Our new X account is live! Follow @wizwand_team for updates

Zero-shot General Language Understanding on GPT-3 Evaluation Suite (11 Tasks)

33.6Average Accuracy

GPT-3 125M (Original)

Updated 4d ago

Evaluation Results

Method	Links
GPT-3 125M (Original) 2021.08		33.6
GPT-3 125M (Baseline Reproduced) 2021.08		31.4
Sequence Length Warmup (SLW 40x LR) 2021.08		31.1
GPT-3 125M (Baseline 30x LR) 2021.08		29.8