Continuum Adaptive Data Mixing Challenge
Prize Challenge
active
LLM
Prize Challenge · Continuum continued pretraining with adaptive data mixing (DoGE / PiKE / fixed). First to cut pinned 8-source teutonic_mean loss by ≥0.0015 wins.
Participate: continue on the challenge websiteEvaluation: challenge-specific external systemPrize pool: $5,000.00Deadline:
1 participants
Sign in to registerAnnouncements
Organizer updates for this challenge.
Hello
Hello