Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userHyperparameter Power Impact in Transformer Language Model Training
تأثير الطاقة HyperParameter في تدريب نموذج لغة المحول
129
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
التدريب نماذج لغة كبيرة يمكن أن تستهلك كمية كبيرة من الطاقة.نفترض أن تكوين نموذج اللغة يؤثر على استهلاكها في مجال الطاقة، وأن هناك مجالا لتحسين استهلاك الطاقة في نماذج اللغة الكبيرة الحديثة.للتحقيق في هذه المطالبات، نقدم عامل استهلاك الطاقة في الوظيفة الموضوعية، واستكشاف مجموعة النماذج وتكوينات HyperParameter التي تؤثر على الطاقة.نحدد عوامل تكوين متعددة يمكن أن تقلل من استهلاك الطاقة أثناء التدريب على نموذج اللغة مع الحفاظ على جودة النموذج.
Training large language models can consume a large amount of energy. We hypothesize that the language model's configuration impacts its energy consumption, and that there is room for power consumption optimisation in modern large language models. To investigate these claims, we introduce a power consumption factor to the objective function, and explore the range of models and hyperparameter configurations that affect power. We identify multiple configuration factors that can reduce power consumption during language model training while retaining model quality.
References used
https://aclanthology.org/
rate research
Read More
Representation learning for text via pretraining a language model on a large corpus has become a standard starting point for building NLP systems. This approach stands in contrast to autoencoders, also trained on raw text, but with the objective of l
earning to encode each input as a vector that allows full reconstruction. Autoencoders are attractive because of their latent space structure and generative properties. We therefore explore the construction of a sentence-level autoencoder from a pretrained, frozen transformer language model. We adapt the masked language modeling objective as a generative, denoising one, while only training a sentence bottleneck and a single-layer modified transformer decoder. We demonstrate that the sentence representations discovered by our model achieve better quality than previous methods that extract representations from pretrained transformers on text similarity tasks, style transfer (an example of controlled generation), and single-sentence classification tasks in the GLUE benchmark, while using fewer parameters than large pretrained models.
We present on-going work of evaluating the, to our knowledge, first large generative language model trained to converse in Swedish, using data from the online discussion forum Flashback. We conduct a human evaluation pilot study that indicates the mo
del is often able to respond to conversations in both a human-like and informative manner, on a diverse set of topics. While data from online forums can be useful to build conversational systems, we reflect on the negative consequences that incautious application might have, and the need for taking active measures to safeguard against them.
Detecting stance on Twitter is especially challenging because of the short length of each tweet, the continuous coinage of new terminology and hashtags, and the deviation of sentence structure from standard prose. Fine-tuned language models using lar
ge-scale in-domain data have been shown to be the new state-of-the-art for many NLP tasks, including stance detection. In this paper, we propose a novel BERT-based fine-tuning method that enhances the masked language model for stance detection. Instead of random token masking, we propose using a weighted log-odds-ratio to identify words with high stance distinguishability and then model an attention mechanism that focuses on these words. We show that our proposed approach outperforms the state of the art for stance detection on Twitter data about the 2020 US Presidential election.
For any E-commerce website it is a nontrivial problem to build enduring advertisements that attract shoppers. It is hard to pass the creative quality bar of the website, especially at a large scale. We thus propose a programmatic solution to generate
product advertising headlines using retail content. We propose a state of the art application of Reinforcement Learning (RL) Policy gradient methods on Transformer (Vaswani et al., 2017) based Masked Language Models (Devlin et al., 2019). Our method creates the advertising headline by jointly conditioning on multiple products that a seller wishes to advertise. We demonstrate that our method outperforms existing Transformer and LSTM + RL methods in overlap metrics and quality audits. We also show that our model generated headlines outperform human submitted headlines in terms of both grammar and creative quality as determined by audits.
Latent Dirichlet allocation (LDA), a widely used topic model, is often employed as a fundamental tool for text analysis in various applications. However, the training process of the LDA model typically requires massive text corpus data. On one hand,
such massive data may expose private information in the training data, thereby incurring significant privacy concerns. On the other hand, the efficiency of the LDA model training may be impacted, since LDA training often needs to handle these massive text corpus data. To address the privacy issues in LDA model training, some recent works have combined LDA training algorithms that are based on collapsed Gibbs sampling (CGS) with differential privacy. Nevertheless, these works usually have a high accumulative privacy budget due to vast iterations in CGS. Moreover, these works always have low efficiency due to handling massive text corpus data. To improve the privacy guarantee and efficiency, we combine a subsampling method with CGS and propose a novel LDA training algorithm with differential privacy, SUB-LDA. We find that subsampling in CGS naturally improves efficiency while amplifying privacy. We propose a novel metric, the efficiency--privacy function, to evaluate improvements of the privacy guarantee and efficiency. Based on a conventional subsampling method, we propose an adaptive subsampling method to improve the model's utility produced by SUB-LDA when the subsampling ratio is small. We provide a comprehensive analysis of SUB-LDA, and the experiment results validate its efficiency and privacy guarantee improvements.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
