Search NASA⌕ Search

Engineering topics

Yin, Junqi

Publications and source records attributed to Yin, Junqi.

At least 19 records
All sourcesNASA NTRSDOE OSTI
DOE OSTI2024

chatHPC: Empowering HPC users with large language models

The ever-growing number of pre-trained large language models (LLMs) across scientific domains presents a challenge for application developers. While these models offer vast potential, fine-tuning them with custom data, aligning them for specific tasks, and evaluating their performance remain crucial steps for effective utilization. However, applying these techniques to models with tens of billions of parameters can take days or even weeks on modern workstations, making the cumulative cost of model comparison and evaluation a significant barrier to LLM-based application development. To address this challenge, we introduce an end-to-end pipeline specifically designed for building conversational and programmable AI agents on high performance computing (HPC) platforms. Our comprehensive pipeline encompasses: model pre-training, fine-tuning, web and API service deployment, along with crucial evaluations for lexical coherence, semantic accuracy, hallucination detection, and privacy considerations. Here, we demonstrate our pipeline through the development of chatHPC, a chatbot for HPC question answering and script generation. Leveraging our scalable pipeline, we achieve end-to-end LLM alignment in under an hour on the Frontier supercomputer. We propose a novel self-improved, self-instruction method for instruction set generation, investigate scaling and fine-tuning strategies, and conduct a systematic evaluation of model performance. The established practices within chatHPC will serve as a valuable guidance for future LLM-based application development on HPC platforms.

97 MATHEMATICS AND COMPUTING↗
DOE OSTI2024

ORBIT: Oak Ridge Base Foundation Model for Earth System Predictability

Earth system predictability is challenged by the complexity of environmental dynamics and the multitude of variables involved. Current AI foundation models, although advanced by leveraging large and heterogeneous data, are often constrained by their size and data integration, limiting their effectiveness in addressing the full range of Earth system prediction challenges. To overcome these limitations, we introduce the Oak Ridge Base Foundation Model for Earth System Predictability (ORBIT), an advanced vision transformer model that scales up to 113 billion parameters using a novel hybrid tensor-data orthogonal parallelism technique. As the largest model of its kind, ORBIT surpasses the current climate AI foundation model size by a thousandfold. Performance scaling tests conducted on the Frontier supercomputer have demonstrated that ORBIT achieves 684 petaFLOPS to 1.6 exaFLOPS sustained throughput, with scaling efficiency maintained at 41% to 85% across 49,152 AMD GPUs. These breakthroughs establish new advances in AI-driven climate modeling and demonstrate promise to significantly improve the Earth system predictability.

Wang, Xiao↗
DOE OSTI2024

Enabling Low-Overhead HT-HPC Workflows at Extreme Scale using GNU Parallel

GNU Parallel is a versatile and powerful tool for process parallelization widely used in scientific computing. This paper demonstrates its effective application in high-performance computing (HPC) environments, particularly focusing on its scalability and efficiency in executing large-scale high-throughput high-performance computing (HT-HPC) workflows. Through real-world examples, we highlight GNU Parallel’s performance across various HPC workloads, including GPU computing, container-based workloads, and node-local NVMe storage. Our results on two leading supercomputers, OLCF’s Frontier and NERSC’s Perlmutter, showcase GNU Parallel’s rapid process dispatching ability and its capacity to maintain low overhead even at extreme scales. We explore GNU Parallel’s application in massive parallel file transfers using a scheduled Data Transfer Node (DTN) cluster, emphasizing its broad utility in diverse scientific workflows. Beyond its direct application as a viable workflow manager, GNU Parallel can be employed in conjunction with other workflow systems as a "last-mile" parallelizing driver and as a quick prototyping tool to design and extract parallel profiles from application executions. We then argue that the potential for GNU Parallel to transform workflow management at extreme scales is substantial, paving the way for more efficient and effective scientific discoveries.

