Commonsense Reasoning on Winogrande (Metric)
81.1Winogrande AccuracyPaLM
Evaluation Results
| Method | Links | |
|---|---|---|
| PaLMModel Size (Billions of Parameters)=540, Num Tokens (Billions of Tokens)=780, Training FLOP Count (Zettaflops)=2527.2, Evaluation Protocol=0-shot2022.04 | 81.1 | |
| PaLMModel Size (Billions of Parameters)=62, Num Tokens (Billions of Tokens)=795, Training FLOP Count (Zettaflops)=295.7, Evaluation Protocol=0-shot2022.04 | 77 | |
| ChinchillaModel Size (Billions of Parameters)=70, Num Tokens (Billions of Tokens)=1400, Training FLOP Count (Zettaflops)=588.0, Evaluation Protocol=0-shot2022.04 | 74.9 | |
| GopherModel Size (Billions of Parameters)=280, Num Tokens (Billions of Tokens)=300, Training FLOP Count (Zettaflops)=504.0, Evaluation Protocol=0-shot2022.04 | 70.1 | |
| PaLMModel Size (Billions of Parameters)=8, Num Tokens (Billions of Tokens)=780, Training FLOP Count (Zettaflops)=37.4, Evaluation Protocol=0-shot2022.04 | 66.3 |