PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation
Large-scale Pretrained Language Models (PLMs) have become the new paradigm for Natural Language Processing (NLP). PLMs with hundreds of billions parameters such as GPT-3 have demonstrated strong performances on natural language understanding and generation with \textit{few-shot in-context} learning. In this work, we present our practice on training large-scale autoregressive language models named PanGu-$\alpha$, with up to 200 billion parameters. PanGu-$\alpha$ is developed under the MindSpore and trained on a cluster of 2048 Ascend 910 AI processors. The training parallelism strategy is implemented based on MindSpore Auto-parallel, which composes five parallelism dimensions to scale the training task to 2048 processors efficiently, including data parallelism, op-level model parallelism, pipeline model parallelism, optimizer model parallelism and rematerialization. To enhance the generalization ability of PanGu-$\alpha$, we collect 1.1TB high-quality Chinese data from a wide range of domains to pretrain the model. We empirically test the generation ability of PanGu-$\alpha$ in various scenarios including text summarization, question answering, dialogue generation, etc. Moreover, we investigate the effect of model scales on the few-shot performances across a broad range of Chinese NLP tasks. The experimental results demonstrate the superior capabilities of PanGu-$\alpha$ in performing various tasks under few-shot or zero-shot settings.
PDF AbstractCode
Tasks
Cloze (multi-choices) (Few-Shot)
Cloze (multi-choices) (One-Shot)
Cloze (multi-choices) (Zero-Shot)
Common Sense Reasoning (Few-Shot)
Common Sense Reasoning (One-Shot)
Common Sense Reasoning (Zero-Shot)
Dialogue Generation
Few-Shot Image Classification
In-Context Learning
Natural Language Inference
Natural Language Inference (Few-Shot)
Natural Language Inference (One-Shot)
Natural Language Inference (Zero-Shot)
Natural Language Understanding
Question Answering
Reading Comprehension
Reading Comprehension (Few-Shot)
Reading Comprehension (One-Shot)
Reading Comprehension (Zero-Shot)
Text Classification
Text Summarization
C4
CMRC
DuReader
DRCD
OCNLI
ChID