Maheshwari, Ketan↗
DOE OSTI2024

A Scalable Real-Time Data Assimilation Framework for Predicting Turbulent Atmosphere Dynamics

AI-based foundation models like FourCastNet, GraphCast are revolutionizing weather and climate predictions but are not yet ready for operational use. Their limitation lies in the absence of a data assimilation system to incorporate real-time Earth system observations, crucial for accurately forecasting events like tropical cyclones. To overcome these obstacles, we introduce a generic real-time data assimilation framework and demonstrate its end-to-end performance on the Frontier supercomputer. This framework comprises two primary modules: an ensemble score filter (EnSF), which significantly outperforms the state-of-the-art data assimilation method, and a vision transformer-based surrogate capable of real-time adaptation through the integration of observational data. We demonstrate both the strong and weak scaling of our framework up to 1024 GPUs on the Exascale supercomputer, Frontier. Our results not only illustrate the framework's exceptional scalability on high-performance computing systems, but also demonstrate the importance of supercomputers in real-time data assimilation for weather and climate predictions.

Lu, Dan↗
DOE OSTI2024

Towards the holistic design of alloys with large language models

Large language models are very effective at solving general tasks, but can also be useful in materials design and extracting and using information from the scientific literature and unstructured corpora. For instance, in the domain of alloy design and manufacturing, they can expedite the materials design process and enable the inclusion of holistic criteria.

36 MATERIALS SCIENCE↗
DOE OSTI2024

The Case for Co-Designing Model Architectures with Hardware

While GPUs are responsible for training the vast majority of state-of-the-art deep learning models, the implications of their architecture are often overlooked when designing new deep learning (DL) models. As a consequence, modifying a DL model to be more amenable to the target hardware can significantly improve the runtime performance of DL training and inference. In this paper, we provide a set of guidelines for users to maximize the runtime performance of their transformer models. These guidelines have been created by carefully considering the impact of various model hyperparameters controlling model shape on the efficiency of the underlying computation kernels executed on the GPU. We find the throughput of models with “efficient” model shapes is up to 39% higher while preserving accuracy compared to models with a similar number of parameters but with unoptimized shapes.

Yin, Junqi↗
DOE OSTI2024

Roadmap on data-centric materials science

Science is and always has been based on data, but the terms ‘data-centric’ and the ‘4th paradigm’ of materials research indicate a radical change in how information is retrieved, handled and research is performed. It signifies a transformative shift towards managing vast data collections, digital repositories, and innovative data analytics methods. The integration of artificial intelligence and its subset machine learning, has become pivotal in addressing all these challenges. This Roadmap on Data-Centric Materials Science explores fundamental concepts and methodologies, illustrating diverse applications in electronic-structure theory, soft matter theory, microstructure research, and experimental techniques like photoemission, atom probe tomography, and electron microscopy. While the roadmap delves into specific areas within the broad interdisciplinary field of materials science, the provided examples elucidate key concepts applicable to a wider range of topics. The discussed instances offer insights into addressing the multifaceted challenges encountered in contemporary materials research.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Designing complex concentrated alloys with quantum machine learning and language modeling

Designing novel complex concentrated alloys (CCAs) is an essential topic in materials science. However, due to the complicated high-dimensional component-property relationship, tuning material properties by researchers’ experience is challenging, even when guided by physical or empirical rules. Here, we adopt quantum computing (QC) technology and machine learning models to provide a proof-of-concept application of QC in physical metallurgy. We propose a quantum support vector machine (QSVM) model to predict single-phase CCAs. We show that fine-tuned quantum kernels with entanglement deliver promising performance, with a maximum accuracy of 89.4%. The QSVM model is then used to identify 1,741 lightweight CCAs jointly with a new text-mining-based method. Meanwhile, we devise a controllable approach to study the effect of noise on model performance and find that the noise level needs to be minimized for high-performance QSVM models. Finally, this study provides a practical and general approach to designing CCAs based on quantum technologies.

