mirror of
https://github.com/open-thought/reasoning-gym.git
synced 2026-04-19 12:58:07 +00:00
5d7fbac0ad
* math prompt improvements * ignore brackets in complex_arithmetic results * improve additional instruction in prompt of polynomial_equations * more strict tests for score_answer in polynomial_equations * simplify special reward handling * fix test_intermediate_integration * fix sokoban dataset * add common dataset score_answer consistency test
66 lines
2.2 KiB
Python
66 lines
2.2 KiB
Python
"""Computhe the power of a number."""
|
|
|
|
from dataclasses import dataclass
|
|
from math import pow
|
|
from random import Random
|
|
from typing import Any, Optional
|
|
|
|
from ..factory import ProceduralDataset, register_dataset
|
|
|
|
QUESTION_TEMPLATE = """Your task is to compute an exponentiation of a number.
|
|
|
|
Compute {base}^{exponent}
|
|
"""
|
|
|
|
|
|
@dataclass
|
|
class PowerFunctionConfig:
|
|
"""Configuration for Power Function dataset generation"""
|
|
|
|
min_base: float = -1e3 # Minimum base value
|
|
max_base: float = 1e3 # Maximum base value
|
|
min_exponent: int = -8 # Minimum exponent value
|
|
max_exponent: int = 8 # Maximum exponent value
|
|
|
|
size: int = 500 # Virtual dataset size
|
|
seed: Optional[int] = None
|
|
|
|
|
|
class PowerFunctionDataset(ProceduralDataset):
|
|
"""Generates Power Function exercises with configurable difficulty"""
|
|
|
|
def __init__(self, config: PowerFunctionConfig):
|
|
super().__init__(config=config, seed=config.seed, size=config.size)
|
|
|
|
def score_answer(self, answer: Optional[str], entry: dict[str, Any]) -> float:
|
|
"""Overwrite this method in derived classes if a single oracle answer is not available."""
|
|
oracle_answer = entry["answer"]
|
|
if answer is not None:
|
|
try:
|
|
answer = round(float(answer), 4)
|
|
oracle_answer = round(float(oracle_answer), 4)
|
|
difference = abs(float(answer) - float(oracle_answer))
|
|
if difference < 1e-4:
|
|
return 1.0
|
|
elif difference < 1e-1:
|
|
return 0.5
|
|
except Exception:
|
|
pass
|
|
return 0.0
|
|
|
|
def __getitem__(self, idx: int) -> dict:
|
|
"""Generate a single Power Function question"""
|
|
rng = Random(self.seed + idx)
|
|
|
|
base = round(rng.uniform(self.config.min_base, self.config.max_base), 4)
|
|
exponent = rng.randint(self.config.min_exponent, self.config.max_exponent)
|
|
answer = pow(base, exponent)
|
|
|
|
return {
|
|
"question": QUESTION_TEMPLATE.format(base=base, exponent=exponent),
|
|
"answer": str(answer),
|
|
"metadata": {"base": base, "exponent": exponent, "solution": answer},
|
|
}
|
|
|
|
|
|
register_dataset("power_function", PowerFunctionDataset, PowerFunctionConfig)
|