diff --git "a/notebook/GPT2_DrugsCom_DepressionReviews_FineTuning.ipynb" "b/notebook/GPT2_DrugsCom_DepressionReviews_FineTuning.ipynb" new file mode 100644--- /dev/null +++ "b/notebook/GPT2_DrugsCom_DepressionReviews_FineTuning.ipynb" @@ -0,0 +1,8340 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "source": [ + "# Fine-Tuning GPT-2 on Drugs.com Reviews for Depression\n", + "\n", + "**Author**: Zakia Salod\n", + "\n", + "**Affiliation**: University of KwaZulu-Natal (UKZN), Durban, South Africa\n", + "\n", + "**Contact**: zakia.salod@gmail.com\n", + "\n", + "**Machine Used**: Google Colab T4 GPU\n", + "\n", + "**Last Updated**: 9 December 2023\n", + "\n", + "**Description**:\n", + "This notebook demonstrates the process of fine-tuning the GPT-2 model using the Drugs.com reviews dataset, focusing specifically on reviews related to depression. The notebook covers the steps of loading and preprocessing the dataset, initializing and preparing the GPT-2 model for fine-tuning, and the fine-tuning process itself. Post-training, the notebook illustrates how to save and push the fine-tuned model to the Hugging Face Hub. This exercise aims to enhance GPT-2's ability to generate more relevant and insightful text related to depression drug reviews.\n", + "\n", + "\n", + "**License**:\n", + "This work is licensed under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0). Free for educational and research use.\n", + "\n" + ], + "metadata": { + "id": "SlML_A8WXRKX" + } + }, + { + "cell_type": "markdown", + "metadata": { + "id": "kJK4WrJB4JR1" + }, + "source": [ + "## STEP 1: SETTING UP THE ENVIRONMENT" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "zzrRM4P14M7-" + }, + "source": [ + "### Load Necessary Libraries" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "zbzxLSs_tKQ4" + }, + "outputs": [], + "source": [ + "# Enable automatic module reloading to reflect changes in external .py files\n", + "%load_ext autoreload\n", + "# Reload all modules before executing code, keeping modules up-to-date\n", + "%autoreload 2" + ] + }, + { + "cell_type": "markdown", + "source": [ + "### Install Required Packages" + ], + "metadata": { + "id": "fq1xfyKlf_Ea" + } + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "Bv85wGPxto3O", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "dab3659e-59ab-41a4-9a70-838773c85c5a" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Collecting git+https://github.com/huggingface/transformers\n", + " Cloning https://github.com/huggingface/transformers to /tmp/pip-req-build-44ijr861\n", + " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers /tmp/pip-req-build-44ijr861\n", + " Resolved https://github.com/huggingface/transformers to commit df5c5c62ae253055336f5bb0828ca8e3e15ab6bd\n", + " Installing build dependencies ... \u001b[?25l\u001b[?25hdone\n", + " Getting requirements to build wheel ... \u001b[?25l\u001b[?25hdone\n", + " Preparing metadata (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (3.13.1)\n", + "Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (0.19.4)\n", + "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (1.23.5)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (23.2)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (6.0.1)\n", + "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (2023.6.3)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (2.31.0)\n", + "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (0.15.0)\n", + "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (0.4.1)\n", + "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers==4.36.0.dev0) (4.66.1)\n", + "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers==4.36.0.dev0) (2023.6.0)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers==4.36.0.dev0) (4.5.0)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.36.0.dev0) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.36.0.dev0) (3.6)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.36.0.dev0) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.36.0.dev0) (2023.11.17)\n", + "Building wheels for collected packages: transformers\n", + " Building wheel for transformers (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", + " Created wheel for transformers: filename=transformers-4.36.0.dev0-py3-none-any.whl size=8195433 sha256=79b5b0d64790d529619e06ffc24ad2f2a2692b0a7d84d20a1e0c4dae56550d23\n", + " Stored in directory: /tmp/pip-ephem-wheel-cache-ogqdggii/wheels/c0/14/d6/6c9a5582d2ac191ec0a483be151a4495fe1eb2a6706ca49f1b\n", + "Successfully built transformers\n", + "Installing collected packages: transformers\n", + " Attempting uninstall: transformers\n", + " Found existing installation: transformers 4.35.2\n", + " Uninstalling transformers-4.35.2:\n", + " Successfully uninstalled transformers-4.35.2\n", + "Successfully installed transformers-4.36.0.dev0\n" + ] + } + ], + "source": [ + "!pip install git+https://github.com/huggingface/transformers" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "ZTZrScZY6NB1", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "5342e849-426d-437f-a9c2-b75adfbcb4bf" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Collecting datasets\n", + " Downloading datasets-2.15.0-py3-none-any.whl (521 kB)\n", + "\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/521.2 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━\u001b[0m\u001b[90m╺\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m143.4/521.2 kB\u001b[0m \u001b[31m4.6 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m521.2/521.2 kB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting evaluate\n", + " Downloading evaluate-0.4.1-py3-none-any.whl (84 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.1/84.1 kB\u001b[0m \u001b[31m11.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.1.0+cu118)\n", + "Collecting wandb\n", + " Downloading wandb-0.16.1-py3-none-any.whl (2.1 MB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.1/2.1 MB\u001b[0m \u001b[31m31.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.23.5)\n", + "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (9.0.0)\n", + "Collecting pyarrow-hotfix (from datasets)\n", + " Downloading pyarrow_hotfix-0.6-py3-none-any.whl (7.9 kB)\n", + "Collecting dill<0.3.8,>=0.3.0 (from datasets)\n", + " Downloading dill-0.3.7-py3-none-any.whl (115 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m15.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)\n", + "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)\n", + "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.1)\n", + "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets) (3.4.1)\n", + "Collecting multiprocess (from datasets)\n", + " Downloading multiprocess-0.70.15-py310-none-any.whl (134 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m18.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: fsspec[http]<=2023.10.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n", + "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.1)\n", + "Requirement already satisfied: huggingface-hub>=0.18.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.19.4)\n", + "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (23.2)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n", + "Collecting responses<0.19 (from evaluate)\n", + " Downloading responses-0.18.0-py3-none-any.whl (38 kB)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch) (3.13.1)\n", + "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch) (4.5.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch) (3.2.1)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch) (3.1.2)\n", + "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch) (2.1.0)\n", + "Requirement already satisfied: Click!=8.0.0,>=7.1 in /usr/local/lib/python3.10/dist-packages (from wandb) (8.1.7)\n", + "Collecting GitPython!=3.1.29,>=1.0.0 (from wandb)\n", + " Downloading GitPython-3.1.40-py3-none-any.whl (190 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m190.6/190.6 kB\u001b[0m \u001b[31m23.