36 MATERIALS SCIENCE↗
DOE OSTI2024

Comparative Study of Large Language Model Architectures on Frontier

Large language models (LLMs) have garnered significant attention in both the AI community and beyond. Among these, the Generative Pre-trained Transformer (GPT) has emerged as the dominant architecture, spawning numerous variants. However, these variants have undergone pre-training under diverse conditions, including variations in input data, data preprocessing, and training methodologies, resulting in a lack of controlled comparative studies. Here we meticulously examine two prominent open-sourced GPT architectures, GPT-NeoX and LLaMA, leveraging the computational power of Frontier, the world’s first Exascale supercomputer. Employing the same materials science text corpus and a comprehensive end-to-end pipeline, we conduct a comparative analysis of their training and downstream performance. Our efforts culminate in achieving state-of-the-art performance on a challenging materials science benchmark. Furthermore, we investigate the computation and energy efficiency, and propose a computationally efficient method for architecture design. To our knowledge, these pre-trained models represent the largest available for materials science. Our findings provide practical guidance for building LLMs on HPC platforms.

Yin, Junqi↗
DOE OSTI2024

Pretraining Billion-Scale Geospatial Foundational Models on Frontier

As AI workloads increase in scope, generalization capability becomes challenging for small task-specific models and their demand for large amounts of labeled training samples increases. On the contrary, Foundation Models (FMs) are trained with internet-scale unlabeled data via self-supervised learning and have been shown to adapt to various tasks with minimal fine-tuning. Although large FMs have demonstrated significant impact in natural language processing and computer vision, efforts toward FMs for geospatial applications have been restricted to smaller size models, as pretraining larger models requires very large computing resources equipped with state-of-the-art hardware accelerators. Current satellite constellations collect 100+TBs of data a day, resulting in images that are billions of pixels and multimodal in nature. Such geospatial data poses unique challenges opening up new opportunities to develop FMs. We investigate billion scale FMs and HPC training profiles for geospatial applications by pretraining on publicly available data. We studied from end-to-end the performance and impact in the solution by scaling the model size. Our larger 3B parameter size model achieves up to 30% improvement in top1 scene classification accuracy when comparing a 100M parameter model. Moreover, we detail performance experiments on the Frontier supercomputer, America's first exascale system, where we study different model and data parallel approaches using PyTorch's Fully Sharded Data Parallel library. Specifically, we study variants of the Vision Transformer architecture (ViT), conducting performance analysis for ViT models with size up to 15B parameters. By discussing throughput and performance bottlenecks under different parallelism configurations, we offer insights on how to leverage such leadership-class HPC resources when developing large models for geospatial imagery applications.

Tsaris, Aristeidis (aris)↗
DOE OSTI2024

Optimizing Distributed Training on Frontier for Large Language Models

Large language models (LLMs) have demonstrated remarkable success as foundational models, benefiting various downstream applications through fine-tuning. Loss scaling studies have demonstrated the superior performance of larger LLMs compared to their smaller counterparts. Nevertheless, training LLMs with billions of parameters poses significant challenges and requires considerable computational resources. For example, training a one trillion parameter GPT-style model on 20 trillion tokens requires a staggering 120 million exaflops. This research explores efficient distributed training strategies to extract this computation from Frontier, the world's first exascale supercomputer. We enable and investigate various model and data parallel training techniques, such as tensor parallelism, pipeline parallelism, and sharded data parallelism, to facilitate training a trillion-parameter model on Frontier. We empirically assess these techniques and their associated parameters to determine their impact on memory footprint, communication latency, and GPU's computational efficiency. We analyze the complex interplay among these techniques and find a strategy to combine them to achieve high throughput through hyperparameter tuning. We have identified efficient strategies for training large LLMs of varying sizes through empirical analysis and hyperparameter tuning. For 22 Billion, 175 Billion, and 1 Trillion parameters, we achieved GPU throughputs of 38.38%, 36.14%, and 31.96%, respectively. For the training of the 175 Billion parameter model and the 1 Trillion parameter model, we achieved 100% weak scaling efficiency on 1024 and 3072 Mi250X GPUs, respectively. We also achieved strong scaling efficiencies of 89% and 87% for these two models. We trained these models only tens of iterations instead of training till completion.

