Download validation-diagnostics.json from jfrick/scholarly-code-modern-gpt-124m-step2: direct link, hf CLI and curl.
- Browser
- Download file 85.8 kB
-
https://huggingface.co/jfrick/scholarly-code-modern-gpt-124m-step2/resolve/main/validation-diagnostics.json
- Command line
-
hf download hf://jfrick/scholarly-code-modern-gpt-124m-step2/validation-diagnostics.json
-
curl -L -o validation-diagnostics.json https://huggingface.co/jfrick/scholarly-code-modern-gpt-124m-step2/resolve/main/validation-diagnostics.json
85.8 kB
[
{
"step": 0,
"tokens": 0,
"per_source": {
"fineweb_edu": 10.519629726890756,
"code_python": 10.525794538943599,
"finemath_4plus": 10.32566055540577,
"pes2o": 10.462692260742188,
"pubmed": 10.545242309570312,
"arxiv": 10.553985595703125,
"pressbooks": 10.5458984375,
"libretexts": 10.647798042704625,
"doab": 10.522146329198794,
"gutenberg": 10.600608825683594,
"pre_1929_books": 10.588775634765625,
"library_of_congress": 10.568008422851562
},
"weighted_loss": 10.49352138870611,
"segment": "simple-llm-124m-8k-5b-20261018-s00"
},
{
"step": 2,
"tokens": 131039,
"per_source": {
"fineweb_edu": 10.509191176470589,
"code_python": 10.508337063563115,
"finemath_4plus": 10.308657994068483,
"pes2o": 10.448966979980469,
"pubmed": 10.531173706054688,
"arxiv": 10.537490844726562,
"pressbooks": 10.53515625,
"libretexts": 10.631728202846976,
"doab": 10.502660911833724,
"gutenberg": 10.584503173828125,
"pre_1929_books": 10.552055358886719,
"library_of_congress": 10.53436279296875
},
"weighted_loss": 10.475746449265205,
"segment": "simple-llm-124m-8k-5b-20261018-s01"
},
{
"step": 4,
"tokens": 257384,
"per_source": {
"fineweb_edu": 10.488314075630251,
"code_python": 10.474317367949865,
"finemath_4plus": 10.143755055270962,
"pes2o": 10.422088623046875,
"pubmed": 10.506561279296875,
"arxiv": 10.510971069335938,
"pressbooks": 10.5135498046875,
"libretexts": 10.60442615658363,
"doab": 10.470530925243043,
"gutenberg": 10.556404113769531,
"pre_1929_books": 10.490371704101562,
"library_of_congress": 10.477531433105469
},
"weighted_loss": 10.416335434889096,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 500,
"tokens": 38433207,
"per_source": {
"fineweb_edu": 5.349017487854517,
"code_python": 4.60803474009624,
"finemath_4plus": 2.7968560427338907,
"pes2o": 5.143681049346924,
"pubmed": 5.251229763031006,
"arxiv": 4.909776210784912,
"pressbooks": 5.0997161865234375,
"libretexts": 5.201687089913256,
"doab": 4.936758166066041,
"gutenberg": 5.204975128173828,
"pre_1929_books": 5.021296501159668,
"library_of_congress": 4.880281925201416
},
"weighted_loss": 4.5114442955840754,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 1000,
"tokens": 77303045,
"per_source": {
"fineweb_edu": 4.551280815060399,
"code_python": 3.3144417594561326,
"finemath_4plus": 1.9642102613575088,
"pes2o": 3.749763011932373,
"pubmed": 3.8531785011291504,
"arxiv": 3.771294355392456,
"pressbooks": 4.586516380310059,
"libretexts": 4.046084366659253,
"doab": 3.476931125335233,
"gutenberg": 4.285614967346191,
"pre_1929_books": 4.3287787437438965,
"library_of_congress": 4.175426006317139
},
"weighted_loss": 3.4489135129907273,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 1500,
"tokens": 116381741,
"per_source": {
"fineweb_edu": 4.182884921546743,
"code_python": 2.707929127965533,
"finemath_4plus": 1.6900300051395254,
"pes2o": 3.2091357707977295,
"pubmed": 3.3013875484466553,
"arxiv": 3.2483131885528564,
"pressbooks": 4.316247940063477,
"libretexts": 3.6590502321508005,
"doab": 2.56122061473349,
"gutenberg": 3.8471758365631104,
"pre_1929_books": 3.970599889755249,
"library_of_congress": 3.7623534202575684
},
"weighted_loss": 2.978473855350987,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 2000,
"tokens": 156492276,
"per_source": {
"fineweb_edu": 3.978084788602941,
"code_python": 2.4555998471771487,
"finemath_4plus": 1.6120462631015773,
"pes2o": 3.052229404449463,
"pubmed": 3.1436569690704346,
"arxiv": 3.0284626483917236,
"pressbooks": 4.079463005065918,
"libretexts": 3.450840417176379,
"doab": 2.2499003140190243,
"gutenberg": 3.6968271732330322,
"pre_1929_books": 3.8512372970581055,
"library_of_congress": 3.631093978881836
},
"weighted_loss": 2.796265492168852,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 2500,
"tokens": 196446608,
"per_source": {
"fineweb_edu": 3.867496522534795,
"code_python": 2.2910540929946284,
"finemath_4plus": 1.5284050936067672,
"pes2o": 2.939160108566284,
"pubmed": 2.9841866493225098,
"arxiv": 2.914051055908203,
"pressbooks": 3.9807677268981934,
"libretexts": 3.3366998964357206,
"doab": 2.1428018864712537,
"gutenberg": 3.594550371170044,
"pre_1929_books": 3.7079238891601562,
"library_of_congress": 3.521735429763794
},
"weighted_loss": 2.671639888179184,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 3000,
"tokens": 235140184,
"per_source": {
"fineweb_edu": 3.6996298397288605,
"code_python": 2.264319929568599,
"finemath_4plus": 1.454397638135279,
"pes2o": 2.8458449840545654,
"pubmed": 2.865652084350586,
"arxiv": 2.8270819187164307,
"pressbooks": 3.851637601852417,
"libretexts": 3.2237796444061386,
"doab": 1.894366907266175,
"gutenberg": 3.457369804382324,
"pre_1929_books": 3.6073131561279297,
"library_of_congress": 3.428806781768799
},
"weighted_loss": 2.583515998060363,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 3500,
"tokens": 273948748,
"per_source": {
"fineweb_edu": 3.7217232840401784,
"code_python": 2.202347334517681,
"finemath_4plus": 1.4746370210130764,
"pes2o": 2.804166793823242,
"pubmed": 2.8693230152130127,
"arxiv": 2.7515451908111572,
"pressbooks": 3.8389458656311035,
"libretexts": 3.079233841539702,
"doab": 1.9193527318869428,
"gutenberg": 3.418907642364502,
"pre_1929_books": 3.586266279220581,
"library_of_congress": 3.383039951324463
},
"weighted_loss": 2.5571259273108766,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 4000,
"tokens": 312603544,
"per_source": {
"fineweb_edu": 3.6438783276982667,
"code_python": 2.2085330317675695,
"finemath_4plus": 1.3831809818600027,
"pes2o": 2.7529594898223877,
"pubmed": 2.7493624687194824,
"arxiv": 2.6861438751220703,