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: psutil>=5.0.0 in /usr/local/lib/python3.10/dist-packages (from wandb) (5.9.5)\n", + "Collecting sentry-sdk>=1.0.0 (from wandb)\n", + " Downloading sentry_sdk-1.38.0-py2.py3-none-any.whl (252 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m252.8/252.8 kB\u001b[0m \u001b[31m28.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hCollecting docker-pycreds>=0.4.0 (from wandb)\n", + " Downloading docker_pycreds-0.4.0-py2.py3-none-any.whl (9.0 kB)\n", + "Collecting setproctitle (from wandb)\n", + " Downloading setproctitle-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (30 kB)\n", + "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from wandb) (67.7.2)\n", + "Requirement already satisfied: appdirs>=1.4.3 in /usr/local/lib/python3.10/dist-packages (from wandb) (1.4.4)\n", + "Requirement already satisfied: protobuf!=4.21.0,<5,>=3.19.0 in /usr/local/lib/python3.10/dist-packages (from wandb) (3.20.3)\n", + "Requirement already satisfied: six>=1.4.0 in /usr/local/lib/python3.10/dist-packages (from docker-pycreds>=0.4.0->wandb) (1.16.0)\n", + "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.1.0)\n", + "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.4)\n", + "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.3)\n", + "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.0)\n", + "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n", + "Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n", + "Collecting gitdb<5,>=4.0.1 (from GitPython!=3.1.29,>=1.0.0->wandb)\n", + " Downloading gitdb-4.0.11-py3-none-any.whl (62 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m62.7/62.7 kB\u001b[0m \u001b[31m9.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.6)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2023.11.17)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch) (2.1.3)\n", + "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n", + "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.3.post1)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch) (1.3.0)\n", + "Collecting smmap<6,>=3.0.1 (from gitdb<5,>=4.0.1->GitPython!=3.1.29,>=1.0.0->wandb)\n", + " Downloading smmap-5.0.1-py3-none-any.whl (24 kB)\n", + "Installing collected packages: smmap, setproctitle, sentry-sdk, pyarrow-hotfix, docker-pycreds, dill, responses, multiprocess, gitdb, GitPython, wandb, datasets, evaluate\n", + "Successfully installed GitPython-3.1.40 datasets-2.15.0 dill-0.3.7 docker-pycreds-0.4.0 evaluate-0.4.1 gitdb-4.0.11 multiprocess-0.70.15 pyarrow-hotfix-0.6 responses-0.18.0 sentry-sdk-1.38.0 setproctitle-1.3.3 smmap-5.0.1 wandb-0.16.1\n" + ] + } + ], + "source": [ + "!pip install datasets evaluate torch wandb" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "CHbwWz_gH1qc", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "18979ebb-9fce-4d87-dccf-ddae7d9df25c" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Collecting accelerate\n", + " Downloading accelerate-0.25.0-py3-none-any.whl (265 kB)\n", + "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m265.7/265.7 kB\u001b[0m \u001b[31m5.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", + "\u001b[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate) (1.23.5)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (23.2)\n", + "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n", + "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate) (6.0.1)\n", + "Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.1.0+cu118)\n", + "Requirement already satisfied: huggingface-hub in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.19.4)\n", + "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from accelerate) (0.4.1)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.13.1)\n", + "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (4.5.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.2.1)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.2)\n", + "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2023.6.0)\n", + "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (2.1.0)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (2.31.0)\n", + "Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub->accelerate) (4.66.1)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (2.1.3)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (3.6)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub->accelerate) (2023.11.17)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->accelerate) (1.3.0)\n", + "Installing collected packages: accelerate\n", + "Successfully installed accelerate-0.25.0\n" + ] + } + ], + "source": [ + "!pip install accelerate -U" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "8ClR-_ktH6-3", + "colab": { + "base_uri": "https://localhost:8080/" + }, + "outputId": "1bc58861-c84b-4b0d-bd02-87f8fb39fbf0" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Requirement already satisfied: transformers[torch] in /usr/local/lib/python3.10/dist-packages (4.36.0.dev0)\n", + "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (3.13.1)\n", + "Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.19.4)\n", + "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (1.23.5)\n", + "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (23.2)\n", + "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (6.0.1)\n", + "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2023.6.3)\n", + "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.31.0)\n", + "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.15.0)\n", + "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.4.1)\n", + "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (4.66.1)\n", + "Requirement already satisfied: torch!=1.12.0,>=1.10 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.1.0+cu118)\n", + "Requirement already satisfied: accelerate>=0.21.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.25.0)\n", + "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.21.0->transformers[torch]) (5.9.5)\n", + "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (2023.6.0)\n", + "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (4.5.0)\n", + "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (1.12)\n", + "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (3.2.1)\n", + "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (3.1.2)\n", + "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch!=1.12.0,>=1.10->transformers[torch]) (2.1.0)\n", + "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.3.2)\n", + "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.6)\n", + "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2.0.7)\n", + "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2023.11.17)\n", + "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch!=1.12.0,>=1.10->transformers[torch]) (2.1.3)\n", + "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch!=1.12.0,>=1.10->transformers[torch]) (1.3.0)\n" + ] + } + ], + "source": [ + "!pip install transformers[torch]" + ] + }, + { + "cell_type": "markdown", + "source": [ + "### Import Necessary Libraries" + ], + "metadata": { + "id": "GXDAGYt9gFFM" + } + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "ZPQo3nOFtpX-" + }, + "outputs": [], + "source": [ + "import numpy as np\n", + "from datasets import load_dataset\n", + "from datasets import concatenate_datasets\n", + "from transformers import GPT2Tokenizer\n", + "from transformers import GPT2LMHeadModel\n", + "import html\n", + "import re\n", + "from collections import Counter\n", + "import pandas as pd" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "CAc15TpfT0m6" + }, + "source": [ + "### Initialize Weights & Biases for Tracking" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "gu1-uIyZT179" + }, + "outputs": [], + "source": [ + "# Import Weights & Biases for experiment tracking\n", + "import wandb" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "FAcoX4eniLWc", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 211 + }, + "outputId": "5726f50d-2232-44bc-c4fb-a8cd9c8fe69f" + }, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "application/javascript": [ + "\n", + " window._wandbApiKey = new Promise((resolve, reject) => {\n", + " function loadScript(url) {\n", + " return new Promise(function(resolve, reject) {\n", + " let newScript = document.createElement(\"script\");\n", + " newScript.onerror = reject;\n", + " newScript.onload = resolve;\n", + " document.body.appendChild(newScript);\n", + " newScript.src = url;\n", + " });\n", + " }\n", + " loadScript(\"https://cdn.jsdelivr.net/npm/postmate/build/postmate.min.js\").then(() => {\n", + " const iframe = document.createElement('iframe')\n", + " iframe.style.cssText = \"width:0;height:0;border:none\"\n", + " document.body.appendChild(iframe)\n", + " const handshake = new Postmate({\n", + " container: iframe,\n", + " url: 'https://wandb.ai/authorize'\n", + " });\n", + " const timeout = setTimeout(() => reject(\"Couldn't auto authenticate\"), 5000)\n", + " handshake.then(function(child) {\n", + " child.on('authorize', data => {\n", + " clearTimeout(timeout)\n", + " resolve(data)\n", + " });\n", + " });\n", + " })\n", + " });\n", + " " + ] + }, + "metadata": {} + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "\u001b[34m\u001b[1mwandb\u001b[0m: Logging into wandb.ai. (Learn how to deploy a W&B server locally: https://wandb.me/wandb-server)\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: You can find your API key in your browser here: https://wandb.ai/authorize\n", + "wandb: Paste an API key from your profile and hit enter, or press ctrl+c to quit:" + ] + }, + { + "name": "stdout", + "output_type": "stream", + "text": [ + " ··········\n" + ] + }, + { + "output_type": "stream", + "name": "stderr", + "text": [ + "\u001b[34m\u001b[1mwandb\u001b[0m: Appending key for api.wandb.ai to your netrc file: /root/.netrc\n" + ] + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "Tracking run with wandb version 0.16.1" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "Run data is saved locally in /content/wandb/run-20231209_123209-kfb5cx1j" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + "Syncing run jumping-energy-8 to Weights & Biases (docs)
" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + " View project at https://wandb.ai/team-zakia/gpt2-drugscom_depression_reviews" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "" + ], + "text/html": [ + " View run at https://wandb.ai/team-zakia/gpt2-drugscom_depression_reviews/runs/kfb5cx1j" + ] + }, + "metadata": {} + }, + { + "output_type": "execute_result", + "data": { + "text/html": [ + "" + ], + "text/plain": [ + "" + ] + }, + "metadata": {}, + "execution_count": 8 + } + ], + "source": [ + "# Initialize wandb for tracking and visualizing the training\n", + "wandb.init(project=\"gpt2-drugscom_depression_reviews\")" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "LGYKu-eF4ZvJ" + }, + "source": [ + "## STEP 2: LOAD AND PRE-PROCESS DRUG REVIEWS DATASET" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "v_FNuZmvtsY1" + }, + "outputs": [], + "source": [ + "dataset_name = \"Zakia/drugscom_reviews\"" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "DyK71VIut7kf", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 241, + "referenced_widgets": [ + "b45c8c73698048aeaee4d34b28d6a27a", + "90e79e1e73ae489199ff3811dca9adae", + "e59b83647a7f483da05b37429322c469", + "66ec2664647846d8b4da85fee9e32df1", + "6b6eec8ea25445a6bc24b88778e1edbf", + "f2722d9ef4484a2a90ca9d6319d04345", + "9cc770f5d35e421cb07b44c9f7e2a730", + "2c52eb43c73e4c7f8831bd6f71809570", + "02587cf05a5547c4ba874c34bf4cec4b", + "0707b92bf1a84a9384beba55789ce6ba", + "57e880d55b0548a0b3a0f61ccdcc930f", + "10311a17cdf645f69a3edd08ca2cad62", + "a6000f68e93d4bf1a343629032dcef04", + "ac869d78cfe146879a2494579c77277d", + "2e35f836eaed419a8431e0c68e8d2cc1", + "a3d694bb06194b138a7abdbf199a1d81", + "5bdaf9e1d6da4b808b2a704b3c8d973b", + "2e5a51a0fb4c4249b55d8af4b0506eca", + "b4fcbf969be2427b92046a1f528db2a6", + "43c31088bf444fd39578f2fe630dc46e", + "3f7cb58407064ebaa1ec3943309c95c3", + "ce17ffc4033b4866b48d5e61467db6c3", + "0ffc9ba03f924bc0ad48fa82c2e711e7", + "0abb262f82df4d728a8f05bf992a5ec3", + "09e3afd0ba9e4b5298d741ce825fdbfb", + "f069002ce14648c3b0269ae3e377879c", + "1b6b3d597a024cfb9a15573cea12891e", + "e48c988e59b8462babda6b5173a337a6", + "43f34a6373a7449a83d86705351d4957", + "3794962a26714723a2b7d345336db7ec", + "19ee2670c44b46e2906b21a73b27ba88", + "16a81359fc4a40dbb83d185c1db81ebf", + "8970468c315b413abb6541205fc3174d", + "84ba5a9fb669445d88a8f18c86986a65", + "74e6479c15a843c196b26eae181f3b50", + "24f3bb13e552446ca3dbf1d5acdd306e", + "adf7780fbbed4baf90f08b113553e0a3", + "59b48ccd44734f2fb869291b1c52a56b", + "bff2b32d8b624af98814c950bf2934d9", + "8b5cf7a76357475d8156886940ad2790", + "a8a19e8b09a84ea9a29a6dd8312d2110", + "654b39a5572f42bfa93ba73c4b251fbd", + "76464bf094c74cd68f3fb5e9975ff56e", + "1a3a890317814810834c117ffe62f390", + "a6687ff1f33a42988536dc04ccf824ad", + "6e79a05a0f6f4e4c8b0ce54d47180df1", + "c7f71309b9a14d9b85a9953f1c5ef919", + "ad491e5e0a8d4106b6942f20206081f4", + "a08bd346d672441994b14340f57fa298", + "d9166639b16c423fa902ef9a23a6582f", + "0e564d1c6ae8447fb431032ee5d64199", + "c22ad507940c46d0bf34dc5efe8ffee3", + "38331b41172b47fa96b2b7950dd4f94b", + "15038217fa3c4c43990aeb222792feed", + "8bad5a126935481497fdb16ad2dacbb5", + "28b5d0115eb44b9483c9f7d345d644e1", + "5aa2e3b0f8024725a260898904739acb", + "bdb27820a5204529987b9e2df414df78", + "f4f30d7e47864e4c9515ef6195661782", + "c4230c8b74d540afa5d2e885310dbf6b", + "bf9000b17de04dd1bd522f94a3eb1ed9", + "97411c1fec18481cbd5bcab1e794cc7f", + "875e1cbc8e634cbaa00a22ff3c9d62f8", + "52d6693766714e91b126d9180dd03346", + "f247e069bb4147e0b6019d66d851ede9", + "6a509c81bfff4f30bc7d2de029bdc93c", + "36a765c57fc349eab616355610980324", + "210adeaaf64e40db8323e085794e7d7a", + "b8b1a3dfbb984ba08b1c862b26af8dbe", + "304df8debe3f4662a4171221d669798e", + "266e9676bce140b69ad73456851ff499", + "9b0b095167de49f4bc5efb5502b3d41c", + "af16b06528824cc9b0ce63fc4b4738ba", + "daa61ca2c88c49be9a115fb81f01caac", + "5edea6130ae64675a5aecbbaffcc5821", + "1b55987264384ee3bd90ba9e97842b61", + "2a4ea7765a984268a58766f089744cdb" + ] + }, + "outputId": "bd5d0427-c53e-4168-efba-44f64eadee42" + }, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Downloading readme: 0%| | 0.00/6.72k [00:00', '', text) # Remove HTML tags\n", + " return text" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "jSEt0xnfuSQu" + }, + "outputs": [], + "source": [ + "# Clean the reviews of the train set\n", + "# Apply the clean_review function in a batched manner\n", + "def clean_reviews(batch):\n", + " # Apply clean_review to each review in the batch and return the modified batch\n", + " return {\"review\": [clean_review(review) for review in batch[\"review\"]]}" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "llYAOpmpuTad", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 49, + "referenced_widgets": [ + "48f3b3e586f74174a0232079ec543e2c", + "57403d31cdb64f11add87566d4f5a325", + "f9e6f05aeb904395a5d5a8a3ec3b9756", + "5b787cdd23f44cb8805e055ccffdfe40", + "e00ea9a3b8cc433a8dffc1cf9d99f609", + "c6cae5d28bd9480eb1eb5642132d4dd5", + "90e73a35476f4e74aba7c02f329a3536", + "dea3da72e6d946029a3760a594356701", + "5c7f4c3d4ebc47a6ba27aeed52a89add", + "23396629e70847a28c247157d27587e7", + "2262d8d8318e453a92e4ae9b37fa484c" + ] + }, + "outputId": "3815254b-c672-41ad-8227-5a925d00d4d7" + }, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "Map: 0%| | 0/9069 [00:00,\n", + "ignore_data_skip=False,\n", + "include_inputs_for_metrics=False,\n", + "include_num_input_tokens_seen=False,\n", + "include_tokens_per_second=False,\n", + "jit_mode_eval=False,\n", + "label_names=None,\n", + "label_smoothing_factor=0.0,\n", + "learning_rate=5e-05,\n", + "length_column_name=length,\n", + "load_best_model_at_end=False,\n", + "local_rank=0,\n", + "log_level=passive,\n", + "log_level_replica=warning,\n", + "log_on_each_node=True,\n", + "logging_dir=./gpt2-drugscom_depression_reviews/runs/Dec09_12-33-34_8acb048be5fa,\n", + "logging_first_step=False,\n", + "logging_nan_inf_filter=True,\n", + "logging_steps=500,\n", + "logging_strategy=steps,\n", + "lr_scheduler_kwargs={},\n", + "lr_scheduler_type=linear,\n", + "max_grad_norm=1.0,\n", + "max_steps=-1,\n", + "metric_for_best_model=None,\n", + "mp_parameters=,\n", + "neftune_noise_alpha=None,\n", + "no_cuda=False,\n", + "num_train_epochs=5.0,\n", + "optim=adamw_torch,\n", + "optim_args=None,\n", + "output_dir=./gpt2-drugscom_depression_reviews,\n", + "overwrite_output_dir=True,\n", + "past_index=-1,\n", + "per_device_eval_batch_size=8,\n", + "per_device_train_batch_size=2,\n", + "prediction_loss_only=False,\n", + "push_to_hub=False,\n", + "push_to_hub_model_id=None,\n", + "push_to_hub_organization=None,\n", + "push_to_hub_token=,\n", + "ray_scope=last,\n", + "remove_unused_columns=True,\n", + "report_to=['wandb'],\n", + "resume_from_checkpoint=None,\n", + "run_name=./gpt2-drugscom_depression_reviews,\n", + "save_on_each_node=False,\n", + "save_only_model=False,\n", + "save_safetensors=True,\n", + "save_steps=500,\n", + "save_strategy=steps,\n", + "save_total_limit=None,\n", + "seed=42,\n", + "skip_memory_metrics=True,\n", + "split_batches=False,\n", + "tf32=None,\n", + "torch_compile=False,\n", + "torch_compile_backend=None,\n", + "torch_compile_mode=None,\n", + "torchdynamo=None,\n", + "tpu_metrics_debug=False,\n", + "tpu_num_cores=None,\n", + "use_cpu=False,\n", + "use_ipex=False,\n", + "use_legacy_prediction_loop=False,\n", + "use_mps_device=False,\n", + "warmup_ratio=0.0,\n", + "warmup_steps=0,\n", + "weight_decay=0.0,\n", + ")\n", + "Using custom data configuration default-99d8365ea3008c01\n", + "12/09/2023 12:33:40 - INFO - datasets.builder - Using custom data configuration default-99d8365ea3008c01\n", + "Loading Dataset Infos from /usr/local/lib/python3.10/dist-packages/datasets/packaged_modules/text\n", + "12/09/2023 12:33:40 - INFO - datasets.info - Loading Dataset Infos from /usr/local/lib/python3.10/dist-packages/datasets/packaged_modules/text\n", + "Generating dataset text (/root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34)\n", + "12/09/2023 12:33:40 - INFO - datasets.builder - Generating dataset text (/root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34)\n", + "Downloading and preparing dataset text/default to /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34...\n", + "12/09/2023 12:33:40 - INFO - datasets.builder - Downloading and preparing dataset text/default to /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34...\n", + "Downloading data files: 100% 1/1 [00:00<00:00, 7256.58it/s]\n", + "Downloading took 0.0 min\n", + "12/09/2023 12:33:40 - INFO - datasets.download.download_manager - Downloading took 0.0 min\n", + "Checksum Computation took 0.0 min\n", + "12/09/2023 12:33:40 - INFO - datasets.download.download_manager - Checksum Computation took 0.0 min\n", + "Extracting data files: 100% 1/1 [00:00<00:00, 1198.72it/s]\n", + "Generating train split\n", + "12/09/2023 12:33:40 - INFO - datasets.builder - Generating train split\n", + "Generating train split: 12943 examples [00:00, 19902.65 examples/s]\n", + "Unable to verify splits sizes.\n", + "12/09/2023 12:33:41 - INFO - datasets.utils.info_utils - Unable to verify splits sizes.\n", + "Dataset text downloaded and prepared to /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34. Subsequent calls will reuse this data.\n", + "12/09/2023 12:33:41 - INFO - datasets.builder - Dataset text downloaded and prepared to /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34. Subsequent calls will reuse this data.\n", + "Using custom data configuration default-99d8365ea3008c01\n", + "12/09/2023 12:33:41 - INFO - datasets.builder - Using custom data configuration default-99d8365ea3008c01\n", + "Loading Dataset Infos from /usr/local/lib/python3.10/dist-packages/datasets/packaged_modules/text\n", + "12/09/2023 12:33:41 - INFO - datasets.info - Loading Dataset Infos from /usr/local/lib/python3.10/dist-packages/datasets/packaged_modules/text\n", + "Overwrite dataset info from restored data version if exists.\n", + "12/09/2023 12:33:41 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists.\n", + "Loading Dataset info from /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34\n", + "12/09/2023 12:33:41 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34\n", + "Found cached dataset text (/root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34)\n", + "12/09/2023 12:33:41 - INFO - datasets.builder - Found cached dataset text (/root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34)\n", + "Loading Dataset info from /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34\n", + "12/09/2023 12:33:41 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34\n", + "Using custom data configuration default-99d8365ea3008c01\n", + "12/09/2023 12:33:41 - INFO - datasets.builder - Using custom data configuration default-99d8365ea3008c01\n", + "Loading Dataset Infos from /usr/local/lib/python3.10/dist-packages/datasets/packaged_modules/text\n", + "12/09/2023 12:33:41 - INFO - datasets.info - Loading Dataset Infos from /usr/local/lib/python3.10/dist-packages/datasets/packaged_modules/text\n", + "Overwrite dataset info from restored data version if exists.\n", + "12/09/2023 12:33:41 - INFO - datasets.builder - Overwrite dataset info from restored data version if exists.\n", + "Loading Dataset info from /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34\n", + "12/09/2023 12:33:41 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34\n", + "Found cached dataset text (/root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34)\n", + "12/09/2023 12:33:41 - INFO - datasets.builder - Found cached dataset text (/root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34)\n", + "Loading Dataset info from /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34\n", + "12/09/2023 12:33:41 - INFO - datasets.info - Loading Dataset info from /root/.cache/huggingface/datasets/text/default-99d8365ea3008c01/0.0.0/c4a140d10f020282918b5dd1b8a49f0104729c6177f60a6b49ec2a365ec69f34\n", + "[INFO|configuration_utils.py:739] 2023-12-09 12:33:41,848 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/config.json\n", + "[INFO|configuration_utils.py:802] 2023-12-09 12:33:41,850 >> Model config GPT2Config {\n", + " \"_name_or_path\": \"gpt2\",\n", + " \"activation_function\": \"gelu_new\",\n", + " \"architectures\": [\n", + " \"GPT2LMHeadModel\"\n", + " ],\n", + " \"attn_pdrop\": 0.1,\n", + " \"bos_token_id\": 50256,\n", + " \"embd_pdrop\": 0.1,\n", + " \"eos_token_id\": 50256,\n", + " \"initializer_range\": 0.02,\n", + " \"layer_norm_epsilon\": 1e-05,\n", + " \"model_type\": \"gpt2\",\n", + " \"n_ctx\": 1024,\n", + " \"n_embd\": 768,\n", + " \"n_head\": 12,\n", + " \"n_inner\": null,\n", + " \"n_layer\": 12,\n", + " \"n_positions\": 1024,\n", + " \"reorder_and_upcast_attn\": false,\n", + " \"resid_pdrop\": 0.1,\n", + " \"scale_attn_by_inverse_layer_idx\": false,\n", + " \"scale_attn_weights\": true,\n", + " \"summary_activation\": null,\n", + " \"summary_first_dropout\": 0.1,\n", + " \"summary_proj_to_labels\": true,\n", + " \"summary_type\": \"cls_index\",\n", + " \"summary_use_proj\": true,\n", + " \"task_specific_params\": {\n", + " \"text-generation\": {\n", + " \"do_sample\": true,\n", + " \"max_length\": 50\n", + " }\n", + " },\n", + " \"transformers_version\": \"4.36.0.dev0\",\n", + " \"use_cache\": true,\n", + " \"vocab_size\": 50257\n", + "}\n", + "\n", + "[INFO|tokenization_auto.py:578] 2023-12-09 12:33:41,919 >> Could not locate the tokenizer configuration file, will try to use the model config instead.