Yin, Junqi↗
DOE OSTI2023

TaV_BCC_SolidSolution_128atoms_VASP6

We performed density functional theory (DFT) calculations for body-centered-cubic (BCC) structures with 128 lattices sites of solid solution binary alloys tantalum-vanadium (Tanu-V). The electronic structures of alloys have been calculated using Vienna Ab initio Simulation Package (VASP). Within this package the DFT approach is used to reduce many-body Schrodinger equation to set of single particle Kohn-Sham (KS) equations. The generalized electronic exchange-correlation functional is described by generalized gradient approximation with the Perdew-Burke-Ernzerhof parametrization. The electron-ion interactions is described by pseudopotentials developed within the plane-wave basis projector augmented-wave (PAW) approach. These pseudopotentials are available at the VASP portal (http://cms.mpi.univie.ac.at/vasp/). Our calculations have been run with the pseudopotentials treating s and p semi-core states as valence in case for the element V. For Ta, p semi-core states as valence were chosen. The electronic densities and potentials are expanded over plane-waves with energy cutoff of 350 eV. 2x2x2 k-mesh and normal precision were used. The alloys were modeled by supercell containing 128 randomly distributed atoms. At initial step the atoms occupy perfect bcc lattice cites. This initial structure was optimized until energy changes less than 1e-6 eV, while forces acting on atoms don't exceed 1e-2 eV/angstrom. The electron-ion interaction is described by PAW pseudopotentials. The calculations have been collected by sampling chemical compositions across the entire compositional range. The chemical compositions have been sampled by progressively changing the number of atoms per constituent by 4. For each chemical composition of binaries and ternaries, the first-principle calculations have been run for 100 randomized arrangements of the constituents on the BCC lattice sites. We collected data for a total of 3,100 randomized atomic structures over 31 chemical compositions. The calculations have been collected on NERSC-Perlmutter and OLCF-Summit using the VASP 6.3.2. The VASP calculations for every atomic structure have been performed in 2 main steps: 1. Starting from an ideal body-centered-cubic (BCC) structure, geometry optimization with low precision has been executed to perform a preliminary optimization of the atomic structure. The output for this calculations is available in the files 0.CONTCAR, 0.OUTCAR, rlx1.out. 2. Using the atomic structure resulting from the preliminary geometry optimization, a second geometry optimization has been performed using normal precision. The output for this calculations is available in the files CONTCAR, OUTCAR, rlx2.out, vaspout.h5, and vasprun.xml. Cases 1-10 have been run without generating the file 'vaspout.h5'. Every chemical composition sampled across the composition range in the dataset has its own directory. The convention used to name the directories for binary alloys is AXBY, where A and B refer to the constituents, whereas X and Y are positive integers that represent the number of atoms for each constituent and their values still sum up to 128. Each atomic structure associated with a specific chemical composition has its own sub-directory within the directory of the corresponding chemical composition. The sub-directories for each atomic structure for each chemical composition are named 'case-*', where * is a positive integer that spans all the values from 1 through 100, extremes included. The files contained in each sub-directory 'case-*' for each atomic structure are as follows: FILES contained in each subdirectory with name case-N where N ranges between 11 and 100, extremes included: 1. INCAR: input file that contains various parameters and settings for controlling the behavior of the electronic structure calculations 2. KPOINTS: input file that specifies the Bloch vectors (k points) used to sample the Brillouin zone 3. 0.POSCAR: input file that defines the atomic structure of a system 4. 0.CONTCAR: output file that provides the atomic positions and cell parameters after the first geometry optimization has been run with the precision variable set to PREC=Low in the INCAR file 5. 0.OUTCAR: output file that contains detailed information about the progress of a calculation after the first geometry optimization has been run with the precision variable set to PREC=Low in the INCAR file 6. rlx1.out: file with diagnostic information about the execution of the first geometry optimization with precision variable set to PREC=Low in the INCAR file 7. POSCAR: input file that defines the atomic structure of a system after the first geometry optimization has been run at low precision. This represents the input for the second geometry optimization run with the precision variable set to PREC=Normal in the INCAR file 8. CONTCAR: output file that provides the atomic positions and cell parameters after the second geometry optimization has been run with the precision variable set to PREC=Normal in the INCAR file 9. OUTCAR: output file that contains detailed information about the progress of a calculation after the second geometry optimization has been run with the precision variable set to PREC=Normal in the INCAR file 10. rlx2.out: file with diagnostic information about the execution of the second geometry optimization with precision variable set to PREC=Normal in the INCAR file 11. vaspout.h5: hierarchical HDF5 file containing the inputs and outputs of a VASP calculation. To analyze the data in this file we recommend using py4vasp. This file is only produced if the VASP version used is compiled with HDF5 support 12. vasprun.xml: contains similar information to OUTCAR, but in an xml format. Subdirectories with name case-N, where N ranges between 1 and 10 (extremes included) contain all the files listed above except 'vaspout.h5'. Subdirectories with name case-N, where N ranges between 41 and 60 (extremes included), contain a duplicate copy of the files listed above except for KPOINTS. The names of the duplicate files end with -bis, and correspond to a second VASP calculation that has converged to a different optimized geometry. This research is sponsored by the Artificial Intelligence Initiative as part of the Laboratory Directed Research and Development (LDRD) Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the US Department of Energy under contract DE-AC05-00OR22725. This work used resources of the Oak Ridge Leadership Computing Facility, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725, under Directorate Discretionary awards MAT025 (Materials Science) and LRN026 (Machine Learning), and INCITE award MAT201. This work also used resources of the National Energy Research Scientific Computing Center, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231, under award ERCAP0025216. REFERENCES (1) Kresse, G. and Hafner, J. Ab initio molecular dynamics for liquid metals. Phys. review B 47, 558 (1993). (2) Kresse, G. and Hafner, J. Ab initio molecular-dynamics simulation of the liquid-metal-amorphous-semiconductor transition in germanium. Phys. Rev. B 49, 14251 (1994) (3) Kresse, G. and Furthmuller, J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput. materials science 6, 15-50 (1996) (4) Kresse, G. and Furthmuller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. review B 54, 11169 (1996) (5) Kresse, G. and Joubert, D. From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. review b 59, 1758 (1999)

