GPT-3 XL

Training compute

2.4×10²¹ FLOP

Parameters

1.3B

Published

Jun 22, 2020

GPT-3 XL is an AI model developed by OpenAI (United States), first published in June 2020. It works in the language domain, on tasks such as text autocompletion and language modeling/generation.

Training it took an estimated 2.4×10²¹ FLOP of compute (estimation method: reported). The model has 1,320,000,000 parameters. It was trained on roughly 300B datapoints. Training ran on NVIDIA Tesla V100 DGXS 32 GB.

The reference paper has 58,240 citations. Epoch AI rates the confidence of this record as confident.

Full record

Organization: OpenAI
Country of organization: United States
Domain: Language
Task: Text autocompletion, Language modeling/generation
Training compute: 2.4×10²¹ FLOP
Compute estimation method: Reported
Parameters: 1,320,000,000
Dataset size: 300B
Training hardware: NVIDIA Tesla V100 DGXS 32 GB
Citations: 58,240
Epoch confidence: Confident