All translations
Enter a message name below to show all available translations.
Found 3 translations.
| Name | Current message text |
|---|---|
| h English (en) | Ablation studies demonstrated that both {{Term|pre-training}} tasks were important, and that bidirectionality was the most significant factor — removing it caused large drops across all tasks. Increasing model size consistently improved results, even on small-scale tasks when fine-tuned appropriately. |
| h Spanish (es) | Los estudios de ablación demostraron que ambas tareas de {{Term|pre-training|preentrenamiento}} eran importantes, y que la bidireccionalidad era el factor más significativo: eliminarla causó grandes caídas en todas las tareas. Aumentar el tamaño del modelo mejoró consistentemente los resultados, incluso en tareas a pequeña escala cuando se ajustaron adecuadamente. |
| h Chinese (zh) | 消融研究表明,两个 {{Term|pre-training|预训练}} 任务都很重要,且双向性是最显著的因素——移除它会在所有任务上造成大幅下降。增大模型规模始终能提升效果,即便在小规模任务上经过适当微调后亦是如此。 |