| { | |
| "corpus": { | |
| "bytes": 1262158944, | |
| "path": "/mnt/donto-data/alpha-corpora/sft-text-v2/sft-v2.txt", | |
| "rows": 511428, | |
| "sha256": "ffad0a376c7eac2e0ec91f0901ec1ff87cba67cc298222828ce3df1a3e60b3fb" | |
| }, | |
| "overall": { | |
| "max": 1024, | |
| "mean": 589.1191018090523, | |
| "min": 16, | |
| "p50": 657, | |
| "p95": 978, | |
| "p99": 1014, | |
| "rows": 511428 | |
| }, | |
| "result": "PASS", | |
| "rows_at_bound": 470, | |
| "rows_over_bound": 0, | |
| "schema": "alpha-sft-length-audit-v1", | |
| "sources": [ | |
| { | |
| "max": 1024, | |
| "mean": 615.071214159795, | |
| "min": 22, | |
| "p50": 689, | |
| "p95": 980, | |
| "p99": 1015, | |
| "rows": 450402, | |
| "source": "smol-smoltalk" | |
| }, | |
| { | |
| "max": 277, | |
| "mean": 185.38842975206612, | |
| "min": 86, | |
| "p50": 188, | |
| "p95": 241, | |
| "p99": 276, | |
| "rows": 121, | |
| "source": "smoltalk2:smoltalk-smollm3_everyday-conversations" | |
| }, | |
| { | |
| "max": 1024, | |
| "mean": 561.594733951672, | |
| "min": 34, | |
| "p50": 556, | |
| "p95": 981, | |
| "p99": 1016, | |
| "rows": 32776, | |
| "source": "smoltalk2:smoltalk-smollm3_systemchats-30k" | |
| }, | |
| { | |
| "max": 1023, | |
| "mean": 447.0511776679267, | |
| "min": 16, | |
| "p50": 423, | |
| "p95": 901, | |
| "p99": 991, | |
| "rows": 3439, | |
| "source": "oasst2" | |
| }, | |
| { | |
| "max": 916, | |
| "mean": 173.9987444309437, | |
| "min": 30, | |
| "p50": 159, | |
| "p95": 319, | |
| "p99": 428, | |
| "rows": 24690, | |
| "source": "soda" | |
| } | |
| ], | |
| "token_bound": 1024, | |
| "tokenizer": { | |
| "path": "/mnt/donto-data/alpha-corpora/tokenizers/hf-bpe-byte-12k-20260722/tokenizer.json", | |
| "vocab_size": 12288 | |
| } | |
| } | |