jfrick's picture
Publish code-focused 32K tokenizer and promote it to the default
0ebdb4f verified
Raw History Blame Contribute Delete
15.7 kB
[
{
"vocab": 16384,
"training_seconds": 9.156001359,
"tokenizer_sha256": "e63d7d483dde1aa536251a2342d6809ff6d327bf958304ead50fd817e72081d5",
"corpus_manifest_sha256": "a4328e99a51bee64daaee66efe25e80ce01a263d568a69a130b94f687edef407",
"execution": "modal-cpu",
"general_metrics": {
"sources": {
"fineweb_edu": {
"bytes": 3355444,
"tokens": 1020901,
"chunks": 927,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.286747686602325,
"chunk_tokens_p95": 2532
},
"code_python": {
"bytes": 10066330,
"tokens": 2609022,
"chunks": 2092,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.8582771628602597,
"chunk_tokens_p95": 2427
},
"finemath_4plus": {
"bytes": 6710887,
"tokens": 2335747,
"chunks": 1789,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 2.8731223886833632,
"chunk_tokens_p95": 3059
},
"pes2o": {
"bytes": 3355444,
"tokens": 1011474,
"chunks": 422,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.317380377548014,
"chunk_tokens_p95": 2800
},
"pubmed": {
"bytes": 1006633,
"tokens": 337939,
"chunks": 128,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 2.978741725577693,
"chunk_tokens_p95": 3348
},
"arxiv": {
"bytes": 671089,
"tokens": 231007,
"chunks": 83,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 2.905059154051609,
"chunk_tokens_p95": 3729
},
"pressbooks": {
"bytes": 1006633,
"tokens": 298450,
"chunks": 359,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.3728698274417828,
"chunk_tokens_p95": 2266
},
"libretexts": {
"bytes": 1006632,
"tokens": 302996,
"chunks": 285,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.3222616800221787,
"chunk_tokens_p95": 2508
},
"doab": {
"bytes": 1342177,
"tokens": 421327,
"chunks": 315,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.1855945619435735,
"chunk_tokens_p95": 2817
},
"gutenberg": {
"bytes": 1677721,
"tokens": 561130,
"chunks": 210,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 2.989897171778376,
"chunk_tokens_p95": 3154
},
"pre_1929_books": {
"bytes": 2348810,
"tokens": 743797,
"chunks": 291,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.157864309751182,
"chunk_tokens_p95": 2958
},
"library_of_congress": {
"bytes": 1006632,
"tokens": 326527,
"chunks": 127,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.0828446039684314,
"chunk_tokens_p95": 3107
}
},
"bytes": 33554432,
"tokens": 10200317,
"bytes_per_token": 3.2895479620878447,
"evaluation_seconds": 17.576802950999998,
"evaluation_mib_per_second": 1.8205813701848108,
"vocabulary_used": 15530,
"vocabulary_use_fraction": 0.9478759765625,
"vocabulary_unseen": 854,
"vocabulary_used_at_most_10_times": 1325,
"roundtrip_failures": 0,
"unk_tokens": 0,
"probes": [
{
"text": "def square(x):\r\n\treturn x ** 2\r\n",
"tokens": 10,
"roundtrip": true
},
{
"text": "\u222b\u2080\u00b9 x\u00b2 dx = \u2153",
"tokens": 17,
"roundtrip": true
},
{
"text": "12345678901234567890",
"tokens": 7,
"roundtrip": true
},
{
"text": "na\u00efve caf\u00e9 \u4e2d\u6587 \u0627\u0644\u0639\u0631\u0628\u064a\u0629 \ud83d\ude00",
"tokens": 31,
"roundtrip": true
},
{
"text": "\u0000\t \r\n",
"tokens": 3,
"roundtrip": true
},
{
"text": "HTTPRequestHandler snake_case_identifier",
"tokens": 6,
"roundtrip": true
},
{
"text": "e\u0301 \u2260 \u00e9",
"tokens": 9,
"roundtrip": true
}
],
"fragmentation": {
"electromagnetism": 6,
"deoxyribonucleic": 9,
"Schr\u00f6dinger": 6,
"HTTPRequestHandler": 2,
"get_user_configuration": 3,
"np.linalg.eigh": 4,
"123456789": 3,
"0.000001": 4,
"\\frac{a}{b}": 7
}
},
