{ "schema_version": 1, "created_at": "2026-08-24T19:25:09+00:00", "seed": 20260825, "sampling": { "method": "deterministic SHA-256 bottom-k, exact duplicates excluded from selected sample", "requested_documents_per_corpus": 100000, "min_chars": 250, "max_chars": 20000, "min_words": 20 }, "tokenizers": { "new": "out/qwen35_2b_sft_lora_r64_grouped_identity_v1/merges/ckpt4749/merged", "base": "/mnt/raid1/qwen3.5/pipelines/uzbek_tokenizer/artifacts/base_checkpoints/qwen35_2b_base", "result_reuse_note": "The evaluated 2B tokenizer files are byte-identical to the evaluated 4B tokenizer files.", "new_tokenizer_sha256": "e4731e5df2c95dbfd98c45e08feae7c5fcd0588172778ac35c3703921f5529f9", "base_tokenizer_sha256": "fe000e3ed39ed12b8d2481d527d44f93c65d37e87645d2dcc80d1bf9d50d2927", "add_special_tokens": false, "raw_text_no_preprocessing": true }, "corpora": { "OSCAR Uzbek": { "domain_status": "held-out web source", "source": "xkas2001/uzbek-language-dataset, community-oscar-uzbek/all_metadata_text.txt", "sampling": { "records_scanned": 4762756, "valid_records": 623128, "sampled_records": 100000, "selected_duplicate_occurrences_skipped": 316611, "records_truncated_before_sampling": 67 }, "result": { "documents": 100000, "words": 7618770, "characters": 62308307, "new_tokens": 15469208, "base_tokens": 25628881, "new_tokens_per_word": 2.0304075329744826, "base_tokens_per_word": 3.363913203837365, "token_reduction": 0.3964150053995724, "token_reduction_95ci": [ 0.3956999048249437, 0.3971071790721872 ], "median_document_tokens_per_word": { "new": 1.9714285714285715, "base": 3.3536585365853657 }, "document_token_count_comparison": { "new_fewer_fraction": 0.99789, "equal_fraction": 0.00171, "new_more_fraction": 0.0004 }, "document_length_chars": { "min": 250, "median": 448, "p90": 1105, "p99": 2908, "max": 19999 }, "by_script": { "latin_dominant": { "documents": 99876, "words": 7609046, "characters": 62243858, "new_tokens": 15444043, "base_tokens": 25601074, "new_tokens_per_word": 2.029695049813078, "base_tokens_per_word": 3.3645576593964606, "token_reduction": 0.39674237885488706, "token_reduction_95ci": [ 0.3960664169063509, 0.3974315537014118 ], "median_document_tokens_per_word": { "new": 1.9714285714285715, "base": 3.3541666666666665 }, "document_token_count_comparison": { "new_fewer_fraction": 0.9980375665825624, "equal_fraction": 0.001571949217029116, "new_more_fraction": 0.00039048420040850655 } }, "cyrillic_dominant": { "documents": 121, "words": 8853, "characters": 61058, "new_tokens": 21987, "base_tokens": 24636, "new_tokens_per_word": 2.4835648932565233, "base_tokens_per_word": 2.782785496441884, "token_reduction": 0.10752557233317095, "token_reduction_95ci": [ 0.06903186700461168, 0.1489608189386225 ], "median_document_tokens_per_word": { "new": 2.220779220779221, "base": 2.5869565217391304 }, "document_token_count_comparison": { "new_fewer_fraction": 0.9008264462809917, "equal_fraction": 0.09917355371900827, "new_more_fraction": 0.0 } }, "other": { "documents": 3, "words": 871, "characters": 3391, "new_tokens": 3178, "base_tokens": 3171, "new_tokens_per_word": 3.6486796785304247, "base_tokens_per_word": 3.640642939150402, "token_reduction": -0.002207505518763808, "token_reduction_95ci": [ -0.06363636363636371, 0.0 ], "median_document_tokens_per_word": { "new": 3.7318295739348373, "base": 3.7318295739348373 }, "document_token_count_comparison": { "new_fewer_fraction": 0.0, "equal_fraction": 0.6666666666666666, "new_more_fraction": 0.3333333333333333 } } }, "by_document_length_quartile": { "q1": { "char_bounds": [ 250, 328 ], "documents": 25225, "words": 886299, "characters": 7229107, "new_tokens": 1742025, "base_tokens": 2981550, "new_tokens_per_word": 