simple-llm-python-124m-5b / data-manifest.json
jfrick's picture
python-124m-muon-5b-20261021-v1: 50065393 training targets
4719692 verified
Raw History Blame Contribute Delete
2.68 kB
{
"format": "scholarly-raw-v1",
"training_ready": true,
"max_passes": 2,
"experiment": "python-124m-muon-5b",
"prefer_collected": true,
"target_tokens": 5000000000,
"tokenizer_sha256": "add5b2c7542e4efded329735825ecdcb94df1432617c3d3e4b7508aa459432f9",
"database": {
"path": "raw.sqlite",
"sha256": "3942c0e7edccc426cbf7f0c3b9d69144f0511960a36e6615151645c38da41565"
},
"sources": {
"python_implementation": {
"weight_percent": 65,
"target_tokens": 3250000000,
"max_passes": 1,
"splits": {
"train": {
"loss_tokens": 3344840434
},
"validation": {
"loss_tokens": 202402128
}
}
},
"python_tests_examples": {
"weight_percent": 15,
"target_tokens": 750000000,
"max_passes": 1,
"splits": {
"train": {
"loss_tokens": 1455959517
},
"validation": {
"loss_tokens": 88631252
}
}
},
"python_documentation": {
"weight_percent": 10,
"target_tokens": 500000000,
"max_passes": 1,
"splits": {
"train": {
"loss_tokens": 638756689
},
"validation": {
"loss_tokens": 32309371
}
}
},
"cs_math": {
"weight_percent": 5,
"target_tokens": 250000000,
"max_passes": 1,
"splits": {
"train": {
"loss_tokens": 255001393
},
"validation": {
"loss_tokens": 31729746
}
}
},
"general_education": {
"weight_percent": 3,
"target_tokens": 150000000,
"max_passes": 1,
"splits": {
"train": {
"loss_tokens": 153000047
},
"validation": {
"loss_tokens": 59391033
}
}
},
"books": {
"weight_percent": 2,
"target_tokens": 100000000,
"max_passes": 1,
"splits": {
"train": {
"loss_tokens": 102061503
},
"validation": {
"loss_tokens": 14413928
}
}
}
},
"heldout": {
"path": "heldout.jsonl.gz",
"sha256": "58ed450084b99893f1e1b09d8f7556653ab36a66db1eb41644e8f92029490325",
"windows": 192,
"tokenizer_sha256": "add5b2c7542e4efded329735825ecdcb94df1432617c3d3e4b7508aa459432f9"
},
"limitations": [
"Exact file/document deduplication; near clones can remain",
"Path and content heuristics are imperfect",
"Documentation includes explanatory Python technical Q&A",
"Collected recent repositories preferred; supplements include older material",
"No benchmark-contamination claim; detailed source provenance remains private"
]
}