"general_evaluation_sha256": "e4e66512ca51226f56844d61a4d0c065064900b6a6d0bd0243e9e64b8698024f"
},
{
"vocab": 32768,
"training_seconds": 11.375954247,
"tokenizer_sha256": "add5b2c7542e4efded329735825ecdcb94df1432617c3d3e4b7508aa459432f9",
"corpus_manifest_sha256": "a4328e99a51bee64daaee66efe25e80ce01a263d568a69a130b94f687edef407",
"execution": "modal-cpu",
"general_metrics": {
"sources": {
"fineweb_edu": {
"bytes": 3355444,
"tokens": 936322,
"chunks": 927,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.583643233844767,
"chunk_tokens_p95": 2327
},
"code_python": {
"bytes": 10066330,
"tokens": 2469754,
"chunks": 2092,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 4.075843181142737,
"chunk_tokens_p95": 2286
},
"finemath_4plus": {
"bytes": 6710887,
"tokens": 2164157,
"chunks": 1789,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.10092428599219,
"chunk_tokens_p95": 2854
},
"pes2o": {
"bytes": 3355444,
"tokens": 923008,
"chunks": 422,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.635335771737623,
"chunk_tokens_p95": 2595
},
"pubmed": {
"bytes": 1006633,
"tokens": 311772,
"chunks": 128,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.2287472896860527,
"chunk_tokens_p95": 3130
},
"arxiv": {
"bytes": 671089,
"tokens": 210824,
"chunks": 83,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.1831717451523547,
"chunk_tokens_p95": 3373
},
"pressbooks": {
"bytes": 1006633,
"tokens": 272469,
"chunks": 359,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.694486345235605,
"chunk_tokens_p95": 2091
},
"libretexts": {
"bytes": 1006632,
"tokens": 278042,
"chunks": 285,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.620431445608937,
"chunk_tokens_p95": 2344
},
"doab": {
"bytes": 1342177,
"tokens": 383761,
"chunks": 315,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.49742938964616,
"chunk_tokens_p95": 2570
},
"gutenberg": {
"bytes": 1677721,
"tokens": 520584,
"chunks": 210,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.2227671230771593,
"chunk_tokens_p95": 2958
},
"pre_1929_books": {
"bytes": 2348810,
"tokens": 686411,
"chunks": 291,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.4218711529972565,
"chunk_tokens_p95": 2744
},
"library_of_congress": {
"bytes": 1006632,
"tokens": 301653,
"chunks": 127,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.337052838857893,
"chunk_tokens_p95": 2890
}
},
"bytes": 33554432,
"tokens": 9458757,
"bytes_per_token": 3.5474462447867094,
"evaluation_seconds": 22.144963078000004,
"evaluation_mib_per_second": 1.4450238588020279,
"vocabulary_used": 28593,
"vocabulary_use_fraction": 0.872589111328125,
"vocabulary_unseen": 4175,
"vocabulary_used_at_most_10_times": 6736,
"roundtrip_failures": 0,
"unk_tokens": 0,
"probes": [
{
"text": "def square(x):\r\n\treturn x ** 2\r\n",
"tokens": 10,
"roundtrip": true
},
{
"text": "\u222b\u2080\u00b9 x\u00b2 dx = \u2153",
"tokens": 17,
"roundtrip": true
},
{
"text": "12345678901234567890",
"tokens": 7,
"roundtrip": true
},
{
"text": "na\u00efve caf\u00e9 \u4e2d\u6587 \u0627\u0644\u0639\u0631\u0628\u064a\u0629 \ud83d\ude00",
"tokens": 30,
"roundtrip": true
},
{
"text": "\u0000\t \r\n",
"tokens": 3,
"roundtrip": true
},
{
"text": "HTTPRequestHandler snake_case_identifier",
"tokens": 4,
"roundtrip": true
},
{
"text": "e\u0301 \u2260 \u00e9",
"tokens": 8,
"roundtrip": true
}
],
"fragmentation": {
"electromagnetism": 6,
"deoxyribonucleic": 8,
"Schr\u00f6dinger": 5,
"HTTPRequestHandler": 1,
"get_user_configuration": 3,
"np.linalg.eigh": 4,
"123456789": 3,
"0.000001": 4,
"\\frac{a}{b}": 7
}
},
"general_evaluation_sha256": "e4e66512ca51226f56844d61a4d0c065064900b6a6d0bd0243e9e64b8698024f"
