simple-llm-python-124m-5b / capacity.json
jfrick's picture
python-124m-muon-5b-20261021-v1: 50065393 training targets
4719692 verified
Raw History Blame Contribute Delete
4.37 kB
{
"stage": "ready_to_freeze",
"updated_unix": 1792550906.6174269,
"tokenizer_sha256": "add5b2c7542e4efded329735825ecdcb94df1432617c3d3e4b7508aa459432f9",
"categories": {
"python_implementation": {
"target": 3250000000,
"unique_train_targets": 3344840434,
"validation_targets": 202402128,
"required_passes": 0.9716457523545949,
"two_pass_shortfall": 0,
"one_pass_shortfall": 0
},
"python_tests_examples": {
"target": 750000000,
"unique_train_targets": 1455959517,
"validation_targets": 88631252,
"required_passes": 0.5151242127565282,
"two_pass_shortfall": 0,
"one_pass_shortfall": 0
},
"python_documentation": {
"target": 500000000,
"unique_train_targets": 638756689,
"validation_targets": 32309371,
"required_passes": 0.782770667783958,
"two_pass_shortfall": 0,
"one_pass_shortfall": 0
},
"cs_math": {
"target": 250000000,
"unique_train_targets": 255001393,
"validation_targets": 31729746,
"required_passes": 0.9803868012595524,
"two_pass_shortfall": 0,
"one_pass_shortfall": 0
},
"general_education": {
"target": 150000000,
"unique_train_targets": 153000047,
"validation_targets": 59391033,
"required_passes": 0.9803918556966195,
"two_pass_shortfall": 0,
"one_pass_shortfall": 0
},
"books": {
"target": 100000000,
"unique_train_targets": 102061503,
"validation_targets": 14413928,
"required_passes": 0.9798013654570618,
"two_pass_shortfall": 0,
"one_pass_shortfall": 0
}
},
"capacity_sufficient": true,
"rejections": {
"repository_license_unresolved": 5,
"generated": 37974,
"not_python_material": 15299,
"size": 1236,
"notice_or_changelog": 121,
"minified_or_long_line": 171,
"exact_duplicate": 910960,
"malformed_or_size": 19,
"boilerplate": 566,
"excluded_path": 76203,
"repository_one_percent_cap": 1372,
"reserved_or_empty_encoding": 4,
"invalid_python3": 175412,
"non_utf8": 17,
"reserved_test_record": 203318,
"heldout_hash_exclusion": 273597,
"older_collected_repository_version": 1440,
"heldout_repository_exclusion": 287838,
"placeholder_test_scaffold": 23,
"documentation_references_heldout_repository": 2926,
"python2_specific_documentation": 5529
},
"repository_count": 58,
"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
}
]
}