36 MATERIALS SCIENCE↗
DOE OSTI2023

NbV_BCC_SolidSolution_128atoms_VASP6

We performed density functional theory (DFT) calculations for body-centered-cubic (BCC) structures with 128 lattices sites of solid solution binary alloys niobium-vanadium (Nb-V). The electronic structures of alloys have been calculated using Vienna Ab initio Simulation Package (VASP). Within this package the DFT approach is used to reduce many-body Schrodinger equation to set of single particle Kohn-Sham (KS) equations. The generalized electronic exchange-correlation functional is described by generalized gradient approximation with the Perdew-Burke-Ernzerhof parametrization. The electron-ion interactions is described by pseudopotentials developed within the plane-wave basis projector augmented-wave (PAW) approach \cite{PAW}. These pseudopotentials are available at the VASP portal (http://cms.mpi.univie.ac.at/vasp/). Our calculations have been run with the pseudopotentials treating s and p semi-core states as valence in case for the elements Nb and V. The electronic densities and potentials are expanded over plane-waves with energy cutoff of 350 eV. 2x2x2 k-mesh and normal precision were used. The alloys were modeled by supercell containing 128 randomly distributed atoms. At initial step the atoms occupy perfect bcc lattice cites. This initial structure was optimized until energy changes less than 1e-6 eV, while forces acting on atoms don't exceed 1e-2 eV/angstrom. The electron-ion interaction is described by PAW pseudopotentials. The calculations have been collected by sampling chemical compositions across the entire compositional range. The chemical compositions have been sampled by progressively changing the number of atoms per constituent by 4. For each chemical composition of binaries and ternaries, the first-principle calculations have been run for 100 randomized arrangements of the constituents on the BCC lattice sites. We collected data for a total of 3,100 randomized atomic structures over 31 chemical compositions. The calculations have been collected on NERSC-Perlmutter and OLCF-Summit using the VASP 6.3.2. The VASP calculations for every atomic structure have been performed in 2 main steps: 1. Starting from an ideal body-centered-cubic (BCC) structure, geometry optimization with low precision has been executed to perform a preliminary optimization of the atomic structure. The output for this calculations is available in the files 0.CONTCAR, 0.OUTCAR, rlx1.out. 2. Using the atomic structure resulting from the preliminary geometry optimization, a second geometry optimization has been performed using normal precision. The output for this calculations is available in the files CONTCAR, OUTCAR, rlx2.out, vaspout.h5, and vasprun.xml. Cases 1-10 have been run without generating the file 'vaspout.h5'. Every chemical composition sampled across the composition range in the dataset has its own directory. The convention used to name the directories for binary alloys is AXBY, where A and B refer to the constituents, whereas X and Y are positive integers that represent the number of atoms for each constituent and their values still sum up to 128. Each atomic structure associated with a specific chemical composition has its own sub-directory within the directory of the corresponding chemical composition. The sub-directories for each atomic structure for each chemical composition are named 'case-*', where * is a positive integer that spans all the values from 1 through 100, extremes included. The files contained in each sub-directory 'case-*' for each atomic structure are as follows: FILES contained in each subdirectory with name case-N where N ranges between 11 and 100, extremes included: 1. INCAR: input file that contains various parameters and settings for controlling the behavior of the electronic structure calculations 2. KPOINTS: input file that specifies the Bloch vectors (k points) used to sample the Brillouin zone 3. 0.POSCAR: input file that defines the atomic structure of a system 4. 0.CONTCAR: output file that provides the atomic positions and cell parameters after the first geometry optimization has been run with the precision variable set to PREC=Low in the INCAR file 5. 0.OUTCAR: output file that contains detailed information about the progress of a calculation after the first geometry optimization has been run with the precision variable set to PREC=Low in the INCAR file 6. rlx1.out: file with diagnostic information about the execution of the first geometry optimization with precision variable set to PREC=Low in the INCAR file 7. POSCAR: input file that defines the atomic structure of a system after the first geometry optimization has been run at low precision. This represents the input for the second geometry optimization run with the precision variable set to PREC=Normal in the INCAR file 8. CONTCAR: output file that provides the atomic positions and cell parameters after the second geometry optimization has been run with the precision variable set to PREC=Normal in the INCAR file 9. OUTCAR: output file that contains detailed information about the progress of a calculation after the second geometry optimization has been run with the precision variable set to PREC=Normal in the INCAR file 10. rlx2.out: file with diagnostic information about the execution of the second geometry optimization with precision variable set to PREC=Normal in the INCAR file 11. vaspout.h5: hierarchical HDF5 file containing the inputs and outputs of a VASP calculation. To analyze the data in this file we recommend using py4vasp. This file is only produced if the VASP version used is compiled with HDF5 support 12. vasprun.xml: contains similar information to OUTCAR, but in an xml format. Subdirectories with name case-N, where N ranges between 1 and 10 (extremes included) contain all the files listed above except 'vaspout.h5'. Subdirectories with name case-N, where N ranges between 41 and 60 (extremes included), contain a duplicate copy of the files listed above except for KPOINTS. The names of the duplicate files end with -bis, and correspond to a second VASP calculation that has converged to a different optimized geometry. This research is sponsored by the Artificial Intelligence Initiative as part of the Laboratory Directed Research and Development (LDRD) Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the US Department of Energy under contract DE-AC05-00OR22725. This work used resources of the Oak Ridge Leadership Computing Facility, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725, under Directorate Discretionary awards MAT025 (Materials Science) and LRN026 (Machine Learning), and INCITE award MAT201. This work also used resources of the National Energy Research Scientific Computing Center, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231, under award ERCAP0025216. REFERENCES (1) Kresse, G. and Hafner, J. Ab initio molecular dynamics for liquid metals. Phys. review B 47, 558 (1993). (2) Kresse, G. and Hafner, J. Ab initio molecular-dynamics simulation of the liquid-metal-amorphous-semiconductor transition in germanium. Phys. Rev. B 49, 14251 (1994) (3) Kresse, G. and Furthmüller, J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput. materials science 6, 15-50 (1996) (4) Kresse, G. and Furthmüller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. review B 54, 11169 (1996) (5) Kresse, G. and Joubert, D. From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. review b 59, 1758 (1999)

