Clean tokenizer swap migration

This commit is contained in:
Codex
2026-06-18 10:10:57 +00:00
commit 5d1e9c4bc3
37 changed files with 9574 additions and 0 deletions
@@ -0,0 +1,118 @@
{
"tokenizer": "/ssd/yi/tokenizer_swap_cepe/models/Qwen3-0.6B-DSV4-tokenizer-remap-v2",
"budgets": {
"english_web": 1250000000,
"english_edu": 1000000000,
"chinese_clean": 1250000000,
"code": 750000000,
"math": 500000000,
"science": 150000000,
"qa_as_text": 100000000
},
"seq_len_for_later_packing": 8192,
"stream_sources": {
"english_web": [
{
"kind": "hf",
"name": "HuggingFaceFW/fineweb",
"config": "CC-MAIN-2025-26",
"split": "train",
"max_rows": 0
},
{
"kind": "hf",
"name": "HuggingFaceFW/fineweb",
"config": "CC-MAIN-2025-21",
"split": "train",
"max_rows": 0
}
],
"english_edu": [
{
"kind": "hf",
"name": "HuggingFaceFW/fineweb-edu",
"config": null,
"split": "train",
"max_rows": 0
}
],
"chinese_clean": [
{
"kind": "hf",
"name": "BAAI/CCI3-HQ",
"config": null,
"split": "train",
"max_rows": 0
},
{
"kind": "hf",
"name": "Skywork/SkyPile-150B",
"config": null,
"split": "train",
"max_rows": 0
}
],
"code": [
{
"kind": "hf",
"name": "bigcode/starcoderdata",
"config": null,
"split": "train",
"max_rows": 0
},
{
"kind": "hf",
"name": "codeparrot/github-code",
"config": null,
"split": "train",
"max_rows": 0
}
],
"math": [
{
"kind": "hf",
"name": "open-web-math/open-web-math",
"config": null,
"split": "train",
"max_rows": 0
},
{
"kind": "hf",
"name": "GAIR/MathPile",
"config": null,
"split": "train",
"max_rows": 0
}
]
},
"local_globs": {
"science": [
"data/offline_text_only_reasoning_sources_20260611/science_reasoning__*.jsonl",
"data/offline_text_only_reasoning_sources_20260611/logic__*.jsonl"
],
"qa_as_text": [
"data/training_mix_v4_train1m_test2p8k_noupsample_nobbh_20260611/train_1m.jsonl",
"data/open_recovery_sft_mix_alt_sources_1m_parquet_20260607/normalized.jsonl"
]
},
"local_parquet_globs": {
"english_web": [
"data/raw_parquets/fineweb_2025/*.parquet"
],
"english_edu": [
"data/raw_parquets/fineweb_edu/*.parquet"
],
"code": [
"data/raw_parquets/starcoder/python/*.parquet",
"data/raw_parquets/starcoder/javascript/*.parquet",
"data/raw_parquets/starcoder/typescript/*.parquet",
"data/raw_parquets/starcoder/java/*.parquet",
"data/raw_parquets/starcoder/cpp/*.parquet",
"data/raw_parquets/starcoder/go/*.parquet",
"data/raw_parquets/starcoder/rust/*.parquet",
"data/raw_parquets/starcoder/shell/*.parquet"
]
},
"min_tokens": 128,
"max_doc_tokens": 32768
}
@@ -0,0 +1,215 @@
{
"scale": 5.0,
"budgets": {
"english_web": 1250000000,
"english_edu": 1000000000,
"chinese_clean": 1250000000,
"code": 750000000,
"math": 500000000,
"science": 150000000,
"qa_as_text": 100000000
},
"tokens_by_category": {
"english_web": 1250000445,
"english_edu": 1000000462,
"code": 750001624,
"math": 96992014,
"science": 30016910,
"qa_as_text": 100000055
},
"docs_by_category": {
"english_web": 1571857,
"english_edu": 973081,
"code": 589463,
"math": 51576,
"science": 48872,
"qa_as_text": 244246
},
"tokens_by_source": {
"data/raw_parquets/fineweb_2025/CC-MAIN-2025-26_000_00000.parquet": 684777289,
"data/raw_parquets/fineweb_edu/CC-MAIN-2024-10_000_00000.parquet": 627654914,
"data/raw_parquets/fineweb_2025/CC-MAIN-2025-26_001_00000.parquet": 565223156,
"data/raw_parquets/fineweb_edu/CC-MAIN-2024-10_000_00001.parquet": 372345548,
"data/raw_parquets/starcoder/python/train-00000-of-00059.parquet": 238778818,
"data/raw_parquets/starcoder/python/train-00002-of-00059.parquet": 233459009,
"data/raw_parquets/starcoder/python/train-00001-of-00059.parquet": 233210510,
