steps-12500
| Task |
Version |
Metric |
Value |
|
Stderr |
| kobest_boolq |
0 |
acc |
0.5064 |
± |
0.0133 |
|
|
macro_f1 |
0.3669 |
± |
0.0094 |
| kobest_copa |
0 |
acc |
0.7260 |
± |
0.0141 |
|
|
macro_f1 |
0.7254 |
± |
0.0141 |
| kobest_hellaswag |
0 |
acc |
0.4380 |
± |
0.0222 |
|
|
acc_norm |
0.5460 |
± |
0.0223 |
|
|
macro_f1 |
0.4345 |
± |
0.0222 |
| kobest_sentineg |
0 |
acc |
0.8161 |
± |
0.0195 |
|
|
macro_f1 |
0.8134 |
± |
0.0199 |
steps-25000
| Task |
Version |
Metric |
Value |
|
Stderr |
| kobest_boolq |
0 |
acc |
0.5028 |
± |
0.0133 |
|
|
macro_f1 |
0.3409 |
± |
0.0069 |
| kobest_copa |
0 |
acc |
0.7170 |
± |
0.0143 |
|
|
macro_f1 |
0.7164 |
± |
0.0142 |
| kobest_hellaswag |
0 |
acc |
0.4380 |
± |
0.0222 |
|
|
acc_norm |
0.5380 |
± |
0.0223 |
|
|
macro_f1 |
0.4329 |
± |
0.0221 |
| kobest_sentineg |
0 |
acc |
0.7809 |
± |
0.0208 |
|
|
macro_f1 |
0.7746 |
± |
0.0214 |
