>
M
Introduction
We introduce MADLAD-400, a manually audited, general domain 3T token monolingual dataset based on CommonCrawl, spanning 419 languages. We discuss the limitations revealed by self-auditing MADLAD-400, and the role data auditing had in the dataset creation process. We then train and release a 10.7B-parameter multilingual machine translation model on 250 billion tokens covering over 450 languages using publicly available data, and find that it is competitive with models that are significantly larger, and report the results on different domains. In addition, we train a 8B-parameter language model, and assess the results on few-shot translation. We make the baseline models available to the research community.
Benchmarking
FLOPs
1.61e+22Notes: 6ND = 10.7B * 250B = 1.6e22 'MADLAD-400-10B-MT is a multilingual machine translation model based on the T5 architecture that was trained on 250 billion tokens covering over 450 languages using publicly available data. ' 10.7B params from appendix A.8
Training
Training Code Accessibility
Apache 2.0:
https://github.com/google-research/google-research/tree/masterSize Notes: MADLAD-400, dataset released with paper, is 3T tokens: 'We introduce MADLAD-400, a manually audited, general domain 3T token monolingual dataset based on CommonCrawl, spanning 419 languages.' However, model in question was trained on only 250B tokens: "We then train and release a 10.7B-parameter multilingual machine translation model on 250 billion tokens covering over 450 languages using publicly available data"
Parameters
Parameters
10700000000Notes: 10.7B from appendix A.8
Authors
Sneha Kudugunta, Isaac Caswell, Biao Zhang, Xavier Garcia, Christopher A. Choquette-Choo, Katherine Lee, Derrick Xin, Aditya Kusupati, Romi Stella, Ankur Bapna, Orhan Firat
Multimodal
Vision
Video
Speech