{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "provenance": [], "gpuType": "T4" }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "language_info": { "name": "python" }, "accelerator": "GPU" }, "cells": [ { "cell_type": "markdown", "source": [ "# osiria/deberta-italian-question-answering\n", "## test set metrics" ], "metadata": { "id": "oub2ir8ZDkrH" } }, { "cell_type": "code", "execution_count": 1, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "02K9xO6Gvto1", "outputId": "10556608-a497-4c01-e07d-8f95f7ec41ac" }, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting git+https://github.com/huggingface/transformers\n", " Cloning https://github.com/huggingface/transformers to /tmp/pip-req-build-wnz73n3o\n", " Running command git clone --filter=blob:none --quiet https://github.com/huggingface/transformers /tmp/pip-req-build-wnz73n3o\n", " Resolved https://github.com/huggingface/transformers to commit 12298cb65c7e9d615b749dde935a0b4966f4ae49\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==4.30.0.dev0) (3.12.0)\n", "Collecting huggingface-hub<1.0,>=0.14.1 (from transformers==4.30.0.dev0)\n", " Downloading huggingface_hub-0.15.1-py3-none-any.whl (236 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m236.8/236.8 kB\u001b[0m \u001b[31m3.3 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 transformers==4.30.0.dev0) (1.22.4)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.0.dev0) (23.1)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.0.dev0) (6.0)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.0.dev0) (2022.10.31)\n", "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.0.dev0) (2.27.1)\n", "Collecting tokenizers!=0.11.3,<0.14,>=0.11.1 (from transformers==4.30.0.dev0)\n", " Downloading tokenizers-0.13.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.8 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m52.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting safetensors>=0.3.1 (from transformers==4.30.0.dev0)\n", " Downloading safetensors-0.3.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m87.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers==4.30.0.dev0) (4.65.0)\n", "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.14.1->transformers==4.30.0.dev0) (2023.4.0)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.14.1->transformers==4.30.0.dev0) (4.5.0)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.30.0.dev0) (1.26.15)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.30.0.dev0) (2022.12.7)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.30.0.dev0) (2.0.12)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers==4.30.0.dev0) (3.4)\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-4.30.0.dev0-py3-none-any.whl size=7166227 sha256=fdfdc040a7686aacafeef0a3fbf5d6b894a22a4967949ffa981ee09e9f574aac\n", " Stored in directory: /tmp/pip-ephem-wheel-cache-mynbfxj2/wheels/c0/14/d6/6c9a5582d2ac191ec0a483be151a4495fe1eb2a6706ca49f1b\n", "Successfully built transformers\n", "Installing collected packages: tokenizers, safetensors, huggingface-hub, transformers\n", "Successfully installed huggingface-hub-0.15.1 safetensors-0.3.1 tokenizers-0.13.3 transformers-4.30.0.dev0\n" ] } ], "source": [ "!pip install git+https://github.com/huggingface/transformers" ] }, { "cell_type": "code", "source": [ "!pip install datasets" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "VKgybrUswa1q", "outputId": "7f2ad166-68a2-433c-d0b4-8312192dee9e" }, "execution_count": 2, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting datasets\n", " Downloading datasets-2.12.0-py3-none-any.whl (474 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m474.6/474.6 kB\u001b[0m \u001b[31m5.4 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) (1.22.4)\n", "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (9.0.0)\n", "Collecting dill<0.3.7,>=0.3.0 (from datasets)\n", " Downloading dill-0.3.6-py3-none-any.whl (110 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m110.5/110.5 kB\u001b[0m \u001b[31m14.2 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) (2.27.1)\n", "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.65.0)\n", "Collecting xxhash (from datasets)\n", " Downloading xxhash-3.2.