"/ssd/yi/tokenizer_swap_cepe/data/training_mix_v4_train1m_test2p8k_noupsample_nobbh_20260611/train_1m.jsonl": 100000055,
"open-web-math/open-web-math": 96992014,
"data/raw_parquets/starcoder/python/train-00003-of-00059.parquet": 44553287,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__openlifescienceai_medmcqa__train.jsonl": 10027949,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_proofwriter__train.jsonl": 6138410,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__derek-thomas_ScienceQA__train.jsonl": 3119670,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_proofwriter__test.jsonl": 1837710,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__GBaker_MedQA-USMLE-4-options__train.jsonl": 1572096,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__sciq__train.jsonl": 1182676,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__derek-thomas_ScienceQA__test.jsonl": 1033827,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__derek-thomas_ScienceQA__validation.jsonl": 1032383,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_proofwriter__validation.jsonl": 895384,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_qasc__train.jsonl": 688074,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__openlifescienceai_medmcqa__test.jsonl": 307416,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_folio__train.jsonl": 261306,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__openlifescienceai_medmcqa__validation.jsonl": 242852,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_openbookqa__main__train.jsonl": 221520,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__GBaker_MedQA-USMLE-4-options__test.jsonl": 203198,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__temporal_sequences__train.jsonl": 141867,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_ai2_arc__ARC-Easy__test.jsonl": 139093,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_ai2_arc__ARC-Easy__train.jsonl": 130752,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__logical_deduction__train.jsonl": 118299,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__sciq__test.jsonl": 102393,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__sciq__validation.jsonl": 99297,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_ai2_arc__ARC-Challenge__test.jsonl": 79458,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_qasc__validation.jsonl": 79086,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_ai2_arc__ARC-Challenge__train.jsonl": 74207,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_folio__validation.jsonl": 53607,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__temporal_sequences__validation.jsonl": 35418,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_ai2_arc__ARC-Easy__validation.jsonl": 33149,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__logical_deduction__validation.jsonl": 31008,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_openbookqa__main__validation.jsonl": 23331,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_openbookqa__main__test.jsonl": 22745,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__qiaojin_PubMedQA__pqa_labeled__train.jsonl": 22169,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/science_reasoning__allenai_ai2_arc__ARC-Challenge__validation.jsonl": 19963,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__disambiguation_qa__train.jsonl": 15771,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__date_understanding__train.jsonl": 14547,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__disambiguation_qa__validation.jsonl": 3843,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__date_understanding__validation.jsonl": 3629,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__logical_args__validation.jsonl": 3136,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__logical_args__train.jsonl": 2729,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__analytic_entailment__train.jsonl": 2277,
