{ "cells": [ { "cell_type": "markdown", "metadata": { "id": "Ac6wadk3rmkK" }, "source": [ "# LM Evaluation Harness (by [EleutherAI](https://www.eleuther.ai/))\n", "\n", "This [`LM-Evaluation-Harness`](https://github.com/EleutherAI/lm-evaluation-harness) provides a unified framework to test generative language models on a large number of different evaluation tasks. For a complete list of available tasks, see the [task table](https://github.com/EleutherAI/lm-evaluation-harness/blob/master/docs/task_table.md), or scroll to the bottom of the page.\n", "\n", "1. Clone the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) and install the necessary libraries (`sentencepiece` is required for the Llama tokenizer)." ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "UA5I86u91e0A", "outputId": "d74b3cab-b292-43db-bd5d-523424d2c97a" }, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Cloning into 'lm-evaluation-harness'...\n", "remote: Enumerating objects: 22343, done.\u001b[K\n", "remote: Counting objects: 100% (7096/7096), done.\u001b[K\n", "remote: Compressing objects: 100% (703/703), done.\u001b[K\n", "remote: Total 22343 (delta 6540), reused 6659 (delta 6392), pack-reused 15247\u001b[K\n", "Receiving objects: 100% (22343/22343), 20.57 MiB | 11.37 MiB/s, done.\n", "Resolving deltas: 100% (15456/15456), done.\n", "Obtaining file:///content/lm-evaluation-harness\n", " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Collecting datasets>=2.0.0 (from lm-eval==0.3.0)\n", " Downloading datasets-2.14.5-py3-none-any.whl (519 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m519.6/519.6 kB\u001b[0m \u001b[31m8.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting einops (from lm-eval==0.3.0)\n", " Downloading einops-0.7.0-py3-none-any.whl (44 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m44.6/44.6 kB\u001b[0m \u001b[31m5.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting jsonlines (from lm-eval==0.3.0)\n", " Downloading jsonlines-4.0.0-py3-none-any.whl (8.7 kB)\n", "Requirement already satisfied: numexpr in /usr/local/lib/python3.10/dist-packages (from lm-eval==0.3.0) (2.8.7)\n", "Collecting openai>=0.6.4 (from lm-eval==0.3.0)\n", " Downloading openai-0.28.1-py3-none-any.whl (76 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m77.0/77.0 kB\u001b[0m \u001b[31m10.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting omegaconf>=2.2 (from lm-eval==0.3.0)\n", " Downloading omegaconf-2.3.0-py3-none-any.whl (79 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m79.5/79.5 kB\u001b[0m \u001b[31m9.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting peft>=0.2.0 (from lm-eval==0.3.0)\n", " Downloading peft-0.5.0-py3-none-any.whl (85 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m85.6/85.6 kB\u001b[0m \u001b[31m11.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting pybind11>=2.6.2 (from lm-eval==0.3.0)\n", " Downloading pybind11-2.11.1-py3-none-any.whl (227 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m227.7/227.7 kB\u001b[0m \u001b[31m26.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting pycountry (from lm-eval==0.3.0)\n", " Downloading pycountry-22.3.5.tar.gz (10.1 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.1/10.1 MB\u001b[0m \u001b[31m85.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h 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", "Collecting pytablewriter (from lm-eval==0.3.0)\n", " Downloading pytablewriter-1.2.0-py3-none-any.whl (111 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m111.1/111.1 kB\u001b[0m \u001b[31m14.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting rouge-score>=0.0.4 (from lm-eval==0.3.0)\n", " Downloading rouge_score-0.1.2.tar.gz (17 kB)\n", " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Collecting sacrebleu==1.5.0 (from lm-eval==0.3.0)\n", " Downloading sacrebleu-1.5.0-py3-none-any.whl (65 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m65.6/65.6 kB\u001b[0m \u001b[31m9.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: scikit-learn>=0.24.1 in /usr/local/lib/python3.10/dist-packages (from lm-eval==0.3.0) (1.2.2)\n", "Collecting sqlitedict (from lm-eval==0.3.0)\n", " Downloading sqlitedict-2.1.0.tar.gz (21 kB)\n", " Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Requirement already satisfied: torch>=1.7 in /usr/local/lib/python3.10/dist-packages (from lm-eval==0.3.0) (2.0.1+cu118)\n", "Collecting tqdm-multiprocess (from lm-eval==0.3.0)\n", " Downloading tqdm_multiprocess-0.0.11-py3-none-any.whl (9.8 kB)\n", "Collecting transformers>=4.1 (from lm-eval==0.3.0)\n", " Downloading transformers-4.34.0-py3-none-any.whl (7.7 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.7/7.7 MB\u001b[0m \u001b[31m63.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting zstandard (from lm-eval==0.3.0)\n", " Downloading zstandard-0.21.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.7 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.7/2.7 MB\u001b[0m \u001b[31m85.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting accelerate>=0.17.1 (from lm-eval==0.3.0)\n", " Downloading accelerate-0.23.0-py3-none-any.whl (258 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m258.1/258.1 kB\u001b[0m \u001b[31m25.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting portalocker (from sacrebleu==1.5.0->lm-eval==0.3.0)\n", " Downloading portalocker-2.8.2-py3-none-any.whl (17 kB)\n", "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.17.1->lm-eval==0.3.0) (1.23.5)\n", "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.17.1->lm-eval==0.3.0) (23.2)\n", "Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.17.1->lm-eval==0.3.0) (5.9.5)\n", "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.17.1->lm-eval==0.3.0) (6.0.1)\n", "Collecting huggingface-hub (from accelerate>=0.17.1->lm-eval==0.3.0)\n", " Downloading huggingface_hub-0.18.0-py3-none-any.whl (301 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m302.0/302.0 kB\u001b[0m \u001b[31m27.