\n", + "[INFO|configuration_utils.py:739] 2023-12-09 12:33:41,991 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/config.json\n", + "[INFO|configuration_utils.py:802] 2023-12-09 12:33:41,992 >> Model config GPT2Config {\n", + " \"_name_or_path\": \"gpt2\",\n", + " \"activation_function\": \"gelu_new\",\n", + " \"architectures\": [\n", + " \"GPT2LMHeadModel\"\n", + " ],\n", + " \"attn_pdrop\": 0.1,\n", + " \"bos_token_id\": 50256,\n", + " \"embd_pdrop\": 0.1,\n", + " \"eos_token_id\": 50256,\n", + " \"initializer_range\": 0.02,\n", + " \"layer_norm_epsilon\": 1e-05,\n", + " \"model_type\": \"gpt2\",\n", + " \"n_ctx\": 1024,\n", + " \"n_embd\": 768,\n", + " \"n_head\": 12,\n", + " \"n_inner\": null,\n", + " \"n_layer\": 12,\n", + " \"n_positions\": 1024,\n", + " \"reorder_and_upcast_attn\": false,\n", + " \"resid_pdrop\": 0.1,\n", + " \"scale_attn_by_inverse_layer_idx\": false,\n", + " \"scale_attn_weights\": true,\n", + " \"summary_activation\": null,\n", + " \"summary_first_dropout\": 0.1,\n", + " \"summary_proj_to_labels\": true,\n", + " \"summary_type\": \"cls_index\",\n", + " \"summary_use_proj\": true,\n", + " \"task_specific_params\": {\n", + " \"text-generation\": {\n", + " \"do_sample\": true,\n", + " \"max_length\": 50\n", + " }\n", + " },\n", + " \"transformers_version\": \"4.36.0.dev0\",\n", + " \"use_cache\": true,\n", + " \"vocab_size\": 50257\n", + "}\n", + "\n", + "[INFO|tokenization_utils_base.py:2026] 2023-12-09 12:33:42,155 >> loading file vocab.json from cache at /root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/vocab.json\n", + "[INFO|tokenization_utils_base.py:2026] 2023-12-09 12:33:42,155 >> loading file merges.txt from cache at /root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/merges.txt\n", + "[INFO|tokenization_utils_base.py:2026] 2023-12-09 12:33:42,155 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/tokenizer.json\n", + "[INFO|tokenization_utils_base.py:2026] 2023-12-09 12:33:42,155 >> loading file added_tokens.json from cache at None\n", + "[INFO|tokenization_utils_base.py:2026] 2023-12-09 12:33:42,155 >> loading file special_tokens_map.json from cache at None\n", + "[INFO|tokenization_utils_base.py:2026] 2023-12-09 12:33:42,155 >> loading file tokenizer_config.json from cache at None\n", + "[INFO|configuration_utils.py:739] 2023-12-09 12:33:42,156 >> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/config.json\n", + "[INFO|configuration_utils.py:802] 2023-12-09 12:33:42,157 >> Model config GPT2Config {\n", + " \"_name_or_path\": \"gpt2\",\n", + " \"activation_function\": \"gelu_new\",\n", + " \"architectures\": [\n", + " \"GPT2LMHeadModel\"\n", + " ],\n", + " \"attn_pdrop\": 0.1,\n", + " \"bos_token_id\": 50256,\n", + " \"embd_pdrop\": 0.1,\n", + " \"eos_token_id\": 50256,\n", + " \"initializer_range\": 0.02,\n", + " \"layer_norm_epsilon\": 1e-05,\n", + " \"model_type\": \"gpt2\",\n", + " \"n_ctx\": 1024,\n", + " \"n_embd\": 768,\n", + " \"n_head\": 12,\n", + " \"n_inner\": null,\n", + " \"n_layer\": 12,\n", + " \"n_positions\": 1024,\n", + " \"reorder_and_upcast_attn\": false,\n", + " \"resid_pdrop\": 0.1,\n", + " \"scale_attn_by_inverse_layer_idx\": false,\n", + " \"scale_attn_weights\": true,\n", + " \"summary_activation\": null,\n", + " \"summary_first_dropout\": 0.1,\n", + " \"summary_proj_to_labels\": true,\n", + " \"summary_type\": \"cls_index\",\n", + " \"summary_use_proj\": true,\n", + " \"task_specific_params\": {\n", + " \"text-generation\": {\n", + " \"do_sample\": true,\n", + " \"max_length\": 50\n", + " }\n", + " },\n", + " \"transformers_version\": \"4.36.0.dev0\",\n", + " \"use_cache\": true,\n", + " \"vocab_size\": 50257\n", + "}\n", + "\n", + "model.safetensors: 100% 548M/548M [00:06<00:00, 78.6MB/s]\n", + "[INFO|modeling_utils.py:3299] 2023-12-09 12:33:49,589 >> loading weights file model.safetensors from cache at /root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/model.safetensors\n", + "[INFO|configuration_utils.py:826] 2023-12-09 12:33:49,639 >> Generate config GenerationConfig {\n", + " \"bos_token_id\": 50256,\n", + " \"eos_token_id\": 50256\n", + "}\n", + "\n", + "[INFO|modeling_utils.py:4139] 2023-12-09 12:33:51,494 >> All model checkpoint weights were used when initializing GPT2LMHeadModel.\n", + "\n", + "[INFO|modeling_utils.py:4147] 2023-12-09 12:33:51,494 >> All the weights of GPT2LMHeadModel were initialized from the model checkpoint at gpt2.\n", + "If your task is similar to the task the model of the checkpoint was trained on, you can already use GPT2LMHeadModel for predictions without further training.\n", + "generation_config.json: 100% 124/124 [00:00<00:00, 629kB/s]\n", + "[INFO|configuration_utils.py:781] 2023-12-09 12:33:51,630 >> loading configuration file generation_config.json from cache at /root/.cache/huggingface/hub/models--gpt2/snapshots/11c5a3d5811f50298f278a704980280950aedb10/generation_config.json\n", + "[INFO|configuration_utils.py:826] 2023-12-09 12:33:51,630 >> Generate config GenerationConfig {\n", + " \"bos_token_id\": 50256,\n", + " \"eos_token_id\": 50256\n", + "}\n", + "\n", + "Running tokenizer on dataset: 0% 0/12296 [00:00> ***** Running training *****\n", + "[INFO|trainer.py:1707] 2023-12-09 12:34:09,306 >> Num examples = 4,308\n", + "[INFO|trainer.py:1708] 2023-12-09 12:34:09,306 >> Num Epochs = 5\n", + "[INFO|trainer.py:1709] 2023-12-09 12:34:09,306 >> Instantaneous batch size per device = 2\n", + "[INFO|trainer.py:1712] 2023-12-09 12:34:09,307 >> Total train batch size (w. parallel, distributed & accumulation) = 2\n", + "[INFO|trainer.py:1713] 2023-12-09 12:34:09,307 >> Gradient Accumulation steps = 1\n", + "[INFO|trainer.py:1714] 2023-12-09 12:34:09,307 >> Total optimization steps = 10,770\n", + "[INFO|trainer.py:1715] 2023-12-09 12:34:09,307 >> Number of trainable parameters = 124,439,808\n", + "[INFO|integration_utils.py:722] 2023-12-09 12:34:09,308 >> Automatic Weights & Biases logging enabled, to disable set os.environ[\"WANDB_DISABLED\"] = \"true\"\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mzakia-salod\u001b[0m (\u001b[33mteam-zakia\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.16.1\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m/content/wandb/run-20231209_123409-bsxtbazc\u001b[0m\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mradiant-firebrand-8\u001b[0m\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/team-zakia/huggingface\u001b[0m\n", + "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/team-zakia/huggingface/runs/bsxtbazc\u001b[0m\n", + "{'loss': 0.7369, 'learning_rate': 4.767873723305478e-05, 'epoch': 0.23}\n", + " 5% 500/10770 [06:09<2:07:10, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 12:40:20,104 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 12:40:20,106 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 12:40:20,107 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 12:40:22,146 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 12:40:22,148 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 12:40:22,148 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-500/special_tokens_map.json\n", + "{'loss': 0.6937, 'learning_rate': 4.535747446610957e-05, 'epoch': 0.46}\n", + " 9% 1000/10770 [12:29<2:00:13, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 12:46:40,220 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 12:46:40,221 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 12:46:40,222 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 12:46:44,783 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 12:46:44,785 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 12:46:44,788 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1000/special_tokens_map.json\n", + "{'loss': 0.6743, 'learning_rate': 4.303621169916435e-05, 'epoch': 0.7}\n", + " 14% 1500/10770 [18:49<1:54:18, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 12:52:59,800 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 12:52:59,801 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 12:52:59,802 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 12:53:01,644 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 12:53:01,645 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 12:53:01,646 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-1500/special_tokens_map.json\n", + "{'loss': 