List your company

Language Model Pre-training on C4 (Eval Loss)

3.86Eval LossGrassWalk
3.76764.39135.0155.6387Oct 2, 2025

Evaluation results

MethodLinks
GrassWalkArch.=LLaMA-1B, Peak Mem. (GB)=32.0, Wall Time (m)=418.62025.103.86
GrassJumpArch.=LLaMA-1B, Peak Mem. (GB)=32.1, Wall Time (m)=415.22025.103.87
SubTrack++Arch.=LLaMA-1B, Peak Mem. (GB)=32.6, Wall Time (m)=429.22025.103.89
AdamW [Full-Rank]Arch.=LLaMA-1B, Peak Mem. (GB)=35.2, Wall Time (m)=417.02025.104.1
LDAdamArch.=LLaMA-1B, Peak Mem. (GB)=34.9, Wall Time (m)=532.82025.104.1
FRUGALArch.=LLaMA-1B, Peak Mem. (GB)=39.3, Wall Time (m)=405.12025.104.22
GrassJumpArch.=Qwen-1.5B, Peak Mem. (GB)=33.1, Wall Time (m)=432.22025.104.67
GrassWalkArch.=Qwen-1.5B, Peak Mem. (GB)=33.6, Wall Time (m)=436.62025.104.68
SubTrack++Arch.=Qwen-1.5B, Peak Mem. (GB)=33.1, Wall Time (m)=436.42025.104.7
AdamW [Full-Rank]Arch.=Qwen-1.5B, Peak Mem. (GB)=37.7, Wall Time (m)=421.02025.104.84
APOLLOArch.=LLaMA-1B, Peak Mem. (GB)=35.5, Wall Time (m)=410.52025.105.71
GaLoreArch.=LLaMA-1B, Peak Mem. (GB)=31.1, Wall Time (m)=522.22025.106.17