wandb run: https://wandb.ai/eleutherai/pythia-rlhf/runs/0c0pmvz8
| Task | Version | Filter | Metric | Value | Stderr | |
|---|---|---|---|---|---|---|
| arc_challenge | Yaml | none | acc | 0.2961 | ± | 0.0133 |
| none | acc_norm | 0.3285 | ± | 0.0137 | ||
| arc_easy | Yaml | none | acc | 0.6452 | ± | 0.0098 |
| none | acc_norm | 0.5678 | ± | 0.0102 | ||
| logiqa | Yaml | none | acc | 0.2151 | ± | 0.0161 |
| none | acc_norm | 0.2857 | ± | 0.0177 | ||
| piqa | Yaml | none | acc | 0.7508 | ± | 0.0101 |
| none | acc_norm | 0.7503 | ± | 0.0101 | ||
| sciq | Yaml | none | acc | 0.8820 | ± | 0.0102 |
| none | acc_norm | 0.8140 | ± | 0.0123 | ||
| winogrande | Yaml | none | acc | 0.6038 | ± | 0.0137 |