alihan/reasoning-gym
1
0
Fork 0
mirror of https://github.com/open-thought/reasoning-gym.git synced 2025-10-09 13:40:09 +03:00
Code Issues Packages Projects Releases Wiki Activity

fix dice

Browse Source
This commit is contained in:
Rich Jones
2025-03-11 00:44:48 +01:00
parent cedba8ec26
commit 60d9a29d38
1 changed files with 5 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
reasoning_gym/arithmetic/dice.py
View File

@@ -75,14 +75,14 @@ def generate_puzzle(num_dice, max_dice_size, rng):
high_target = min_total + 2 * (max_total - min_total) // 3 high_target = min_total + 2 * (max_total - min_total) // 3
target = rng.randint(low_target, high_target) target = rng.randint(low_target, high_target)
# Compute probability. # Compute probability. Don't change this.
(num, den) = compute_probability(dice, target) (num, den), probability = compute_probability(dice, target)
# Create a string representing the dice, e.g., "1d20, 1d17, 1d6" etc. # Create a string representing the dice, e.g., "1d20, 1d17, 1d6" etc.
dice_str = ", ".join(f"1d{s}" for s in dice) dice_str = ", ".join(f"1d{s}" for s in dice)
# Return the puzzle. # Return the puzzle.
return {"dice_str": dice_str, "target": target, "num": num, "den": den} return {"dice_str": dice_str, "target": target, "num": num, "den": den, "probability": probability}
@dataclass @dataclass
@@ -127,7 +127,8 @@ class DiceDataset(ProceduralDataset):
"difficulty": { "difficulty": {
"num_dice": self.config.num_dice, "num_dice": self.config.num_dice,
"max_dice_size": self.config.max_dice_size, "max_dice_size": self.config.max_dice_size,
} },
"puzzle": puzzle,
}, },
} }