List your company

Question Answering on HotPot D2 (test)

96.1Macro F1SURGELLM-S-DistilBERT
93.29294.02194.7595.479Jun 23, 2026

Evaluation results

MethodLinks
SURGELLM-S-DistilBERTFamily=SURGELLM-S, Parameters=66M, Training Time (s)=1192026.0696.1
SURGELLM-FULL-ALBERTFamily=SURGELLM-FULL, Parameters=11M, Training Time (s)=3172026.0696.1
SURGELLM-IWN-RoBERTaFamily=IWN, Parameters=125M, Training Time (s)=3322026.0695.4
SURGELLM-FULL-RoBERTaFamily=SURGELLM-FULL, Parameters=125M, Training Time (s)=326, Early Stopping=true2026.0695
SURGELLM-G-RoBERTaFamily=SURGELLM-G, Parameters=125M, Training Time (s)=327, Early Stopping=true2026.0694.9
Baseline-RoBERTaFamily=Baseline, Parameters=125M, Training Time (s)=2332026.0694.7
SURGELLM-IWN-BERTFamily=IWN, Parameters=110M, Training Time (s)=3222026.0694.6
Baseline-DistilBERTFamily=Baseline, Parameters=66M, Training Time (s)=822026.0694
T5-baseFamily=T5-T2T, Parameters=220M, Training Time (s)=4122026.0693.9
SURGELLM-S-BERTFamily=SURGELLM-S, Parameters=110M, Training Time (s)=3172026.0693.9
Baseline-BERTFamily=Baseline, Parameters=110M, Training Time (s)=2272026.0693.4