{"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/amos-an-adam-style-optimizer-with-adaptive","title":"Amos: An Adam-style Optimizer with Adaptive Weight Decay towards Model-Oriented Scale","arxiv_id":"2210.11693","date":"2022-10-21","proceeding":null,"authors":["Ran Tian","Ankur P. Parikh"],"abstract":"We present Amos, a stochastic gradient-based optimizer designed for training deep neural networks. It can be viewed as an Adam optimizer with theoretically supported, adaptive learning-rate decay and weight decay. A key insight behind Amos is that it leverages model-specific information to determine the initial learning-rate and decaying schedules. When used for pre-training BERT variants and T5, Amos consistently converges faster than the state-of-the-art settings of AdamW, achieving better validation loss within <=70% training steps and time, while requiring <=51% memory for slot variables. Our code is open-sourced at: https://github.com/google-research/jestimator","url_abs":"https://arxiv.org/abs/2210.11693v2","url_pdf":"https://arxiv.org/pdf/2210.11693v2.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":"amos-an-adam-style-optimizer-with-adaptive","repo_url":"https://github.com/google-research/jestimator","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"adamw","method_name":"AdamW"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.11693","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.11693"}},"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/google-research/jestimator","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":18},"by_repo_kind":{"official":{"samples":18,"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":0,"samples":[{"code_sha256_prefix":"2bb6c564f3751916","entry":"amos","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/amos.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/amos.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2bb6c564f3751916"}},{"code_sha256_prefix":"6589ebccf58154e2","entry":"count_dataset","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/data_utils.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6589ebccf58154e2"}},{"code_sha256_prefix":"0cdb17a2cb7ed2ea","entry":"extract_axes","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/states.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/states.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0cdb17a2cb7ed2ea"}},{"code_sha256_prefix":"d8fb636561abd584","entry":"get_dataset_filenames","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/data_utils.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d8fb636561abd584"}},{"code_sha256_prefix":"03eacb055758e4ce","entry":"get_eta_fn","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/models/bert/modeling.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/models/bert/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"03eacb055758e4ce"}},{"code_sha256_prefix":"f35f7c250f470dec","entry":"get_eta_fn","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/models/bert_rpe/modeling.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/models/bert_rpe/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f35f7c250f470dec"}},{"code_sha256_prefix":"ae4f81e47ffe8ec4","entry":"get_mode_heuristic","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/estimator.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/estimator.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ae4f81e47ffe8ec4"}},{"code_sha256_prefix":"e1fa28ec4113168f","entry":"get_shape_fn","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/models/bert/modeling.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/models/bert/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e1fa28ec4113168f"}},{"code_sha256_prefix":"08fa84f42053f15a","entry":"get_shape_fn","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/models/bert_rpe/modeling.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/models/bert_rpe/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"08fa84f42053f15a"}},{"code_sha256_prefix":"93deb8b469412f3b","entry":"last_evaluated_ckpt","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/checkpoint_utils.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/checkpoint_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"93deb8b469412f3b"}},{"code_sha256_prefix":"b13a2245fd60febd","entry":"latest_ckpt_path","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/checkpoint_utils.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/checkpoint_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b13a2245fd60febd"}},{"code_sha256_prefix":"8eb387dfd7170af5","entry":"maybe_reduce_axis_names","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/amos_helper.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/amos_helper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8eb387dfd7170af5"}},{"code_sha256_prefix":"3435635af154f27d","entry":"normalize_loss_by_size","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/modeling.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3435635af154f27d"}},{"code_sha256_prefix":"48d615d3ce949e18","entry":"scale_by_amos","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/amos.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/amos.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"48d615d3ce949e18"}},{"code_sha256_prefix":"7aa1ce8753bf1f47","entry":"sparse_xe_with_logits","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/modeling.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7aa1ce8753bf1f47"}},{"code_sha256_prefix":"31bc709a794648a0","entry":"to_attention_mask","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/models/bert/modeling.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/models/bert/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"31bc709a794648a0"}},{"code_sha256_prefix":"2f530f6e8d717b5a","entry":"transpose_dataset","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/data_utils.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/data_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2f530f6e8d717b5a"}},{"code_sha256_prefix":"c1163fa4442ceef8","entry":"unstack","repo":"google-research/jestimator","repo_kind":"official","path":"jestimator/modeling.py","file_url":"https://github.com/google-research/jestimator/blob/HEAD/jestimator/modeling.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c1163fa4442ceef8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}