Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?

• URL: http://arxiv.org/abs/2502.11895v1
• Date: Mon, 17 Feb 2025 15:21:11 GMT
• Title: Continual Quantization-Aware Pre-Training: When to transition from 16-bit to 1.58-bit pre-training for BitNet language models?
• Authors: Jacob Nielsen, Peter Schneider-Kamp, Lukas Galke,
• Abstract summary: Large language models (LLMs) require immense resources for training and inference. Recent research suggests that training LLMs with 1.58 bits per weight parameter from scratch can maintain model accuracy.
• Score: 5.67099529296254
• License:
• Abstract: Large language models (LLMs) require immense resources for training and inference. Quantization, a technique that reduces the precision of model parameters, offers a promising solution for improving LLM efficiency and sustainability. While post-training quantization methods typically achieve 4-8 bits per parameter, recent research suggests that training LLMs with 1.58 bits per weight parameter from scratch can maintain model accuracy while greatly reducing memory requirements and energy consumption at inference time. Here, we investigate a training strategy for quantization-aware pre-training, where the models are first trained with 16-bit precision and then transition into 1.58-bit quantization-aware training. Our results on 11 downstream tasks show that this 16-to-1.58-bit training strategy is preferable over full 1.58-bit training and leaves models closer to those which have undergone 16-bit training. We further investigate the effects of retaining the optimizer state at the transition point and gradually phasing in quantization strength -- finding that both techniques alleviate the magnitude of loss spikes, but also that these effects can be compensated through further training.

Related papers

• Optimizing Large Language Model Training Using FP4 Quantization [73.55459961002371]
  Quantized training presents a promising solution by enabling low-bit arithmetic operations to reduce costs. This work introduces the first FP4 training framework for large language models (LLMs)
  arXiv  Detail & Related papers  (2025-01-28T18:04:50Z)
• Direct Quantized Training of Language Models with Stochastic Rounding [12.028887152979046]
  This paper explores the potential of directly updating the quantized low-precision weight matrices without relying on the straight-through estimator during backpropagation. Experimental results on our LLaMA-structured models indicate that training with only low-precision weights is feasible even when they are constrained to ternary values. Our models can also perform inference using ternary weights, showcasing their flexibility in deployment.
  arXiv  Detail & Related papers  (2024-12-06T05:41:11Z)
• Towards Accurate and Efficient Sub-8-Bit Integer Training [24.853958178296587]
  Quantization enables low-bitwidth formats in neural network training. Recent methods have developed new data formats and additional pre-processing operations on quantizers. It remains quite challenging to achieve high accuracy and efficiency simultaneously.
  arXiv  Detail & Related papers  (2024-11-17T03:32:36Z)
• COAT: Compressing Optimizer states and Activation for Memory-Efficient FP8 Training [47.07768822212081]
  COAT (States and Activations for FP8 Training) is a novel FP8 training framework designed to significantly reduce memory footprint when training large models. COAT effectively reduces end-to-end training memory footprint by 1.54x compared to BF16. COAT also achieves a 1.43x end-to-end training speedup compared to BF16.
  arXiv  Detail & Related papers  (2024-10-25T05:59:30Z)
• EfficientQAT: Efficient Quantization-Aware Training for Large Language Models [50.525259103219256]
  quantization-aware training (QAT) offers a solution by reducing memory consumption through low-bit representations with minimal accuracy loss. We propose Efficient Quantization-Aware Training (EfficientQAT), a more feasible QAT algorithm. EfficientQAT involves two consecutive phases: Block-wise training of all parameters (Block-AP) and end-to-end training of quantization parameters (E2E-QP)
  arXiv  Detail & Related papers  (2024-07-10T17:53:30Z)
• BitNet b1.58 Reloaded: State-of-the-art Performance Also on Smaller Networks [2.2300270962881075]
  In this work, we investigate 1.58-bit quantization for small language and vision models ranging from 100K to 48M parameters. We introduce a variant of BitNet b1.58, which allows to rely on the median rather than the mean in the quantization process.
  arXiv  Detail & Related papers  (2024-06-24T20:55:36Z)
• GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection [133.45193150403537]
  Training Large Language Models (LLMs) presents significant memory challenges due to the growing size of weights and GPU states. In this work, we propose Gradient Low-Rank Projection (GaLore) as a memory-efficient training strategy. Our 8-bit GaLore further reduces memory by up to 82.5% and total training memory by 63.3%, compared to a BF16 baseline.
  arXiv  Detail & Related papers  (2024-03-06T07:29:57Z)
• Stable and low-precision training for large-scale vision-language models [108.62077651227607]
  We introduce new methods for accelerating and stabilizing training for large language-vision models. For acceleration, we introduce SwitchBack, a linear layer for int8 quantized training which provides a speed-up of 13-25%. For stability, we analyze loss spikes and find they consistently occur 1-8 after the squared gradients become under-estimated.
  arXiv  Detail & Related papers  (2023-04-25T17:38:18Z)
• 8-bit Optimizers via Block-wise Quantization [57.25800395197516]
  Statefuls maintain statistics over time, e.g., the exponentially smoothed sum (SGD with momentum) or squared sum (Adam) of past values. This state can be used to accelerate optimization compared to plain gradient descent but uses memory that might otherwise be allocated to model parameters. In this paper, we develop first gradients that use 8-bit statistics while maintaining the performance levels of using 32-bit gradient states.
  arXiv  Detail & Related papers  (2021-10-06T15:43:20Z)
• Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks [13.929168096016957]
  We introduce a novel methodology for training deep neural networks using 8-bit floating point (FP8) numbers. Reduced bit precision allows for a larger effective memory and increased computational speed. We show that, unlike previous 8-bit precision training methods, the proposed method works out-of-the-box for representative models.
  arXiv  Detail & Related papers  (2020-01-16T06:38:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.