List your company

Machine Translation on WMT20

0.2RewardRLOO
0.10640.13070.1550.1793Mar 5, 2025

Evaluation results

MethodLinks
RLOOModel=Llama 3.2 1B, Hardware=4 x A100 (40GB VRAM)2025.030.2360.005—
ZOPrOModel=Llama 3.2 1B, Hardware=4 x A100 (40GB VRAM)2025.030.1560.025—
PPOModel=Llama 3.2 1B, Hardware=4 x A100 (40GB VRAM)2025.030.111150.0015—