HRM-Text: Efficient Pretraining Beyond Scaling

TL;DR

HRM-Text introduces a biologically inspired hierarchical recurrent model for language pretraining, achieving competitive performance with significantly less data and compute, thus lowering barriers for foundational research.

Contribution

The paper presents HRM-Text, a novel hierarchical recurrent architecture with new stabilization techniques, enabling efficient pretraining on limited data and compute.

Findings

Achieves 60.7% on MMLU with only 40 billion tokens

Uses 100-900x less tokens and 96-432x less compute than standard models

Performs competitively with larger open models (2-7B parameters)

Abstract

The current pretraining paradigm for large language models relies on massive compute and internet-scale raw text, creating a significant barrier to foundational research. In contrast, biological systems demonstrate highly sample-efficient learning through multi-timescale processing, such as the functional organization of the frontoparietal loop. Taking this as inspiration, we introduce HRM-Text, which replaces standard Transformers with a Hierarchical Recurrent Model (HRM) that decouples computation into slow-evolving strategic and fast-evolving execution layers. To stabilize this deep recurrence for language modeling, we introduce MagicNorm and warmup deep credit assignment. Furthermore, instead of standard raw-text pretraining, we train exclusively on instruction-response pairs using a task-completion objective and PrefixLM masking. Serving as an empirical existence proof of efficient pretraining, a 1B-parameter HRM-Text model trained from scratch on only 40 billion unique tokens and $1,500 budget achieves 60.7% on MMLU, 81.9% on ARC-C, 82.2% on DROP, 84.5% on GSM8K, and 56.2% on MATH. Despite utilizing roughly 100-900x fewer training tokens and 96-432x less estimated compute than standard baselines, HRM-Text performs competitively with 2-7B parameter open models. These results demonstrate that co-designing architectures and objectives can radically reduce the compute-to-performance ratio, making pretraining from scratch accessible to the broader research community.