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (212 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m212.5/212.5 kB\u001b[0m \u001b[31m23.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting multiprocess (from datasets)\n", " Downloading multiprocess-0.70.14-py310-none-any.whl (134 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.3/134.3 kB\u001b[0m \u001b[31m17.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: fsspec[http]>=2021.11.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.4.0)\n", "Collecting aiohttp (from datasets)\n", " Downloading aiohttp-3.8.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.0 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m24.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: huggingface-hub<1.0.0,>=0.11.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.15.1)\n", "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (23.1)\n", "Collecting responses<0.19 (from datasets)\n", " Downloading responses-0.18.0-py3-none-any.whl (38 kB)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0)\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: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (2.0.12)\n", "Collecting multidict<7.0,>=4.5 (from aiohttp->datasets)\n", " Downloading multidict-6.0.4-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (114 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m114.5/114.5 kB\u001b[0m \u001b[31m14.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting async-timeout<5.0,>=4.0.0a3 (from aiohttp->datasets)\n", " Downloading async_timeout-4.0.2-py3-none-any.whl (5.8 kB)\n", "Collecting yarl<2.0,>=1.0 (from aiohttp->datasets)\n", " Downloading yarl-1.9.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (268 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m268.8/268.8 kB\u001b[0m \u001b[31m26.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting frozenlist>=1.1.1 (from aiohttp->datasets)\n", " Downloading frozenlist-1.3.3-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl (149 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m149.6/149.6 kB\u001b[0m \u001b[31m20.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting aiosignal>=1.1.2 (from aiohttp->datasets)\n", " Downloading aiosignal-1.3.1-py3-none-any.whl (7.6 kB)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0.0,>=0.11.0->datasets) (3.12.0)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0.0,>=0.11.0->datasets) (4.5.0)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (1.26.15)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2022.12.7)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.4)\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) (2022.7.1)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n", "Installing collected packages: xxhash, multidict, frozenlist, dill, async-timeout, yarl, responses, multiprocess, aiosignal, aiohttp, datasets\n", "Successfully installed aiohttp-3.8.4 aiosignal-1.3.1 async-timeout-4.0.2 datasets-2.12.0 dill-0.3.6 frozenlist-1.3.3 multidict-6.0.4 multiprocess-0.70.14 responses-0.18.0 xxhash-3.2.0 yarl-1.9.2\n" ] } ] }, { "cell_type": "code", "source": [ "!pip install accelerate" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "xYEW0Hjqz2lo", "outputId": "773d7aa2-0675-4edf-cb7e-34046a4fba55" }, "execution_count": 3, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting accelerate\n", " Downloading accelerate-0.20.0-py3-none-any.whl (227 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m227.4/227.4 kB\u001b[0m \u001b[31m3.5 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) (1.22.4)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (23.1)\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)\n", "Requirement already satisfied: torch>=1.6.