Multilingual-Transfer
Collection
Pretraining models to find what allows multilingual transfer • 30 items • Updated • 2
LLaMA-3 7B pretrained on English and translated Arabic data, 34k steps.
Final checkpoint: step 33,400
| Validation set | Cross-entropy loss (nats) | Perplexity |
|---|---|---|
| English (en) | 2.3798 | 10.80 |
AR (ar) |
2.3891 | 10.90 |
EEE-format evaluation results are stored under eval_results/eee/ in this repository.
Tasks: Global MMLU (EN/AR/RU), PIQA, ECLeKTic, Fictive Entity (2-rate mix).
Part of the The-CoLab multilingual-transfer collection.