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->lm-eval==0.3.0) (9.0.0)\n", "Collecting dill<0.3.8,>=0.3.0 (from datasets>=2.0.0->lm-eval==0.3.0)\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[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->lm-eval==0.3.0) (1.5.3)\n", "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->lm-eval==0.3.0) (2.31.0)\n", "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->lm-eval==0.3.0) (4.66.1)\n", "Collecting xxhash (from datasets>=2.0.0->lm-eval==0.3.0)\n", " Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m21.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting multiprocess (from datasets>=2.0.0->lm-eval==0.3.0)\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[31m16.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: fsspec[http]<2023.9.0,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->lm-eval==0.3.0) (2023.6.0)\n", "Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->lm-eval==0.3.0) (3.8.6)\n", "Collecting antlr4-python3-runtime==4.9.* (from omegaconf>=2.2->lm-eval==0.3.0)\n", " Downloading antlr4-python3-runtime-4.9.3.tar.gz (117 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m117.0/117.0 kB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n", "Collecting safetensors (from peft>=0.2.0->lm-eval==0.3.0)\n", " Downloading safetensors-0.4.0-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[31m66.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: absl-py in /usr/local/lib/python3.10/dist-packages (from rouge-score>=0.0.4->lm-eval==0.3.0) (1.4.0)\n", "Requirement already satisfied: nltk in /usr/local/lib/python3.10/dist-packages (from rouge-score>=0.0.4->lm-eval==0.3.0) (3.8.1)\n", "Requirement already satisfied: six>=1.14.0 in /usr/local/lib/python3.10/dist-packages (from rouge-score>=0.0.4->lm-eval==0.3.0) (1.16.0)\n", "Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.24.1->lm-eval==0.3.0) (1.11.3)\n", "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.24.1->lm-eval==0.3.0) (1.3.2)\n", "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn>=0.24.1->lm-eval==0.3.0) (3.2.0)\n", "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.7->lm-eval==0.3.0) (3.12.4)\n", "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch>=1.7->lm-eval==0.3.0) (4.5.0)\n", "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.7->lm-eval==0.3.0) (1.12)\n", "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.7->lm-eval==0.3.0) (3.1)\n", "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.7->lm-eval==0.3.0) (3.1.2)\n", "Requirement already satisfied: triton==2.0.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.7->lm-eval==0.3.0) (2.0.0)\n", "Requirement already satisfied: cmake in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.7->lm-eval==0.3.0) (3.27.6)\n", "Requirement already satisfied: lit in /usr/local/lib/python3.10/dist-packages (from triton==2.0.0->torch>=1.7->lm-eval==0.3.0) (17.0.2)\n", "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers>=4.1->lm-eval==0.3.0) (2023.6.3)\n", "Collecting tokenizers<0.15,>=0.14 (from transformers>=4.1->lm-eval==0.3.0)\n", " Downloading tokenizers-0.14.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.8 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.8/3.8 MB\u001b[0m \u001b[31m118.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: attrs>=19.2.0 in /usr/local/lib/python3.10/dist-packages (from jsonlines->lm-eval==0.3.0) (23.1.0)\n", "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from pycountry->lm-eval==0.3.0) (67.7.2)\n", "Collecting DataProperty<2,>=1.0.1 (from pytablewriter->lm-eval==0.3.0)\n", " Downloading DataProperty-1.0.1-py3-none-any.whl (27 kB)\n", "Collecting mbstrdecoder<2,>=1.0.0 (from pytablewriter->lm-eval==0.3.0)\n", " Downloading mbstrdecoder-1.1.3-py3-none-any.whl (7.8 kB)\n", "Collecting pathvalidate<4,>=2.3.0 (from pytablewriter->lm-eval==0.3.0)\n", " Downloading pathvalidate-3.2.0-py3-none-any.whl (23 kB)\n", "Collecting tabledata<2,>=1.3.1 (from pytablewriter->lm-eval==0.3.0)\n", " Downloading tabledata-1.3.3-py3-none-any.whl (11 kB)\n", "Collecting tcolorpy<1,>=0.0.5 (from pytablewriter->lm-eval==0.3.0)\n", " Downloading tcolorpy-0.1.4-py3-none-any.whl (7.9 kB)\n", "Collecting typepy[datetime]<2,>=1.3.2 (from pytablewriter->lm-eval==0.3.0)\n", " Downloading typepy-1.3.2-py3-none-any.whl (31 kB)\n", "Collecting colorama (from tqdm-multiprocess->lm-eval==0.3.0)\n", " Downloading colorama-0.4.6-py2.py3-none-any.whl (25 kB)\n", "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->lm-eval==0.3.0) (3.3.0)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->lm-eval==0.3.0) (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->lm-eval==0.3.0) (4.0.3)\n", "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->lm-eval==0.3.0) (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->lm-eval==0.3.0) (1.4.0)\n", "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->lm-eval==0.3.0) (1.3.1)\n", "Requirement already satisfied: chardet<6,>=3.0.4 in /usr/local/lib/python3.10/dist-packages (from mbstrdecoder<2,>=1.0.0->pytablewriter->lm-eval==0.3.0) (5.2.0)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets>=2.0.0->lm-eval==0.3.0) (3.4)\n", "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets>=2.0.0->lm-eval==0.3.0) (2.0.6)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets>=2.0.0->lm-eval==0.3.0) (2023.7.22)\n", "Collecting huggingface-hub (from accelerate>=0.17.1->lm-eval==0.3.0)\n", " Downloading huggingface_hub-0.17.3-py3-none-any.whl (295 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m295.0/295.0 kB\u001b[0m \u001b[31m34.