In machine translation tasks, the relationship between model complexity and performance is often presumed to be linear, driving an increase in the number of parameters and consequent demands for computational resources like multiple GPUs. To explore this assumption, this study systematically investigates the effects of hyperparameters through ablation on a sequence-to-sequence machine translation pipeline, utilizing a single NVIDIA A100 GPU. Contrary to expectations, our experiments reveal that combinations with the most parameters were not necessarily the most effective. This unexpected insight prompted a careful reduction in parameter sizes, uncovering "sweet spots" that enable training sophisticated models on a single GPU without compromising translation quality. The findings demonstrate an intricate relationship between hyperparameter selection, model size, and computational resource needs. The insights from this study contribute to the ongoing efforts to make machine translation more accessible and cost-effective, emphasizing the importance of precise hyperparameter tuning over mere scaling.

翻译：在机器翻译任务中，模型复杂度与性能之间的关系常被假定为线性，这推动了参数数量的增加以及对多GPU等计算资源的相应需求。为探究这一假设，本研究利用单块NVIDIA A100 GPU，通过消融方法系统考察了超参数对序列到序列机器翻译流水线的影响。与预期相反，我们的实验表明，参数最多的组合并非一定最有效。这一意外发现促使我们谨慎削减参数规模，从而在不影响翻译质量的前提下，揭示出能够在单GPU上训练复杂模型的“最佳平衡点”。研究结果揭示了超参数选择、模型规模与计算资源需求之间的复杂关系。本研究的洞察有助于推动机器翻译的普及和成本效益优化，强调了精准超参数调优相较于单纯规模扩展的重要性。