Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Question Generation on SQuAD (F1 score)

90.68F1 Score

First Order Adamw FT

6.044828.017449.9971.9626May 19, 2025Jul 21, 2025Sep 22, 2025Nov 25, 2025Jan 27, 2026Mar 31, 2026Jun 3, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.06
90.68
2026.06
89.2
2026.06
88.58
2025.05
88.3
2026.06
87.32
2025.05
86.9
2026.06
86.26
2025.05
85.5
2026.01
85.3
2026.01
85.2
2026.01
85.1
2026.01
84.9
2026.01
84.9
2026.01
84.9
2026.01
84.9
2025.05
84.9
2026.01
84.7
2026.01
84.5
2026.01
84.3
2026.01
84.2
2026.01
83.8
2026.01
83.8
2026.01
83.7
2026.01
83.7
2025.05
83.7
2026.01
83.2
2026.01
82.4
2026.01
81.9
2025.05
80.7
2026.05
80.7
2025.05
79.6
2026.01
78.8
2026.01
78.7
2025.05
78.5
2025.05
77.6
2026.01
77.5
2026.01
76.8
2026.01
76
2026.01
75.9
2026.01
75.2
2026.01
72
2025.05
64.8
2026.06
60.43
2025.05
59.2
2026.01
58.7
2026.05
58.6
2025.05
55.6
2025.05
53.6
2026.05
53.6
2026.01
46.2
2026.05
38.8
2025.05
36.5
2025.05
35.9
2026.05
33.3
2026.05
30.5
2026.01
27.2
2026.05
19.1
2026.05
9.3