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.0.1+cu118)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->accelerate) (3.12.0)\n", "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->accelerate) (4.5.0)\n", "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->accelerate) (1.11.1)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->accelerate) (3.1)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->accelerate) (3.1.2)\n", "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.6.0->accelerate) (2.0.0)\n", "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.6.0->accelerate) (3.25.2)\n", "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.6.0->accelerate) (16.0.5)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.6.0->accelerate) (2.1.2)\n", "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.6.0->accelerate) (1.3.0)\n", "Installing collected packages: accelerate\n", "Successfully installed accelerate-0.20.0\n" ] } ] }, { "cell_type": "code", "source": [ "!pip install evaluate" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "9OFz3JdR0cQ_", "outputId": "202b4d5c-8d48-4f01-c760-9bfb413fbb30" }, "execution_count": 4, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n", "Collecting evaluate\n", " Downloading evaluate-0.4.0-py3-none-any.whl (81 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.4/81.4 kB\u001b[0m \u001b[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: datasets>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.12.0)\n", "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from evaluate) (1.22.4)\n", "Requirement already satisfied: dill in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.3.6)\n", "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from evaluate) (1.5.3)\n", "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.27.1)\n", "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from evaluate) (4.65.0)\n", "Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from evaluate) (3.2.0)\n", "Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.70.14)\n", "Requirement already satisfied: fsspec[http]>=2021.05.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2023.4.0)\n", "Requirement already satisfied: huggingface-hub>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.15.1)\n", "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from evaluate) (23.1)\n", "Requirement already satisfied: responses<0.19 in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.18.0)\n", "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (9.0.0)\n", "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (3.8.4)\n", "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (6.0)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.7.0->evaluate) (3.12.0)\n", "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.7.0->evaluate) (4.5.0)\n", "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (1.26.15)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (2022.12.7)\n", "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (2.0.12)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (3.4)\n", "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2.8.2)\n", "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2022.7.1)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (23.1.0)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (6.0.4)\n", "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (4.0.2)\n", "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.9.2)\n", "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.3.3)\n", "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.3.1)\n", "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->evaluate) (1.16.0)\n", "Installing collected packages: evaluate\n", "Successfully installed evaluate-0.4.0\n" ] } ] }, { "cell_type": "code", "source": [ "!wget https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/run_qa.py\n", "!wget https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/trainer_qa.py\n", "!wget https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/utils_qa.py" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "JJhpBNwpxOTK", "outputId": "bbb60e1c-bde4-49b0-bfb2-eaf01cbcad29" }, "execution_count": 5, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "--2023-06-07 16:47:01-- https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/run_qa.py\n", "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n", "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 31717 (31K) [text/plain]\n", "Saving to: ‘run_qa.py’\n", "\n", "run_qa.py 100%[===================>] 30.97K --.