2" } }, "87f33e5bd27c4885892c9826a384e8a5": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "8eb0d1b9b2e54c5f8515768af89677aa": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "92da558bad0e4330a2b4b3041ed24aad": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_1a6305f14afe472c911c243151a7d754", "IPY_MODEL_1334bfd9e02f46baaced48e306753b61", "IPY_MODEL_07b887a58fa24b6bbac72e1912ce6f2d" ], "layout": "IPY_MODEL_46660e1d775d4280b3d942b03d1bb54e" } }, "944f3bb3fc0f4ef594424d1ed90f391b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_430e25b60ae544ca932139c6232e8580", "IPY_MODEL_637ccbae2ae14930be31fd9484a86b52", "IPY_MODEL_7963938987694831aedd24fd6061a8df" ], "layout": "IPY_MODEL_b94ada6bb88f48e0a53f8a048b05d21f" } }, "9a80eab1ff094eab808ae272670a4f54": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "9aeb5170934f4e7da9748e8859e40e30": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_b92b53c1c7f7451dafcc0e12c701040d", "IPY_MODEL_e6b7217de79c44429aa4ca0cace148d5", "IPY_MODEL_e7aead7914b54afa8c293ef84bb3e2b0" ], "layout": "IPY_MODEL_bc9b2ac4aead46daa51e5d14cf3600c1" } }, "9fd39fcb80594936a1b160dfe290877b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a03228389e2841db96cafad58e0a45f1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "a12807eb4e4f4ad7bcd78339c990cdd4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "a24ef002e2284485b815a060326d1754": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "a27d39bbfd7642269fa34a53496bf3c9": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "a3f2617affcc4004a6c90a0aff265efa": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_71c42de5a7fd4df1a85295b07c33c1e6", "max": 4125687906, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_a24ef002e2284485b815a060326d1754", "value": 4125687906 } }, "a7298a133c0c4735afb22c3622b47124": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "a96c934ca8474a3a8376256b78e9eedf": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "ab97cbd99a3c4013a9ad37fabbb1cc9f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "aeb4c56bfa5f44dfa78b95944c76e1cd": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e5a882949c3346808f857cf04d74d7de", "placeholder": "​", "style": "IPY_MODEL_0115b7fb1d69489db936630116a2fd95", "value": " 10000/10000 [00:04<00:00, 2544.61 examples/s]" } }, "b0496f143171468fa45614691e9a47f8": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "b1040d0671624ccd965ea5f99adbd0d3": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_533ef0f3916b423cbc151d4b1929030e", "placeholder": "​", "style": "IPY_MODEL_c6264af6bcf3482caefca09fce59935b", "value": " 1.80M/1.80M [00:00<00:00, 25.2MB/s]" } }, "b178f8303b8548d49eb4d1bd4e419f6e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "b83b5e49b46742f1b266dc5f96fa7c73": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "b92b53c1c7f7451dafcc0e12c701040d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_b178f8303b8548d49eb4d1bd4e419f6e", "placeholder": "​", "style": "IPY_MODEL_6d4015e9a13b4ce99d5d1b2b1aa86ded", "value": "tokenizer_config.json: 100%" } }, "b94ada6bb88f48e0a53f8a048b05d21f": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "bc9b2ac4aead46daa51e5d14cf3600c1": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "bf88208e773c423b904ce0f8820f85bc": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c03125a200e1408fbb7fa0a20abebda0": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "c112e03f254a4cfe92ae9e0d584aa462": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_e0406a70ccb64deb833e45b38f3a680e", "placeholder": "​", "style": "IPY_MODEL_e18b8e5bfe714bc680f59a70ac38c014", "value": "adapter_model.safetensors: 100%" } }, "c6135b0b86f6471181ee3cf4945652c8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_0c08cdcc7686498f9dfca58fd546aa81", "placeholder": "​", "style": "IPY_MODEL_a96c934ca8474a3a8376256b78e9eedf", "value": " 168M/168M [00:04<00:00, 31.3MB/s]" } }, "c6264af6bcf3482caefca09fce59935b": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "c858048f53f94de2a1b0a1982834c358": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_a12807eb4e4f4ad7bcd78339c990cdd4", "max": 579, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_0d0bc50934304ebbbd5767774c1bba6c", "value": 579 } }, "c8edb73b6d7f4e97a737a3bfd67d8a75": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "c923307d2ec34dcbb6ffc9c72d6bd907": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ca92331767b848c5af22af298c030b7d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "cd246bcf2d034bb2af58ceb7524df6c1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_c112e03f254a4cfe92ae9e0d584aa462", "IPY_MODEL_720036ee71e346ce909dfd8c5e3a7e29", "IPY_MODEL_c6135b0b86f6471181ee3cf4945652c8" ], "layout": "IPY_MODEL_4646579350cb4e44b075a18f9eee2d33" } }, "cfdedb4f201c4a1d82c6dd2c19d66eab": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d181e166c5624b939f1e52ea36f0b501": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d368cc755f8142f7852135fcac43007b": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "d3995c4222f9481b81dd057d8177afd8": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_c8edb73b6d7f4e97a737a3bfd67d8a75", "max": 