"/ssd/yi/tokenizer_swap_cepe/data/offline_text_only_reasoning_sources_20260611/logic__tasksource_bigbench__analytic_entailment__validation.jsonl": 665
},
"rejected": {
"english_web": {
"too_short": 168039,
"too_long": 179
},
"english_edu": {
"too_short": 18375,
"too_long": 221
},
"code": {
"too_short": 106203,
"too_long": 816
},
"math": {
"too_short": 3669,
"too_long": 152
},
"science": {
"pack_too_short": 5591
},
"qa_as_text": {
"too_short": 108331
}
},
"sources": [
{
"category": "english_web",
"kind": "local_parquet",
"source": "data/raw_parquets/fineweb_2025/CC-MAIN-2025-26_000_00000.parquet",
"rows_seen": 961000,
"docs_written": 864351,
"tokens": 684777289,
"error": ""
},
{
"category": "english_web",
"kind": "local_parquet",
"source": "data/raw_parquets/fineweb_2025/CC-MAIN-2025-26_001_00000.parquet",
"rows_seen": 779076,
"docs_written": 707506,
"tokens": 565223156,
"error": ""
},
{
"category": "english_edu",
"kind": "local_parquet",
"source": "data/raw_parquets/fineweb_edu/CC-MAIN-2024-10_000_00000.parquet",
"rows_seen": 621759,
"docs_written": 610163,
"tokens": 627654914,
"error": ""
},
{
"category": "english_edu",
"kind": "local_parquet",
"source": "data/raw_parquets/fineweb_edu/CC-MAIN-2024-10_000_00001.parquet",
"rows_seen": 369919,
"docs_written": 362918,
"tokens": 372345548,
"error": ""
},
{
"category": "chinese_clean",
"kind": "hf_stream",
"source": "BAAI/CCI3-HQ",
"rows_seen": 0,
"docs_written": 0,
"tokens": 0,
"error": "DatasetNotFoundError(\"Dataset 'BAAI/CCI3-HQ' is a gated dataset on the Hub. You must be authenticated to access it.\")"
},
{
"category": "chinese_clean",
"kind": "hf_stream",
"source": "Skywork/SkyPile-150B",
"rows_seen": 0,
"docs_written": 0,
"tokens": 0,
"error": "RuntimeError('Cannot send a request, as the client has been closed.')"
},
{
"category": "code",
"kind": "local_parquet",
"source": "data/raw_parquets/starcoder/python/train-00000-of-00059.parquet",
"rows_seen": 218079,
"docs_written": 184958,
"tokens": 238778818,
"error": ""
},
{
"category": "code",
"kind": "local_parquet",
"source": "data/raw_parquets/starcoder/python/train-00001-of-00059.parquet",
"rows_seen": 218079,
"docs_written": 184495,
"tokens": 233210510,
"error": ""
},
{
"category": "code",
"kind": "local_parquet",
"source": "data/raw_parquets/starcoder/python/train-00002-of-00059.parquet",
"rows_seen": 218079,
"docs_written": 184331,
"tokens": 233459009,
"error": ""
},
{
"category": "code",
"kind": "local_parquet",
"source": "data/raw_parquets/starcoder/python/train-00003-of-00059.parquet",
"rows_seen": 42246,
"docs_written": 35679,
"tokens": 44553287,
"error": ""
},
{
"category": "math",
"kind": "hf_stream",
"source": "open-web-math/open-web-math",
"rows_seen": 55397,
"docs_written": 51576,
"tokens": 96992014,
"error": "ProxyError('503 Service Unavailable')"
},
{
"category": "math",
"kind": "hf_stream",
"source": "GAIR/MathPile",
"rows_seen": 0,
"docs_written": 0,
"tokens": 0,
"error": "DatasetNotFoundError(\"Dataset 'GAIR/MathPile' is a gated dataset on the Hub. You must be authenticated to access it.\")"
}
],
"elapsed_sec": 10098.068085193634
}
@@ -0,0 +1,393 @@
{
"docs_seen": 960549,
"train_blocks": 121041,
"eval_blocks": 1024,
"train_tokens": 991567872,
"eval_tokens": 8388608,
"source_docs": {