"pressbooks": 3.8065550327301025,
"libretexts": 3.0199752210298043,
"doab": 1.8393962270574924,
"gutenberg": 3.4062743186950684,
"pre_1929_books": 3.498791456222534,
"library_of_congress": 3.2947449684143066
},
"weighted_loss": 2.5075268628362197,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 4500,
"tokens": 352088189,
"per_source": {
"fineweb_edu": 3.609343713071166,
"code_python": 2.1045789590560653,
"finemath_4plus": 1.5237749130072122,
"pes2o": 2.7013800144195557,
"pubmed": 2.705015182495117,
"arxiv": 2.696319341659546,
"pressbooks": 3.754187822341919,
"libretexts": 3.0174004497052938,
"doab": 1.805234708923483,
"gutenberg": 3.349958658218384,
"pre_1929_books": 3.431877374649048,
"library_of_congress": 3.2598423957824707
},
"weighted_loss": 2.483159542903561,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 5000,
"tokens": 390356198,
"per_source": {
"fineweb_edu": 3.5872815556886817,
"code_python": 2.134398211937668,
"finemath_4plus": 1.3421849723645187,
"pes2o": 2.6476564407348633,
"pubmed": 2.6584978103637695,
"arxiv": 2.623499870300293,
"pressbooks": 3.6925272941589355,
"libretexts": 2.93014710993105,
"doab": 1.7116942295403117,
"gutenberg": 3.3197290897369385,
"pre_1929_books": 3.428985118865967,
"library_of_congress": 3.2255804538726807
},
"weighted_loss": 2.434406017141435,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 5500,
"tokens": 428842816,
"per_source": {
"fineweb_edu": 3.5532385561646533,
"code_python": 2.0550903211028424,
"finemath_4plus": 1.3239929742265435,
"pes2o": 2.621879816055298,
"pubmed": 2.6429529190063477,
"arxiv": 2.5888257026672363,
"pressbooks": 3.672851800918579,
"libretexts": 2.8870191472280915,
"doab": 1.6835488994929602,
"gutenberg": 3.276890516281128,
"pre_1929_books": 3.412748336791992,
"library_of_congress": 3.2049543857574463
},
"weighted_loss": 2.3929262554080295,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 6000,
"tokens": 467246994,
"per_source": {
"fineweb_edu": 3.533538049008666,
"code_python": 2.001098304960273,
"finemath_4plus": 1.3116823362513481,
"pes2o": 2.602236747741699,
"pubmed": 2.604219913482666,
"arxiv": 2.5658063888549805,
"pressbooks": 3.6407251358032227,
"libretexts": 2.8755886308663254,
"doab": 1.6827929883925579,
"gutenberg": 3.243234872817993,
"pre_1929_books": 3.3698062896728516,
"library_of_congress": 3.1784682273864746
},
"weighted_loss": 2.3618895268703497,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 6500,
"tokens": 506170691,
"per_source": {
"fineweb_edu": 3.5002728630514706,
"code_python": 1.9986820340476723,
"finemath_4plus": 1.2898404061488946,
"pes2o": 2.5483670234680176,
"pubmed": 2.560537338256836,
"arxiv": 2.542081117630005,
"pressbooks": 3.6568045616149902,
"libretexts": 2.807248370078959,
"doab": 1.6029682523885351,
"gutenberg": 3.2276291847229004,
"pre_1929_books": 3.358417272567749,
"library_of_congress": 3.1747279167175293
},
"weighted_loss": 2.3398472464601077,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 7000,
"tokens": 544829954,
"per_source": {
"fineweb_edu": 3.468265309053309,
"code_python": 2.0041464563982765,
"finemath_4plus": 1.2857374745130088,
"pes2o": 2.5283589363098145,
"pubmed": 2.533996105194092,
"arxiv": 2.5054545402526855,
"pressbooks": 3.597473621368408,
"libretexts": 2.7939846269600754,
"doab": 1.6198227128205664,
"gutenberg": 3.2035892009735107,
"pre_1929_books": 3.328643798828125,
"library_of_congress": 3.154270648956299
},
"weighted_loss": 2.328532131717284,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 7500,
"tokens": 583548901,
"per_source": {
"fineweb_edu": 3.484887900472689,
"code_python": 2.0354261816668533,
"finemath_4plus": 1.2697624233283904,
"pes2o": 2.512752056121826,
"pubmed": 2.5274453163146973,
"arxiv": 2.4797022342681885,
"pressbooks": 3.6278152465820312,
"libretexts": 2.7782579741019795,
"doab": 1.5882908421157391,
"gutenberg": 3.2123160362243652,
"pre_1929_books": 3.336923599243164,
"library_of_congress": 3.12457537651062
},
"weighted_loss": 2.3334132843586985,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 8000,
"tokens": 621927994,
"per_source": {
"fineweb_edu": 3.416378245634191,
"code_python": 1.9658924399899285,
"finemath_4plus": 1.2680532414818684,
"pes2o": 2.506383180618286,
"pubmed": 2.521512746810913,
"arxiv": 2.4711294174194336,
"pressbooks": 3.6559579372406006,
"libretexts": 2.7526012705738436,
"doab": 1.5734934485522125,
"gutenberg": 3.1479735374450684,
"pre_1929_books": 3.329843521118164,
"library_of_congress": 3.11576247215271
},
"weighted_loss": 2.299879605362944,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 8500,
"tokens": 662450483,
"per_source": {
"fineweb_edu": 3.424385647813813,
"code_python": 1.968285979814794,
"finemath_4plus": 1.269644598653613,
"pes2o": 2.4831433296203613,
"pubmed": 2.5162458419799805,
"arxiv": 2.46229887008667,
"pressbooks": 3.5741350650787354,
"libretexts": 2.7383792103397466,
"doab": 1.5713952960002515,
"gutenberg": 3.1664178371429443,
"pre_1929_books": 3.3091042041778564,
"library_of_congress": 3.0921690464019775
},
"weighted_loss": 2.294855461723932,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 9000,
"tokens": 701633024,
"per_source": {
"fineweb_edu": 3.3768123338202467,
"code_python": 1.998953714259736,
"finemath_4plus": 1.2391826416739686,
"pes2o": 2.42470645904541,
"pubmed": 2.483095645904541,
"arxiv": 2.438408136367798,
"pressbooks": 3.546781539916992,
"libretexts": 2.7098195357679047,
"doab": 1.5457314757584646,
"gutenberg": 3.163879871368408,
"pre_1929_books": 3.277555227279663,
"library_of_congress": 3.0829639434814453
},
"weighted_loss": 2.280574623087098,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 9500,
"tokens": 740427708,
"per_source": {
"fineweb_edu": 3.4014084759880516,
"code_python": 1.9393385952887199,
"finemath_4plus": 1.2241363648810326,
"pes2o": 2.4231674671173096,
"pubmed": 2.4707627296447754,
"arxiv": 2.4154908657073975,
"pressbooks": 3.528549909591675,
"libretexts": 2.7205732352368774,
"doab": 1.5589111409968992,
"gutenberg": 3.1097617149353027,
"pre_1929_books": 3.2477502822875977,
"library_of_congress": 3.0510783195495605