36 MATERIALS SCIENCE↗
DOE OSTI2023

NbTa_BCC_SolidSolution_128atoms_VASP6

We performed density functional theory (DFT) calculations for body-centered-cubic (BCC) structures with 128 lattices sites of solid solution binary alloys niobium-tantalum (Nb-Ta). The electronic structures of alloys have been calculated using Vienna Ab initio Simulation Package (VASP). Within this package the DFT approach is used to reduce many-body Schrodinger equation to set of single particle Kohn-Sham (KS) equations. The generalized electronic exchange-correlation functional is described by generalized gradient approximation with the Perdew-Burke-Ernzerhof parametrization. The electron-ion interactions is described by pseudopotentials developed within the plane-wave basis projector augmented-wave (PAW) approach \cite{PAW}. These pseudopotentials are available at the VASP portal (http://cms.mpi.univie.ac.at/vasp/). Our calculations have been run with the pseudopotentials treating s and p semi-core states as valence in case for the elements Nb. For Ta, p semi-core states as valence were chosen. The electronic densities and potentials are expanded over plane-waves with energy cutoff of 350 eV. 2x2x2 k-mesh and normal precision were used. The alloys were modeled by supercell containing 128 randomly distributed atoms. At initial step the atoms occupy perfect bcc lattice cites. This initial structure was optimized until energy changes less than 1e-6 eV, while forces acting on atoms don't exceed 1e-2 eV/angstrom. The electron-ion interaction is described by PAW pseudopotentials. The calculations have been collected by sampling chemical compositions across the entire compositional range. The chemical compositions have been sampled by progressively changing the number of atoms per constituent by 4. For each chemical composition of binaries and ternaries, the first-principle calculations have been run for 100 randomized arrangements of the constituents on the BCC lattice sites. We collected data for a total of 3,100 randomized atomic structures over 31 chemical compositions. The calculations have been collected on NERSC-Perlmutter using the VASP 6.3.2. The VASP calculations for every atomic structure have been performed in 2 main steps: 1. Starting from an ideal body-centered-cubic (BCC) structure, geometry optimization with low precision has been executed to perform a preliminary optimization of the atomic structure. The output for this calculations is available in the files 0.CONTCAR, 0.OUTCAR, rlx1.out. 2. Using the atomic structure resulting from the preliminary geometry optimization, a second geometry optimization has been performed using normal precision. The output for this calculations is available in the files CONTCAR, OUTCAR, rlx2.out, vaspout.h5, and vasprun.xml. Cases 1-10 have been run without generating the file 'vaspout.h5'. Every chemical composition sampled across the composition range in the dataset has its own directory. The convention used to name the directories for ternary alloys is AXBYCZ, where A, B, and C refer to the constituents, and X, Y, and Z are positive integers that represent the number of atoms for each constituent and their values still sum up to 128. Each atomic structure associated with a specific chemical composition has its own sub-directory within the directory of the corresponding chemical composition. The sub-directories for each atomic structure for each chemical composition are named 'case-*', where * is a positive integer that spans all the values from 1 through 100, extremes included. The files contained in each sub-directory 'case-*' for each atomic structure are as follows: FILES contained in each subdirectory with name case-N where N ranges between 11 and 100, extremes included: 1. INCAR: input file that contains various parameters and settings for controlling the behavior of the electronic structure calculations 2. KPOINTS: input file that specifies the Bloch vectors (k points) used to sample the Brillouin zone 3. 