#80·HRM

Full-Scale Experiment with exact_accuracy 0

Author: andreyferriyanCreated Sep 5, 2025Updated May 2, 2026

Hi, we have finished training for over a week with a single NVIDIA RTX A6000.

This is how we run the experiment OMP_NUM_THREADS=8 torchrun --nproc-per-node 1 pretrain.py global_batch_size=16.

Image

Compared to the small experiment, this full experiment was worse. Is there anything wrong with my configuration?.