| { |
| "experiment": "python-124m-muon-5b", |
| "public_source_snapshots": [ |
| { |
| "dataset": "codeparrot/codeparrot-clean-train", |
| "revision": "3e6ab65f2864931e041f6a82db9b5a6ec2b71ab4", |
| "representation": "complete Python files; dataset snapshot is pinned, individual upstream Git commits are not supplied" |
| }, |
| { |
| "dataset": "common-pile/stackexchange", |
| "revision": "5ec3aa2e65b7c61b7c18f1ff18ccbc4d3279a23c", |
| "representation": "complete explanatory Python Stack Overflow threads with per-record CC-BY-SA attribution" |
| } |
| ], |
| "collected_repositories": "Complete pinned Git blobs from the user's collected snapshots; prefer recent snapshots and consume retained collected files first within each category. Repository identities, commits and notices remain in the private ledger.", |
| "existing_source_pools": "Pinned prepared CodeParrot, FineWeb-Edu, FineMath, Gutenberg and programming-documentation pools. Original database hashes, upstream record metadata and license evidence remain in the private ledger.", |
| "filters": [ |
| "Exclusive implementation, tests/examples, Python documentation and supporting-text categories", |
| "Exclude vendored, generated, minified, boilerplate-heavy and malformed files; preserve accepted text unchanged", |
| "Python 3.12 AST validation; newer syntax can be conservatively excluded", |
| "Exact file/document deduplication across sources; near clones can remain", |
| "Per-repository/category cap of 1 percent of that category's training budget", |
| "Repository/thread holdouts before window construction; cross-source heldout repository and exact document-hash exclusions", |
| "Exclude exact MBPP reference hashes; no exhaustive benchmark-contamination claim" |
| ], |
| "token_accounting": "Nonpadding next-token labels, including each document's EOS target. Existing frozen tokenizer; exact six-category budgets; prefer one pass, never exceed two.", |
| "limitations": "Supplemental code and technical Q&A include older material. Heuristic filters and upstream licensing metadata are imperfect. Detailed provenance is retained privately; this file contains only aggregate and public-source information.", |
| "corpus_database_sha256": "3942c0e7edccc426cbf7f0c3b9d69144f0511960a36e6615151645c38da41565", |
| "tokenizer_sha256": "add5b2c7542e4efded329735825ecdcb94df1432617c3d3e4b7508aa459432f9", |
| "capacity_by_origin": [ |
| { |
| "category": "books", |
| "origin": "existing_pinned_pool", |
| "documents": 923, |
| "unique_train_targets": 102061503 |
| }, |
| { |
| "category": "cs_math", |
| "origin": "existing_pinned_pool", |
| "documents": 153044, |
| "unique_train_targets": 255001393 |
| }, |
| { |
| "category": "general_education", |
| "origin": "existing_pinned_pool", |
| "documents": 113805, |
| "unique_train_targets": 153000047 |
| }, |
| { |
| "category": "python_documentation", |
| "origin": "collected_git", |
| "documents": 8796, |
| "unique_train_targets": 27901636 |
| }, |
| { |
| "category": "python_documentation", |
| "origin": "existing_pinned_pool", |
| "documents": 55, |
| "unique_train_targets": 1975348 |
| }, |
| { |
| "category": "python_documentation", |
| "origin": "python_explanatory_qa", |
| "documents": 620563, |
| "unique_train_targets": 608879705 |
| }, |
| { |
| "category": "python_implementation", |
| "origin": "collected_git", |
| "documents": 10392, |
| "unique_train_targets": 41406577 |
| }, |
| { |
| "category": "python_implementation", |
| "origin": "existing_pinned_pool", |
| "documents": 708699, |
| "unique_train_targets": 1422349105 |
| }, |
| { |
| "category": "python_implementation", |
| "origin": "supplemental_python_file", |
| "documents": 870723, |
| "unique_train_targets": 1881084752 |
| }, |
| { |
| "category": "python_tests_examples", |
| "origin": "collected_git", |
| "documents": 11828, |
| "unique_train_targets": 38755717 |
| }, |
| { |
| "category": "python_tests_examples", |
| "origin": "existing_pinned_pool", |
| "documents": 274648, |
| "unique_train_targets": 680803158 |
| }, |
| { |
| "category": "python_tests_examples", |
| "origin": "supplemental_python_file", |
| "documents": 281242, |
| "unique_train_targets": 736400642 |
| } |
| ] |
| } |
