__main__.py

import os
import re
import sys
import json
import logging
import argparse
import numpy as np

from pathlib import Path
from typing import Union

from lm_eval import evaluator, utils
from lm_eval.tasks import initialize_tasks, include_path
from lm_eval.api.registry import ALL_TASKS


def _handle_non_serializable(o):
    if isinstance(o, np.int64) or isinstance(o, np.int32):
        return int(o)
    elif isinstance(o, set):
        return list(o)
    else:
        return str(o)


def parse_eval_args() -> argparse.Namespace:
    parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter)
    parser.add_argument("--model", default="hf", help="Name of model e.g. `hf`")
    parser.add_argument(
        "--tasks",
        default=None,
        help="To get full list of tasks, use the command lm-eval --tasks list",
    )
    parser.add_argument(
        "--model_args",
        default="",
        help="String arguments for model, e.g. `pretrained=EleutherAI/pythia-160m,dtype=float32`",
    )
    parser.add_argument(
        "--num_fewshot",
        type=int,
        default=None,
        help="Number of examples in few-shot context",
    )
    parser.add_argument("--batch_size", type=str, default=1)
    parser.add_argument(
        "--max_batch_size",
        type=int,
        default=None,
        help="Maximal batch size to try with --batch_size auto",
    )
    parser.add_argument(
        "--device",
        type=str,
        default=None,
        help="Device to use (e.g. cuda, cuda:0, cpu)",
    )
    parser.add_argument(
        "--output_path",
        default=None,
        type=str,
        metavar="= [dir/file.jsonl] [DIR]",
        help="The path to the output file where the result metrics will be saved. If the path is a directory and log_samples is true, the results will be saved in the directory. Else the parent directory will be used.",
    )
    parser.add_argument(
        "--limit",
        type=float,
        default=None,
        help="Limit the number of examples per task. "
        "If <1, limit is a percentage of the total number of examples.",
    )
    parser.add_argument(
        "--use_cache",
        type=str,
        default=None,
        help="A path to a sqlite db file for caching model responses. `None` if not caching.",
    )
    parser.add_argument("--decontamination_ngrams_path", default=None)  # TODO: not used
    parser.add_argument(
        "--check_integrity",
        action="store_true",
        help="Whether to run the relevant part of the test suite for the tasks",
    )
    parser.add_argument(
        "--write_out",
        action="store_true",
        default=False,
        help="Prints the prompt for the first few documents",
    )
    parser.add_argument(
        "--log_samples",
        action="store_true",
        default=False,
        help="If True, write out all model outputs and documents for per-sample measurement and post-hoc analysis",
    )
    parser.add_argument(
        "--show_config",
        action="store_true",
        default=False,
        help="If True, shows the the full config of all tasks at the end of the evaluation.",
    )
    parser.add_argument(
        "--include_path",
        type=str,
        default=None,
        help="Additional path to include if there are external tasks to include.",
    )
    parser.add_argument(
        "--verbosity",
        type=str,
        default="INFO",
        help="Log error when tasks are not registered.",
    )
    return parser.parse_args()


def cli_evaluate(args: Union[argparse.Namespace, None] = None) -> None:
    if not args:
        # we allow for args to be passed externally, else we parse them ourselves
        args = parse_eval_args()

    eval_logger = utils.eval_logger
    eval_logger.setLevel(getattr(logging, f"{args.verbosity}"))
    eval_logger.info(f"Verbosity set to {args.verbosity}")
    os.environ["TOKENIZERS_PARALLELISM"] = "false"

    initialize_tasks(args.verbosity)

    if args.limit:
        eval_logger.warning(
            " --limit SHOULD ONLY BE USED FOR TESTING."
            "REAL METRICS SHOULD NOT BE COMPUTED USING LIMIT."
        )
    if args.include_path is not None:
        eval_logger.info(f"Including path: {args.include_path}")
        include_path(args.include_path)

