ros/nanochat
1
0
Fork 0
mirror of https://github.com/karpathy/nanochat.git synced 2026-01-30 04:22:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

change test/train split approach because random.seed(1) and random.seed(-1) do the same thing

Browse Source
This commit is contained in:
Eric Silberstein
2025-11-19 14:51:02 -05:00
parent 4a87a0d19f
commit 97770700f2
1 changed files with 4 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tasks/spellingbee.py
View File

@@ -35,6 +35,8 @@ from nanochat.common import download_file_with_lock
LETTERS = "abcdefghijklmnopqrstuvwxyz"
# A list of 370K English words of large variety
WORD_LIST_URL = "https://raw.githubusercontent.com/dwyl/english-words/refs/heads/master/words_alpha.txt"
# A number bigger than 370K to separate train and test random seeds
TEST_RANDOM_SEED_OFFSET = 10_000_000
# Identical to gsm8k's answer extraction
ANSWER_RE = re.compile(r"#### (\-?[0-9\.\,]+)")
@@ -131,7 +133,7 @@ class SpellingBee(Task):
return self.size
def get_example(self, index):
seed = index if self.split == "train" else -(index + 1) # avoid collision at 0
seed = index if self.split == 'train' else TEST_RANDOM_SEED_OFFSET + index
rng = random.Random(seed)
# pick a random word
@@ -252,7 +254,7 @@ class SimpleSpelling(Task):
return self.size
def get_example(self, index):
seed = index if self.split == "train" else -(index + 1) # avoid collision at 0
seed = index if self.split == 'train' else TEST_RANDOM_SEED_OFFSET + index
rng = random.Random(seed)
# pick a random word
word = rng.choice(self.words)