ssnym

# ===========================================================================================================
# GPT-2 Implementation
# Based on Andrej Karpathy's "Let's reproduce GPT-2" lecture
# https://www.youtube.com/watch?v=l8pRSuU81PU
#
# Modifications done:
# - Custom DataLoader with sequential batching and train/val split
# - Custom tiktokenizer wrapper
# - Checkpoint save/load
# - EOT stop token inference

ssnym

import sys

def main():
    input_lines = sys.stdin.read().strip().split('\n')
    idx = 0
    N = int(input_lines[idx])
    idx += 1
    results = []

    for _ in range(N):