Language Model Evaluation Harness

Overview

This project provides a unified framework to test autoregressive language models (GPT-2, GPT-3, GPTNeo, etc) on a large number of different evaluation tasks.

Features:

200+ tasks implemented. See the task-table for a complete list.
Support for GPT-2, GPT-3, GPT-Neo, GPT-NeoX, and GPT-J, with flexible tokenization-agnostic interface.
Task versioning to ensure reproducibility.

Install

pip install lm-eval

To install additional multlingual tokenization and text segmenation packages, you must install the package with the multilingual extra:

pip install "lm-eval[multilingual]"

Basic Usage

Note: When reporting results from eval harness, please include the task versions (shown in results["versions"]) for reproducibility. This allows bug fixes to tasks while also ensuring that previously reported scores are reproducible. See the Task Versioning section for more info.

To evaluate a model hosted on the HuggingFace Hub (e.g. GPT-J-6B) you can use the following command:

python main.py \
    --model hf-causal \
    --model_args pretrained=EleutherAI/gpt-j-6B \
    --tasks lambada_openai,hellaswag \
    --device 0

Additional arguments can be provided to the model constructor using the --model_args flag. Most notably, this supports the common practice of using the revisions feature on the Hub to store partialy trained checkpoints:

python main.py \
    --model hf-causal \
    --model_args pretrained=EleutherAI/pythia-160m,revision=step100000 \
    --tasks lambada_openai,hellaswag \
    --device 0

To evaluate models that are called via AutoSeq2SeqLM, you instead use hf-seq2seq.

Warning: Choosing the wrong model may result in erroneous outputs despite not erroring.

Our library also supports the OpenAI API:

export OPENAI_API_SECRET_KEY=YOUR_KEY_HERE
python main.py \
    --model gpt3 \
    --model_args engine=davinci \
    --tasks lambada_openai,hellaswag

While this functionality is only officially mantained for the official OpenAI API, it tends to also work for other hosting services that use the same API such as goose.ai with minor modification. We also have an implementation for the TextSynth API, using --model textsynth.

To verify the data integrity of the tasks you're performing in addition to running the tasks themselves, you can use the --check_integrity flag:

python main.py \
    --model gpt3 \
    --model_args engine=davinci \
    --tasks lambada_openai,hellaswag \
    --check_integrity

To evaluate mesh-transformer-jax models that are not available on HF, please invoke eval harness through this script.

💡 Tip: You can inspect what the LM inputs look like by running the following command:

python write_out.py \
    --tasks all_tasks \
    --num_fewshot 5 \
    --num_examples 10 \
    --output_base_path /path/to/output/folder

This will write out one text file for each task.

Implementing new tasks

To implement a new task in the eval harness, see this guide.

Task Versioning

To help improve reproducibility, all tasks have a VERSION field. When run from the command line, this is reported in a column in the table, or in the "version" field in the evaluator return dict. The purpose of the version is so that if the task definition changes (i.e to fix a bug), then we can know exactly which metrics were computed using the old buggy implementation to avoid unfair comparisons. To enforce this, there are unit tests that make sure the behavior of all tests remains the same as when they were first implemented. Task versions start at 0, and each time a breaking change is made, the version is incremented by one.

When reporting eval harness results, please also report the version of each task. This can be done either with a separate column in the table, or by reporting the task name with the version appended as such: taskname-v0.

Test Set Decontamination

For details on text decontamination, see the decontamination guide.

Note that the directory provided to the --decontamination_ngrams_path argument should contain the ngram files and info.json. See the above guide for ngram generation for the pile, this could be adapted for other training sets.

python main.py \
    --model gpt2 \
    --tasks sciq \
    --decontamination_ngrams_path path/containing/training/set/ngrams \
    --device 0

Cite as

@software{eval-harness,
  author       = {Gao, Leo and
                  Tow, Jonathan and
                  Biderman, Stella and
                  Black, Sid and
                  DiPofi, Anthony and
                  Foster, Charles and
                  Golding, Laurence and
                  Hsu, Jeffrey and
                  McDonell, Kyle and
                  Muennighoff, Niklas and
                  Phang, Jason and
                  Reynolds, Laria and
                  Tang, Eric and
                  Thite, Anish and
                  Wang, Ben and
                  Wang, Kevin and
                  Zou, Andy},
  title        = {A framework for few-shot language model evaluation},
  month        = sep,
  year         = 2021,
  publisher    = {Zenodo},
  version      = {v0.0.1},
  doi          = {10.5281/zenodo.5371628},
  url          = {https://doi.org/10.5281/zenodo.5371628}
}

afcruzs/lm-eval2