"english_web": 318271,
"english_edu": 194585,
"chinese_clean": 181655,
"code": 116242,
"math": 53125,
"science": 47973,
"qa_as_text": 48698
},
"source_tokens": {
"english_web": 249999374,
"english_edu": 199998420,
"chinese_clean": 249999618,
"code": 149999958,
"math": 99987860,
"science": 29999428,
"qa_as_text": 19999497
},
"train_blocks_by_category": {
"english_web": 30261,
"english_edu": 24208,
"chinese_clean": 30261,
"code": 18156,
"math": 12103,
"science": 3631,
"qa_as_text": 2421
},
"eval_blocks_by_category": {
"english_web": 256,
"english_edu": 205,
"chinese_clean": 256,
"code": 154,
"math": 102,
"science": 31,
"qa_as_text": 20
},
"start_time": 1781429820.1093097,
"leftover_tokens_by_category": {
"english_web": 4110,
"english_edu": 7124,
"chinese_clean": 4354,
"code": 4438,
"math": 4500,
"science": 324,
"qa_as_text": 2825
},
"tokenizer": "/ssd/yi/tokenizer_swap_cepe/models/Qwen3-0.6B-DSV4-tokenizer-remap-v2",
"seq_len": 8192,
"seed": 42,
"budgets": {
"english_web": 250000000,
"english_edu": 200000000,
"chinese_clean": 250000000,
"code": 150000000,
"math": 100000000,
"science": 30000000,
"qa_as_text": 20000000
},
"sources": {
"english_web": "data/cpt_docmix_parquet_sources_8192_20260613/documents/english_web.jsonl.gz",
"english_edu": "data/cpt_docmix_parquet_sources_8192_20260613/documents/english_edu.jsonl.gz",
"chinese_clean": "data/cpt_docmix_cci3_science_fixed_8192_20260614/documents/chinese_clean.jsonl.gz",
"code": "data/cpt_docmix_parquet_sources_8192_20260613/documents/code.jsonl.gz",
"math": "data/cpt_docmix_available_sources_8192_20260613/documents/math.jsonl.gz",
"science": "data/cpt_docmix_cci3_science_fixed_8192_20260614/documents/science.jsonl.gz",
"qa_as_text": "data/cpt_docmix_available_sources_8192_20260613/documents/qa_as_text.jsonl.gz"
},
"eval_quota_blocks": {
"english_web": 256,
"english_edu": 205,
"chinese_clean": 256,
"code": 154,
"math": 102,
"science": 31,
"qa_as_text": 20
},
"train_shards": [
{
"path": "train_00000.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00001.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00002.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00003.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00004.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00005.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00006.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00007.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00008.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00009.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00010.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00011.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00012.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00013.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00014.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00015.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00016.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00017.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00018.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00019.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00020.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00021.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00022.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00023.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00024.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00025.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00026.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00027.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00028.