-KB/s in 0.006s \n", "\n", "2023-06-07 16:47:01 (5.21 MB/s) - ‘run_qa.py’ saved [31717/31717]\n", "\n", "--2023-06-07 16:47:02-- https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/trainer_qa.py\n", "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.108.133, 185.199.109.133, 185.199.110.133, ...\n", "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.108.133|:443... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 6253 (6.1K) [text/plain]\n", "Saving to: ‘trainer_qa.py’\n", "\n", "trainer_qa.py 100%[===================>] 6.11K --.-KB/s in 0s \n", "\n", "2023-06-07 16:47:02 (87.1 MB/s) - ‘trainer_qa.py’ saved [6253/6253]\n", "\n", "--2023-06-07 16:47:02-- https://raw.githubusercontent.com/huggingface/transformers/main/examples/pytorch/question-answering/utils_qa.py\n", "Resolving raw.githubusercontent.com (raw.githubusercontent.com)... 185.199.110.133, 185.199.109.133, 185.199.111.133, ...\n", "Connecting to raw.githubusercontent.com (raw.githubusercontent.com)|185.199.110.133|:443... connected.\n", "HTTP request sent, awaiting response... 200 OK\n", "Length: 22777 (22K) [text/plain]\n", "Saving to: ‘utils_qa.py’\n", "\n", "utils_qa.py 100%[===================>] 22.24K --.-KB/s in 0.004s \n", "\n", "2023-06-07 16:47:02 (4.95 MB/s) - ‘utils_qa.py’ saved [22777/22777]\n", "\n" ] } ] }, { "cell_type": "code", "source": [ "!ls" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "Loa6y9XqzXJ4", "outputId": "3be368ce-5d9e-4df2-c3c9-f6a5a537c405" }, "execution_count": 6, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "run_qa.py sample_data\ttrainer_qa.py utils_qa.py\n" ] } ] }, { "cell_type": "code", "source": [ "!mkdir eval_results" ], "metadata": { "id": "QDNxV31P0reW" }, "execution_count": 7, "outputs": [] }, { "cell_type": "code", "source": [ "!python -m run_qa --model_name_or_path osiria/deberta-italian-question-answering --dataset_name squad_it --do_predict --per_device_eval_batch_size=5 --output_dir eval_results" ], "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "B5O5Lom8x_c4", "outputId": "ebb24d93-3e0c-4eae-ca30-28d1c9a46bc6" }, "execution_count": 8, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "2023-06-07 16:47:10.607285: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n", "06/07/2023 16:47:13 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False\n", "06/07/2023 16:47:13 - INFO - __main__ - Training/evaluation parameters TrainingArguments(\n", "_n_gpu=1,\n", "adafactor=False,\n", "adam_beta1=0.9,\n", "adam_beta2=0.999,\n", "adam_epsilon=1e-08,\n", "auto_find_batch_size=False,\n", "bf16=False,\n", "bf16_full_eval=False,\n", "data_seed=None,\n", "dataloader_drop_last=False,\n", "dataloader_num_workers=0,\n", "dataloader_pin_memory=True,\n", "ddp_backend=None,\n", "ddp_bucket_cap_mb=None,\n", "ddp_find_unused_parameters=None,\n", "ddp_timeout=1800,\n", "debug=[],\n", "deepspeed=None,\n", "disable_tqdm=False,\n", "do_eval=False,\n", "do_predict=True,\n", "do_train=False,\n", "eval_accumulation_steps=None,\n", "eval_delay=0,\n", "eval_steps=None,\n", "evaluation_strategy=no,\n", "fp16=False,\n", "fp16_backend=auto,\n", "fp16_full_eval=False,\n", "fp16_opt_level=O1,\n", "fsdp=[],\n", "fsdp_config={'fsdp_min_num_params': 0, 'xla': False, 'xla_fsdp_grad_ckpt': False},\n", "fsdp_min_num_params=0,\n", "fsdp_transformer_layer_cls_to_wrap=None,\n", "full_determinism=False,\n", "gradient_accumulation_steps=1,\n", "gradient_checkpointing=False,\n", "greater_is_better=None,\n", "group_by_length=False,\n", "half_precision_backend=auto,\n", "hub_model_id=None,\n", "hub_private_repo=False,\n", "hub_strategy=every_save,\n", "hub_token=,\n", "ignore_data_skip=False,\n", "include_inputs_for_metrics=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=eval_results/runs/Jun07_16-47-13_0d4f01f1a5fc,\n", "logging_first_step=False,\n", "logging_nan_inf_filter=True,\n", "logging_steps=500,\n", "logging_strategy=steps,\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