Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Dialogue Generation on 4 dialogue datasets Aggregate (test val)
Loading...
12.9
Dialogue Avg F1
OPT
2.188
4.969
7.75
10.531
Oct 4, 2022
Dialogue Avg F1
Updated 4d ago
Evaluation Results
Method
Method
Links
Dialogue Avg F1
OPT
Params=2.7B
2022.10
12.9
NEO + UL
Params=2.7B, Epoch=5.4
2022.10
12.5
OPT
Params=1.3B
2022.10
12.4
NEO + UL
Params=1.3B, Epoch=8
2022.10
11.6
NEO
Params=1.3B
2022.10
11.5
NEO
Params=2.7B
2022.10
11.5
NEO + UL+
Params=2.7B, Epoch=10.8
2022.10
11.1
OPT
Params=125M
2022.10
10.2
NEO
Params=125M
2022.10
9.4
NEO + UL+
Params=1.3B, Epoch=13.8
2022.10
8.5
NEO + UL
Params=125M, Epoch=11
2022.10
8
NEO + DPD+
Params=125M
2022.10
7.3
NEO + DPD+
Params=1.3B
2022.10
7.1
NEO + DPD+
Params=2.7B
2022.10
6.9
NEO + UL+
Params=125M, Epoch=17.2
2022.10
2.6
Feedback
Search any
task
Search any
task