Language Modeling on Core
28.44ScoreParcae
Evaluation Results
| Method | Links | |
|---|---|---|
| ParcaeNumber of Parameters=1.3B, T=82026.04 | 28.44 | |
| TransformerNumber of Parameters=1.3B, T=-2026.04 | 25.45 | |
| ParcaeNumber of Parameters=770M, T=82026.04 | 25.07 | |
| TransformerNumber of Parameters=770M, T=-2026.04 | 22.42 | |
| ParcaeNumber of Parameters=370M, T=82026.04 | 20 | |
| TransformerNumber of Parameters=370M, T=-2026.04 | 17.46 | |
| ParcaeNumber of Parameters=140M, T=82026.04 | 14.04 | |
| TransformerNumber of Parameters=140M, T=-2026.04 | 13 |