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00029.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00030.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00031.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00032.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00033.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00034.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00035.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00036.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00037.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00038.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00039.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00040.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00041.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00042.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00043.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00044.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00045.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00046.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00047.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00048.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00049.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00050.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00051.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00052.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00053.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00054.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00055.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00056.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00057.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00058.npy",
"blocks": 2048,
"tokens": 16777216
},
{
"path": "train_00059.npy",
"blocks": 209,
"tokens": 1712128
}
],
"eval_shards": [
{
"path": "eval_00000.npy",
"blocks": 1024,
"tokens": 8388608
}
],
"elapsed_sec": 2387.9453027248383
}
File diff suppressed because it is too large Load Diff
@@ -0,0 +1,309 @@
{
"args": {
"out": "data/training_mix_v4_train1m_test2p8k_noupsample_nobbh_20260611",
"tokenizer": "/ssd/yi/tokenizer_swap_cepe/models/Qwen3-0.6B-DSV4-tokenizer-remap-v2",
"train_total": 1000000,
"test_per_group": 400,
"seed": 20260611,
"hf_endpoint": "https://hf-mirror.com",
"use_hf": true,
"allow_shortfall": true,
"upsample_train_shortfall": false,
"min_prompt_tokens": 4,
"min_answer_tokens": 8,
"max_prompt_tokens": 1024,
"max_answer_tokens": 1024,
"trust_metadata_lengths": true,
"max_seen_per_source": 500000,
"stop_empty_source_early": false
},
"train_ratios": {
"chinese_exam": 0,
"chinese_dialogue": 35,
"code": 30,
"math": 20,
"logic": 5,
"science_reasoning": 5,
"english_dialogue": 5
},
"test_quotas": {
"chinese_exam": 400,
"chinese_dialogue": 400,
"code": 400,
"math": 400,
"logic": 400,
"science_reasoning": 400,
"english_dialogue": 400
},
"loaders": {
"test_hf": {
"test:chinese_exam:ceval/ceval-exam": {
"seen": 728,
"accepted": 400,
"too_short": 328
},
"test:chinese_dialogue:m-a-p/COIG-CQIA": {
"seen": 414,
"accepted": 400,
"too_long": 14
},
"test:code:openai/openai_humaneval": {
"seen": 164,
"accepted": 154,
"too_short": 8,
"too_long": 2
},
"test:code:google-research-datasets/mbpp": {
"seen": 246,
"accepted": 246
},
"test:math:gsm8k": {
"seen": 400,
"accepted": 400
},
"test:logic:cais/mmlu": {
"seen": 331,
"accepted": 164,
"too_short": 167
},
"test:logic:lighteval/bbh": {
"load_error:test:logical_deduction_three_objects": 1,
"error:ValueError(\"Bad split: test. Available splits: ['train']\")": 1,
