Text Classification on MARC-ja
96.36MARC-ja ScoreLlama3.1-8B-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama3.1-8B-InstructTarget Language Adaptation Setting=Japanese2026.01 | 96.36 | |
| Llama3.1-FFTTarget Language Adaptation Setting=Japanese, CP / ELO pretraining Data size (Tokens)=10 GB (2.7 B), CP / ELO pretraining Time=19.4 h, Total training time=19.4 h2026.01 | 96.25 | |
| Llama3.1-ELOTarget Language Adaptation Setting=Japanese, CP / ELO pretraining Data size (Tokens)=9 GB (2.4 B), CP / ELO pretraining Time=1.4 h, Layer alignment Data size (Tokens)=1 GB (0.3 B), Layer alignment Time=2.0 h, Total training time=3.4 h2026.01 | 95.35 | |
| Mistral-ELOTarget Language Adaptation Setting=Japanese, CP / ELO pretraining Data size (Tokens)=9 GB (3.7 B), CP / ELO pretraining Time=1.7 h, Layer alignment Data size (Tokens)=1 GB (0.4 B), Layer alignment Time=3.0 h, Total training time=4.7 h2026.01 | 89.53 | |
| Mistral-7B-Instruct-v0.3Target Language Adaptation Setting=Japanese2026.01 | 83.43 | |
| Mistral-FFTTarget Language Adaptation Setting=Japanese, CP / ELO pretraining Data size (Tokens)=10 GB (4.1 B), CP / ELO pretraining Time=29.7 h, Total training time=29.7 h2026.01 | 80.05 |