In this paper cum technical report, we present PHUDGE A fine tuned Phi3 model that achieved SOTA results in 4 tasks as Feedback Test, Feedback OOD, MT Human, Preference Test surpassing each and every existing model in latency and throughput. It shows very strong correlation not only with GPT4 but with Human annotators too in unseen data as well as in both absolute and relative grading tasks. We have not only addressed the usage of small LMs for cost effective production grade systems but have also shown that Causal modelling is not only slow in nature but sometimes it can hinder models learning capabilities and should be replaced by simpler tasks whenever we can to make the overall system faster and better. We show that by following systematic ML experimentation, thoughtful data augmentation and re purposing the problem itself, we can even beat 10x bigger models even with lesser training data. To the best of our knowledge, we are re the first one to experiment and showcase the usage of generalised version of Earth Movers Distance AKA Wasserstein distance by using Minkowski Distance with a penalty to control loss smoothing and can be used as a loss function instead of Cross Entropy to get stable training and better results for grading tasks.
翻译:在本文及技术报告中,我们提出了PHUDGE——一个经过微调的Phi-3模型,在反馈测试、反馈域外泛化、MT人工评估、偏好测试四项任务中均实现了最先进水平,在延迟和吞吐量方面超越所有现有模型。该模型不仅与GPT-4表现出强相关性,在与人工标注者的对比中,在未见数据以及绝对/相对评分任务中也展现出高度一致性。我们不仅解决了小语言模型在成本效益型生产系统中的应用问题,更揭示了因果建模不仅本质缓慢,有时还会阻碍模型学习能力,应尽可能代之以更简单的任务以提升系统整体速度与性能。通过系统性机器学习实验、审慎的数据增强以及问题重构,我们证明即使在训练数据更少的情况下,也能击败规模大10倍的模型。据我们所知,我们首次实验并展示了广义推土机距离(即Wasserstein距离)的实用方法——通过引入带惩罚系数的闵可夫斯基距离控制损失平滑度,可替代交叉熵作为损失函数,在评分任务中实现稳定训练与更优结果。