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: python-dateutil<3.0.0,>=2.8.0 in /usr/local/lib/python3.10/dist-packages (from typepy[datetime]<2,>=1.3.2->pytablewriter->lm-eval==0.3.0) (2.8.2)\n", "Requirement already satisfied: pytz>=2018.9 in /usr/local/lib/python3.10/dist-packages (from typepy[datetime]<2,>=1.3.2->pytablewriter->lm-eval==0.3.0) (2023.3.post1)\n", "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.7->lm-eval==0.3.0) (2.1.3)\n", "Requirement already satisfied: click in /usr/local/lib/python3.10/dist-packages (from nltk->rouge-score>=0.0.4->lm-eval==0.3.0) (8.1.7)\n", "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.7->lm-eval==0.3.0) (1.3.0)\n", "Building wheels for collected packages: antlr4-python3-runtime, rouge-score, pycountry, sqlitedict\n", " Building wheel for antlr4-python3-runtime (setup.py) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for antlr4-python3-runtime: filename=antlr4_python3_runtime-4.9.3-py3-none-any.whl size=144554 sha256=a2f0b8953193e72a5cc4d402cd57becdaf2e11c29b664a7bc1dd0a2be7b14c34\n", " Stored in directory: /root/.cache/pip/wheels/12/93/dd/1f6a127edc45659556564c5730f6d4e300888f4bca2d4c5a88\n", " Building wheel for rouge-score (setup.py) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for rouge-score: filename=rouge_score-0.1.2-py3-none-any.whl size=24932 sha256=b800533290e8b115b69386f5528faaeec21bdaf0b27df954f91293ce884d2fae\n", " Stored in directory: /root/.cache/pip/wheels/5f/dd/89/461065a73be61a532ff8599a28e9beef17985c9e9c31e541b4\n", " Building wheel for pycountry (pyproject.toml) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for pycountry: filename=pycountry-22.3.5-py2.py3-none-any.whl size=10681833 sha256=c76dd8d8880795167eba1833e4b4f85fd1d2989d3e3c2a3c14ac581d784ec607\n", " Stored in directory: /root/.cache/pip/wheels/03/57/cc/290c5252ec97a6d78d36479a3c5e5ecc76318afcb241ad9dbe\n", " Building wheel for sqlitedict (setup.py) ... \u001b[?25l\u001b[?25hdone\n", " Created wheel for sqlitedict: filename=sqlitedict-2.1.0-py3-none-any.whl size=16864 sha256=38ab29686a73c7df8c33252ed6b8986475d0548f9adf841373e4ecaf8d995201\n", " Stored in directory: /root/.cache/pip/wheels/79/d6/e7/304e0e6cb2221022c26d8161f7c23cd4f259a9e41e8bbcfabd\n", "Successfully built antlr4-python3-runtime rouge-score pycountry sqlitedict\n", "Installing collected packages: sqlitedict, antlr4-python3-runtime, zstandard, xxhash, tcolorpy, safetensors, pycountry, pybind11, portalocker, pathvalidate, omegaconf, mbstrdecoder, jsonlines, einops, dill, colorama, typepy, tqdm-multiprocess, sacrebleu, rouge-score, multiprocess, huggingface-hub, tokenizers, openai, transformers, datasets, DataProperty, tabledata, pytablewriter, accelerate, peft, lm-eval\n", " Running setup.py develop for lm-eval\n", "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n", "llmx 0.0.15a0 requires cohere, which is not installed.\n", "llmx 0.0.15a0 requires tiktoken, which is not installed.\u001b[0m\u001b[31m\n", "\u001b[0mSuccessfully installed DataProperty-1.0.1 accelerate-0.23.0 antlr4-python3-runtime-4.9.3 colorama-0.4.6 datasets-2.14.5 dill-0.3.7 einops-0.7.0 huggingface-hub-0.17.3 jsonlines-4.0.0 lm-eval-0.3.0 mbstrdecoder-1.1.3 multiprocess-0.70.15 omegaconf-2.3.0 openai-0.28.1 pathvalidate-3.2.0 peft-0.5.0 portalocker-2.8.2 pybind11-2.11.1 pycountry-22.3.5 pytablewriter-1.2.0 rouge-score-0.1.2 sacrebleu-1.5.0 safetensors-0.4.0 sqlitedict-2.1.0 tabledata-1.3.3 tcolorpy-0.1.4 tokenizers-0.14.1 tqdm-multiprocess-0.0.11 transformers-4.34.0 typepy-1.3.2 xxhash-3.4.1 zstandard-0.21.0\n", "Collecting cohere\n", " Downloading cohere-4.30-py3-none-any.whl (47 kB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m47.8/47.8 kB\u001b[0m \u001b[31m1.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting tiktoken\n", " Downloading tiktoken-0.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.0 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.0/2.0 MB\u001b[0m \u001b[31m30.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hCollecting sentencepiece\n", " Downloading sentencepiece-0.1.99-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (1.3 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m75.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: aiohttp<4.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from cohere) (3.8.6)\n", "Collecting backoff<3.0,>=2.0 (from cohere)\n", " Downloading backoff-2.2.1-py3-none-any.whl (15 kB)\n", "Collecting fastavro==1.8.2 (from cohere)\n", " Downloading fastavro-1.8.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (2.7 MB)\n", "\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m2.7/2.7 MB\u001b[0m \u001b[31m97.