Intermediate-task training---fine-tuning a pretrained model on an intermediate task before fine-tuning again on the target task---often improves model performance substantially on language understanding tasks in monolingual English settings. We investigate whether English intermediate-task training is still helpful on non-English target tasks. Using nine intermediate language-understanding tasks, we evaluate intermediate-task transfer in a zero-shot cross-lingual setting on the XTREME benchmark. We see large improvements from intermediate training on the BUCC and Tatoeba sentence retrieval tasResearch goal: What is the impact of using domain-adaptive intermediate tasks (e.g., legal or medical domain-specific tasks) on zero-shot cross-lingual performance in XTREME, and how does it compare to general language understanding tasks in terms of accuracy and robustness across domains?Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 8.0/10.