A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules

• URL: http://arxiv.org/abs/2503.12811v1
• Date: Mon, 17 Mar 2025 04:36:45 GMT
• Title: A Multi-Power Law for Loss Curve Prediction Across Learning Rate Schedules
• Authors: Kairong Luo, Haodong Wen, Shengding Hu, Zhenbo Sun, Zhiyuan Liu, Maosong Sun, Kaifeng Lyu, Wenguang Chen,
• Abstract summary: We present an empirical law that describes how the pretraining loss of large language models evolves under different learning rate schedules.<n>Our proposed law takes a multi-power form, combining a power law based on the sum of learning rates and additional power laws to account for a loss reduction effect induced by learning rate decay.
• Score: 67.87680482844884
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Training large models is both resource-intensive and time-consuming, making it crucial to understand the quantitative relationship between model performance and hyperparameters. In this paper, we present an empirical law that describes how the pretraining loss of large language models evolves under different learning rate schedules, such as constant, cosine, and step decay schedules. Our proposed law takes a multi-power form, combining a power law based on the sum of learning rates and additional power laws to account for a loss reduction effect induced by learning rate decay. We extensively validate this law on various model sizes and architectures, and demonstrate that after fitting on a few learning rate schedules, the law accurately predicts the loss curves for unseen schedules of different shapes and horizons. Moreover, by minimizing the predicted final pretraining loss across learning rate schedules, we are able to find a schedule that outperforms the widely used cosine learning rate schedule. Interestingly, this automatically discovered schedule bears some resemblance to the recently proposed Warmup-Stable-Decay (WSD) schedule (Hu et al, 2024) but achieves a slightly lower final loss. We believe these results could offer valuable insights for understanding the dynamics of pretraining and designing learning rate schedules to improve efficiency.

Related papers

• Temporal Difference Flows [82.24174052059352]
  Geometric Horizon Models (GHMs) offer a compelling alternative by directly making predictions of future states.<n>Existing methods are negatively affected by bootstrapping predictions at train time and struggle to generate high-quality predictions at long horizons.<n>This paper introduces Temporal Difference Flows (TD-Flow), which leverages the structure of a novel Bellman equation on probability paths alongside flow-matching techniques to learn accurate GHMs at over 5x the horizon length of prior methods.
  arXiv  Detail & Related papers  (2025-03-12T20:30:07Z)
• Beyond Cosine Decay: On the effectiveness of Infinite Learning Rate Schedule for Continual Pre-training [17.371995357694736]
  Unlabeled data presents both opportunities and challenges for training artificial intelligence systems. While self-supervised learning has emerged as a powerful paradigm for extracting meaningful representations from vast amounts of unlabeled data, existing methods still struggle to adapt to the non-stationary, non-IID nature of real-world data streams without forgetting previously learned knowledge. In this work, we systematically compare the widely used cosine schedule with the recently proposed infinite learning rate schedule and empirically find the latter to be a more effective alternative.
  arXiv  Detail & Related papers  (2025-03-04T18:15:57Z)
• The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws [51.608402959163925]
  We present the first systematic exploration of optimal sparse pre-training configurations for large language models.<n>We find that initiating pruning at 25% of total training compute and concluding at 75% achieves near-optimal final evaluation loss.<n>We propose a new scaling law that modifies the Chinchilla scaling law to use the average parameter count over pre-training.
  arXiv  Detail & Related papers  (2025-01-21T20:23:22Z)
• Normalization and effective learning rates in reinforcement learning [52.59508428613934]
  Normalization layers have recently experienced a renaissance in the deep reinforcement learning and continual learning literature. We show that normalization brings with it a subtle but important side effect: an equivalence between growth in the norm of the network parameters and decay in the effective learning rate. We propose to make the learning rate schedule explicit with a simple re- parameterization which we call Normalize-and-Project.
  arXiv  Detail & Related papers  (2024-07-01T20:58:01Z)
• Temporal Scaling Law for Large Language Models [24.12384260752973]
  We propose the novel concept of Temporal Scaling Law, studying how the test loss of an LLM evolves as the training steps scale up. In contrast to modeling the test loss as a whole in a coarse-grained manner, we break it down and dive into the fine-grained test loss of each token position. We derive the much more precise temporal scaling law by studying the temporal patterns of the parameters in the dynamic hyperbolic-law.
  arXiv  Detail & Related papers  (2024-04-27T05:49:11Z)
• Optimal Linear Decay Learning Rate Schedules and Further Refinements [46.79573408189601]
  Learning rate schedules used in practice bear little resemblance to those recommended by theory. We close much of this theory/practice gap, and as a consequence are able to derive new problem-adaptive learning rate schedules.
  arXiv  Detail & Related papers  (2023-10-11T19:16:35Z)
• Learning Rate Schedules in the Presence of Distribution Shift [18.310336156637774]
  We design learning schedules that regret networks cumulatively learning in the presence of a changing data distribution. We provide experiments for high-dimensional regression models to increase regret models.
  arXiv  Detail & Related papers  (2023-03-27T23:29:02Z)
• Scaling Laws Beyond Backpropagation [64.0476282000118]
  We study the ability of Direct Feedback Alignment to train causal decoder-only Transformers efficiently. We find that DFA fails to offer more efficient scaling than backpropagation.
  arXiv  Detail & Related papers  (2022-10-26T10:09:14Z)
• Learning Rate Perturbation: A Generic Plugin of Learning Rate Schedule towards Flatter Local Minima [40.70374106466073]
  We propose a generic learning rate schedule plugin called LEArning Rate Perturbation (LEAP) LEAP can be applied to various learning rate schedules to improve the model training by introducing a certain perturbation to the learning rate. We conduct extensive experiments which show that training with LEAP can improve the performance of various deep learning models on diverse datasets.
  arXiv  Detail & Related papers  (2022-08-25T05:05:18Z)
• An Empirical Investigation of the Role of Pre-training in Lifelong Learning [21.995593026269578]
  We show that generic pre-training implicitly alleviates the effects of catastrophic forgetting when learning multiple tasks sequentially. We study this phenomenon by analyzing the loss landscape, finding that pre-trained weights appear to ease forgetting by leading to wider minima.
  arXiv  Detail & Related papers  (2021-12-16T19:00:55Z)

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.