", "no_cuda=False,\n", "num_train_epochs=3.0,\n", "optim=adamw_hf,\n", "optim_args=None,\n", "output_dir=eval_results,\n", "overwrite_output_dir=False,\n", "past_index=-1,\n", "per_device_eval_batch_size=5,\n", "per_device_train_batch_size=8,\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=['tensorboard'],\n", "resume_from_checkpoint=None,\n", "run_name=eval_results,\n", "save_on_each_node=False,\n", "save_safetensors=False,\n", "save_steps=500,\n", "save_strategy=steps,\n", "save_total_limit=None,\n", "seed=42,\n", "sharded_ddp=[],\n", "skip_memory_metrics=True,\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_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", "xpu_backend=None,\n", ")\n", "06/07/2023 16:47:13 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/squad_it/resolve/main/squad_it.py not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmp6fvibkw8\n", "Downloading builder script: 100% 4.74k/4.74k [00:00<00:00, 6.03MB/s]\n", "06/07/2023 16:47:14 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/squad_it/resolve/main/squad_it.py in cache at /root/.cache/huggingface/datasets/downloads/2f7a246f661e6acb3a9ad072ed14241ea343265e7d863b88717897941c3ab1dd.671c3c3daf2f05e0355b498b0f5a7f2167fa94dc6de36195fe1ba0503e6dcc30.py\n", "06/07/2023 16:47:14 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/2f7a246f661e6acb3a9ad072ed14241ea343265e7d863b88717897941c3ab1dd.671c3c3daf2f05e0355b498b0f5a7f2167fa94dc6de36195fe1ba0503e6dcc30.py\n", "06/07/2023 16:47:14 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/squad_it/resolve/main/dataset_infos.json not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmpax6jsbgs\n", "Downloading metadata: 100% 2.51k/2.51k [00:00<00:00, 2.96MB/s]\n", "06/07/2023 16:47:14 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/squad_it/resolve/main/dataset_infos.json in cache at /root/.cache/huggingface/datasets/downloads/f6d7650a1e4a9f0e42b54f34ac614f7c1142ad26c1bd19a448eb606fe09f7515.b459489a7b1a4d859decbeef851034c7846ef6cce8ec2cf192cf4b4f40d0865d\n", "06/07/2023 16:47:14 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/f6d7650a1e4a9f0e42b54f34ac614f7c1142ad26c1bd19a448eb606fe09f7515.b459489a7b1a4d859decbeef851034c7846ef6cce8ec2cf192cf4b4f40d0865d\n", "06/07/2023 16:47:14 - INFO - datasets.utils.file_utils - https://huggingface.co/datasets/squad_it/resolve/main/README.md not found in cache or force_download set to True, downloading to /root/.cache/huggingface/datasets/downloads/tmpmy7om6r1\n", "Downloading readme: 100% 7.27k/7.27k [00:00<00:00, 9.54MB/s]\n", "06/07/2023 16:47:14 - INFO - datasets.utils.file_utils - storing https://huggingface.co/datasets/squad_it/resolve/main/README.md in cache at /root/.cache/huggingface/datasets/downloads/b664892e5965a1ef2e173eadc7e9cbf6ad4aeb6240d7b3bb6ab9f32850363a6f.71fe7dbf5f3b574d85b57b5a722ebc49fe8ec8b03d655344891fb1b05c4634fb\n", "06/07/2023 16:47:14 - INFO - datasets.utils.file_utils - creating metadata file for /root/.cache/huggingface/datasets/downloads/b664892e5965a1ef2e173eadc7e9cbf6ad4aeb6240d7b3bb6ab9f32850363a6f.71fe7dbf5f3b574d85b57b5a722ebc49fe8ec8b03d655344891fb1b05c4634fb\n", "06/07/2023 16:47:14 - INFO - datasets.info - Loading Dataset Infos from /root/.cache/huggingface/modules/datasets_modules/datasets/squad_it/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71\n", "06/07/2023 16:47:14 - INFO - datasets.builder - Generating dataset squad_it (/root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71)\n", "Downloading and preparing dataset squad_it/default to /root/.cache/huggingface/datasets/squad_it/default/0.1.0/d442bdb4794b4bae227ab19105b76d706ed7cf2ac342e4c9da4a5c36bde19d71...