ConvS2S (ensemble of 8 models)

Training compute

5.6×10¹⁹ FLOP

Published

Jul 25, 2017

ConvS2S (ensemble of 8 models) is an AI model developed by Meta AI (United States), first published in July 2017. It works in the language domain, on tasks such as translation.

Training it took an estimated 5.6×10¹⁹ FLOP of compute (estimation method: hardware). It was trained on roughly 1.2B datapoints. Training ran on NVIDIA M40.

Epoch AI rates the confidence of this record as likely.

Full record

Organization: Meta AI
Country of organization: United States
Domain: Language
Task: Translation
Training compute: 5.6×10¹⁹ FLOP
Compute estimation method: Hardware
Dataset size: 1.2B
Training hardware: NVIDIA M40
Epoch confidence: Likely