0.6565, 'learning_rate': 4.071494893221913e-05, 'epoch': 0.93}\n", + " 19% 2000/10770 [25:05<1:48:39, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 12:59:15,817 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 12:59:15,818 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 12:59:15,819 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 12:59:17,871 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 12:59:17,872 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 12:59:17,873 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2000/special_tokens_map.json\n", + "{'loss': 0.6237, 'learning_rate': 3.8393686165273915e-05, 'epoch': 1.16}\n", + " 23% 2500/10770 [31:29<1:41:45, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 13:05:39,969 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 13:05:39,971 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 13:05:39,971 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 13:05:43,191 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 13:05:43,192 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 13:05:43,192 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-2500/special_tokens_map.json\n", + "{'loss': 0.6237, 'learning_rate': 3.607242339832869e-05, 'epoch': 1.39}\n", + " 28% 3000/10770 [37:48<1:35:53, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 13:11:58,874 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 13:11:58,876 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 13:11:58,877 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 13:12:00,785 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 13:12:00,787 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 13:12:00,788 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3000/special_tokens_map.json\n", + "{'loss': 0.6167, 'learning_rate': 3.375116063138347e-05, 'epoch': 1.62}\n", + " 32% 3500/10770 [44:04<1:29:41, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 13:18:15,187 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 13:18:15,188 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 13:18:15,189 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 13:18:19,719 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 13:18:19,720 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 13:18:19,721 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-3500/special_tokens_map.json\n", + "{'loss': 0.6143, 'learning_rate': 3.1429897864438255e-05, 'epoch': 1.86}\n", + " 37% 4000/10770 [50:25<1:23:55, 1.34it/s][INFO|trainer.py:2877] 2023-12-09 13:24:35,665 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 13:24:35,667 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 13:24:35,668 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 13:24:37,671 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 13:24:37,672 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 13:24:37,673 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4000/special_tokens_map.json\n", + "{'loss': 0.6003, 'learning_rate': 2.9108635097493035e-05, 'epoch': 2.09}\n", + " 42% 4500/10770 [56:41<1:17:15, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 13:30:52,074 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 13:30:52,076 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 13:30:52,079 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 13:30:54,225 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 13:30:54,227 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 13:30:54,228 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-4500/special_tokens_map.json\n", + "{'loss': 0.5719, 'learning_rate': 2.678737233054782e-05, 'epoch': 2.32}\n", + " 46% 5000/10770 [1:02:58<1:11:11, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 13:37:08,692 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 13:37:08,693 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 13:37:08,694 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 13:37:10,841 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 13:37:10,843 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 13:37:10,846 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5000/special_tokens_map.json\n", + "{'loss': 0.5824, 'learning_rate': 2.44661095636026e-05, 'epoch': 2.55}\n", + " 51% 5500/10770 [1:09:14<1:04:55, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 13:43:25,363 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 13:43:25,364 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 13:43:25,365 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 13:43:27,212 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 13:43:27,214 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 13:43:27,214 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-5500/special_tokens_map.json\n", + "{'loss': 0.5766, 'learning_rate': 2.214484679665738e-05, 'epoch': 2.79}\n", + " 56% 6000/10770 [1:15:31<58:47, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 13:49:41,984 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 13:49:41,986 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 13:49:41,987 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 13:49:43,886 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 13:49:43,887 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 13:49:43,888 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6000/special_tokens_map.json\n", + "{'loss': 0.5798, 'learning_rate': 1.9823584029712165e-05, 'epoch': 3.02}\n", + " 60% 6500/10770 [1:21:47<52:35, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 13:55:58,283 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 13:55:58,284 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 13:55:58,286 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 13:56:00,185 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 13:56:00,187 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 13:56:00,187 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-6500/special_tokens_map.json\n", + "{'loss': 0.5537, 'learning_rate': 1.7502321262766948e-05, 'epoch': 3.25}\n", + " 65% 7000/10770 [1:28:03<46:29, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 14:02:14,355 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 14:02:14,357 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 14:02:14,358 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 14:02:17,406 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 14:02:17,407 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 14:02:17,408 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7000/special_tokens_map.json\n", + "{'loss': 0.5553, 'learning_rate': 1.518105849582173e-05, 'epoch': 3.48}\n", + " 70% 7500/10770 [1:34:22<40:34, 1.34it/s][INFO|trainer.py:2877] 2023-12-09 14:08:33,229 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 14:08:33,231 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 14:08:33,232 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 14:08:35,154 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 14:08:35,155 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 14:08:35,155 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-7500/special_tokens_map.json\n", + "{'loss': 0.5479, 'learning_rate': 1.2859795728876508e-05, 'epoch': 3.71}\n", + " 74% 8000/10770 [1:40:38<34:27, 1.34it/s][INFO|trainer.py:2877] 2023-12-09 14:14:49,206 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 14:14:49,209 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 14:14:49,210 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 14:14:51,216 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 14:14:51,218 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 14:14:51,219 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8000/special_tokens_map.json\n", + "{'loss': 0.5538, 'learning_rate': 1.0538532961931291e-05, 'epoch': 3.95}\n", + " 79% 8500/10770 [1:46:55<27:57, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 14:21:06,112 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 