Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Utility Evaluation on Downstream Tasks
Loading...
63.4
Average Accuracy
DAPT (nontoxic)
45.304
50.002
54.7
59.398
Feb 8, 2022
Average Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Accuracy
DAPT (nontoxic)
Parameter Size=530B
2022.02
63.4
SGEAT (augmented)
Parameter Size=530B, T...
2022.02
62.6
SGEAT (augmented)
Parameter Size=530B, T...
2022.02
62
DAPT (nontoxic)
Parameter Size=8.3B
2022.02
59.1
SGEAT (augmented)
Parameter Size=8.3B
2022.02
59.1
SGEAT (augmented)
Parameter Size=530B, T...
2022.02
58.8
DAPT (nontoxic)
Parameter Size=1.3B
2022.02
54.7
SGEAT (augmented)
Parameter Size=1.3B
2022.02
54.4
DAPT (nontoxic)
Parameter Size=357M
2022.02
49.9
SGEAT (augmented)
Parameter Size=357M
2022.02
49.3
SGEAT (augmented)
Parameter Size=126M
2022.02
46.3
DAPT (nontoxic)
Parameter Size=126M
2022.02
46
Feedback
Search any
task
Search any
task