1795303, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_a03228389e2841db96cafad58e0a45f1", "value": 1795303 } }, "d8e77b14b649416bbe4f177d7c3013ed": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "dd636d310bfe41d7a22230b10918ffe3": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "dfc5e79bc6df4103862801033bf223c4": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e0406a70ccb64deb833e45b38f3a680e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e18b8e5bfe714bc680f59a70ac38c014": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e1cfa28343e844c1ae94eb516a91c2b4": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "ProgressStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "ProgressStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "bar_color": null, "description_width": "" } }, "e363d483a5134f5d873c11f936d2d9f5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HBoxModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HBoxModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HBoxView", "box_style": "", "children": [ "IPY_MODEL_235497034e5c4a3293591576999865e8", "IPY_MODEL_0ae97a9e92204ba3adeda272690ca00a", "IPY_MODEL_aeb4c56bfa5f44dfa78b95944c76e1cd" ], "layout": "IPY_MODEL_9fd39fcb80594936a1b160dfe290877b" } }, "e5601c035def4d1ab1e146370d3c0dc9": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e5a882949c3346808f857cf04d74d7de": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e6b7217de79c44429aa4ca0cace148d5": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_374a7e4da1474ba1b4827d867f1a49ad", "max": 971, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_48d009073a83434f946f292e830a371d", "value": 971 } }, "e7aead7914b54afa8c293ef84bb3e2b0": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_107e30bda0f7447ba2cae4b4b8e439d8", "placeholder": "​", "style": "IPY_MODEL_792a56bc40ea4529886d964473d96954", "value": " 971/971 [00:00<00:00, 74.7kB/s]" } }, "e8060f5acdc44fb4b08b9031cda127be": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "e8d7de2bb23a4d67b5f9e8b72e8b6e86": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "e9db2da5e7604322a8ef642e23eb9e3d": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_9a80eab1ff094eab808ae272670a4f54", "placeholder": "​", "style": "IPY_MODEL_2543f037a9b048b6a49d074fac474e7a", "value": "config.json: 100%" } }, "eeef8455b81547249bff4b71af02f6b1": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "HTMLModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "HTMLModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "HTMLView", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_87f33e5bd27c4885892c9826a384e8a5", "placeholder": "​", "style": "IPY_MODEL_b83b5e49b46742f1b266dc5f96fa7c73", "value": "special_tokens_map.json: 100%" } }, "f2786dfcd82a4e14b70e5bae4a78fe51": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "FloatProgressModel", "state": { "_dom_classes": [], "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "FloatProgressModel", "_view_count": null, "_view_module": "@jupyter-widgets/controls", "_view_module_version": "1.5.0", "_view_name": "ProgressView", "bar_style": "success", "description": "", "description_tooltip": null, "layout": "IPY_MODEL_83fd232b47314e42bbe7526e0ab7aecf", "max": 1055, "min": 0, "orientation": "horizontal", "style": "IPY_MODEL_4728bc10d9e64cee99025ee07689a449", "value": 1055 } }, "f364f4bbb7f847f780ffc157ab872703": { "model_module": "@jupyter-widgets/controls", "model_module_version": "1.5.0", "model_name": "DescriptionStyleModel", "state": { "_model_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_model_name": "DescriptionStyleModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "StyleView", "description_width": "" } }, "f5610eccab294c99ab9004d5cd496185": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } }, "ff7a5292b7d649e3a089c5efa790122e": { "model_module": "@jupyter-widgets/base", "model_module_version": "1.2.0", "model_name": "LayoutModel", "state": { "_model_module": "@jupyter-widgets/base", "_model_module_version": "1.2.0", "_model_name": "LayoutModel", "_view_count": null, "_view_module": "@jupyter-widgets/base", "_view_module_version": "1.2.0", "_view_name": "LayoutView", "align_content": null, "align_items": null, "align_self": null, "border": null, "bottom": null, "display": null, "flex": null, "flex_flow": null, "grid_area": null, "grid_auto_columns": null, "grid_auto_flow": null, "grid_auto_rows": null, "grid_column": null, "grid_gap": null, "grid_row": null, "grid_template_areas": null, "grid_template_columns": null, "grid_template_rows": null, "height": null, "justify_content": null, "justify_items": null, "left": null, "margin": null, "max_height": null, "max_width": null, "min_height": null, "min_width": null, "object_fit": null, "object_position": null, "order": null, "overflow": null, "overflow_x": null, "overflow_y": null, "padding": null, "right": null, "top": null, "visibility": null, "width": null } } }, "version_major": 2, "version_minor": 0 } } }, "nbformat": 4, "nbformat_minor": 5 }