14:21:06,114 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 14:21:06,115 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 14:21:08,009 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 14:21:08,011 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 14:21:08,012 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-8500/special_tokens_map.json\n", + "{'loss': 0.5429, 'learning_rate': 8.217270194986073e-06, 'epoch': 4.18}\n", + " 84% 9000/10770 [1:53:11<21:43, 1.36it/s][INFO|trainer.py:2877] 2023-12-09 14:27:22,134 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 14:27:22,135 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 14:27:22,136 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 14:27:24,023 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 14:27:24,024 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 14:27:24,025 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9000/special_tokens_map.json\n", + "{'loss': 0.5361, 'learning_rate': 5.896007428040855e-06, 'epoch': 4.41}\n", + " 88% 9500/10770 [1:59:27<15:39, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 14:33:38,093 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 14:33:38,095 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 14:33:38,096 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 14:33:39,987 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 14:33:39,988 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 14:33:39,988 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-9500/special_tokens_map.json\n", + "{'loss': 0.5425, 'learning_rate': 3.574744661095636e-06, 'epoch': 4.64}\n", + " 93% 10000/10770 [2:05:51<09:27, 1.36it/s][INFO|trainer.py:2877] 2023-12-09 14:40:02,357 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10000\n", + "[INFO|configuration_utils.py:483] 2023-12-09 14:40:02,358 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10000/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 14:40:02,359 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10000/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 14:40:08,494 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10000/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 14:40:08,501 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10000/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 14:40:08,502 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10000/special_tokens_map.json\n", + "{'loss': 0.5388, 'learning_rate': 1.253481894150418e-06, 'epoch': 4.87}\n", + " 97% 10500/10770 [2:12:12<03:20, 1.35it/s][INFO|trainer.py:2877] 2023-12-09 14:46:23,328 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10500\n", + "[INFO|configuration_utils.py:483] 2023-12-09 14:46:23,330 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10500/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 14:46:23,331 >> Configuration saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10500/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 14:46:25,338 >> Model weights saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10500/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 14:46:25,339 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10500/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 14:46:25,339 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/tmp-checkpoint-10500/special_tokens_map.json\n", + "100% 10770/10770 [2:15:39<00:00, 1.36it/s][INFO|trainer.py:1947] 2023-12-09 14:49:49,384 >> \n", + "\n", + "Training completed. Do not forget to share your model on huggingface.co/models =)\n", + "\n", + "\n", + "{'train_runtime': 8140.1135, 'train_samples_per_second': 2.646, 'train_steps_per_second': 1.323, 'train_loss': 0.5943892072502285, 'epoch': 5.0}\n", + "100% 10770/10770 [2:15:39<00:00, 1.32it/s]\n", + "[INFO|trainer.py:2877] 2023-12-09 14:49:49,424 >> Saving model checkpoint to ./gpt2-drugscom_depression_reviews\n", + "[INFO|configuration_utils.py:483] 2023-12-09 14:49:49,429 >> Configuration saved in ./gpt2-drugscom_depression_reviews/config.json\n", + "[INFO|configuration_utils.py:594] 2023-12-09 14:49:49,430 >> Configuration saved in ./gpt2-drugscom_depression_reviews/generation_config.json\n", + "[INFO|modeling_utils.py:2349] 2023-12-09 14:49:51,305 >> Model weights saved in ./gpt2-drugscom_depression_reviews/pytorch_model.bin\n", + "[INFO|tokenization_utils_base.py:2432] 2023-12-09 14:49:51,306 >> tokenizer config file saved in ./gpt2-drugscom_depression_reviews/tokenizer_config.json\n", + "[INFO|tokenization_utils_base.py:2441] 2023-12-09 14:49:51,307 >> Special tokens file saved in ./gpt2-drugscom_depression_reviews/special_tokens_map.json\n", + "***** train metrics *****\n", + " epoch = 5.0\n", + " train_loss = 0.5944\n", + " train_runtime = 2:15:40.11\n", + " train_samples = 4308\n", + " train_samples_per_second = 2.646\n", + " train_steps_per_second = 1.323\n", + "[INFO|modelcard.py:452] 2023-12-09 14:49:51,959 >> Dropping the following result as it does not have all the necessary fields:\n", + "{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}\n" + ] + } + ], + "source": [ + "# Fine-tuning command for Google Colab\n", + "# Note: run_clm.py should be present in the working directory\n", + "!python run_clm.py \\\n", + " --train_file train_dataset.txt \\\n", + " --model_name_or_path gpt2 \\\n", + " --output_dir ./gpt2-drugscom_depression_reviews \\\n", + " --do_train \\\n", + " --per_device_train_batch_size 2 \\\n", + " --num_train_epochs 5 \\\n", + " --overwrite_output_dir \\\n", + " --use_fast_tokenizer True \\\n", + " --report_to \"wandb\"" + ] + }, + { + "cell_type": "markdown", + "metadata": { + "id": "EFH89vCQ0pMf" + }, + "source": [ + "## STEP 5: SAVE THE FINE-TUNED GPT-2 MODEL: gpt2-drugscom_depression_reviews" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "LthX-XqW5Agq" + }, + "outputs": [], + "source": [ + "from huggingface_hub import notebook_login # To log to our Hugging Face account to be able to upload models to the Hub." + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "id": "X_g76SB35CDE", + "colab": { + "base_uri": "https://localhost:8080/", + "height": 145, + "referenced_widgets": [ + "9290ccab8e20428a8c6a61e2ce67e0c7", + "95db8459bbae45c9ac3b05898c06dc70", + "983e2f804ad24fe3b34a33c800417ca2", + "231839169648413991d11e48bb43a7a7", + "bd9f134683a84df09aadcab94fad8831", + "f6933a18f84f4678a360ffcc3e13f083", + "15fdfbc426924d5091533d4462c9b53b", + "44aa945dc5e743b8a6aa3f3078caac77", + "fa8d2f6085ab4a31b61270aa6a1ea4c5", + "7f3d379eb619439c98379c9b4f0795ec", + "6b048e6506aa454b9c5858828fbcd40c", + "4690ab39fdb348359cb42526a3ebeb86", + "0c3bc5d3a65d4a8980e321caf5a5d4f6", + "b5ea618a490448b4aa95637a03f9adb0", + "379537673a7b46a8bdcdbfdf346be8dd", + "bef797322e0940a0a4b0116bc502480d", + "8f9941f463cc4e7688daf9d70fb8937e", + "9502b7944c4948cd9850aa515ba5f2d3", + "56eeae6e18784dd2903addb05112e495", + "8bc3ad27022a45c29c0d7eac1da9956f", + "9fec786322d047299a289cb80487ed52", + "99801da567c5403284ac7555ea967dd3", + "d2dfcff538f54c449386cc843c2e7c6d", + "7728b2f00d96487a9397a55c3cd336ce", + "77dfd24b45f24da09dfe0c426d741aa7", + "c5313e81a1784396afd3cdc03f0920ea", + "65e11d956f2b4f59a9ccc26176cd4a58", + "452967ad3cd94a21bcde37e3ea2784eb", + "9fbe272599ed450e840a918a8b6a1fbc", + "d3c9c4c34afd4ebfb8b911c2aac756b5", + "1852d779e7c8448d87ce381d4348868d", + "6a2cbfb5e7b64c8cac850d0b05ce8f47" + ] + }, + "outputId": "52df4679-af8f-4961-b006-6d11ee1ec163" + }, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "VBox(children=(HTML(value='

Copy a token from your Hugging Face\ntokens page and paste it below.
Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file.
