Mathematical Reasoning on GSM8K (GSM & Average)
92.55GSM ScoreCRDS-W
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| CRDS-WModel=Ling-mini-2.0 (16B), Data Selection Budget=3.5%, Truncation length=2048, Parallel runs=Average of 52026.02 | 92.55 | 83.96 | |
| CRDS-RModel=Ling-mini-2.0 (16B), Data Selection Budget=3.5%, Truncation length=2048, Parallel runs=Average of 52026.02 | 91.4 | 83.26 | |
| RandomModel=Ling-mini-2.0 (16B), Data Selection Budget=3.5%, Truncation length=2048, Parallel runs=Average of 52026.02 | 91.28 | 82.58 | |
| Mid PPLModel=Ling-mini-2.0 (16B), Data Selection Budget=3.5%, Truncation length=2048, Parallel runs=Average of 52026.02 | 91.22 | 81.87 | |
| RDS+Model=Ling-mini-2.0 (16B), Data Selection Budget=3.5%, Truncation length=2048, Parallel runs=Average of 52026.02 | 91.1 | 82.6 | |
| Ling-mini-2.0Model=Ling-mini-2.0 (16B), Data Selection Budget=100%, Truncation length=2048, Parallel runs=Average of 52026.02 | 90.75 | 83.25 | |
| LengthModel=Ling-mini-2.0 (16B), Data Selection Budget=3.5%, Truncation length=2048, Parallel runs=Average of 52026.02 | 89.02 | 74.24 |