},
"weighted_loss": 2.255712240154966,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 10000,
"tokens": 780377017,
"per_source": {
"fineweb_edu": 3.4116608435366333,
"code_python": 1.9582285663328112,
"finemath_4plus": 1.222124130072122,
"pes2o": 2.429441213607788,
"pubmed": 2.4719395637512207,
"arxiv": 2.4153265953063965,
"pressbooks": 3.5310864448547363,
"libretexts": 2.718174401551379,
"doab": 1.5519116792029837,
"gutenberg": 3.1256797313690186,
"pre_1929_books": 3.2299280166625977,
"library_of_congress": 3.060425043106079
},
"weighted_loss": 2.2622143120356926,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 10500,
"tokens": 818674341,
"per_source": {
"fineweb_edu": 3.3687656947544644,
"code_python": 1.8884795350268577,
"finemath_4plus": 1.2275255027888246,
"pes2o": 2.408869981765747,
"pubmed": 2.4807071685791016,
"arxiv": 2.416353464126587,
"pressbooks": 3.5451712608337402,
"libretexts": 2.7034399500945283,
"doab": 1.5334787755615154,
"gutenberg": 3.072868585586548,
"pre_1929_books": 3.214425563812256,
"library_of_congress": 3.0159995555877686
},
"weighted_loss": 2.2304915058218753,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 11000,
"tokens": 858536498,
"per_source": {
"fineweb_edu": 3.339982746028099,
"code_python": 1.906979580489033,
"finemath_4plus": 1.2138326958074952,
"pes2o": 2.408499240875244,
"pubmed": 2.449234962463379,
"arxiv": 2.3687922954559326,
"pressbooks": 3.4258809089660645,
"libretexts": 2.677810614643572,
"doab": 1.5341656103335568,
"gutenberg": 3.1087558269500732,
"pre_1929_books": 3.206244945526123,
"library_of_congress": 3.0284206867218018
},
"weighted_loss": 2.225766435039181,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 11500,
"tokens": 897682203,
"per_source": {
"fineweb_edu": 3.3517750972459295,
"code_python": 1.930828207181625,
"finemath_4plus": 1.1738050866557697,
"pes2o": 2.378962516784668,
"pubmed": 2.429945945739746,
"arxiv": 2.377609968185425,
"pressbooks": 3.4770925045013428,
"libretexts": 2.640478602507785,
"doab": 1.5419195100360374,
"gutenberg": 3.101341485977173,
"pre_1929_books": 3.1932239532470703,
"library_of_congress": 2.9868123531341553
},
"weighted_loss": 2.2209348538564955,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 12000,
"tokens": 935998541,
"per_source": {
"fineweb_edu": 3.3374185001148895,
"code_python": 1.8964955219757162,
"finemath_4plus": 1.1875741176445807,
"pes2o": 2.3994927406311035,
"pubmed": 2.418705701828003,
"arxiv": 2.368375539779663,
"pressbooks": 3.4925129413604736,
"libretexts": 2.6302164423932384,
"doab": 1.5160851269171136,
"gutenberg": 3.058180809020996,
"pre_1929_books": 3.203143835067749,
"library_of_congress": 2.9963560104370117
},
"weighted_loss": 2.2114283618548622,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 12500,
"tokens": 974448949,
"per_source": {
"fineweb_edu": 3.286708286830357,
"code_python": 1.882662999384512,
"finemath_4plus": 1.1840940111889997,
"pes2o": 2.3753485679626465,
"pubmed": 2.4045557975769043,
"arxiv": 2.3502440452575684,
"pressbooks": 3.4757583141326904,
"libretexts": 2.603644645935276,
"doab": 1.517081823038887,
"gutenberg": 3.0547306537628174,
"pre_1929_books": 3.1994881629943848,
"library_of_congress": 3.007209539413452
},
"weighted_loss": 2.196947294368658,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 13000,
"tokens": 1013198314,
"per_source": {
"fineweb_edu": 3.284645657579438,
"code_python": 1.8466333510519248,
"finemath_4plus": 1.1999882306972904,
"pes2o": 2.3755908012390137,
"pubmed": 2.3893189430236816,
"arxiv": 2.348431348800659,
"pressbooks": 3.4490699768066406,
"libretexts": 2.624197203069395,
"doab": 1.4804831545424069,
"gutenberg": 3.0585837364196777,
"pre_1929_books": 3.1980838775634766,
"library_of_congress": 2.9999136924743652
},
"weighted_loss": 2.18686930320624,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 13500,
"tokens": 1051167636,
"per_source": {
"fineweb_edu": 3.2951283174402572,
"code_python": 1.8491119138876455,
"finemath_4plus": 1.1832705549423699,
"pes2o": 2.3448009490966797,
"pubmed": 2.383732557296753,
"arxiv": 2.322158098220825,
"pressbooks": 3.388357400894165,
"libretexts": 2.5953634133118326,
"doab": 1.4636578305711532,
"gutenberg": 3.043764352798462,
"pre_1929_books": 3.173523426055908,
"library_of_congress": 3.005095958709717
},
"weighted_loss": 2.175881424365935,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 14000,
"tokens": 1090278233,
"per_source": {
"fineweb_edu": 3.2816849396008405,
"code_python": 1.819363367802988,
"finemath_4plus": 1.1886661351610945,
"pes2o": 2.3250932693481445,
"pubmed": 2.352487087249756,
"arxiv": 2.310730218887329,
"pressbooks": 3.4237539768218994,
"libretexts": 2.616776544428381,
"doab": 1.4478436072640797,
"gutenberg": 3.021934986114502,
"pre_1929_books": 3.167613983154297,
"library_of_congress": 2.957875967025757
},
"weighted_loss": 2.161704942328623,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 14500,
"tokens": 1130016411,
"per_source": {
"fineweb_edu": 3.2731813062138917,
"code_python": 1.8504071487522382,
"finemath_4plus": 1.1590140747169049,
"pes2o": 2.3214893341064453,
"pubmed": 2.334656238555908,
"arxiv": 2.301518678665161,
"pressbooks": 3.435765266418457,
"libretexts": 2.5657292159002445,
"doab": 1.517892405925243,
"gutenberg": 3.013111114501953,
"pre_1929_books": 3.161405324935913,
"library_of_congress": 2.9871039390563965
},
"weighted_loss": 2.164789661679941,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 15000,
"tokens": 1168632792,
"per_source": {
"fineweb_edu": 3.2472854742482933,
"code_python": 1.8666740834126008,
"finemath_4plus": 1.1683701437803315,
"pes2o": 2.3135242462158203,
"pubmed": 2.400381565093994,
"arxiv": 2.298497200012207,
"pressbooks": 3.4229726791381836,
"libretexts": 2.5602853578180604,
"doab": 1.4865199673147838,
"gutenberg": 3.025700569152832,
"pre_1929_books": 3.1646852493286133,
"library_of_congress": 2.969463586807251
},
"weighted_loss": 2.1685940600954625,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 15500,
"tokens": 1207145298,
"per_source": {
"fineweb_edu": 3.2367674242548583,
