@article{characterizinglearningcurvesduring, title = {Characterizing Learning Curves During Language Model Pre-Training: Learning, Forgetting, and Stability}, author = {Tyler A. Chang and Zhuowen Tu and Benjamin K. Bergen}, year = {2023}, eprint = {2308.15419}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2308.15419v2}, }