Related papers: Small Batch Size Training for Language Models: Whe…
Stochastic Gradient Descent (SGD) is a cornerstone of large-scale optimization, yet its theoretical behavior under heavy-tailed noise -- common in modern machine learning and reinforcement learning -- remains poorly understood. In this…
Large language models are powerful but costly. We ask whether meta-learning can make the pretraining of small language models not only better but also more interpretable. We integrate first-order MAML with subset-masked LM pretraining,…
Learning rate, batch size and momentum are three important hyperparameters in the SGD algorithm. It is known from the work of Jastrzebski et al. arXiv:1711.04623 that large batch size training of neural networks yields models which do not…
Preserving training dynamics across batch sizes is an important tool for practical machine learning as it enables the trade-off between batch size and wall-clock time. This trade-off is typically enabled by a scaling rule, for example, in…
Scheduling the batch size to increase is an effective strategy to control gradient noise when training deep neural networks. Current approaches implement scheduling heuristics that neglect structure within the optimization procedure,…
Adam is the go-to optimizer for training modern machine learning models, but it requires additional memory to maintain the moving averages of the gradients and their squares. While various low-memory optimizers have been proposed that…
Large-batch training is an efficient approach for current distributed deep learning systems. It has enabled researchers to reduce the ImageNet/ResNet-50 training from 29 hours to around 1 minute. In this paper, we focus on studying the…
Small Language models (SLMs) offer an efficient and accessible alternative to Large Language Models (LLMs), delivering strong performance while using far fewer resources. We introduce a simple and effective framework for pretraining SLMs…
The choice of batch-size in a stochastic optimization algorithm plays a substantial role for both optimization and generalization. Increasing the batch-size used typically improves optimization but degrades generalization. To address the…
We present SmolTulu-1.7b-Instruct, referenced in this report as SmolTulu-DPO-1130, an instruction-tuned language model that adapts AllenAI's Tulu 3 post-training pipeline to enhance Huggingface's SmolLM2-1.7B base model. Through…
The unprecedented growth of deep learning models has enabled remarkable advances but introduced substantial computational bottlenecks. A key factor contributing to training efficiency is batch-size and learning-rate scheduling in stochastic…
The convergence behavior of mini-batch stochastic gradient descent (SGD) is highly sensitive to the batch size and learning rate settings. Recent theoretical studies have identified the existence of a critical batch size that minimizes…
With an increasing demand for training powers for deep learning algorithms and the rapid growth of computation resources in data centers, it is desirable to dynamically schedule different distributed deep learning tasks to maximize resource…
Large Language Models (LLMs) are typically trained in two phases: pre-training on large internet-scale datasets, and fine-tuning for downstream tasks. Given the higher computational demand of pre-training, it's intuitive to assume that…
Adaptive optimizers such as Adam (Kingma & Ba, 2015) have been central to the success of large language models. However, they often require to maintain optimizer states throughout training, which can result in memory requirements several…
Efficiently training large language models requires parallelizing across hundreds of hardware accelerators and invoking various compute and memory optimizations. When combined, many of these strategies have complex interactions regarding…
Improving the effectiveness and efficiency of large language models (LLMs) simultaneously is a critical yet challenging research goal. In this paper, we find that low-rank pre-training, normally considered as efficient methods that will…
Recent trends towards training ever-larger language models have substantially improved machine learning performance across linguistic tasks. However, the huge cost of training larger models can make tuning them prohibitively expensive,…
Fueled by their remarkable ability to tackle diverse tasks across multiple domains, large language models (LLMs) have grown at an unprecedented rate, with some recent models containing trillions of parameters. This growth is accompanied by…
Large Language Models (LLMs) are difficult to fully fine-tune (e.g., with instructions or human feedback) due to their sheer number of parameters. A family of parameter-efficient sparse fine-tuning methods have proven promising in terms of…