"seen": 296,
"accepted": 236,
"too_short": 60
},
"test:science_reasoning:Idavidrein/gpqa": {
"seen": 448,
"too_short": 195,
"accepted": 252,
"too_long": 1
},
"test:science_reasoning:allenai/ai2_arc": {
"seen": 287,
"accepted": 148,
"too_short": 139
},
"test:english_dialogue:HuggingFaceH4/ultrachat_200k": {
"seen": 420,
"too_long": 20,
"accepted": 400
}
},
"train_local": {
"data/open_recovery_sft_mix_alt_sources_1m_parquet_20260607/normalized.jsonl": {
"accepted": 1051916,
"heldout_excluded": 411,
"duplicate": 30
},
"data/open_recovery_sft_mix_100k_4_3_2_1_20260604/normalized.jsonl": {
"duplicate": 88687,
"accepted": 9020,
"heldout_excluded": 401
},
"data/modelscope_alt_sources_20260607/CodeAlpaca-20k.jsonl": {
"duplicate": 18820,
"too_short": 1193,
"no_messages": 6,
"too_long": 3
},
"data/modelscope_alt_sources_20260607/alpaca-gpt4-data-zh_train.csv": {
"duplicate": 46476,
"too_short": 2342
}
},
"train_hf": {
"train:chinese_dialogue:m-a-p/COIG-CQIA": {
"seen": 10116,
"duplicate": 7211,
"too_short": 1138,
"too_long": 1354,
"no_messages": 1,
"accepted": 1,
"heldout_excluded": 411
},
"train:chinese_dialogue:BelleGroup/train_0.5M_CN": {
"seen": 330837,
"too_short": 34263,
"duplicate": 2188,
"accepted": 294334,
"too_long": 32,
"no_messages": 20
},
"train:code:ise-uiuc/Magicoder-OSS-Instruct-75K": {
"seen": 75197,
"duplicate": 69998,
"bad_code_fence": 34,
"too_long": 48,
"accepted": 5117
},
"train:code:bigcode/self-oss-instruct-sc2-exec-filter-50k": {
"seen": 50661,
"duplicate": 31578,
"accepted": 19076,
"too_long": 6,
"bad_code_fence": 1
},
"train:code:HuggingFaceTB/smoltalk": {
"seen": 131271,
"duplicate": 78743,
"too_long": 1498,
"bad_code_fence": 1,
"accepted": 51029
},
"train:code:nvidia/OpenCodeInstruct": {
"seen": 43455,
"duplicate": 6678,
"too_long": 39,
"accepted": 36738
},
"train:logic:tasksource/bigbench": {
"seen": 8291,
"too_short": 5767,
"accepted": 2338,
"heldout_excluded": 186
},
"train:logic:tau/commonsense_qa": {
"seen": 10962,
"too_short": 10961,
"accepted": 1
},
"train:logic:metaeval/reclor": {
"seen": 5138,
"accepted": 5117,
"too_short": 21
},
"train:science_reasoning:allenai/ai2_arc": {
"seen": 1418,
"too_short": 739,
"accepted": 679
},
"train:science_reasoning:allenai/qasc": {
"iter_error:train:None": 1,
"error:ProxyError('503 Service Unavailable')": 2,
"iter_error:validation:None": 1
},
"train:science_reasoning:allenai/openbookqa": {
"iter_error:train:main": 1,
"error:ProxyError('503 Service Unavailable')": 4,
"iter_error:validation:main": 1,
"iter_error:train:additional": 1,
"iter_error:validation:additional": 1
},
"train:science_reasoning:sciq": {
"seen": 12679,
"accepted": 11370,
"too_short": 1309
},
"train:science_reasoning:qiaojin/PubMedQA": {
"seen": 1000,
"accepted": 1000
}
}
},
"result": {
"failed": false,
"test_total": 2800,
"train_total": 921360,
"test_counts": {
"science_reasoning": 400,
"logic": 400,
"code": 400,
"chinese_exam": 400,
"math": 400,
"chinese_dialogue": 400,
"english_dialogue": 400
},
"train_counts": {
"chinese_dialogue": 350000,
"code": 300000,
"english_dialogue": 50000,
"math": 200000,
"science_reasoning": 13904,
"logic": 7456
},
"test_shortfall": {},
"train_shortfall": {
"logic": 42544,
"science_reasoning": 36096
},
"train_upsampled": {},
"train_quotas": {
"chinese_exam": 0,
"chinese_dialogue": 350000,
"code": 300000,
"math": 200000,
"logic": 50000,
"science_reasoning": 50000,
"english_dialogue": 50000
},
"train_source_top": {
"BelleGroup/train_0.5M_CN": 296334,
"nvidia/OpenMathInstruct-2": 89260,
"TIGER-Lab/MathInstruct": 85173,
"ise-uiuc/Magicoder-OSS-Instruct-75K": 75115,
