Skip to main content
stanford-mercury
Projects
suhas-data-efficiency
Reports
Project
Workspace
Runs
Automat.
Sweeps
Reports
Artifacts
Reports
Created by
Created On
Last edited
Pre-training under infinite compute
1
kothasuhas
2025-09-15
Self-distill first try (300M models)
Best single model loss: 3.587 Best two ensemble loss: approximately 3.43
0
kothasuhas
2025-07-16
data efficiency hyperparams
0
konwook
2025-06-22
Standard scaling runs
0
kothasuhas
2025-08-05
Data efficiency scaling laws
0
kothasuhas
2025-06-11