Transformer-XL + AutoDropout (PTB)

Training compute

5.8×10¹⁶ FLOP

Parameters

24M

Published

Jan 5, 2021

Transformer-XL + AutoDropout (PTB) is an AI model developed by Google Research (United States), first published in January 2021. It works in the language domain, on tasks such as language modeling.

Training it took an estimated 5.8×10¹⁶ FLOP of compute. The model has 24,000,000 parameters. Training ran on 4 Google TPU v2 for about 0.66 hours.

Access: Unreleased. Its weights are not openly released. The reference paper has 63 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: Google Research
Country of organization: United States
Domain: Language
Task: Language modeling
Training compute: 5.8×10¹⁶ FLOP
Parameters: 24,000,000
Training hardware: Google TPU v2
Chips used: 4
Training time: 1 h
Training power draw: 2.3 kW
Model accessibility: Unreleased
Open weights: No
Citations: 63
Epoch confidence: Confident