},
{
"vocab": 50000,
"training_seconds": 9.773740467,
"tokenizer_sha256": "ce4bf31da579b5be65d25bea6670d071cdbbf2ef95a22ec26807cd8fc997660c",
"corpus_manifest_sha256": "a4328e99a51bee64daaee66efe25e80ce01a263d568a69a130b94f687edef407",
"execution": "modal-cpu",
"general_metrics": {
"sources": {
"fineweb_edu": {
"bytes": 3355444,
"tokens": 887035,
"chunks": 927,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.782763927015281,
"chunk_tokens_p95": 2216
},
"code_python": {
"bytes": 10066330,
"tokens": 2411019,
"chunks": 2092,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 4.175135077740988,
"chunk_tokens_p95": 2224
},
"finemath_4plus": {
"bytes": 6710887,
"tokens": 2067410,
"chunks": 1789,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.2460358612950504,
"chunk_tokens_p95": 2725
},
"pes2o": {
"bytes": 3355444,
"tokens": 880780,
"chunks": 422,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.8096278298780626,
"chunk_tokens_p95": 2488
},
"pubmed": {
"bytes": 1006633,
"tokens": 298208,
"chunks": 128,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.3756069589011695,
"chunk_tokens_p95": 3008
},
"arxiv": {
"bytes": 671089,
"tokens": 201611,
"chunks": 83,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.32863286229422,
"chunk_tokens_p95": 3256
},
"pressbooks": {
"bytes": 1006633,
"tokens": 258196,
"chunks": 359,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.8987164789539728,
"chunk_tokens_p95": 1950
},
"libretexts": {
"bytes": 1006632,
"tokens": 265207,
"chunks": 285,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.7956464195892266,
"chunk_tokens_p95": 2232
},
"doab": {
"bytes": 1342177,
"tokens": 364241,
"chunks": 315,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.6848597494515993,
"chunk_tokens_p95": 2448
},
"gutenberg": {
"bytes": 1677721,
"tokens": 497991,
"chunks": 210,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.3689785558373546,
"chunk_tokens_p95": 2852
},
"pre_1929_books": {
"bytes": 2348810,
"tokens": 657482,
"chunks": 291,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.5724324011912114,
"chunk_tokens_p95": 2649
},
"library_of_congress": {
"bytes": 1006632,
"tokens": 288605,
"chunks": 127,
"roundtrip_failures": 0,
"unk_tokens": 0,
"bytes_per_token": 3.4879229396580103,
"chunk_tokens_p95": 2684
}
},
"bytes": 33554432,
"tokens": 9077785,
"bytes_per_token": 3.6963237177351083,
"evaluation_seconds": 21.129434848000002,
"evaluation_mib_per_second": 1.5144749601776002,
"vocabulary_used": 39147,
"vocabulary_use_fraction": 0.78294,
"vocabulary_unseen": 10853,
"vocabulary_used_at_most_10_times": 13602,
"roundtrip_failures": 0,
"unk_tokens": 0,
"probes": [
{
"text": "def square(x):\r\n\treturn x ** 2\r\n",
"tokens": 10,
"roundtrip": true
},
{
"text": "\u222b\u2080\u00b9 x\u00b2 dx = \u2153",
"tokens": 17,
"roundtrip": true
},
{
"text": "12345678901234567890",
"tokens": 7,
"roundtrip": true
},
{
"text": "na\u00efve caf\u00e9 \u4e2d\u6587 \u0627\u0644\u0639\u0631\u0628\u064a\u0629 \ud83d\ude00",
"tokens": 30,
"roundtrip": true
},
{
"text": "\u0000\t \r\n",
"tokens": 3,
"roundtrip": true
},
{
"text": "HTTPRequestHandler snake_case_identifier",
"tokens": 4,
"roundtrip": true
},
{
"text": "e\u0301 \u2260 \u00e9",
"tokens": 8,
"roundtrip": true
}
],
"fragmentation": {
"electromagnetism": 6,
"deoxyribonucleic": 8,
"Schr\u00f6dinger": 5,
"HTTPRequestHandler": 1,
"get_user_configuration": 3,
"np.linalg.eigh": 4,
"123456789": 3,
"0.000001": 4,
"\\frac{a}{b}": 7
}
},
"general_evaluation_sha256": "e4e66512ca51226f56844d61a4d0c065064900b6a6d0bd0243e9e64b8698024f"
}
]