"code_python": 1.8627853188647046,
"finemath_4plus": 1.1461014118950525,
"pes2o": 2.3026788234710693,
"pubmed": 2.3665804862976074,
"arxiv": 2.2924745082855225,
"pressbooks": 3.388545513153076,
"libretexts": 2.5727617257006226,
"doab": 1.4629105949337915,
"gutenberg": 3.0305368900299072,
"pre_1929_books": 3.1674129962921143,
"library_of_congress": 2.934105157852173
},
"weighted_loss": 2.1574719575061243,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 16000,
"tokens": 1245139626,
"per_source": {
"fineweb_edu": 3.239999210133272,
"code_python": 1.8347132997845792,
"finemath_4plus": 1.1358267053114046,
"pes2o": 2.2972733974456787,
"pubmed": 2.3601911067962646,
"arxiv": 2.2874927520751953,
"pressbooks": 3.415156364440918,
"libretexts": 2.5720227876167705,
"doab": 1.4577917443638955,
"gutenberg": 2.9983174800872803,
"pre_1929_books": 3.1409497261047363,
"library_of_congress": 2.9267685413360596
},
"weighted_loss": 2.1433746354090055,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 16500,
"tokens": 1284689530,
"per_source": {
"fineweb_edu": 3.230189732142857,
"code_python": 1.7767476053673343,
"finemath_4plus": 1.1332970951149233,
"pes2o": 2.3068315982818604,
"pubmed": 2.3467559814453125,
"arxiv": 2.2801263332366943,
"pressbooks": 3.416707992553711,
"libretexts": 2.553756768168928,
"doab": 1.4383452847385183,
"gutenberg": 2.970602035522461,
"pre_1929_books": 3.1584866046905518,
"library_of_congress": 2.932922840118408
},
"weighted_loss": 2.123650643302984,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 17000,
"tokens": 1323475559,
"per_source": {
"fineweb_edu": 3.234157786649816,
"code_python": 1.7681292445934982,
"finemath_4plus": 1.1293509558674846,
"pes2o": 2.275733232498169,
"pubmed": 2.3351690769195557,
"arxiv": 2.282017707824707,
"pressbooks": 3.445122718811035,
"libretexts": 2.5196607053491995,
"doab": 1.4417848603021288,
"gutenberg": 2.979184150695801,
"pre_1929_books": 3.1396920680999756,
"library_of_congress": 2.949831962585449
},
"weighted_loss": 2.11684100124667,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 17500,
"tokens": 1361131824,
"per_source": {
"fineweb_edu": 3.1939033059512867,
"code_python": 1.811564856164671,
"finemath_4plus": 1.133552623264357,
"pes2o": 2.257544755935669,
"pubmed": 2.3157145977020264,
"arxiv": 2.267299175262451,
"pressbooks": 3.353027820587158,
"libretexts": 2.540500410086744,
"doab": 1.427142479257459,
"gutenberg": 2.9501352310180664,
"pre_1929_books": 3.1480448246002197,
"library_of_congress": 2.927075147628784
},
"weighted_loss": 2.119715908919576,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 18000,
"tokens": 1400688733,
"per_source": {
"fineweb_edu": 3.1862739114200367,
"code_python": 1.7817050588910026,
"finemath_4plus": 1.1279948531022512,
"pes2o": 2.2747111320495605,
"pubmed": 2.301034927368164,
"arxiv": 2.2493956089019775,
"pressbooks": 3.3543877601623535,
"libretexts": 2.5000267164562944,
"doab": 1.407843829879735,
"gutenberg": 2.971298933029175,
"pre_1929_books": 3.125236988067627,
"library_of_congress": 2.9120287895202637
},
"weighted_loss": 2.1068665396293444,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 18500,
"tokens": 1439465628,
"per_source": {
"fineweb_edu": 3.2009369665835083,
"code_python": 1.807558283383225,
"finemath_4plus": 1.142264145280062,
"pes2o": 2.2697715759277344,
"pubmed": 2.330618381500244,
"arxiv": 2.226047992706299,
"pressbooks": 3.3372483253479004,
"libretexts": 2.5083359687778026,
"doab": 1.410977963669125,
"gutenberg": 2.9439384937286377,
"pre_1929_books": 3.1227810382843018,
"library_of_congress": 2.9204723834991455
},
"weighted_loss": 2.1174430958630808,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 19000,
"tokens": 1477760080,
"per_source": {
"fineweb_edu": 3.2056223124015233,
"code_python": 1.772674587867894,
"finemath_4plus": 1.1106103818414668,
"pes2o": 2.248295545578003,
"pubmed": 2.2912588119506836,
"arxiv": 2.2319862842559814,
"pressbooks": 3.3704535961151123,
"libretexts": 2.483723379114769,
"doab": 1.418900298304978,
"gutenberg": 2.9488959312438965,
"pre_1929_books": 3.126286506652832,
"library_of_congress": 2.9234609603881836
},
"weighted_loss": 2.0990637305988886,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 19500,
"tokens": 1516849952,
"per_source": {
"fineweb_edu": 3.191769383534664,
"code_python": 1.7984401665314458,
"finemath_4plus": 1.098002154282657,
"pes2o": 2.2575876712799072,
"pubmed": 2.3109290599823,
"arxiv": 2.2317986488342285,
"pressbooks": 3.3423423767089844,
"libretexts": 2.4673941941447954,
"doab": 1.404011075783607,
"gutenberg": 2.9459476470947266,
"pre_1929_books": 3.0904083251953125,
"library_of_congress": 2.914459466934204
},
"weighted_loss": 2.099544320356968,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 20000,
"tokens": 1555839605,
"per_source": {
"fineweb_edu": 3.1740776510799633,
"code_python": 1.811857846771486,
"finemath_4plus": 1.175695679007145,
"pes2o": 2.2300972938537598,
"pubmed": 2.28434419631958,
"arxiv": 2.2360951900482178,
"pressbooks": 3.3541364669799805,
"libretexts": 2.469925958490881,
"doab": 1.4090772188233323,
"gutenberg": 2.918184518814087,
"pre_1929_books": 3.089482545852661,
"library_of_congress": 2.890042543411255
},
"weighted_loss": 2.1123254559865865,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 20500,
"tokens": 1594268630,
"per_source": {
"fineweb_edu": 3.177490234375,
"code_python": 1.7573118696494516,
"finemath_4plus": 1.1050532699177675,
"pes2o": 2.222085952758789,
"pubmed": 2.284785747528076,
"arxiv": 2.2182719707489014,
"pressbooks": 3.33769154548645,
"libretexts": 2.509345329529026,
"doab": 1.4086185650980556,
"gutenberg": 2.9082069396972656,
"pre_1929_books": 3.075566291809082,
"library_of_congress": 2.8945953845977783
},
"weighted_loss": 2.0803645432364073,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 21000,
"tokens": 1633802599,
"per_source": {
"fineweb_edu": 3.138838567653624,
"code_python": 1.7333082781375895,
"finemath_4plus": 1.1114671449514695,
"pes2o": 2.2251288890838623,
"pubmed": 2.271509885787964,
"arxiv": 2.2181994915008545,
"pressbooks": 3.3218750953674316,
