{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/what-happens-during-the-loss-plateau","title":"What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers","arxiv_id":"2506.13688","date":"2025-06-16","proceeding":null,"authors":["Pulkit Gopalani","Wei Hu"],"abstract":"Training Transformers on algorithmic tasks frequently demonstrates an intriguing abrupt learning phenomenon: an extended performance plateau followed by a sudden, sharp improvement. This work investigates the underlying mechanisms for such dynamics, primarily in shallow Transformers. We reveal that during the plateau, the model often develops an interpretable partial solution while simultaneously exhibiting a strong repetition bias in their outputs. This output degeneracy is accompanied by internal representation collapse, where hidden states across different tokens become nearly parallel. We further identify the slow learning of optimal attention maps as a key bottleneck. Hidden progress in attention configuration during the plateau precedes the eventual rapid convergence, and directly intervening on attention significantly alters plateau duration and the severity of repetition bias and representational collapse. We validate that these identified phenomena-repetition bias and representation collapse-are not artifacts of toy setups but also manifest in the early pre-training stage of large language models like Pythia and OLMo.","url_abs":"https://arxiv.org/abs/2506.13688v1","url_pdf":"https://arxiv.org/pdf/2506.13688v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"what-happens-during-the-loss-plateau","repo_url":"https://github.com/pulkitgopalani/tf-loss-plateau","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[{"method_slug":"pythia","method_name":"Pythia"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2506.13688","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13688"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pulkitgopalani/tf-loss-plateau","reach":{"status":"ok"}}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":2,"samples":[{"code_sha256_prefix":"bab1a80183a65742","entry":"batch_count","repo":"pulkitgopalani/tf-loss-plateau","repo_kind":"official","path":"src/train_add.py","file_url":"https://github.com/pulkitgopalani/tf-loss-plateau/blob/HEAD/src/train_add.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bab1a80183a65742"}},{"code_sha256_prefix":"df1baca5141c4e64","entry":"compute_entropy","repo":"pulkitgopalani/tf-loss-plateau","repo_kind":"official","path":"src/train_add.py","file_url":"https://github.com/pulkitgopalani/tf-loss-plateau/blob/HEAD/src/train_add.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"df1baca5141c4e64"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}