Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
- URL: http://arxiv.org/abs/2401.00448v2
- Date: Thu, 18 Jul 2024 14:23:29 GMT
- Title: Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws
- Authors: Nikhil Sardana, Jacob Portes, Sasha Doubov, Jonathan Frankle,
- Abstract summary: We modify the Chinchilla scaling laws to calculate the optimal LLM parameter count and pre-training data size to train and deploy a model of a given quality and inference demand.
We train 47 models of varying sizes and parameter counts to validate our formula and find that model quality continues to improve as we scale tokens per parameter to extreme ranges.
- Score: 14.546425605156578
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Large language model (LLM) scaling laws are empirical formulas that estimate changes in model quality as a result of increasing parameter count and training data. However, these formulas, including the popular Deepmind Chinchilla scaling laws, neglect to include the cost of inference. We modify the Chinchilla scaling laws to calculate the optimal LLM parameter count and pre-training data size to train and deploy a model of a given quality and inference demand. We conduct our analysis both in terms of a compute budget and real-world costs and find that LLM researchers expecting reasonably large inference demand (~1B requests) should train models smaller and longer than Chinchilla-optimal. Furthermore, we train 47 models of varying sizes and parameter counts to validate our formula and find that model quality continues to improve as we scale tokens per parameter to extreme ranges (up to 10,000). Finally, we ablate the procedure used to fit the Chinchilla scaling law coefficients and find that developing scaling laws only from data collected at typical token/parameter ratios overestimates the impact of additional tokens at these extreme ranges.
Related papers
- Scaling Inference-Efficient Language Models [3.271571137474847]
We show that model architecture affects inference latency, where models of the same size can have up to 3.5x difference in latency.
We modify the Chinchilla scaling laws to co-optimize the model parameter count, the number of training tokens, and the model architecture.
We release the Morph-1B model, which improves inference latency by 1.8x while maintaining accuracy on downstream tasks compared to open-source models.
arXiv Detail & Related papers (2025-01-30T03:16:44Z) - 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.
We find that initiating pruning at 25% of total training compute and concluding at 75% achieves near-optimal final evaluation loss.
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) - Scaling Law for Language Models Training Considering Batch Size [17.09348741898811]
Large language models (LLMs) have made remarkable advances in recent years, with scaling laws playing a critical role in this rapid progress.
We empirically investigate how a critical hyper- parameter, i.e., the global batch size, influences the LLM training prdocess.
We establish a basic scaling law on model size and training data amount.
We then examine how varying batch sizes and learning rates affect the convergence and generalization of these models.
arXiv Detail & Related papers (2024-12-02T13:58:35Z) - Scaling Laws for Precision [73.24325358259753]
We devise "precision-aware" scaling laws for both training and inference.
For inference, we find that the degradation introduced by post-training quantization increases as models are trained on more data.
For training, our scaling laws allow us to predict the loss of a model with different parts in different precisions.
arXiv Detail & Related papers (2024-11-07T00:10:10Z) - A Hitchhiker's Guide to Scaling Law Estimation [56.06982415792523]
Scaling laws predict the loss of a target machine learning model by extrapolating from easier-to-train models with fewer parameters or smaller training sets.
We estimate more than 1000 scaling laws, then derive a set of best practices for estimating scaling laws in new model families.
arXiv Detail & Related papers (2024-10-15T17:59:10Z) - More Compute Is What You Need [3.184416958830696]
We propose a new scaling law that suggests model performance depends mostly on the amount of compute spent for transformer-based models.
We predict that (a) for inference efficiency, training should prioritize smaller model sizes and larger training datasets, and (b) assuming the exhaustion of available web datasets, scaling the model size might be the only way to further improve model performance.
arXiv Detail & Related papers (2024-04-30T12:05:48Z) - The Languini Kitchen: Enabling Language Modelling Research at Different
Scales of Compute [66.84421705029624]
We introduce an experimental protocol that enables model comparisons based on equivalent compute, measured in accelerator hours.
We pre-process an existing large, diverse, and high-quality dataset of books that surpasses existing academic benchmarks in quality, diversity, and document length.
This work also provides two baseline models: a feed-forward model derived from the GPT-2 architecture and a recurrent model in the form of a novel LSTM with ten-fold throughput.
arXiv Detail & Related papers (2023-09-20T10:31:17Z) - nanoLM: an Affordable LLM Pre-training Benchmark via Accurate Loss Prediction across Scales [65.01417261415833]
We present an approach to predict the pre-training loss based on our observations that Maximal Update Parametrization (muP) enables accurate fitting of scaling laws.
With around 14% of the one-time pre-training cost, we can accurately forecast the loss for models up to 52B.
Our goal with nanoLM is to empower researchers with limited resources to reach meaningful conclusions on large models.
arXiv Detail & Related papers (2023-04-14T00:45:01Z) - A Solvable Model of Neural Scaling Laws [72.8349503901712]
Large language models with a huge number of parameters, when trained on near internet-sized number of tokens, have been empirically shown to obey neural scaling laws.
We propose a statistical model -- a joint generative data model and random feature model -- that captures this neural scaling phenomenology.
Key findings are the manner in which the power laws that occur in the statistics of natural datasets are extended by nonlinear random feature maps.
arXiv Detail & Related papers (2022-10-30T15:13:18Z) - Scaling Laws Under the Microscope: Predicting Transformer Performance
from Small Scale Experiments [42.793379799720434]
We investigate whether scaling laws can be used to accelerate model development.
We find that scaling laws emerge at finetuning time in some NLP tasks.
For tasks where scaling laws exist, they can be used to predict the performance of larger models.
arXiv Detail & Related papers (2022-02-13T19:13:00Z)
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.