src/backend/envs.py

import os

import torch

from dataclasses import dataclass
from enum import Enum

from src.envs import CACHE_PATH


@dataclass
class Task:
    benchmark: str
    metric: str
    col_name: str


class Tasks(Enum):
    # task_key in the json file, metric_key in the json file, name to display in the leaderboard
    # task0 = Task("anli_r1", "acc", "ANLI")
    # task1 = Task("logiqa", "acc_norm", "LogiQA")
    task0 = Task("nq_open", "em", "NQ Open")
    task1 = Task("triviaqa", "em", "TriviaQA")


NUM_FEWSHOT = 64  # Change with your few shot

EVAL_REQUESTS_PATH_BACKEND = os.path.join(CACHE_PATH, "eval-queue-bk")
EVAL_RESULTS_PATH_BACKEND = os.path.join(CACHE_PATH, "eval-results-bk")

DEVICE = "cuda:0" if torch.cuda.is_available() else 'cpu'

LIMIT = 32  # Testing; needs to be None