List your company

Generation Quality on RedPajama Generation Quality Prefixes (test)

32.4Standard Prefix CountSelf-Improving Pretraining: RF-NLL (rollout vs. rewrite)
0.0568.45316.8525.247Jan 29, 2026

Evaluation results

MethodLinks
Self-Improving Pretraining: RF-NLL (rollout vs. rewrite)Pretraining Strategy=from scratch, Model Scale=1.4B, Training Steps=21k steps, Number of rollouts=12026.0132.412.1
Self-Improving Pretraining: RF-NLL (suffix vs. rewrite)Pretraining Strategy=from scratch, Model Scale=1.4B, Training Steps=21k steps, Number of rollouts=12026.015.325.8
Pretrain on RewritesPretraining Strategy=from scratch, Model Scale=1.4B, Training Steps=21k steps, Number of rollouts=12026.011.62.4
Pretrain BaselinePretraining Strategy=from scratch, Model Scale=1.4B, Training Steps=21k steps, Number of rollouts=12026.011.32.4