0.POSCAR: input file that defines the atomic structure of a system 4. 0.CONTCAR: output file that provides the atomic positions and cell parameters after the first geometry optimization has been run with the precision variable set to PREC=Low in the INCAR file 5. 0.OUTCAR: output file that contains detailed information about the progress of a calculation after the first geometry optimization has been run with the precision variable set to PREC=Low in the INCAR file 6. rlx1.out: file with diagnostic information about the execution of the first geometry optimization with precision variable set to PREC=Low in the INCAR file 7. POSCAR: input file that defines the atomic structure of a system after the first geometry optimization has been run at low precision. This represents the input for the second geometry optimization run with the precision variable set to PREC=Normal in the INCAR file 8. CONTCAR: output file that provides the atomic positions and cell parameters after the second geometry optimization has been run with the precision variable set to PREC=Normal in the INCAR file 9. OUTCAR: output file that contains detailed information about the progress of a calculation after the second geometry optimization has been run with the precision variable set to PREC=Normal in the INCAR file 10. rlx2.out: file with diagnostic information about the execution of the second geometry optimization with precision variable set to PREC=Normal in the INCAR file 11. vaspout.h5: hierarchical HDF5 file containing the inputs and outputs of a VASP calculation. To analyze the data in this file we recommend using py4vasp. This file is only produced if the VASP version used is compiled with HDF5 support 12. vasprun.xml: contains similar information to OUTCAR, but in an xml format. Subdirectories with name case-N, where N ranges between 1 and 10 (extremes included) contain all the files listed above except 'vaspout.h5'. Subdirectories with name case-N, where N ranges between 41 and 60 (extremes included), contain a duplicate copy of the files listed above except for KPOINTS. The names of the duplicate files end with -bis, and correspond to a second VASP calculation that has converged to a different optimized geometry. This research is sponsored by the Artificial Intelligence Initiative as part of the Laboratory Directed Research and Development (LDRD) Program of Oak Ridge National Laboratory, managed by UT-Battelle, LLC, for the US Department of Energy under contract DE-AC05-00OR22725. This work used resources of the Oak Ridge Leadership Computing Facility, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC05-00OR22725, under Directorate Discretionary awards MAT025 (Materials Science) and LRN026 (Machine Learning), and INCITE award MAT201. This work also used resources of the National Energy Research Scientific Computing Center, which is supported by the Office of Science of the U.S. Department of Energy under Contract No. DE-AC02-05CH11231, under award ERCAP0025216. REFERENCES (1) Kresse, G. and Hafner, J. Ab initio molecular dynamics for liquid metals. Phys. review B 47, 558 (1993). (2) Kresse, G. and Hafner, J. Ab initio molecular-dynamics simulation of the liquid-metal-amorphous-semiconductor transition in germanium. Phys. Rev. B 49, 14251 (1994) (3) Kresse, G. and Furthmüller, J. Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set. Comput. materials science 6, 15-50 (1996) (4) Kresse, G. and Furthmüller, J. Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. Phys. review B 54, 11169 (1996) (5) Kresse, G. and Joubert, D. From ultrasoft pseudopotentials to the projector augmented-wave method. Phys. review b 59, 1758 (1999)

