Single layer tiny Co4 outpaces {GPT}-2 and {GPT}-{BERT}

Abstract

We show that a tiny Co4 machine (CITATION) with a single layer, two heads, and 8M parameters, operating at O(N) computational cost (where N is the number of input tokens), in just 2 epochs outpaces GPT-2 (124M, 12 layers, O(N2)) and GPT-BERT (30M, 12 layers, O(N 2), both trained for 10 epochs. Co4 achieves orders-of-magnitude greater training efficiency on 10M tokens, demonstrating sample-efficient pretraining. On the BabyLM challenge evaluation pipeline, Co4 performs comparably or better across complex benchmarks, showing strong zero-shot and fine-tuning performance on SuperGLUE tasks. Specifically, Co4 outperforms GPT-2 in 5 out of 7 zero-shot metrics and 6 out of 7 fine-tuning tasks, and GPT-BERT in 4 out of 7 metrics in both cases. These results strongly suggest a need to rethink prevailing deep learning paradigms and associated scaling laws.