" + } + }, + "983e2f804ad24fe3b34a33c800417ca2": { + "model_module": "@jupyter-widgets/controls", + "model_name": "PasswordModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "PasswordModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "PasswordView", + "continuous_update": true, + "description": "Token:", + "description_tooltip": null, + "disabled": false, + "layout": "IPY_MODEL_7f3d379eb619439c98379c9b4f0795ec", + "placeholder": "​", + "style": "IPY_MODEL_6b048e6506aa454b9c5858828fbcd40c", + "value": "" + } + }, + "231839169648413991d11e48bb43a7a7": { + "model_module": "@jupyter-widgets/controls", + "model_name": "CheckboxModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "CheckboxModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "CheckboxView", + "description": "Add token as git credential?", + "description_tooltip": null, + "disabled": false, + "indent": true, + "layout": "IPY_MODEL_4690ab39fdb348359cb42526a3ebeb86", + "style": "IPY_MODEL_0c3bc5d3a65d4a8980e321caf5a5d4f6", + "value": true + } + }, + "bd9f134683a84df09aadcab94fad8831": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ButtonModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "ButtonView", + "button_style": "", + "description": "Login", + "disabled": false, + "icon": "", + "layout": "IPY_MODEL_b5ea618a490448b4aa95637a03f9adb0", + "style": "IPY_MODEL_379537673a7b46a8bdcdbfdf346be8dd", + "tooltip": "" + } + }, + "f6933a18f84f4678a360ffcc3e13f083": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_bef797322e0940a0a4b0116bc502480d", + "placeholder": "​", + "style": "IPY_MODEL_8f9941f463cc4e7688daf9d70fb8937e", + "value": "\nPro Tip: If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. " + } + }, + "15fdfbc426924d5091533d4462c9b53b": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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": "center", + "align_self": null, + "border": null, + "bottom": null, + "display": "flex", + "flex": null, + "flex_flow": "column", + "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": "50%" + } + }, + "44aa945dc5e743b8a6aa3f3078caac77": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "fa8d2f6085ab4a31b61270aa6a1ea4c5": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "7f3d379eb619439c98379c9b4f0795ec": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "6b048e6506aa454b9c5858828fbcd40c": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "4690ab39fdb348359cb42526a3ebeb86": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "0c3bc5d3a65d4a8980e321caf5a5d4f6": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "b5ea618a490448b4aa95637a03f9adb0": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "379537673a7b46a8bdcdbfdf346be8dd": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ButtonStyleModel", + "model_module_version": "1.5.0", + "state": { + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "ButtonStyleModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/base", + "_view_module_version": "1.2.0", + "_view_name": "StyleView", + "button_color": null, + "font_weight": "" + } + }, + "bef797322e0940a0a4b0116bc502480d": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "8f9941f463cc4e7688daf9d70fb8937e": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "9502b7944c4948cd9850aa515ba5f2d3": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_56eeae6e18784dd2903addb05112e495", + "placeholder": "​", + "style": "IPY_MODEL_8bc3ad27022a45c29c0d7eac1da9956f", + "value": "Connecting..." + } + }, + "56eeae6e18784dd2903addb05112e495": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "8bc3ad27022a45c29c0d7eac1da9956f": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "9fec786322d047299a289cb80487ed52": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_77dfd24b45f24da09dfe0c426d741aa7", + "placeholder": "​", + "style": "IPY_MODEL_c5313e81a1784396afd3cdc03f0920ea", + "value": "Token is valid (permission: write)." + } + }, + "99801da567c5403284ac7555ea967dd3": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_65e11d956f2b4f59a9ccc26176cd4a58", + "placeholder": "​", + "style": "IPY_MODEL_452967ad3cd94a21bcde37e3ea2784eb", + "value": "Your token has been saved in your configured git credential helpers (store)." + } + }, + "d2dfcff538f54c449386cc843c2e7c6d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_9fbe272599ed450e840a918a8b6a1fbc", + "placeholder": "​", + "style": "IPY_MODEL_d3c9c4c34afd4ebfb8b911c2aac756b5", + "value": "Your token has been saved to /root/.cache/huggingface/token" + } + }, + "7728b2f00d96487a9397a55c3cd336ce": { + "model_module": "@jupyter-widgets/controls", + "model_name": "LabelModel", + "model_module_version": "1.5.0", + "state": { + "_dom_classes": [], + "_model_module": "@jupyter-widgets/controls", + "_model_module_version": "1.5.0", + "_model_name": "LabelModel", + "_view_count": null, + "_view_module": "@jupyter-widgets/controls", + "_view_module_version": "1.5.0", + "_view_name": "LabelView", + "description": "", + "description_tooltip": null, + "layout": "IPY_MODEL_1852d779e7c8448d87ce381d4348868d", + "placeholder": "​", + "style": "IPY_MODEL_6a2cbfb5e7b64c8cac850d0b05ce8f47", + "value": "Login successful" + } + }, + "77dfd24b45f24da09dfe0c426d741aa7": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "c5313e81a1784396afd3cdc03f0920ea": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "65e11d956f2b4f59a9ccc26176cd4a58": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "452967ad3cd94a21bcde37e3ea2784eb": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "9fbe272599ed450e840a918a8b6a1fbc": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "d3c9c4c34afd4ebfb8b911c2aac756b5": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "1852d779e7c8448d87ce381d4348868d": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "6a2cbfb5e7b64c8cac850d0b05ce8f47": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "d2ce25900eae4b41b8107401f174b78d": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HBoxModel", + "model_module_version": "1.5.0", + "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_84433208e40d4271b4db101602d267ef", + "IPY_MODEL_c58122cb38ef4486a96966ac861cf913", + "IPY_MODEL_121add4c3f014c04926701a1da4782f0" + ], + "layout": "IPY_MODEL_74c8e8e472904e6c9651509d8bfc6a50" + } + }, + "84433208e40d4271b4db101602d267ef": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_9ada60f4d6374e3ab1d616970fea8b57", + "placeholder": "​", + "style": "IPY_MODEL_7ce21dd248a047fe8b4a8be37a05bfac", + "value": "model.safetensors: 100%" + } + }, + "c58122cb38ef4486a96966ac861cf913": { + "model_module": "@jupyter-widgets/controls", + "model_name": "FloatProgressModel", + "model_module_version": "1.5.0", + "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_a3a9ece98352459baa56c051886a8924", + "max": 497774208, + "min": 0, + "orientation": "horizontal", + "style": "IPY_MODEL_ea47214f28704e6ea43cb064bf9f5294", + "value": 497774208 + } + }, + "121add4c3f014c04926701a1da4782f0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "HTMLModel", + "model_module_version": "1.5.0", + "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_c43afb5ad3ed429285c3a6d871a734d7", + "placeholder": "​", + "style": "IPY_MODEL_62a83b49f10f49ee9a8b85ad601b45c0", + "value": " 498M/498M [00:17<00:00, 26.5MB/s]" + } + }, + "74c8e8e472904e6c9651509d8bfc6a50": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "9ada60f4d6374e3ab1d616970fea8b57": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "7ce21dd248a047fe8b4a8be37a05bfac": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "a3a9ece98352459baa56c051886a8924": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "ea47214f28704e6ea43cb064bf9f5294": { + "model_module": "@jupyter-widgets/controls", + "model_name": "ProgressStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + }, + "c43afb5ad3ed429285c3a6d871a734d7": { + "model_module": "@jupyter-widgets/base", + "model_name": "LayoutModel", + "model_module_version": "1.2.0", + "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 + } + }, + "62a83b49f10f49ee9a8b85ad601b45c0": { + "model_module": "@jupyter-widgets/controls", + "model_name": "DescriptionStyleModel", + "model_module_version": "1.5.0", + "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": "" + } + } + } + } + }, + "nbformat": 4, + "nbformat_minor": 0 +} \ No newline at end of file