\n", "06/07/2023 16:47:14 - INFO - datasets.builder - Dataset not on Hf google storage. Downloading and preparing it from source\n", "Downloading data files: 0% 0/2 [00:00> loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--osiria--deberta-italian-question-answering/snapshots/e93341adad1d2140bacd231c54d7c3e0fd1317c3/config.json\n", "[INFO|configuration_utils.py:725] 2023-06-07 16:47:23,850 >> Model config DebertaV2Config {\n", " \"_name_or_path\": \"osiria/deberta-italian-question-answering\",\n", " \"architectures\": [\n", " \"DebertaV2ForQuestionAnswering\"\n", " ],\n", " \"attention_probs_dropout_prob\": 0.1,\n", " \"hidden_act\": \"gelu\",\n", " \"hidden_dropout_prob\": 0.1,\n", " \"hidden_size\": 768,\n", " \"initializer_range\": 0.02,\n", " \"intermediate_size\": 3072,\n", " \"layer_norm_eps\": 1e-07,\n", " \"max_position_embeddings\": 512,\n", " \"max_relative_positions\": -1,\n", " \"model_type\": \"deberta-v2\",\n", " \"norm_rel_ebd\": \"layer_norm\",\n", " \"num_attention_heads\": 12,\n", " \"num_hidden_layers\": 12,\n", " \"pad_token_id\": 0,\n", " \"pooler_dropout\": 0,\n", " \"pooler_hidden_act\": \"gelu\",\n", " \"pooler_hidden_size\": 768,\n", " \"pos_att_type\": [\n", " \"p2c\",\n", " \"c2p\"\n", " ],\n", " \"position_biased_input\": false,\n", " \"position_buckets\": 256,\n", " \"relative_attention\": true,\n", " \"share_att_key\": true,\n", " \"torch_dtype\": \"float32\",\n", " \"transformers_version\": \"4.30.0.dev0\",\n", " \"type_vocab_size\": 0,\n", " \"vocab_size\": 50256\n", "}\n", "\n", "Downloading (…)okenizer_config.json: 100% 412/412 [00:00<00:00, 2.41MB/s]\n", "Downloading (…)/main/tokenizer.json: 100% 2.02M/2.02M [00:00<00:00, 12.6MB/s]\n", "[INFO|tokenization_utils_base.py:1823] 2023-06-07 16:47:24,622 >> loading file spm.model from cache at None\n", "[INFO|tokenization_utils_base.py:1823] 2023-06-07 16:47:24,622 >> loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--osiria--deberta-italian-question-answering/snapshots/e93341adad1d2140bacd231c54d7c3e0fd1317c3/tokenizer.json\n", "[INFO|tokenization_utils_base.py:1823] 2023-06-07 16:47:24,622 >> loading file added_tokens.json from cache at None\n", "[INFO|tokenization_utils_base.py:1823] 2023-06-07 16:47:24,622 >> loading file special_tokens_map.json from cache at None\n", "[INFO|tokenization_utils_base.py:1823] 2023-06-07 16:47:24,622 >> loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--osiria--deberta-italian-question-answering/snapshots/e93341adad1d2140bacd231c54d7c3e0fd1317c3/tokenizer_config.json\n", "Downloading pytorch_model.bin: 100% 496M/496M [00:07<00:00, 66.0MB/s]\n", "[INFO|modeling_utils.py:2578] 2023-06-07 16:47:32,789 >> loading weights file pytorch_model.bin from cache at /root/.cache/huggingface/hub/models--osiria--deberta-italian-question-answering/snapshots/e93341adad1d2140bacd231c54d7c3e0fd1317c3/pytorch_model.bin\n", "[INFO|modeling_utils.py:3295] 2023-06-07 16:47:34,943 >> All model checkpoint weights were used when initializing DebertaV2ForQuestionAnswering.\n", "\n", "[INFO|modeling_utils.py:3303] 2023-06-07 16:47:34,943 >> All the weights of DebertaV2ForQuestionAnswering were initialized from the model checkpoint at osiria/deberta-italian-question-answering.\n", "If your task is similar to the task the model of the checkpoint was trained on, you can already use DebertaV2ForQuestionAnswering for predictions without further training.\n", "Running tokenizer on prediction dataset: 0% 0/7609 [00:00> The following columns in the test set don't have a corresponding argument in `DebertaV2ForQuestionAnswering.forward` and have been ignored: offset_mapping, example_id. If offset_mapping, example_id are not expected by `DebertaV2ForQuestionAnswering.forward`, you can safely ignore this message.\n", "[INFO|trainer.py:3163] 2023-06-07 16:47:48,899 >> ***** Running Prediction *****\n", "[INFO|trainer.py:3165] 2023-06-07 16:47:48,899 >> Num examples = 8565\n", "[INFO|trainer.py:3168] 2023-06-07 16:47:48,899 >> Batch size = 5\n", "100% 1713/1713 [04:44<00:00, 5.97it/s]06/07/2023 16:52:48 - INFO - utils_qa - Post-processing 7609 example predictions split into 8565 features.\n", "\n", " 0% 0/7609 [00:00> Dropping the following result as it does not have all the necessary fields:\n", "{'task': {'name': 'Question Answering', 'type': 'question-answering'}, 'dataset': {'name': 'squad_it', 'type': 'squad_it'}}\n", "100% 1713/1713 [05:28<00:00, 5.22it/s]\n" ] } ] }, { "cell_type": "code", "source": [], "metadata": { "id": "ij8YkY0xyNXI" }, "execution_count": null, "outputs": [] } ] }