"libretexts": 2.4635218284308276,
"doab": 1.3983222636607442,
"gutenberg": 2.911965847015381,
"pre_1929_books": 3.069960355758667,
"library_of_congress": 2.85258412361145
},
"weighted_loss": 2.0667597837315723,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 21500,
"tokens": 1673272828,
"per_source": {
"fineweb_edu": 3.150617583459165,
"code_python": 1.7354075159467324,
"finemath_4plus": 1.1043332887486519,
"pes2o": 2.216519832611084,
"pubmed": 2.2748875617980957,
"arxiv": 2.1932787895202637,
"pressbooks": 3.2910075187683105,
"libretexts": 2.4574098417343193,
"doab": 1.3888977644150184,
"gutenberg": 2.9061272144317627,
"pre_1929_books": 3.0527536869049072,
"library_of_congress": 2.8738577365875244
},
"weighted_loss": 2.0635381390793603,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 22000,
"tokens": 1711736479,
"per_source": {
"fineweb_edu": 3.1715082761620272,
"code_python": 1.6976522720596463,
"finemath_4plus": 1.1140875920480589,
"pes2o": 2.2159619331359863,
"pubmed": 2.25876522064209,
"arxiv": 2.2058210372924805,
"pressbooks": 3.282087564468384,
"libretexts": 2.453903252543928,
"doab": 1.3896955796387864,
"gutenberg": 2.9679160118103027,
"pre_1929_books": 3.067857027053833,
"library_of_congress": 2.878324031829834
},
"weighted_loss": 2.0599026594575185,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 22500,
"tokens": 1750970199,
"per_source": {
"fineweb_edu": 3.1309029715401784,
"code_python": 1.705495371600828,
"finemath_4plus": 1.10101418740732,
"pes2o": 2.2098305225372314,
"pubmed": 2.2521657943725586,
"arxiv": 2.1890106201171875,
"pressbooks": 3.2759642601013184,
"libretexts": 2.451681442532251,
"doab": 1.387349276106269,
"gutenberg": 2.9209511280059814,
"pre_1929_books": 3.0717241764068604,
"library_of_congress": 2.873899459838867
},
"weighted_loss": 2.051878559270177,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 23000,
"tokens": 1790247619,
"per_source": {
"fineweb_edu": 3.1363102247735033,
"code_python": 1.7102718506952215,
"finemath_4plus": 1.1055785441662174,
"pes2o": 2.221893548965454,
"pubmed": 2.2449655532836914,
"arxiv": 2.2020037174224854,
"pressbooks": 3.291759967803955,
"libretexts": 2.434246239713078,
"doab": 1.3989036833724438,
"gutenberg": 2.91178035736084,
"pre_1929_books": 3.06294322013855,
"library_of_congress": 2.8579673767089844
},
"weighted_loss": 2.054877080502085,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 23500,
"tokens": 1828700197,
"per_source": {
"fineweb_edu": 3.12019155806854,
"code_python": 1.6710105629616159,
"finemath_4plus": 1.0790373184315178,
"pes2o": 2.2103796005249023,
"pubmed": 2.2346208095550537,
"arxiv": 2.182706832885742,
"pressbooks": 3.291001796722412,
"libretexts": 2.4367860407167483,
"doab": 1.3989555724627054,
"gutenberg": 2.9044809341430664,
"pre_1929_books": 3.0645806789398193,
"library_of_congress": 2.872194528579712
},
"weighted_loss": 2.034562897490514,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 24000,
"tokens": 1867644282,
"per_source": {
"fineweb_edu": 3.1361437885701156,
"code_python": 1.6588359890820836,
"finemath_4plus": 1.1007924268881437,
"pes2o": 2.211458444595337,
"pubmed": 2.2409613132476807,
"arxiv": 2.17490816116333,
"pressbooks": 3.2841570377349854,
"libretexts": 2.4426408543705516,
"doab": 1.395818983353587,
"gutenberg": 2.888793706893921,
"pre_1929_books": 3.035923719406128,
"library_of_congress": 2.855625629425049
},
"weighted_loss": 2.033556318722682,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 24500,
"tokens": 1906496917,
"per_source": {
"fineweb_edu": 3.1657868713891806,
"code_python": 1.6874107149101947,
"finemath_4plus": 1.0834769390123686,
"pes2o": 2.196035861968994,
"pubmed": 2.231064796447754,
"arxiv": 2.1901373863220215,
"pressbooks": 3.305091381072998,
"libretexts": 2.459324521102091,
"doab": 1.3829971400435803,
"gutenberg": 2.8841190338134766,
"pre_1929_books": 3.038745641708374,
"library_of_congress": 2.8478541374206543
},
"weighted_loss": 2.040441700631098,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 25000,
"tokens": 1944700166,
"per_source": {
"fineweb_edu": 3.1096806886817228,
"code_python": 1.7122647550987578,
"finemath_4plus": 1.0847586608376585,
"pes2o": 2.1837687492370605,
"pubmed": 2.2271037101745605,
"arxiv": 2.164583921432495,
"pressbooks": 3.266948938369751,
"libretexts": 2.4210398392320953,
"doab": 1.3813925067570398,
"gutenberg": 2.8814337253570557,
"pre_1929_books": 3.0156495571136475,
"library_of_congress": 2.8431057929992676
},
"weighted_loss": 2.036436584877047,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 25500,
"tokens": 1983815327,
"per_source": {
"fineweb_edu": 3.1488824411600578,
"code_python": 1.6738970832517346,
"finemath_4plus": 1.081017562853869,
"pes2o": 2.1911189556121826,
"pubmed": 2.213674545288086,
"arxiv": 2.159165143966675,
"pressbooks": 3.304154634475708,
"libretexts": 2.452121503836744,
"doab": 1.3752046099773718,
"gutenberg": 2.8702855110168457,
"pre_1929_books": 3.0326602458953857,
"library_of_congress": 2.8432657718658447
},
"weighted_loss": 2.0307612509294573,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 26000,
"tokens": 2022989064,
"per_source": {
"fineweb_edu": 3.12825589220063,
"code_python": 1.7076040078404768,
"finemath_4plus": 1.0879490107466636,
"pes2o": 2.191602945327759,
"pubmed": 2.2262768745422363,
"arxiv": 2.165888786315918,
"pressbooks": 3.2231216430664062,
"libretexts": 2.4122692393238436,
"doab": 1.370482866451559,
"gutenberg": 2.8766989707946777,
"pre_1929_books": 3.0138347148895264,
"library_of_congress": 2.8162732124328613
},
"weighted_loss": 2.0351355863016565,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 26500,
"tokens": 2062428728,
"per_source": {
"fineweb_edu": 3.1359473476890756,
"code_python": 1.685462507693599,
"finemath_4plus": 1.0624041604880021,
"pes2o": 2.1909143924713135,
"pubmed": 2.2219460010528564,
"arxiv": 2.1679186820983887,
"pressbooks": 3.252044677734375,
"libretexts": 2.4157686606844972,
"doab": 1.3630826146339674,
"gutenberg": 2.8658885955810547,
"pre_1929_books": 3.032886028289795,
"library_of_congress": 2.8279783725738525
},