1.9655048691243022, "base_tokens_per_word": 3.3640453165353903, "token_reduction": 0.41573175026412434, "token_reduction_95ci": [ 0.41438530829534354, 0.4170515905402432 ], "median_document_tokens_per_word": { "new": 1.9142857142857144, "base": 3.3636363636363638 }, "document_token_count_comparison": { "new_fewer_fraction": 0.9958771060455897, "equal_fraction": 0.004083250743310208, "new_more_fraction": 3.9643211100099105e-05 } }, "q2": { "char_bounds": [ 329, 448 ], "documents": 24838, "words": 1159735, "characters": 9510849, "new_tokens": 2254196, "base_tokens": 3895455, "new_tokens_per_word": 1.943716452465434, "base_tokens_per_word": 3.358918201140778, "token_reduction": 0.42132664861999436, "token_reduction_95ci": [ 0.4200747806331761, 0.42257126807643025 ], "median_document_tokens_per_word": { "new": 1.9166666666666667, "base": 3.3617021276595747 }, "document_token_count_comparison": { "new_fewer_fraction": 0.9986311297205894, "equal_fraction": 0.001328609388839681, "new_more_fraction": 4.0260890570899426e-05 } }, "q3": { "char_bounds": [ 449, 694 ], "documents": 24973, "words": 1683343, "characters": 13783621, "new_tokens": 3372637, "base_tokens": 5654412, "new_tokens_per_word": 2.0035352272234475, "base_tokens_per_word": 3.359037344141984, "token_reduction": 0.4035388648722449, "token_reduction_95ci": [ 0.4023960313587086, 0.4046209067071377 ], "median_document_tokens_per_word": { "new": 1.9710144927536233, "base": 3.3466666666666667 }, "document_token_count_comparison": { "new_fewer_fraction": 0.9995194810395227, "equal_fraction": 0.0004004324670644296, "new_more_fraction": 8.008649341288591e-05 } }, "q4": { "char_bounds": [ 695, 19999 ], "documents": 24964, "words": 3889393, "characters": 31784730, "new_tokens": 8100350, "base_tokens": 13097464, "new_tokens_per_word": 2.0826771683910574, "base_tokens_per_word": 3.367482792302038, "token_reduction": 0.3815329440874966, "token_reduction_95ci": [ 0.38033518553908646, 0.38274511916670123 ], "median_document_tokens_per_word": { "new": 2.05603738317757, "base": 3.347826086956522 }, "document_token_count_comparison": { "new_fewer_fraction": 0.9975564813331197, "equal_fraction": 0.00100144207659029, "new_more_fraction": 0.0014420765902900176 } } } } }, "Uzbek legal corpus": { "domain_status": "held-out legal source/domain", "source": "sukhrobnurali/uzbek-legal-corpus-v1, articles", "sampling": { "records_scanned": 21021, "valid_records": 18832, "sampled_records": 18832, "selected_duplicate_occurrences_skipped": 0, "records_truncated_before_sampling": 3 }, "result": { "documents": 18832, "words": 2534566, "characters": 21314804, "new_tokens": 6018932, "base_tokens": 7529043, "new_tokens_per_word": 2.374738712663233, "base_tokens_per_word": 2.970545253112367, "token_reduction": 0.20057144048719078, "token_reduction_95ci": [ 0.19550471065059247, 0.20567097138760268 ], "median_document_tokens_per_word": { "new": 1.8397191231160697, "base": 3.3333333333333335 }, "document_token_count_comparison": { "new_fewer_fraction": 0.385089209855565, "equal_fraction": 0.614910790144435, "new_more_fraction": 0.0 }, "document_length_chars": { "min": 250, "median": 812, "p90": 2183, "p99": 5637, "max": 19997 }, "by_script": { "latin_dominant": { "documents": 6354, "words": 858053, "characters": 7499938, "new_tokens": 1410490, "base_tokens": 2916524, "new_tokens_per_word": 1.6438261972162558, "base_tokens_per_word": 3.3990021595402613, "token_reduction": 0.51637977263345, "token_reduction_95ci": [ 0.5147582025646525, 0.5179880323158793 ], "median_document_tokens_per_word": { "new": 1.6153846153846154, "base": 3.369890856442811 }, "document_token_count_comparison": { "new_fewer_fraction": 1.0, "equal_fraction": 0.0, "new_more_fraction": 0.0 } }, "cyrillic_dominant": { "documents": 12478, "words": 1676513, "characters": 13814866, "new_tokens": 4608442, "base_tokens": 4612519, "new_tokens_per_word": 2.74882568760278, "base_tokens_per_word": 2.7512575208185086, "token_reduction": 0.0008838987980320789, "token_reduction_95ci": [ 0.000797593938754379, 0.0009744198560997175 ], "median_document_tokens_per_word": { "new": 3.1314814814814813, "base": 3.1314814814814813 }, "document_token_count_comparison": { "new_fewer_fraction": 0.07196666132393012, "equal_fraction": 0.9280333386760699, "new_more_fraction": 0.0 } } }, "by_document_length_quartile": { "q1": { "char_bounds": [ 250, 506 ], "documents": 4715, "words": 213503, "characters": 1769357, "new_tokens": 505325, "base_tokens": 619444, "new_tokens_per_word": 2.366828569153595, "base_tokens_per_word": 2.901336280989026, "token_reduction": 0.1842281142443869, "token_reduction_95ci": [ 0.17673651196691142, 0.19222917798968833 ], "median_document_tokens_per_word": { "new": 1.868421052631579, "base": 3.2857142857142856 }, "document_token_count_comparison": { "new_fewer_fraction": 0.34612937433722163, "equal_fraction": 0.6538706256627783, "new_more_fraction": 0.0 } }, "q2": { "char_bounds": [ 507, 812 ], "documents": 4703, "words": 369537, "characters": 3066781, "new_tokens": 873369, "base_tokens": 1074262, "new_tokens_per_word": 2.3634142183326703, "base_tokens_per_word": 2.907048549942225, "token_reduction": 0.18700559081490364, "token_reduction_95ci": [ 0.17978162099648665, 0.19424970760537358 ], "median_document_tokens_per_word": { "new": 1.8421052631578947, "base": 3.3076923076923075 }, "document_token_count_comparison": { "new_fewer_fraction": 0.35721879651286415, "equal_fraction": 0.6427812034871359, "new_more_fraction": 0.0 } }, "q3": { "char_bounds": [ 813, 1347 ], "documents": 4711, "words": 594780, "characters": 4943320, "new_tokens": 1407482, "base_tokens": 1750853, "new_tokens_per_word": 2.366390934463163, "base_tokens_per_word": 2.9436985103735833, "token_reduction": 0.19611640725977564, "token_reduction_95ci": [ 0.18856405345722932, 0.20422906152284168 ], "median_document_tokens_per_word": { "new": 1.8333333333333333, "base": 3.3286713286713288 }, "document_token_count_comparison": { "new_fewer_fraction": 0.3922734026745914, "equal_fraction": 0.6077265973254086, "new_more_fraction": 0.0 } }, "q4": { "char_bounds": [ 1348, 19997 ], "documents": 4703, "words": 1356746, "characters": 11535346, "new_tokens": 3232756, "base_tokens": 4084484, "new_tokens_per_word": 2.3827274965247733, "base_tokens_per_word": 3.0105001230886255, "token_reduction": 0.2085276867286051, "token_reduction_95ci": [ 0.1998185981685246, 0.21714855506411254 ], "median_document_tokens_per_word": { "new": 1.819905213270142, "base": 3.3981481481481484 }, "document_token_count_comparison": { "new_fewer_fraction": 0.4448224537529237, "equal_fraction": 0.5551775462470764, "new_more_fraction": 0.0 } } } } }, "uz-crawl control": { "domain_status": "training-source control", "source": "tahrirchi/uz-crawl local training source", "sampling": { "records_scanned": 1618035, "valid_records": 1441908, "sampled_records": 100000, "selected_duplicate_occurrences_skipped": 174, "records_truncated_before_sampling": 9216 }, "result": { "documents": 100000, "words": 20825680, "characters": 174743319, "new_tokens": 48327821, "base_tokens": 69191245, "new_tokens_per_word": 2.3205878991706395, "base_tokens_per_word": 3.3224002769657464, "token_reduction": 0.3015327155914018, "token_reduction_95ci": [ 0.3001693372220501, 0.302962741125678 ], "median_document_tokens_per_word": { "new": 2.0866859344894024, "base": 3.2613636363636362 }, "document_token_count_comparison": { "new_fewer_fraction": 0.86481, "equal_fraction": 