Zero-shot Evaluation on GPT-3 Evaluation Suite (LAMBADA, TriviaQA, WebQs, PIQA, RACE-h, BoolQ)
44.4Overall Accuracy
GPT-3 1.3B (Original)
Updated 4d ago
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
2021.08 | 44.4 | 63.6 | 19.7 | 4.63 | 75.1 | 40.9 | 62.4 | |
2021.08 | 41.9 | 65 | 11.3 | 2.36 | 73.8 | 37.1 | 61.8 | |
2021.08 | 41.6 | 63.7 | 10.1 | 3.25 | 73.4 | 35.6 | 63.4 |