"bigcode/self-oss-instruct-sc2-exec-filter-50k": 66632,
"HuggingFaceTB/smoltalk:apigen-80k": 51029,
"AI-ModelScope/alpaca-gpt4-data-zh:file": 46476,
"nvidia/OpenCodeInstruct": 43404,
"AI-ModelScope/smoltalk:self-oss-instruct-file": 25000,
"AI-ModelScope/smoltalk:apigen-80k-file": 20000,
"AI-ModelScope/CodeAlpaca-20k:file": 18820,
"AI-ModelScope/smoltalk:numina-cot-100k-file": 17080,
"HuggingFaceTB/smoltalk:all": 15260,
"HuggingFaceH4/ultrachat_200k": 15238,
"allenai/tulu-3-sft-mixture": 15198,
"sciq": 11370,
"AI-ModelScope/smoltalk:metamathqa-50k-file": 8487,
"metaeval/reclor": 5117,
"m-a-p/COIG-CQIA:zhihu": 4978,
"AI-ModelScope/smoltalk:openhermes-100k": 4304,
"m-a-p/COIG-CQIA:coig_pc": 1877,
"qiaojin/PubMedQA:pqa_labeled": 1000,
"allenai/ai2_arc:ARC-Easy": 855,
"tasksource/bigbench:logical_deduction": 812,
"tasksource/bigbench:temporal_sequences": 800,
"allenai/ai2_arc:ARC-Challenge": 679,
"tasksource/bigbench:social_iqa": 343,
"m-a-p/COIG-CQIA:wikihow": 335,
"tasksource/bigbench:date_understanding": 296,
"tasksource/bigbench:disambiguation_qa": 71,
"tasksource/bigbench:logical_args": 16,
"tau/commonsense_qa": 1
},
"test_source_top": {
"gsm8k:main": 400,
"m-a-p/COIG-CQIA:zhihu": 400,
"HuggingFaceH4/ultrachat_200k": 400,
"Idavidrein/gpqa": 252,
"google-research-datasets/mbpp": 246,
"lighteval/bbh:logical_deduction_three_objects": 236,
"openai/openai_humaneval": 154,
"allenai/ai2_arc:ARC-Challenge": 148,
"cais/mmlu:formal_logic": 98,
"cais/mmlu:logical_fallacies": 66,
"ceval/ceval-exam:civil_servant": 38,
"ceval/ceval-exam:college_economics": 36,
"ceval/ceval-exam:accountant": 31,
"ceval/ceval-exam:college_programming": 23,
"ceval/ceval-exam:fire_engineer": 22,
"ceval/ceval-exam:advanced_mathematics": 22,
"ceval/ceval-exam:high_school_chinese": 21,
"ceval/ceval-exam:high_school_biology": 19,
"ceval/ceval-exam:college_chemistry": 18,
"ceval/ceval-exam:college_physics": 18,
"ceval/ceval-exam:high_school_chemistry": 17,
"ceval/ceval-exam:environmental_impact_assessment_engineer": 16,
"ceval/ceval-exam:business_administration": 15,
"ceval/ceval-exam:discrete_mathematics": 14,
"ceval/ceval-exam:education_science": 13,
"ceval/ceval-exam:clinical_medicine": 13,
"ceval/ceval-exam:electrical_engineer": 12,
"ceval/ceval-exam:computer_network": 11,
"ceval/ceval-exam:art_studies": 11,
"ceval/ceval-exam:computer_architecture": 11,
"ceval/ceval-exam:chinese_language_and_literature": 10,
"ceval/ceval-exam:basic_medicine": 9
}
}
}
@@ -0,0 +1,164 @@
{
"tokenizer": "/ssd/yi/tokenizer_swap_cepe/models/dsv4_chat_full_sft_remap_v2_alt1m_5epoch_bsz8_accum16_20260610",
"encoding_dir": "/ssd/yi/tokenizer_swap_cepe/external/deepseek_v4_encoding",
"cutoff_len": 2048,
"eos_token": "<end▁of▁sentence>",
"eos_token_id": 1,
"splits": {
"train": {
"split": "train",
"source": "/ssd/yi/tokenizer_swap_cepe/data/training_mix_v4_train1m_test2p8k_noupsample_nobbh_20260611/train_1m.jsonl",
"output": "/ssd/yi/tokenizer_swap_cepe/data/dsv4_chat_tokenized_v4_noupsample_nobbh_921k_20260611/train_dsv4_chat_tokenized.jsonl.gz",
"cutoff_len": 2048,
"rows_seen": 921360,
"rows_written": 921360,
"skipped_no_messages": 0,
"truncated": 0,
"eos_in_labels": 921360,
"prefix_mismatch": 0,
"capability_counts": {
"chinese_dialogue": 350000,
"code": 300000,
"math": 200000,
"english_dialogue": 50000,
"science_reasoning": 13904,
"logic": 7456
},
"prompt_tokens": {
"p50": 65,
"p90": 461,
"p95": 698,
"p99": 951,
"max": 1028
},
"response_tokens": {
"p50": 101,
"p90": 340,
"p95": 457,
"p99": 748,
"max": 1025
},
"total_tokens": {
"p50": 223,
"p90": 699,
"p95": 889,
"p99": 1165,
"max": 1957