0.13306, "new_more_fraction": 0.00213 }, "document_length_chars": { "min": 250, "median": 1036, "p90": 3408, "p99": 14367, "max": 19999 }, "by_script": { "latin_dominant": { "documents": 82818, "words": 17899459, "characters": 152194135, "new_tokens": 37942391, "base_tokens": 58788459, "new_tokens_per_word": 2.119750714253431, "base_tokens_per_word": 3.284370717573084, "token_reduction": 0.3545945642154015, "token_reduction_95ci": [ 0.35375779400897717, 0.35539015324512163 ], "median_document_tokens_per_word": { "new": 2.0297619047619047, "base": 3.2142857142857144 }, "document_token_count_comparison": { "new_fewer_fraction": 1.0, "equal_fraction": 0.0, "new_more_fraction": 0.0 } }, "cyrillic_dominant": { "documents": 17182, "words": 2926221, "characters": 22549184, "new_tokens": 10385430, "base_tokens": 10402786, "new_tokens_per_word": 3.5490928402195188, "base_tokens_per_word": 3.5550240395376838, "token_reduction": 0.0016683992153639915, "token_reduction_95ci": [ 0.0013899888640842822, 0.001964975103579841 ], "median_document_tokens_per_word": { "new": 3.542372881355932, "base": 3.5457593062605754 }, "document_token_count_comparison": { "new_fewer_fraction": 0.21318822023047376, "equal_fraction": 0.7744150855546502, "new_more_fraction": 0.012396694214876033 } } }, "by_document_length_quartile": { "q1": { "char_bounds": [ 250, 642 ], "documents": 25014, "words": 1443765, "characters": 11560305, "new_tokens": 3580625, "base_tokens": 4717032, "new_tokens_per_word": 2.4800608132209883, "base_tokens_per_word": 3.2671743670195634, "token_reduction": 0.2409156859652426, "token_reduction_95ci": [ 0.2388878125954489, 0.243056097563355 ], "median_document_tokens_per_word": { "new": 2.2058823529411766, "base": 3.2567567567567566 }, "document_token_count_comparison": { "new_fewer_fraction": 0.7540577276725035, "equal_fraction": 0.24566242903973776, "new_more_fraction": 0.00027984328775885504 } }, "q2": { "char_bounds": [ 643, 1036 ], "documents": 25032, "words": 2534284, "characters": 20698884, "new_tokens": 5852869, "base_tokens": 8233439, "new_tokens_per_word": 2.3094763649220056, "base_tokens_per_word": 3.248822547117845, "token_reduction": 0.2891343459276251, "token_reduction_95ci": [ 0.2871033465654421, 0.2910416333852472 ], "median_document_tokens_per_word": { "new": 2.0697674418604652, "base": 3.2268041237113403 }, "document_token_count_comparison": { "new_fewer_fraction": 0.8623761585170981, "equal_fraction": 0.13690476190476192, "new_more_fraction": 0.0007190795781399808 } }, "q3": { "char_bounds": [ 1037, 1827 ], "documents": 24959, "words": 4090354, "characters": 34187499, "new_tokens": 9144176, "base_tokens": 13420837, "new_tokens_per_word": 2.235546361024009, "base_tokens_per_word": 3.281094252477903, "token_reduction": 0.31865829232558296, "token_reduction_95ci": [ 0.3168107024780933, 0.3205574932440705 ], "median_document_tokens_per_word": { "new": 2.051851851851852, "base": 3.261904761904762 }, "document_token_count_comparison": { "new_fewer_fraction": 0.9184662847069194, "equal_fraction": 0.08033174406025882, "new_more_fraction": 0.0012019712328218278 } }, "q4": { "char_bounds": [ 1828, 19999 ], "documents": 24995, "words": 12757277, "characters": 108296631, "new_tokens": 29750151, "base_tokens": 42819937, "new_tokens_per_word": 2.3320141908026297, "base_tokens_per_word": 3.3565107193329737, "token_reduction": 0.30522665178138864, "token_reduction_95ci": [ 0.3030310155219502, 0.30739078599543024 ], "median_document_tokens_per_word": { "new": 2.07344398340249, "base": 3.2913907284768213 }, "document_token_count_comparison": { "new_fewer_fraction": 0.924504900980196, "equal_fraction": 0.0691738347669534, "new_more_fraction": 0.00632126425285057 } } } } } } }