Task | Version | Metric | Value | Stderr | |
---|---|---|---|---|---|
kobest_boolq | 0 | acc | 0.5520 | ± | 0.0133 |
macro_f1 | 0.5341 | ± | 0.0134 | ||
kobest_copa | 0 | acc | 0.7090 | ± | 0.0144 |
macro_f1 | 0.7085 | ± | 0.0144 | ||
kobest_hellaswag | 0 | acc | 0.4240 | ± | 0.0221 |
acc_norm | 0.5240 | ± | 0.0224 | ||
macro_f1 | 0.4192 | ± | 0.0220 | ||
kobest_sentineg | 0 | acc | 0.7582 | ± | 0.0215 |
macro_f1 | 0.7487 | ± | 0.0223 |