"weighted_loss": 2.0258160197697515,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 27000,
"tokens": 2101622194,
"per_source": {
"fineweb_edu": 3.1306044634650734,
"code_python": 1.701745834965309,
"finemath_4plus": 1.0798403692875438,
"pes2o": 2.192018508911133,
"pubmed": 2.212536573410034,
"arxiv": 2.161533832550049,
"pressbooks": 3.318868637084961,
"libretexts": 2.424513847378225,
"doab": 1.3685633793318388,
"gutenberg": 2.857728958129883,
"pre_1929_books": 3.011951208114624,
"library_of_congress": 2.8184971809387207
},
"weighted_loss": 2.0336828530478726,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 27500,
"tokens": 2139619371,
"per_source": {
"fineweb_edu": 3.1029034782858456,
"code_python": 1.7166805967435095,
"finemath_4plus": 1.0764821027610205,
"pes2o": 2.1814088821411133,
"pubmed": 2.2096216678619385,
"arxiv": 2.1525862216949463,
"pressbooks": 3.2339413166046143,
"libretexts": 2.4264528539257118,
"doab": 1.359528293795047,
"gutenberg": 2.8457701206207275,
"pre_1929_books": 3.0078492164611816,
"library_of_congress": 2.8027069568634033
},
"weighted_loss": 2.029184326844643,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 28000,
"tokens": 2178941820,
"per_source": {
"fineweb_edu": 3.11824894752823,
"code_python": 1.693618487543364,
"finemath_4plus": 1.0779619543466905,
"pes2o": 2.157956600189209,
"pubmed": 2.2109193801879883,
"arxiv": 2.142897129058838,
"pressbooks": 3.2777047157287598,
"libretexts": 2.436660060678937,
"doab": 1.370015291731269,
"gutenberg": 2.843493938446045,
"pre_1929_books": 2.9988186359405518,
"library_of_congress": 2.804917335510254
},
"weighted_loss": 2.0229550923558377,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 28500,
"tokens": 2218607198,
"per_source": {
"fineweb_edu": 3.1015776305639444,
"code_python": 1.6855704803603402,
"finemath_4plus": 1.0726298941342005,
"pes2o": 2.1794424057006836,
"pubmed": 2.213561773300171,
"arxiv": 2.150970220565796,
"pressbooks": 3.245640277862549,
"libretexts": 2.393175878558719,
"doab": 1.3544736907580457,
"gutenberg": 2.846172332763672,
"pre_1929_books": 3.0000531673431396,
"library_of_congress": 2.811691999435425
},
"weighted_loss": 2.017731914829952,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 29000,
"tokens": 2257090071,
"per_source": {
"fineweb_edu": 3.0978873116629466,
"code_python": 1.69661910040846,
"finemath_4plus": 1.0683736587734227,
"pes2o": 2.155510902404785,
"pubmed": 2.1941416263580322,
"arxiv": 2.1431467533111572,
"pressbooks": 3.271543264389038,
"libretexts": 2.3838516181049823,
"doab": 1.3606870410188987,
"gutenberg": 2.8392815589904785,
"pre_1929_books": 3.001729965209961,
"library_of_congress": 2.8166956901550293
},
"weighted_loss": 2.0173628414754083,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 29500,
"tokens": 2296491257,
"per_source": {
"fineweb_edu": 3.0933112136456145,
"code_python": 1.6924617156026187,
"finemath_4plus": 1.0674508085273995,
"pes2o": 2.1437807083129883,
"pubmed": 2.196408987045288,
"arxiv": 2.1384403705596924,
"pressbooks": 3.222057342529297,
"libretexts": 2.412862431536366,
"doab": 1.3543064016405464,
"gutenberg": 2.8345117568969727,
"pre_1929_books": 2.9943599700927734,
"library_of_congress": 2.794787645339966
},
"weighted_loss": 2.0119932100038116,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 30000,
"tokens": 2335025439,
"per_source": {
"fineweb_edu": 3.1017022653788078,
"code_python": 1.7220555154361572,
"finemath_4plus": 1.0676899465405096,
"pes2o": 2.13899564743042,
"pubmed": 2.196486711502075,
"arxiv": 2.1354305744171143,
"pressbooks": 3.2534995079040527,
"libretexts": 2.391641094167037,
"doab": 1.3521141284989944,
"gutenberg": 2.8441319465637207,
"pre_1929_books": 2.9813015460968018,
"library_of_congress": 2.7943806648254395
},
"weighted_loss": 2.020995556755094,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 30500,
"tokens": 2374631449,
"per_source": {
"fineweb_edu": 3.098443295775341,
"code_python": 1.6859239050609893,
"finemath_4plus": 1.0583931189336748,
"pes2o": 2.1354098320007324,
"pubmed": 2.1701037883758545,
"arxiv": 2.1255245208740234,
"pressbooks": 3.234025001525879,
"libretexts": 2.3885537144128115,
"doab": 1.338894605236968,
"gutenberg": 2.860114336013794,
"pre_1929_books": 2.981411933898926,
"library_of_congress": 2.8023815155029297
},
"weighted_loss": 2.006463855477737,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 31000,
"tokens": 2413385337,
"per_source": {
"fineweb_edu": 3.104532450187106,
"code_python": 1.6766096232934198,
"finemath_4plus": 1.0540302489510314,
"pes2o": 2.129478931427002,
"pubmed": 2.1854796409606934,
"arxiv": 2.122239589691162,
"pressbooks": 3.2273762226104736,
"libretexts": 2.376546296360654,
"doab": 1.353842673587831,
"gutenberg": 2.8274991512298584,
"pre_1929_books": 3.0004656314849854,
"library_of_congress": 2.7852399349212646
},
"weighted_loss": 2.002435388288014,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 31500,
"tokens": 2451801627,
"per_source": {
"fineweb_edu": 3.0852799615940127,
"code_python": 1.6879918876244964,
"finemath_4plus": 1.0510016940423632,
"pes2o": 2.11055850982666,
"pubmed": 2.18597674369812,
"arxiv": 2.1168558597564697,
"pressbooks": 3.2183430194854736,
"libretexts": 2.356458127710743,
"doab": 1.345923367179643,
"gutenberg": 2.8101255893707275,
"pre_1929_books": 2.9764208793640137,
"library_of_congress": 2.7822229862213135
},
"weighted_loss": 1.997501571457691,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 32000,
"tokens": 2490729507,
"per_source": {
"fineweb_edu": 3.098108115316439,
"code_python": 1.6547284378147382,
"finemath_4plus": 1.0622804116675655,
"pes2o": 2.129236936569214,
"pubmed": 2.1683127880096436,
"arxiv": 2.1169848442077637,
"pressbooks": 3.2480149269104004,
"libretexts": 2.363016474713634,
"doab": 1.3323213051039222,
"gutenberg": 2.824578285217285,
"pre_1929_books": 2.9697978496551514,
"library_of_congress": 2.772341251373291
},
"weighted_loss": 1.992906994921746,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 32500,
"tokens": 2529692648,
"per_source": {
"fineweb_edu": 3.072634143989627,
"code_python": 1.678096542426701,
