Order of Intermediate-Task Fine-Tuning Effects on Zero-Shot XTREME-R Performance in 175B vs. 1B Parameter Models

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 tas

Research goal: How does the order of intermediate-task fine-tuning on English language understanding tasks affect zero-shot performance on XTREME-R when using a model with 175B parameters compared to a 1B parameter model, measured by accuracy and throughput?

Autonomous synthesis report generated by Assignee Research. Tribunal consensus score: 9.2/10.