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n", "\u001b[?25hRequirement already satisfied: importlib_metadata<7.0,>=6.0 in /usr/local/lib/python3.10/dist-packages (from cohere) (6.8.0)\n", "Requirement already satisfied: requests<3.0.0,>=2.25.0 in /usr/local/lib/python3.10/dist-packages (from cohere) (2.31.0)\n", "Requirement already satisfied: urllib3<3,>=1.26 in /usr/local/lib/python3.10/dist-packages (from cohere) (2.0.6)\n", "Requirement already satisfied: regex>=2022.1.18 in /usr/local/lib/python3.10/dist-packages (from tiktoken) (2023.6.3)\n", "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (23.1.0)\n", "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (3.3.0)\n", "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (6.0.4)\n", "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (4.0.3)\n", "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (1.9.2)\n", "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (1.4.0)\n", "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp<4.0,>=3.0->cohere) (1.3.1)\n", "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.10/dist-packages (from importlib_metadata<7.0,>=6.0->cohere) (3.17.0)\n", "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.25.0->cohere) (3.4)\n", "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3.0.0,>=2.25.0->cohere) (2023.7.22)\n", "Installing collected packages: sentencepiece, fastavro, backoff, tiktoken, cohere\n", "Successfully installed backoff-2.2.1 cohere-4.30 fastavro-1.8.2 sentencepiece-0.1.99 tiktoken-0.5.1\n" ] } ], "source": [ "%git clone https://github.com/EleutherAI/lm-evaluation-harness\n", "%cd lm-evaluation-harness && pip install -e .\n", "%pip install cohere tiktoken sentencepiece" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "colab": { "base_uri": "https://localhost:8080/" }, "id": "pnHoAVK25QZn", "outputId": "4253b115-702c-4f31-f1b3-f0483c527841" }, "outputs": [], "source": [ "%cd lm-evaluation-harness && python main.py \\\n", " --model hf-causal \\\n", " --model_args pretrained=nicholasKluge/Aira-2-1B1 \\\n", " --tasks hendrycksTest-abstract_algebra,hendrycksTest-anatomy,hendrycksTest-astronomy,hendrycksTest-business_ethics,hendrycksTest-clinical_knowledge,hendrycksTest-college_biology,hendrycksTest-college_chemistry,hendrycksTest-college_computer_science,hendrycksTest-college_mathematics,hendrycksTest-college_medicine,hendrycksTest-college_physics,hendrycksTest-computer_security,hendrycksTest-conceptual_physics,hendrycksTest-econometrics,hendrycksTest-electrical_engineering,hendrycksTest-elementary_mathematics,hendrycksTest-formal_logic,hendrycksTest-global_facts,hendrycksTest-high_school_biology,hendrycksTest-high_school_chemistry,hendrycksTest-high_school_computer_science,hendrycksTest-high_school_european_history,hendrycksTest-high_school_geography,hendrycksTest-high_school_government_and_politics,hendrycksTest-high_school_macroeconomics,hendrycksTest-high_school_mathematics,hendrycksTest-high_school_microeconomics,hendrycksTest-high_school_physics,hendrycksTest-high_school_psychology,hendrycksTest-high_school_statistics,hendrycksTest-high_school_us_history,hendrycksTest-high_school_world_history,hendrycksTest-human_aging,hendrycksTest-human_sexuality,hendrycksTest-international_law,hendrycksTest-jurisprudence,hendrycksTest-logical_fallacies,hendrycksTest-machine_learning,hendrycksTest-management,hendrycksTest-marketing,hendrycksTest-medical_genetics,hendrycksTest-miscellaneous,hendrycksTest-moral_disputes,hendrycksTest-moral_scenarios,hendrycksTest-nutrition,hendrycksTest-philosophy,hendrycksTest-prehistory,hendrycksTest-professional_accounting,hendrycksTest-professional_law,hendrycksTest-professional_medicine,hendrycksTest-professional_psychology,hendrycksTest-public_relations,hendrycksTest-security_studies,hendrycksTest-sociology,hendrycksTest-us_foreign_policy,hendrycksTest-virology,hendrycksTest-world_religions \\\n", " --device cuda:0" ] }, { "cell_type": "markdown", "metadata": { "id": "4Bm78wiZ4Own" }, "source": [ "## Task Table 📚\n", "\n", "| Task Name |Train|Val|Test|Val/Test Docs| Metrics |\n", "|---------------------------------------------------------|-----|---|----|------------:|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n", "|anagrams1 | |✓ | | 10000|acc |\n", "|anagrams2 | |✓ | | 10000|acc |\n", "|anli_r1 |✓ |✓ |✓ | 1000|acc |\n", "|anli_r2 |✓ |✓ |✓ | 1000|acc |\n", "|anli_r3 |✓ |✓ |✓ | 1200|acc |\n", "|arc_challenge |✓ |✓ |✓ | 1172|acc, acc_norm |\n", "|arc_easy |✓ |✓ |✓ | 2376|acc, acc_norm |\n", "|arithmetic_1dc | |✓ | | 2000|acc |\n", "|arithmetic_2da | |✓ | | 2000|acc |\n", "|arithmetic_2dm | |✓ | | 2000|acc |\n", "|arithmetic_2ds | |✓ | | 2000|acc |\n", "|arithmetic_3da | |✓ | | 2000|acc |\n", "|arithmetic_3ds | |✓ | | 2000|acc |\n", "|arithmetic_4da | |✓ | | 2000|acc |\n", "|arithmetic_4ds | |✓ | | 2000|acc |\n", "|arithmetic_5da | |✓ | | 2000|acc |\n", "|arithmetic_5ds | |✓ | | 2000|acc |\n", "|bigbench_causal_judgement | | |✓ | 190|multiple_choice_grade, exact_str_match |\n", "|bigbench_date_understanding | | |✓ | 369|multiple_choice_grade, exact_str_match |\n", "|bigbench_disambiguation_qa | | |✓ | 258|multiple_choice_grade, exact_str_match |\n", "|bigbench_dyck_languages | | |✓ | 1000|multiple_choice_grade, exact_str_match |\n", "|bigbench_formal_fallacies_syllogisms_negation | | |✓ | 14200|multiple_choice_grade, exact_str_match |\n", "|bigbench_geometric_shapes | | |✓ | 359|multiple_choice_grade, exact_str_match |\n", "|bigbench_hyperbaton | | |✓ | 50000|multiple_choice_grade, exact_str_match |\n", "|bigbench_logical_deduction_five_objects | | |✓ | 500|multiple_choice_grade, exact_str_match |\n", "|bigbench_logical_deduction_seven_objects | | |✓ | 700|multiple_choice_grade, exact_str_match |\n", "|bigbench_logical_deduction_three_objects | | |✓ | 300|multiple_choice_grade, exact_str_match |\n", "|bigbench_movie_recommendation | | |✓ | 500|multiple_choice_grade, exact_str_match |\n", "|bigbench_navigate | | |✓ | 1000|multiple_choice_grade, exact_str_match |\n", "|bigbench_reasoning_about_colored_objects | | |✓ | 2000|multiple_choice_grade, exact_str_match |\n", "|bigbench_ruin_names | | |✓ | 448|multiple_choice_grade, exact_str_match |\n", "|bigbench_salient_translation_error_detection | | |✓ | 998|multiple_choice_grade, exact_str_match |\n", "|bigbench_snarks | | |✓ | 181|multiple_choice_grade, exact_str_match |\n", "|bigbench_sports_understanding | | |✓ | 986|multiple_choice_grade, exact_str_match |\n", "|bigbench_temporal_sequences | | |✓ | 1000|multiple_choice_grade, exact_str_match |\n", "|bigbench_tracking_shuffled_objects_five_objects | | |✓ | 1250|multiple_choice_grade, exact_str_match |\n", "|bigbench_tracking_shuffled_objects_seven_objects | | |✓ | 1750|multiple_choice_grade, exact_str_match |\n", "|bigbench_tracking_shuffled_objects_three_objects | | |✓ | 300|multiple_choice_grade, exact_str_match |\n", "|blimp_adjunct_island | |✓ | | 1000|acc |\n", "|blimp_anaphor_gender_agreement | |✓ | | 1000|acc |\n", "|blimp_anaphor_number_agreement | |✓ | | 1000|acc |\n", "|blimp_animate_subject_passive | |✓ | | 1000|acc |\n", "|blimp_animate_subject_trans | |✓ | | 1000|acc |\n", "|blimp_causative | |✓ | | 1000|acc |\n", "|blimp_complex_NP_island | |✓ | | 1000|acc |\n", "|blimp_coordinate_structure_constraint_complex_left_branch| |✓ | | 1000|acc |\n", "|blimp_coordinate_structure_constraint_object_extraction | |✓ | | 1000|acc |\n", "|blimp_determiner_noun_agreement_1 | |✓ | | 1000|acc |\n", "|blimp_determiner_noun_agreement_2 | |✓ | | 1000|acc |\n", "|blimp_determiner_noun_agreement_irregular_1 | |✓ | | 1000|acc |\n", "|blimp_determiner_noun_agreement_irregular_2 | |✓ | | 1000|acc |\n", "|blimp_determiner_noun_agreement_with_adj_2 | |✓ | | 1000|acc |\n", "|blimp_determiner_noun_agreement_with_adj_irregular_1 | |✓ | | 1000|acc |\n", "|blimp_determiner_noun_agreement_with_adj_irregular_2 | |✓ | | 1000|acc |\n", "|blimp_determiner_noun_agreement_with_adjective_1 | |✓ | | 1000|acc |\n", "|blimp_distractor_agreement_relational_noun | |✓ | | 1000|acc |\n", "|blimp_distractor_agreement_relative_clause | |✓ | | 1000|acc |\n", "|blimp_drop_argument | |✓ | | 1000|acc |\n", "|blimp_ellipsis_n_bar_1 | |✓ | | 1000|acc |\n", "|blimp_ellipsis_n_bar_2 | |✓ | | 1000|acc |\n", "|blimp_existential_there_object_raising | |✓ | | 1000|acc |\n", "|blimp_existential_there_quantifiers_1 | |✓ | | 1000|acc |\n", "|blimp_existential_there_quantifiers_2 | |✓ | | 1000|acc |\n", "|blimp_existential_there_subject_raising | |✓ | | 1000|acc |\n", "|blimp_expletive_it_object_raising | |✓ | | 1000|acc |\n", "|blimp_inchoative | |✓ | | 1000|acc |\n", "|blimp_intransitive | |✓ | | 1000|acc |\n", "|blimp_irregular_past_participle_adjectives | |✓ | | 1000|acc |\n", "|blimp_irregular_past_participle_verbs | |✓ | | 1000|acc |\n", "|blimp_irregular_plural_subject_verb_agreement_1 | |✓ | | 1000|acc |\n", "|blimp_irregular_plural_subject_verb_agreement_2 | |✓ | | 1000|acc |\n", "|blimp_left_branch_island_echo_question | |✓ | | 1000|acc |\n", "|blimp_left_branch_island_simple_question | |✓ | | 1000|acc |\n", "|blimp_matrix_question_npi_licensor_present | |✓ | | 1000|acc |\n", "|blimp_npi_present_1 | |✓ | | 1000|acc |\n", "|blimp_npi_present_2 | |✓ | | 1000|acc |\n", "|blimp_only_npi_licensor_present | |✓ | | 1000|acc |\n", "|blimp_only_npi_scope | |✓ | | 1000|acc |\n", "|blimp_passive_1 | |✓ | | 1000|acc |\n", "|blimp_passive_2 | |✓ | | 1000|acc |\n", "|blimp_principle_A_c_command | |✓ | | 1000|acc |\n", "|blimp_principle_A_case_1 | |✓ | | 1000|acc |\n", "|blimp_principle_A_case_2 | |✓ | | 1000|acc |\n", "|blimp_principle_A_domain_1 | |✓ | | 1000|acc |\n", "|blimp_principle_A_domain_2 | |✓ | | 1000|acc |\n", "|blimp_principle_A_domain_3 | |✓ | | 1000|acc |\n", "|blimp_principle_A_reconstruction | |✓ | | 1000|acc |\n", "|blimp_regular_plural_subject_verb_agreement_1 | |✓ | | 1000|acc |\n", "|blimp_regular_plural_subject_verb_agreement_2 | |✓ | | 1000|acc |\n", "|blimp_sentential_negation_npi_licensor_present | |✓ | | 1000|acc |\n", "|blimp_sentential_negation_npi_scope | |✓ | | 1000|acc |\n", "|blimp_sentential_subject_island | |✓ | | 1000|acc |\n", "|blimp_superlative_quantifiers_1 | |✓ | | 1000|acc |\n", "|blimp_superlative_quantifiers_2 | |✓ | | 1000|acc |\n", "|blimp_tough_vs_raising_1 | |✓ | | 1000|acc |\n", "|blimp_tough_vs_raising_2 | |✓ | | 1000|acc |\n", "|blimp_transitive | |✓ | | 1000|acc |\n", "|blimp_wh_island | |✓ | | 1000|acc |\n", "|blimp_wh_questions_object_gap | |✓ | | 1000|acc |\n", "|blimp_wh_questions_subject_gap | |✓ | | 1000|acc |\n", "|blimp_wh_questions_subject_gap_long_distance | |✓ | | 1000|acc |\n", "|blimp_wh_vs_that_no_gap | |✓ | | 1000|acc |\n", "|blimp_wh_vs_that_no_gap_long_distance | |✓ | | 1000|acc |\n", "|blimp_wh_vs_that_with_gap | |✓ | | 1000|acc |\n", "|blimp_wh_vs_that_with_gap_long_distance | |✓ | | 1000|acc |\n", "|boolq |✓ |✓ | | 3270|acc |\n", "|cb |✓ |✓ | | 56|acc, f1 |\n", "|cola |✓ |✓ | | 1043|mcc |\n", "|copa |✓ |✓ | | 100|acc |\n", "|coqa |✓ |✓ | | 500|f1, em |\n", "|crows_pairs_english | |✓ | | 1677|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_age | |✓ | | 91|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_autre | |✓ | | 11|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_disability | |✓ | | 65|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_gender | |✓ | | 320|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_nationality | |✓ | | 216|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_physical_appearance | |✓ | | 72|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_race_color | |✓ | | 508|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_religion | |✓ | | 111|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_sexual_orientation | |✓ | | 93|likelihood_difference, pct_stereotype |\n", "|crows_pairs_english_socioeconomic | |✓ | | 190|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french | |✓ | | 1677|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_age | |✓ | | 90|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_autre | |✓ | | 13|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_disability | |✓ | | 66|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_gender | |✓ | | 321|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_nationality | |✓ | | 253|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_physical_appearance | |✓ | | 72|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_race_color | |✓ | | 460|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_religion | |✓ | | 115|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_sexual_orientation | |✓ | | 91|likelihood_difference, pct_stereotype |\n", "|crows_pairs_french_socioeconomic | |✓ | | 196|likelihood_difference, pct_stereotype |\n", "|cycle_letters | |✓ | | 10000|acc |\n", "|drop |✓ |✓ | | 9536|em, f1 |\n", "|ethics_cm |✓ | |✓ | 3885|acc |\n", "|ethics_deontology |✓ | |✓ | 3596|acc, em |\n", "|ethics_justice |✓ | |✓ | 2704|acc, em |\n", "|ethics_utilitarianism |✓ | |✓ | 4808|acc |\n", "|ethics_utilitarianism_original | | |✓ | 4808|acc |\n", "|ethics_virtue |✓ | |✓ | 4975|acc, em |\n", "|gsm8k |✓ | |✓ | 1319|acc |\n", "|headqa |✓ |✓ |✓ | 2742|acc, acc_norm |\n", "|headqa_en |✓ |✓ |✓ | 2742|acc, acc_norm |\n", "|headqa_es |✓ |✓ |✓ | 2742|acc, acc_norm |\n", "|hellaswag |✓ |✓ | | 10042|acc, acc_norm |\n", "|hendrycksTest-abstract_algebra | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-anatomy | |✓ |✓ | 135|acc, acc_norm |\n", "|hendrycksTest-astronomy | |✓ |✓ | 152|acc, acc_norm |\n", "|hendrycksTest-business_ethics | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-clinical_knowledge | |✓ |✓ | 265|acc, acc_norm |\n", "|hendrycksTest-college_biology | |✓ |✓ | 144|acc, acc_norm |\n", "|hendrycksTest-college_chemistry | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-college_computer_science | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-college_mathematics | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-college_medicine | |✓ |✓ | 173|acc, acc_norm |\n", "|hendrycksTest-college_physics | |✓ |✓ | 102|acc, acc_norm |\n", "|hendrycksTest-computer_security | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-conceptual_physics | |✓ |✓ | 235|acc, acc_norm |\n", "|hendrycksTest-econometrics | |✓ |✓ | 114|acc, acc_norm |\n", "|hendrycksTest-electrical_engineering | |✓ |✓ | 145|acc, acc_norm |\n", "|hendrycksTest-elementary_mathematics | |✓ |✓ | 378|acc, acc_norm |\n", "|hendrycksTest-formal_logic | |✓ |✓ | 126|acc, acc_norm |\n", "|hendrycksTest-global_facts | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-high_school_biology | |✓ |✓ | 310|acc, acc_norm |\n", "|hendrycksTest-high_school_chemistry | |✓ |✓ | 203|acc, acc_norm |\n", "|hendrycksTest-high_school_computer_science | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-high_school_european_history | |✓ |✓ | 165|acc, acc_norm |\n", "|hendrycksTest-high_school_geography | |✓ |✓ | 198|acc, acc_norm |\n", "|hendrycksTest-high_school_government_and_politics | |✓ |✓ | 193|acc, acc_norm |\n", "|hendrycksTest-high_school_macroeconomics | |✓ |✓ | 390|acc, acc_norm |\n", "|hendrycksTest-high_school_mathematics | |✓ |✓ | 270|acc, acc_norm |\n", "|hendrycksTest-high_school_microeconomics | |✓ |✓ | 238|acc, acc_norm |\n", "|hendrycksTest-high_school_physics | |✓ |✓ | 151|acc, acc_norm |\n", "|hendrycksTest-high_school_psychology | |✓ |✓ | 545|acc, acc_norm |\n", "|hendrycksTest-high_school_statistics | |✓ |✓ | 216|acc, acc_norm |\n", "|hendrycksTest-high_school_us_history | |✓ |✓ | 204|acc, acc_norm |\n", "|hendrycksTest-high_school_world_history | |✓ |✓ | 237|acc, acc_norm |\n", "|hendrycksTest-human_aging | |✓ |✓ | 223|acc, acc_norm |\n", "|hendrycksTest-human_sexuality | |✓ |✓ | 131|acc, acc_norm |\n", "|hendrycksTest-international_law | |✓ |✓ | 121|acc, acc_norm |\n", "|hendrycksTest-jurisprudence | |✓ |✓ | 108|acc, acc_norm |\n", "|hendrycksTest-logical_fallacies | |✓ |✓ | 163|acc, acc_norm |\n", "|hendrycksTest-machine_learning | |✓ |✓ | 112|acc, acc_norm |\n", "|hendrycksTest-management | |✓ |✓ | 103|acc, acc_norm |\n", "|hendrycksTest-marketing | |✓ |✓ | 234|acc, acc_norm |\n", "|hendrycksTest-medical_genetics | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-miscellaneous | |✓ |✓ | 783|acc, acc_norm |\n", "|hendrycksTest-moral_disputes | |✓ |✓ | 346|acc, acc_norm |\n", "|hendrycksTest-moral_scenarios | |✓ |✓ | 895|acc, acc_norm |\n", "|hendrycksTest-nutrition | |✓ |✓ | 306|acc, acc_norm |\n", "|hendrycksTest-philosophy | |✓ |✓ | 311|acc, acc_norm |\n", "|hendrycksTest-prehistory | |✓ |✓ | 324|acc, acc_norm |\n", "|hendrycksTest-professional_accounting | |✓ |✓ | 282|acc, acc_norm |\n", "|hendrycksTest-professional_law | |✓ |✓ | 1534|acc, acc_norm |\n", "|hendrycksTest-professional_medicine | |✓ |✓ | 272|acc, acc_norm |\n", "|hendrycksTest-professional_psychology | |✓ |✓ | 612|acc, acc_norm |\n", "|hendrycksTest-public_relations | |✓ |✓ | 110|acc, acc_norm |\n", "|hendrycksTest-security_studies | |✓ |✓ | 245|acc, acc_norm |\n", "|hendrycksTest-sociology | |✓ |✓ | 201|acc, acc_norm |\n", "|hendrycksTest-us_foreign_policy | |✓ |✓ | 100|acc, acc_norm |\n", "|hendrycksTest-virology | |✓ |✓ | 166|acc, acc_norm |\n", "|hendrycksTest-world_religions | |✓ |✓ | 171|acc, acc_norm |\n", "|iwslt17-ar-en | | |✓ | 1460|bleu, chrf, ter |\n", "|iwslt17-en-ar | | |✓ | 1460|bleu, chrf, ter |\n", "|lambada_openai | | |✓ | 5153|ppl, acc |\n", "|lambada_openai_cloze | | |✓ | 5153|ppl, acc |\n", "|lambada_openai_mt_de | | |✓ | 5153|ppl, acc |\n", "|lambada_openai_mt_en | | |✓ | 5153|ppl, acc |\n", "|lambada_openai_mt_es | | |✓ | 5153|ppl, acc |\n", "|lambada_openai_mt_fr | | |✓ | 5153|ppl, acc |\n", "|lambada_openai_mt_it | | |✓ | 5153|ppl, acc |\n", "|lambada_standard | |✓ |✓ | 5153|ppl, acc |\n", "|lambada_standard_cloze | |✓ |✓ | 5153|ppl, acc |\n", "|logiqa |✓ |✓ |✓ | 651|acc, acc_norm |\n", "|math_algebra |✓ | |✓ | 1187|acc |\n", "|math_asdiv | |✓ | | 2305|acc |\n", "|math_counting_and_prob |✓ | |✓ | 474|acc |\n", "|math_geometry |✓ | |✓ | 479|acc |\n", "|math_intermediate_algebra |✓ | |✓ | 903|acc |\n", "|math_num_theory |✓ | |✓ | 540|acc |\n", "|math_prealgebra |✓ | |✓ | 871|acc |\n", "|math_precalc |✓ | |✓ | 546|acc |\n", "|mathqa |✓ |✓ |✓ | 2985|acc, acc_norm |\n", "|mc_taco | |✓ |✓ | 9442|f1, em |\n", "|mgsm_bn |✓ | |✓ | 250|acc |\n", "|mgsm_de |✓ | |✓ | 250|acc |\n", "|mgsm_en |✓ | |✓ | 250|acc |\n", "|mgsm_es |✓ | |✓ | 250|acc |\n", "|mgsm_fr |✓ | |✓ | 250|acc |\n", "|mgsm_ja |✓ | |✓ | 250|acc |\n", "|mgsm_ru |✓ | |✓ | 250|acc |\n", "|mgsm_sw |✓ | |✓ | 250|acc |\n", "|mgsm_te |✓ | |✓ | 250|acc |\n", "|mgsm_th |✓ | |✓ | 250|acc |\n", "|mgsm_zh |✓ | |✓ | 250|acc |\n", "|mnli |✓ |✓ | | 9815|acc |\n", "|mnli_mismatched |✓ |✓ | | 9832|acc |\n", "|mrpc |✓ |✓ | | 408|acc, f1 |\n", "|multirc |✓ |✓ | | 4848|acc |\n", "|mutual |✓ |✓ | | 886|r@1, r@2, mrr |\n", "|mutual_plus |✓ |✓ | | 886|r@1, r@2, mrr |\n", "|openbookqa |✓ |✓ |✓ | 500|acc, acc_norm |\n", "|pawsx_de |✓ |✓ |✓ | 2000|acc |\n", "|pawsx_en |✓ |✓ |✓ | 2000|acc |\n", "|pawsx_es |✓ |✓ |✓ | 2000|acc |\n", "|pawsx_fr |✓ |✓ |✓ | 2000|acc |\n", "|pawsx_ja |✓ |✓ |✓ | 2000|acc |\n", "|pawsx_ko |✓ |✓ |✓ | 2000|acc |\n", "|pawsx_zh |✓ |✓ |✓ | 2000|acc |\n", "|pile_arxiv | |✓ |✓ | 2407|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_bookcorpus2 | |✓ |✓ | 28|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_books3 | |✓ |✓ | 269|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_dm-mathematics | |✓ |✓ | 1922|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_enron | |✓ |✓ | 1010|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_europarl | |✓ |✓ | 157|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_freelaw | |✓ |✓ | 5101|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_github | |✓ |✓ | 18195|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_gutenberg | |✓ |✓ | 80|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_hackernews | |✓ |✓ | 1632|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_nih-exporter | |✓ |✓ | 1884|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_opensubtitles | |✓ |✓ | 642|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_openwebtext2 | |✓ |✓ | 32925|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_philpapers | |✓ |✓ | 68|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_pile-cc | |✓ |✓ | 52790|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_pubmed-abstracts | |✓ |✓ | 29895|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_pubmed-central | |✓ |✓ | 5911|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_stackexchange | |✓ |✓ | 30378|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_ubuntu-irc | |✓ |✓ | 22|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_uspto | |✓ |✓ | 11415|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_wikipedia | |✓ |✓ | 17511|word_perplexity, byte_perplexity, bits_per_byte |\n", "|pile_youtubesubtitles | |✓ |✓ | 342|word_perplexity, byte_perplexity, bits_per_byte |\n", "|piqa |✓ |✓ | | 1838|acc, acc_norm |\n", "|prost | | |✓ | 18736|acc, acc_norm |\n", "|pubmedqa | | |✓ | 1000|acc |\n", "|qa4mre_2011 | | |✓ | 120|acc, acc_norm |\n", "|qa4mre_2012 | | |✓ | 160|acc, acc_norm |\n", "|qa4mre_2013 | | |✓ | 284|acc, acc_norm |\n", "|qasper |✓ |✓ | | 1764|f1_yesno, f1_abstractive |\n", "|qnli |✓ |✓ | | 5463|acc |\n", "|qqp |✓ |✓ | | 40430|acc, f1 |\n", "|race |✓ |✓ |✓ | 1045|acc |\n", "|random_insertion | |✓ | | 10000|acc |\n", "|record |✓ |✓ | | 10000|f1, em |\n", "|reversed_words | |✓ | | 10000|acc |\n", "|rte |✓ |✓ | | 277|acc |\n", "|sciq |✓ |✓ |✓ | 1000|acc, acc_norm |\n", "|scrolls_contractnli |✓ |✓ | | 1037|em, acc, acc_norm |\n", "|scrolls_govreport |✓ |✓ | | 972|rouge1, rouge2, rougeL |\n", "|scrolls_narrativeqa |✓ |✓ | | 3425|f1 |\n", "|scrolls_qasper |✓ |✓ | | 984|f1 |\n", "|scrolls_qmsum |✓ |✓ | | 272|rouge1, rouge2, rougeL |\n", "|scrolls_quality |✓ |✓ | | 2086|em, acc, acc_norm |\n", "|scrolls_summscreenfd |✓ |✓ | | 338|rouge1, rouge2, rougeL |\n", "|squad2 |✓ |✓ | | 11873|exact, f1, HasAns_exact, HasAns_f1, NoAns_exact, NoAns_f1, best_exact, best_f1 |\n", "|sst |✓ |✓ | | 872|acc |\n", "|swag |✓ |✓ | | 20006|acc, acc_norm |\n", "|toxigen |✓ | |✓ | 940|acc, acc_norm |\n", "|triviaqa |✓ |✓ | | 11313|acc |\n", "|truthfulqa_gen | |✓ | | 817|bleurt_max, bleurt_acc, bleurt_diff, bleu_max, bleu_acc, bleu_diff, rouge1_max, rouge1_acc, rouge1_diff, rouge2_max, rouge2_acc, rouge2_diff, rougeL_max, rougeL_acc, rougeL_diff|\n", "|truthfulqa_mc | |✓ | | 817|mc1, mc2 |\n", "|webqs |✓ | |✓ | 2032|acc |\n", "|wic |✓ |✓ | | 638|acc |\n", "|wikitext |✓ |✓ |✓ | 62|word_perplexity, byte_perplexity, bits_per_byte |\n", "|winogrande |✓ |✓ | | 1267|acc |\n", "|wmt14-en-fr | | |✓ | 3003|bleu, chrf, ter |\n", "|wmt14-fr-en | | |✓ | 3003|bleu, chrf, ter |\n", "|wmt16-de-en | | |✓ | 2999|bleu, chrf, ter |\n", "|wmt16-en-de | | |✓ | 2999|bleu, chrf, ter |\n", "|wmt16-en-ro | | |✓ | 1999|bleu, chrf, ter |\n", "|wmt16-ro-en | | |✓ | 1999|bleu, chrf, ter |\n", "|wmt20-cs-en | | |✓ | 664|bleu, chrf, ter |\n", "|wmt20-de-en | | |✓ | 785|bleu, chrf, ter |\n", "|wmt20-de-fr | | |✓ | 1619|bleu, chrf, ter |\n", "|wmt20-en-cs | | |✓ | 1418|bleu, chrf, ter |\n", "|wmt20-en-de | | |✓ | 1418|bleu, chrf, ter |\n", "|wmt20-en-iu | | |✓ | 2971|bleu, chrf, ter |\n", "|wmt20-en-ja | | |✓ | 1000|bleu, chrf, ter |\n", "|wmt20-en-km | | |✓ | 2320|bleu, chrf, ter |\n", "|wmt20-en-pl | | |✓ | 1000|bleu, chrf, ter |\n", "|wmt20-en-ps | | |✓ | 2719|bleu, chrf, ter |\n", "|wmt20-en-ru | | |✓ | 2002|bleu, chrf, ter |\n", "|wmt20-en-ta | | |✓ | 1000|bleu, chrf, ter |\n", "|wmt20-en-zh | | |✓ | 1418|bleu, chrf, ter |\n", "|wmt20-fr-de | | |✓ | 1619|bleu, chrf, ter |\n", "|wmt20-iu-en | | |✓ | 2971|bleu, chrf, ter |\n", "|wmt20-ja-en | | |✓ | 993|bleu, chrf, ter |\n", "|wmt20-km-en | | |✓ | 2320|bleu, chrf, ter |\n", "|wmt20-pl-en | | |✓ | 1001|bleu, chrf, ter |\n", "|wmt20-ps-en | | |✓ | 2719|bleu, chrf, ter |\n", "|wmt20-ru-en | | |✓ | 991|bleu, chrf, ter |\n", "|wmt20-ta-en | | |✓ | 997|bleu, chrf, ter |\n", "|wmt20-zh-en | | |✓ | 2000|bleu, chrf, ter |\n", "|wnli |✓ |✓ | | 71|acc |\n", "|wsc |✓ |✓ | | 104|acc |\n", "|wsc273 | | |✓ | 273|acc |\n", "|xcopa_et | |✓ |✓ | 500|acc |\n", "|xcopa_ht | |✓ |✓ | 500|acc |\n", "|xcopa_id | |✓ |✓ | 500|acc |\n", "|xcopa_it | |✓ |✓ | 500|acc |\n", "|xcopa_qu | |✓ |✓ | 500|acc |\n", "|xcopa_sw | |✓ |✓ | 500|acc |\n", "|xcopa_ta | |✓ |✓ | 500|acc |\n", "|xcopa_th | |✓ |✓ | 500|acc |\n", "|xcopa_tr | |✓ |✓ | 500|acc |\n", "|xcopa_vi | |✓ |✓ | 500|acc |\n", "|xcopa_zh | |✓ |✓ | 500|acc |\n", "|xnli_ar |✓ |✓ |✓ | 5010|acc |\n", "|xnli_bg |✓ |✓ |✓ | 5010|acc |\n", "|xnli_de |✓ |✓ |✓ | 5010|acc |\n", "|xnli_el |✓ |✓ |✓ | 5010|acc |\n", "|xnli_en |✓ |✓ |✓ | 5010|acc |\n", "|xnli_es |✓ |✓ |✓ | 5010|acc |\n", "|xnli_fr |✓ |✓ |✓ | 5010|acc |\n", "|xnli_hi |✓ |✓ |✓ | 5010|acc |\n", "|xnli_ru |✓ |✓ |✓ | 5010|acc |\n", "|xnli_sw |✓ |✓ |✓ | 5010|acc |\n", "|xnli_th |✓ |✓ |✓ | 5010|acc |\n", "|xnli_tr |✓ |✓ |✓ | 5010|acc |\n", "|xnli_ur |✓ |✓ |✓ | 5010|acc |\n", "|xnli_vi |✓ |✓ |✓ | 5010|acc |\n", "|xnli_zh |✓ |✓ |✓ | 5010|acc |\n", "|xstory_cloze_ar |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_en |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_es |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_eu |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_hi |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_id |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_my |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_ru |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_sw |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_te |✓ |✓ | | 1511|acc |\n", "|xstory_cloze_zh |✓ |✓ | | 1511|acc |\n", "|xwinograd_en | | |✓ | 2325|acc |\n", "|xwinograd_fr | | |✓ | 83|acc |\n", "|xwinograd_jp | | |✓ | 959|acc |\n", "|xwinograd_pt | | |✓ | 263|acc |\n", "|xwinograd_ru | | |✓ | 315|acc |\n", "|xwinograd_zh | | |✓ | 504|acc |\n", "| Ceval-valid-computer_network | | ✓ | | 19 | acc |\n", "| Ceval-valid-operating_system | | ✓ | | 19 | acc |\n", "| Ceval-valid-computer_architecture | | ✓ | | 21 | acc |\n", "| Ceval-valid-college_programming | | ✓ | | 37 | acc |\n", "| Ceval-valid-college_physics | | ✓ | | 19 | acc |\n", "| Ceval-valid-college_chemistry | | ✓ | | 24 | acc |\n", "| Ceval-valid-advanced_mathematics | | ✓ | | 19 | acc |\n", "| Ceval-valid-probability_and_statistics | | ✓ | | 18 | acc |\n", "| Ceval-valid-discrete_mathematics | | ✓ | | 16 | acc |\n", "| Ceval-valid-electrical_engineer | | ✓ | | 37 | acc |\n", "| Ceval-valid-metrology_engineer | | ✓ | | 24 | acc |\n", "| Ceval-valid-high_school_mathematics | | ✓ | | 18 | acc |\n", "| Ceval-valid-high_school_physics | | ✓ | | 19 | acc |\n", "| Ceval-valid-high_school_chemistry | | ✓ | | 19 | acc |\n", "| Ceval-valid-high_school_biology | | ✓ | | 19 | acc |\n", "| Ceval-valid-middle_school_mathematics | | ✓ | | 19 | acc |\n", "| Ceval-valid-middle_school_biology | | ✓ | | 21 | acc |\n", "| Ceval-valid-middle_school_physics | | ✓ | | 19 | acc |\n", "| Ceval-valid-middle_school_chemistry | | ✓ | | 20 | acc |\n", "| Ceval-valid-veterinary_medicine | | ✓ | | 23 | acc |\n", "| Ceval-valid-college_economics | | ✓ | | 55 | acc |\n", "| Ceval-valid-business_administration | | ✓ | | 33 | acc |\n", "| Ceval-valid-marxism | | ✓ | | 19 | acc |\n", "| Ceval-valid-mao_zedong_thought | | ✓ | | 24 | acc |\n", "| Ceval-valid-education_science | | ✓ | | 29 | acc |\n", "| Ceval-valid-teacher_qualification | | ✓ | | 44 | acc |\n", "| Ceval-valid-high_school_politics | | ✓ | | 19 | acc |\n", "| Ceval-valid-high_school_geography | | ✓ | | 19 | acc |\n", "| Ceval-valid-middle_school_politics | | ✓ | | 21 | acc |\n", "| Ceval-valid-middle_school_geography | | ✓ | | 12 | acc |\n", "| Ceval-valid-modern_chinese_history | | ✓ | | 23 | acc |\n", "| Ceval-valid-ideological_and_moral_cultivation | | ✓ | | 19 | acc |\n", "| Ceval-valid-logic | | ✓ | | 22 | acc |\n", "| Ceval-valid-law | | ✓ | | 24 | acc |\n", "| Ceval-valid-chinese_language_and_literature | | ✓ | | 23 | acc |\n", "| Ceval-valid-art_studies | | ✓ | | 33 | acc |\n", "| Ceval-valid-professional_tour_guide | | ✓ | | 29 | acc |\n", "| Ceval-valid-legal_professional | | ✓ | | 23 | acc |\n", "| Ceval-valid-high_school_chinese | | ✓ | | 19 | acc |\n", "| Ceval-valid-high_school_history | | ✓ | | 20 | acc |\n", "| Ceval-valid-middle_school_history | | ✓ | | 22 | acc |\n", "| Ceval-valid-civil_servant | | ✓ | | 47 | acc |\n", "| Ceval-valid-sports_science | | ✓ | | 19 | acc |\n", "| Ceval-valid-plant_protection | | ✓ | | 22 | acc |\n", "| Ceval-valid-basic_medicine | | ✓ | | 19 | acc |\n", "| Ceval-valid-clinical_medicine | | ✓ | | 22 | acc |\n", "| Ceval-valid-urban_and_rural_planner | | ✓ | | 46 | acc |\n", "| Ceval-valid-accountant | | ✓ | | 49 | acc |\n", "| Ceval-valid-fire_engineer | | ✓ | | 31 | acc |\n", "| Ceval-valid-environmental_impact_assessment_engineer | | ✓ | | 31 | acc |\n", "| Ceval-valid-tax_accountant | | ✓ | | 49 | acc |\n", "| Ceval-valid-physician | | ✓ | | 49 | acc |" ] } ], "metadata": { "accelerator": "GPU", "colab": { "gpuType": "T4", "provenance": [] }, "kernelspec": { "display_name": "Python 3", "name": "python3" }, "language_info": { "name": "python" } }, "nbformat": 4, "nbformat_minor": 0 }