"finemath_4plus": 1.0526421557992383,
"pes2o": 2.1234242916107178,
"pubmed": 2.188079833984375,
"arxiv": 2.1236040592193604,
"pressbooks": 3.2242345809936523,
"libretexts": 2.3696221728341857,
"doab": 1.3377354487931612,
"gutenberg": 2.8107316493988037,
"pre_1929_books": 2.9753589630126953,
"library_of_congress": 2.782198190689087
},
"weighted_loss": 1.995280489819874,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 33000,
"tokens": 2568916741,
"per_source": {
"fineweb_edu": 3.051138485179228,
"code_python": 1.6915585920014549,
"finemath_4plus": 1.0522391164228904,
"pes2o": 2.1221773624420166,
"pubmed": 2.177983283996582,
"arxiv": 2.1045944690704346,
"pressbooks": 3.192349672317505,
"libretexts": 2.366650129976646,
"doab": 1.3478521026703403,
"gutenberg": 2.809760570526123,
"pre_1929_books": 2.968367099761963,
"library_of_congress": 2.7817275524139404
},
"weighted_loss": 1.995088003806145,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 33500,
"tokens": 2607501841,
"per_source": {
"fineweb_edu": 3.0671368767233456,
"code_python": 1.6899489468512199,
"finemath_4plus": 1.0579045085644716,
"pes2o": 2.132530927658081,
"pubmed": 2.16310453414917,
"arxiv": 2.104154586791992,
"pressbooks": 3.201134443283081,
"libretexts": 2.3855603852730205,
"doab": 1.3351567083263494,
"gutenberg": 2.824979305267334,
"pre_1929_books": 2.97086763381958,
"library_of_congress": 2.7710161209106445
},
"weighted_loss": 1.9988558904145115,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 34000,
"tokens": 2646452373,
"per_source": {
"fineweb_edu": 3.0225745449547006,
"code_python": 1.6653979514044315,
"finemath_4plus": 1.0470374532387436,
"pes2o": 2.117297887802124,
"pubmed": 2.156602144241333,
"arxiv": 2.1042356491088867,
"pressbooks": 3.218111038208008,
"libretexts": 2.33702244877391,
"doab": 1.3247998423357359,
"gutenberg": 2.787280559539795,
"pre_1929_books": 2.9674582481384277,
"library_of_congress": 2.775240421295166
},
"weighted_loss": 1.9797862129425998,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 34500,
"tokens": 2685106743,
"per_source": {
"fineweb_edu": 3.0781975754168855,
"code_python": 1.6346656300707811,
"finemath_4plus": 1.0506879117939472,
"pes2o": 2.1089463233947754,
"pubmed": 2.1594111919403076,
"arxiv": 2.104891777038574,
"pressbooks": 3.2280871868133545,
"libretexts": 2.3579223198398576,
"doab": 1.3341763810027656,
"gutenberg": 2.789391279220581,
"pre_1929_books": 2.970019578933716,
"library_of_congress": 2.763007164001465
},
"weighted_loss": 1.9773403224063106,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 35000,
"tokens": 2723741035,
"per_source": {
"fineweb_edu": 3.044505912716649,
"code_python": 1.6614937778018688,
"finemath_4plus": 1.0455805741734632,
"pes2o": 2.1151816844940186,
"pubmed": 2.1554932594299316,
"arxiv": 2.1116139888763428,
"pressbooks": 3.226383686065674,
"libretexts": 2.3139448607095194,
"doab": 1.3302705402227204,
"gutenberg": 2.8020737171173096,
"pre_1929_books": 2.9596166610717773,
"library_of_congress": 2.763864278793335
},
"weighted_loss": 1.9800435439635993,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 35500,
"tokens": 2763615078,
"per_source": {
"fineweb_edu": 3.0584437266117384,
"code_python": 1.652748866068431,
"finemath_4plus": 1.0337699999157455,
"pes2o": 2.108412504196167,
"pubmed": 2.159353494644165,
"arxiv": 2.1068265438079834,
"pressbooks": 3.1798598766326904,
"libretexts": 2.3442135196563614,
"doab": 1.3245471080916862,
"gutenberg": 2.792383909225464,
"pre_1929_books": 2.960893392562866,
"library_of_congress": 2.772284984588623
},
"weighted_loss": 1.974935787290625,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 36000,
"tokens": 2804053534,
"per_source": {
"fineweb_edu": 3.0642715582326683,
"code_python": 1.6277526472974486,
"finemath_4plus": 1.0424002953120788,
"pes2o": 2.117945432662964,
"pubmed": 2.153947353363037,
"arxiv": 2.0975425243377686,
"pressbooks": 3.2020974159240723,
"libretexts": 2.340828566364546,
"doab": 1.311357539730347,
"gutenberg": 2.7929720878601074,
"pre_1929_books": 2.9494848251342773,
"library_of_congress": 2.7343177795410156
},
"weighted_loss": 1.9684809800253678,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 36500,
"tokens": 2843111028,
"per_source": {
"fineweb_edu": 3.0382472446986606,
"code_python": 1.592299800316137,
"finemath_4plus": 1.0375217613617216,
"pes2o": 2.111408233642578,
"pubmed": 2.1443421840667725,
"arxiv": 2.096784830093384,
"pressbooks": 3.2140626907348633,
"libretexts": 2.3584286292676824,
"doab": 1.3229552424677338,
"gutenberg": 2.798187494277954,
"pre_1929_books": 2.9272966384887695,
"library_of_congress": 2.7519896030426025
},
"weighted_loss": 1.9538985791233556,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 37000,
"tokens": 2881338950,
"per_source": {
"fineweb_edu": 3.0480567226890756,
"code_python": 1.6372640775374887,
"finemath_4plus": 1.0333134457569426,
"pes2o": 2.104680061340332,
"pubmed": 2.1475040912628174,
"arxiv": 2.089243173599243,
"pressbooks": 3.185199737548828,
"libretexts": 2.3664133743883453,
"doab": 1.320992050656847,
"gutenberg": 2.7903196811676025,
"pre_1929_books": 2.9277169704437256,
"library_of_congress": 2.7386457920074463
},
"weighted_loss": 1.9653291981594987,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 37500,
"tokens": 2920269010,
"per_source": {
"fineweb_edu": 3.0355383608521533,
"code_python": 1.6099338787628692,
"finemath_4plus": 1.0366418282598073,
"pes2o": 2.1044018268585205,
"pubmed": 2.1402487754821777,
"arxiv": 2.0731191635131836,
"pressbooks": 3.1893911361694336,
"libretexts": 2.348109778136121,
"doab": 1.3108064022952983,
"gutenberg": 2.7701995372772217,
"pre_1929_books": 2.918447732925415,
"library_of_congress": 2.7269115447998047
},
"weighted_loss": 1.9531383426202313,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 38000,
"tokens": 2959349262,
"per_source": {
"fineweb_edu": 3.021271521303834,
"code_python": 1.6033476553757273,
"finemath_4plus": 1.047117034262099,
"pes2o": 2.1059911251068115,
"pubmed": 2.1311309337615967,
"arxiv": 2.0867958068847656,
"pressbooks": 3.2062020301818848,
