List your company

Fine-tuning on GSM8K (test)

2.4887Test PerplexityGaLore-AF
2.4409162.7634583.0863.408542May 6, 2026

Evaluation results

MethodLinks
GaLore-AFModel=Llama_3.2_3B, State (MB)=6.9551 ± 0.0000, Time (s)=4191.0108 ± 162.96932026.052.4887
GaLore-AFModel=Llama_3.2_1B, State (MB)=3.4351 ± 0.0000, Time (s)=344.5018 ± 0.41292026.052.7346
Adam-miniModel=Llama_3.2_1B, State (MB)=4715.5338 ± 0.0000, Time (s)=338.5162 ± 0.79522026.053.0536
BAOC0.5Model=Llama_3.2_1B, State (MB)=2140.1338 ± 0.0000, Time (s)=336.2259 ± 0.27602026.053.403
GaLore-AW32Model=Llama_3.2_1B, State (MB)=9428.5000 ± 0.0000, Time (s)=339.3417 ± 1.72662026.053.4293
AdamW16Model=Llama_3.2_1B, State (MB)=4714.5000 ± 0.0000, Time (s)=339.7833 ± 1.30112026.053.4436
AdamW8Model=Llama_3.2_1B, State (MB)=2394.5488 ± 0.0000, Time (s)=335.7520 ± 1.35822026.053.4735
GaLore-AW32Model=Llama_3.2_3B, State (MB)=24511.3125 ± 0.0000, Time (s)=4125.9537 ± 165.64562026.053.5431
AdamW16Model=Llama_3.2_3B, State (MB)=12256.3125 ± 0.0000, Time (s)=4085.5169 ± 168.23402026.053.5495
BAOC0.5Model=Llama_3.2_3B, State (MB)=6127.4092 ± 0.0000, Time (s)=4030.8570 ± 157.74222026.053.5713
AdamW8Model=Llama_3.2_3B, State (MB)=6224.9395 ± 0.0000, Time (s)=3945.8413 ± 160.40612026.053.6559
Adam-miniModel=Llama_3.2_3B, State (MB)=12258.1823 ± 0.0000, Time (s)=4135.7124 ± 140.34102026.053.6833