36 MATERIALS SCIENCE↗
DOE OSTI2023

FORGE: Pre-Training Open Foundation Models for Science

Large language models (LLMs) are poised to revolutionize the way we conduct scientific research. However, both model complexity and pre-training cost are impeding effective adoption for the wider science community. Identifying suitable scientific use cases, finding the optimal balance between model and data sizes, and scaling up model training are among the most pressing issues that need to be addressed. In this study, we provide practical solutions for building and using LLM-based foundation models targeting scientific research use cases. We present an end-to-end examination of the effectiveness of LLMs in scientific research, including their scaling behavior and computational requirements on Frontier, the first Exascale supercomputer. We have also developed for release to the scientific community a suite of open foundation models called FORGE with up to 26B parameters using 257B tokens from over 200M scientific articles, with performance either on par or superior to other state-of-the-art comparable models. We have demonstrated the use and effectiveness of FORGE on scientific downstream tasks. Our research establishes best practices that can be applied across various fields to take advantage of LLMs for scientific discovery.

Yin, Junqi↗
DOE OSTI2023

Tokenized Data for FORGE Foundation Models

This dataset comprises a vast corpus of 257 billion tokens, accompanied by the corresponding vocabulary file employed in the pre-training of FORGE foundation models. The primary data source for this corpus is scientific documents derived from diverse origins, and they have been tokenized using the Hugging Face BPE tokenizer. Further details about this research can be found in the publication titled FORGE: Pre-Training Open Foundation Models for Science authored by Junqi Yin, Sajal Dash, Feiyi Wang, and Mallikarjun (Arjun) Shankar, presented at SC'23. The data tokenization pipeline and resulting artifacts use CORE data [Ref: Knoth, P., and Zdrahal, Z. (2012). CORE: three access levels to underpin open access. D-Lib Magazine, 18(11/12)]. For use of these data sets for any purpose, please follow the guidelines provided in https://core.ac.uk/terms .

Yin, Junqi↗