%0 Journal Article %1 journals/corr/abs-2306-03241 %A Sanyal, Sunny %A Kaddour, Jean %A Kumar, Abhishek %A Sanghavi, Sujay %D 2023 %J CoRR %K dblp %T Understanding the Effectiveness of Early Weight Averaging for Training Large Language Models. %U http://dblp.uni-trier.de/db/journals/corr/corr2306.html#abs-2306-03241 %V abs/2306.03241

@article{journals/corr/abs-2306-03241, added-at = {2023-06-13T00:00:00.000+0200}, author = {Sanyal, Sunny and Kaddour, Jean and Kumar, Abhishek and Sanghavi, Sujay}, biburl = {https://www.bibsonomy.org/bibtex/23f696a649e9f96c0154bec4f35246cc9/dblp}, ee = {https://doi.org/10.48550/arXiv.2306.03241}, interhash = {c1eddd555b105feea5ab41d199b3cddd}, intrahash = {3f696a649e9f96c0154bec4f35246cc9}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T23:16:28.000+0200}, title = {Understanding the Effectiveness of Early Weight Averaging for Training Large Language Models.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2306.html#abs-2306-03241}, volume = {abs/2306.03241}, year = 2023 }