BIG LSTM+CNN INPUTS

Training compute

10²⁰ FLOP

Parameters

1B

Published

Feb 11, 2016

BIG LSTM+CNN INPUTS is an AI model developed by Google Brain (United States), first published in February 2016. It works in the language domain, on tasks such as language modeling. It counts among the frontier models: the systems trained with the most compute of their moment.

Training it took an estimated 10²⁰ FLOP of compute (estimation method: hardware,operation counting). The model has 1,040,000,000 parameters. Training ran on 32 NVIDIA Tesla K40s. The compute alone is estimated at $71 in 2023 dollars.

Epoch AI rates the confidence of this record as likely.

Full record

Organization: Google Brain
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 10²⁰ FLOP
Compute estimation method: Hardware, Operation counting
Parameters: 1,040,000,000
Training hardware: NVIDIA Tesla K40s
Chips used: 32
Chip-hours: 240
Training power draw: 16.6 kW
Training cost (2023 USD): $71
Epoch confidence: Likely