    if args.tasks is None:
        task_names = ALL_TASKS
    elif args.tasks == "list":
        eval_logger.info(
            "Available Tasks:\n - {}".format(f"\n - ".join(sorted(ALL_TASKS)))
        )
        sys.exit()
    else:
        if os.path.isdir(args.tasks):
            import glob

            task_names = []
            yaml_path = os.path.join(args.tasks, "*.yaml")
            for yaml_file in glob.glob(yaml_path):
                config = utils.load_yaml_config(yaml_file)
                task_names.append(config)
        else:
            tasks_list = args.tasks.split(",")
            task_names = utils.pattern_match(tasks_list, ALL_TASKS)
            for task in [task for task in tasks_list if task not in task_names]:
                if os.path.isfile(task):
                    config = utils.load_yaml_config(task)
                    task_names.append(config)
            task_missing = [
                task
                for task in tasks_list
                if task not in task_names and "*" not in task
            ]  # we don't want errors if a wildcard ("*") task name was used

            if task_missing:
                missing = ", ".join(task_missing)
                eval_logger.error(
                    f"Tasks were not found: {missing}\n"
                    f"{utils.SPACING}Try `lm-eval --tasks list` for list of available tasks",
                )
                raise ValueError(
                    f"Tasks {missing} were not found. Try `lm-eval --tasks list` for list of available tasks."
                )

    if args.output_path:
        path = Path(args.output_path)
        # check if file or 'dir/results.json' exists
        if path.is_file() or Path(args.output_path).joinpath("results.json").is_file():
            eval_logger.warning(
                f"File already exists at {path}. Results will be overwritten."
            )
            output_path_file = path.joinpath("results.json")
            assert not path.is_file(), "File already exists"
        # if path json then get parent dir
        elif path.suffix in (".json", ".jsonl"):
            output_path_file = path
            path.parent.mkdir(parents=True, exist_ok=True)
            path = path.parent
        else:
            path.mkdir(parents=True, exist_ok=True)
            output_path_file = path.joinpath("results.json")
    elif args.log_samples and not args.output_path:
        assert args.output_path, "Specify --output_path"

    eval_logger.info(f"Selected Tasks: {task_names}")

    results = evaluator.simple_evaluate(
        model=args.model,
        model_args=args.model_args,
        tasks=task_names,
        num_fewshot=args.num_fewshot,
        batch_size=args.batch_size,
        max_batch_size=args.max_batch_size,
        device=args.device,
        use_cache=args.use_cache,
        limit=args.limit,
        decontamination_ngrams_path=args.decontamination_ngrams_path,
        check_integrity=args.check_integrity,
        write_out=args.write_out,
        log_samples=args.log_samples,
    )

    if results is not None:
        if args.log_samples:
            samples = results.pop("samples")
        dumped = json.dumps(results, indent=2, default=_handle_non_serializable)
        if args.show_config:
            print(dumped)

        batch_sizes = ",".join(map(str, results["config"]["batch_sizes"]))

        if args.output_path:
            output_path_file.open("w").write(dumped)

            if args.log_samples:
                for task_name, config in results["configs"].items():
                    output_name = "{}_{}".format(
                        re.sub("/|=", "__", args.model_args), task_name
                    )
                    filename = path.joinpath(f"{output_name}.jsonl")
                    samples_dumped = json.dumps(
                        samples[task_name], indent=2, default=_handle_non_serializable
                    )
                    filename.open("w").write(samples_dumped)

        print(
            f"{args.model} ({args.model_args}), limit: {args.limit}, num_fewshot: {args.num_fewshot}, "
            f"batch_size: {args.batch_size}{f' ({batch_sizes})' if batch_sizes else ''}"
        )
        print(evaluator.make_table(results))
        if "groups" in results:
            print(evaluator.make_table(results, "groups"))


if __name__ == "__main__":
    cli_evaluate()