},
"truncated_rate": 0.0,
"eos_label_rate": 1.0,
"source_counts_top50": {
"BelleGroup/train_0.5M_CN": 296334,
"nvidia/OpenMathInstruct-2": 89260,
"TIGER-Lab/MathInstruct": 85173,
"ise-uiuc/Magicoder-OSS-Instruct-75K": 75115,
"bigcode/self-oss-instruct-sc2-exec-filter-50k": 66632,
"HuggingFaceTB/smoltalk:apigen-80k": 51029,
"AI-ModelScope/alpaca-gpt4-data-zh:file": 46476,
"nvidia/OpenCodeInstruct": 43404,
"AI-ModelScope/smoltalk:self-oss-instruct-file": 25000,
"AI-ModelScope/smoltalk:apigen-80k-file": 20000,
"AI-ModelScope/CodeAlpaca-20k:file": 18820,
"AI-ModelScope/smoltalk:numina-cot-100k-file": 17080,
"HuggingFaceTB/smoltalk:all": 15260,
"HuggingFaceH4/ultrachat_200k": 15238,
"allenai/tulu-3-sft-mixture": 15198,
"sciq": 11370,
"AI-ModelScope/smoltalk:metamathqa-50k-file": 8487,
"metaeval/reclor": 5117,
"m-a-p/COIG-CQIA:zhihu": 4978,
"AI-ModelScope/smoltalk:openhermes-100k": 4304,
"m-a-p/COIG-CQIA:coig_pc": 1877,
"qiaojin/PubMedQA:pqa_labeled": 1000,
"allenai/ai2_arc:ARC-Easy": 855,
"tasksource/bigbench:logical_deduction": 812,
"tasksource/bigbench:temporal_sequences": 800,
"allenai/ai2_arc:ARC-Challenge": 679,
"tasksource/bigbench:social_iqa": 343,
"m-a-p/COIG-CQIA:wikihow": 335,
"tasksource/bigbench:date_understanding": 296,
"tasksource/bigbench:disambiguation_qa": 71,
"tasksource/bigbench:logical_args": 16,
"tau/commonsense_qa": 1
}
},
"validation": {
"split": "validation",
"source": "/ssd/yi/tokenizer_swap_cepe/data/training_mix_v4_train1m_test2p8k_noupsample_nobbh_20260611/heldout_2p8k.jsonl",
"output": "/ssd/yi/tokenizer_swap_cepe/data/dsv4_chat_tokenized_v4_noupsample_nobbh_921k_20260611/validation_dsv4_chat_tokenized.jsonl.gz",
"cutoff_len": 2048,
"rows_seen": 2800,
"rows_written": 2800,
"skipped_no_messages": 0,
"truncated": 0,
"eos_in_labels": 2800,
"prefix_mismatch": 0,
"capability_counts": {
"science_reasoning": 400,
"logic": 400,
"code": 400,
"chinese_exam": 400,
"math": 400,
"chinese_dialogue": 400,
"english_dialogue": 400
},
"prompt_tokens": {
"p50": 85,
"p90": 238,
"p95": 346,
"p99": 687,
"max": 1020
},
"response_tokens": {
"p50": 53,
"p90": 416,
"p95": 547,
"p99": 837,
"max": 1019
},
"total_tokens": {
"p50": 177,
"p90": 543,
"p95": 688,
"p99": 981,
"max": 1162
},
"truncated_rate": 0.0,
"eos_label_rate": 1.0,
"source_counts_top50": {
"gsm8k:main": 400,
"m-a-p/COIG-CQIA:zhihu": 400,
"HuggingFaceH4/ultrachat_200k": 400,
"Idavidrein/gpqa": 252,
"google-research-datasets/mbpp": 246,
"lighteval/bbh:logical_deduction_three_objects": 236,
"openai/openai_humaneval": 154,
"allenai/ai2_arc:ARC-Challenge": 148,
"cais/mmlu:formal_logic": 98,
"cais/mmlu:logical_fallacies": 66,
"ceval/ceval-exam:civil_servant": 38,
"ceval/ceval-exam:college_economics": 36,
"ceval/ceval-exam:accountant": 31,
"ceval/ceval-exam:college_programming": 23,
"ceval/ceval-exam:fire_engineer": 22,
"ceval/ceval-exam:advanced_mathematics": 22,
"ceval/ceval-exam:high_school_chinese": 21,
"ceval/ceval-exam:high_school_biology": 19,
"ceval/ceval-exam:college_chemistry": 18,
"ceval/ceval-exam:college_physics": 18,
"ceval/ceval-exam:high_school_chemistry": 17,
"ceval/ceval-exam:environmental_impact_assessment_engineer": 16,
"ceval/ceval-exam:business_administration": 15,
"ceval/ceval-exam:discrete_mathematics": 14,
"ceval/ceval-exam:education_science": 13,
"ceval/ceval-exam:clinical_medicine": 13,
"ceval/ceval-exam:electrical_engineer": 12,
"ceval/ceval-exam:computer_network": 11,
"ceval/ceval-exam:art_studies": 11,
"ceval/ceval-exam:computer_architecture": 11,
"ceval/ceval-exam:chinese_language_and_literature": 10,
"ceval/ceval-exam:basic_medicine": 9
}
}
}
}