pass config to ProceduralDataset base

This commit is contained in:
Andreas Koepf 2025-01-25 00:23:05 +01:00
parent df2b8d2809
commit e9549f2a63
20 changed files with 45 additions and 80 deletions

View file

@ -18,7 +18,7 @@ class WordReversalConfig:
seed: Optional[int] = None
size: int = 500 # Virtual dataset size
def validate(self):
def validate(self) -> None:
"""Validate configuration parameters"""
assert self.min_words > 0, "min_words must be positive"
assert self.max_words >= self.min_words, "max_words must be >= min_words"
@ -28,9 +28,7 @@ class WordReversalDataset(ProceduralDataset):
"""Generates word reversal tasks from text spans"""
def __init__(self, config: WordReversalConfig):
self.config = config
self.config.validate()
super().__init__(seed=config.seed, size=config.size)
super().__init__(config=config, seed=config.seed, size=config.size)
# Load and preprocess text
text = read_data_file("in_the_year_2889.txt")