Toto 2.0: Time Series Forecasting Enters the Scaling Era
We show that time series foundation models scale: a single training recipe produces reliable forecast-quality improvements from 4M to 2.5B parameters. We release Toto 2.0, a family of five open-weights forecasting models trained under this recipe. The Toto 2.0 family sets a new state of the art on three forecasting benchmarks: BOOM, our observability benchmark; GIFT-Eval, the standard general-purpose benchmark; and the recent contamination-resistant TIME benchmark. This report describes our experimental results and details the design decisions behind Toto 2.0: its architecture and training recipe, training data, and the u-muP hyperparameter transfer pipeline. All five base checkpoints are released under Apache 2.0.
Code (0)
등록된 구현이 없습니다.
Tasks
Time Series ForecastingSimilar Papers 제목 키워드 기반
Toto: Time Series Optimized Transformer for Observability
This technical report describes the Time Series Optimized Transformer for Observability (Toto), a new state of the art foundation model for time series forecasting developed by Datadog. In addition to advancing the state…
Time SeriesTime Series ForecastingThis Time is Different: An Observability Perspective on Time Series Foundation Models
We introduce Toto, a time series forecasting foundation model with 151 million parameters. Toto uses a modern decoder-only architecture coupled with architectural innovations designed to account for specific challenges f…
DecoderMultivariate Time Series ForecastingTime SeriesTime Series ForecastingScaling Law for Time Series Forecasting
Scaling law that rewards large datasets, complex models and enhanced data granularity has been observed in various fields of deep learning. Yet, studies on time series forecasting have cast doubt on scaling behaviors of …
Time SeriesTime Series ForecastingTOTOPO: Classifying univariate and multivariate time series with Topological Data Analysis
This work is devoted to a comprehensive analysis of topological data analysis fortime series classification. Previous works have significant shortcomings, such aslack of large-scale benchmarking or missing state-of-the-a…
BenchmarkingTime SeriesTime Series AnalysisTopological Data AnalysisForecasting Method for Grouped Time Series with the Use of k-Means Algorithm
The paper is focused on the forecasting method for time series groups with the use of algorithms for cluster analysis. $K$-means algorithm is suggested to be a basic one for clustering. The coordinates of the centers of …
ClusteringTime SeriesTime Series AnalysisTime Series Forecasting