|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
import os |
|
from dataclasses import dataclass, field |
|
from typing import Literal, Optional |
|
|
|
from datasets import DownloadMode |
|
|
|
|
|
@dataclass |
|
class EvaluationArguments: |
|
r""" |
|
Arguments pertaining to specify the evaluation parameters. |
|
""" |
|
|
|
task: str = field( |
|
metadata={"help": "Name of the evaluation task."}, |
|
) |
|
task_dir: str = field( |
|
default="evaluation", |
|
metadata={"help": "Path to the folder containing the evaluation datasets."}, |
|
) |
|
batch_size: int = field( |
|
default=4, |
|
metadata={"help": "The batch size per GPU for evaluation."}, |
|
) |
|
seed: int = field( |
|
default=42, |
|
metadata={"help": "Random seed to be used with data loaders."}, |
|
) |
|
lang: Literal["en", "zh"] = field( |
|
default="en", |
|
metadata={"help": "Language used at evaluation."}, |
|
) |
|
n_shot: int = field( |
|
default=5, |
|
metadata={"help": "Number of examplars for few-shot learning."}, |
|
) |
|
save_dir: Optional[str] = field( |
|
default=None, |
|
metadata={"help": "Path to save the evaluation results."}, |
|
) |
|
download_mode: DownloadMode = field( |
|
default=DownloadMode.REUSE_DATASET_IF_EXISTS, |
|
metadata={"help": "Download mode used for the evaluation datasets."}, |
|
) |
|
|
|
def __post_init__(self): |
|
if self.save_dir is not None and os.path.exists(self.save_dir): |
|
raise ValueError("`save_dir` already exists, use another one.") |
|
|