"libretexts": 2.3255491426406807,
"doab": 1.3173849404437648,
"gutenberg": 2.7687840461730957,
"pre_1929_books": 2.938527822494507,
"library_of_congress": 2.7377448081970215
},
"weighted_loss": 1.9537402391883543,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 38500,
"tokens": 2998507670,
"per_source": {
"fineweb_edu": 3.0350226394268645,
"code_python": 1.64243671140611,
"finemath_4plus": 1.0246992772015706,
"pes2o": 2.1035001277923584,
"pubmed": 2.1243863105773926,
"arxiv": 2.082515001296997,
"pressbooks": 3.1682322025299072,
"libretexts": 2.336650373248443,
"doab": 1.315215992839633,
"gutenberg": 2.765085458755493,
"pre_1929_books": 2.918797492980957,
"library_of_congress": 2.7248313426971436
},
"weighted_loss": 1.958975189641623,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 39000,
"tokens": 3037264299,
"per_source": {
"fineweb_edu": 3.0151141511292017,
"code_python": 1.6213128645716763,
"finemath_4plus": 1.0206240574026018,
"pes2o": 2.090089797973633,
"pubmed": 2.119985580444336,
"arxiv": 2.073064088821411,
"pressbooks": 3.2051093578338623,
"libretexts": 2.3397214624805382,
"doab": 1.2962328520470163,
"gutenberg": 2.7360119819641113,
"pre_1929_books": 2.9196465015411377,
"library_of_congress": 2.735816717147827
},
"weighted_loss": 1.9475445093638977,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 39500,
"tokens": 3074885979,
"per_source": {
"fineweb_edu": 2.9978724888392856,
"code_python": 1.6088437701082698,
"finemath_4plus": 1.0261514169503236,
"pes2o": 2.084735870361328,
"pubmed": 2.1228549480438232,
"arxiv": 2.077451229095459,
"pressbooks": 3.155363082885742,
"libretexts": 2.314422716025356,
"doab": 1.3054777855766007,
"gutenberg": 2.749058961868286,
"pre_1929_books": 2.919694423675537,
"library_of_congress": 2.7104551792144775
},
"weighted_loss": 1.940836821883364,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 40000,
"tokens": 3113522245,
"per_source": {
"fineweb_edu": 3.0264330952107406,
"code_python": 1.6121616346449754,
"finemath_4plus": 1.0305736600372406,
"pes2o": 2.0834128856658936,
"pubmed": 2.1167728900909424,
"arxiv": 2.067058563232422,
"pressbooks": 3.1550958156585693,
"libretexts": 2.2959210270240216,
"doab": 1.3076707134700805,
"gutenberg": 2.738896131515503,
"pre_1929_books": 2.901811122894287,
"library_of_congress": 2.7013981342315674
},
"weighted_loss": 1.942543041480584,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 40500,
"tokens": 3152812263,
"per_source": {
"fineweb_edu": 3.0296618036863183,
"code_python": 1.5880058104157342,
"finemath_4plus": 1.0224108455572594,
"pes2o": 2.078770875930786,
"pubmed": 2.1145856380462646,
"arxiv": 2.0606751441955566,
"pressbooks": 3.159649610519409,
"libretexts": 2.298191708602091,
"doab": 1.2999724676814448,
"gutenberg": 2.742525577545166,
"pre_1929_books": 2.9132940769195557,
"library_of_congress": 2.7157139778137207
},
"weighted_loss": 1.9346406741001232,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 41000,
"tokens": 3190900721,
"per_source": {
"fineweb_edu": 3.0399031438747373,
"code_python": 1.596607450725996,
"finemath_4plus": 1.0192616355486654,
"pes2o": 2.0656633377075195,
"pubmed": 2.1193387508392334,
"arxiv": 2.070668935775757,
"pressbooks": 3.171966075897217,
"libretexts": 2.3036827005949734,
"doab": 1.3055692871584814,
"gutenberg": 2.7521541118621826,
"pre_1929_books": 2.9076027870178223,
"library_of_congress": 2.7122769355773926
},
"weighted_loss": 1.9373851952592331,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 41500,
"tokens": 3229714172,
"per_source": {
"fineweb_edu": 2.9969487550879728,
"code_python": 1.5907666540188563,
"finemath_4plus": 1.0214529770280063,
"pes2o": 2.0653300285339355,
"pubmed": 2.1061391830444336,
"arxiv": 2.061556577682495,
"pressbooks": 3.1683568954467773,
"libretexts": 2.2947476750166813,
"doab": 1.3039529501812352,
"gutenberg": 2.735743522644043,
"pre_1929_books": 2.910244941711426,
"library_of_congress": 2.7024121284484863
},
"weighted_loss": 1.9297917180450415,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 42000,
"tokens": 3269746474,
"per_source": {
"fineweb_edu": 3.008285137785583,
"code_python": 1.6070554454943486,
"finemath_4plus": 1.0223380443894918,
"pes2o": 2.0764307975769043,
"pubmed": 2.1160688400268555,
"arxiv": 2.0582292079925537,
"pressbooks": 3.1646132469177246,
"libretexts": 2.2873055128864546,
"doab": 1.3000320501068554,
"gutenberg": 2.7292559146881104,
"pre_1929_books": 2.906045436859131,
"library_of_congress": 2.6898374557495117
},
"weighted_loss": 1.935842430208538,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 42500,
"tokens": 3308719895,
"per_source": {
"fineweb_edu": 2.9948591985622373,
"code_python": 1.6072341249580349,
"finemath_4plus": 1.0290732055894445,
"pes2o": 2.0597755908966064,
"pubmed": 2.114020824432373,
"arxiv": 2.056424140930176,
"pressbooks": 3.15316104888916,
"libretexts": 2.2836594768266236,
"doab": 1.3104282830571152,
"gutenberg": 2.7371933460235596,
"pre_1929_books": 2.909721612930298,
"library_of_congress": 2.709127426147461
},
"weighted_loss": 1.935333215187239,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 43000,
"tokens": 3348279002,
"per_source": {
"fineweb_edu": 3.019291469029018,
"code_python": 1.5726647304442705,
"finemath_4plus": 1.0216972493006875,
"pes2o": 2.053337335586548,
"pubmed": 2.1124749183654785,
"arxiv": 2.0578315258026123,
"pressbooks": 3.1577529907226562,
"libretexts": 2.283666210242438,
"doab": 1.309120416081755,
"gutenberg": 2.7258479595184326,
"pre_1929_books": 2.893749475479126,
"library_of_congress": 2.6901278495788574
},
"weighted_loss": 1.923098716941041,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 43500,
"tokens": 3387037346,
"per_source": {
"fineweb_edu": 3.0111112193901,
"code_python": 1.6112283486389325,
"finemath_4plus": 1.0092173782311606,
"pes2o": 2.052372455596924,
"pubmed": 2.106574535369873,
"arxiv": 2.05743408203125,
"pressbooks": 3.152493476867676,
"libretexts": 2.295705123304048,
"doab": 1.3072508537965135,
"gutenberg": 2.7303879261016846,
"pre_1929_books": 2.904883861541748,
"library_of_congress": 2.7053699493408203
},
"weighted_loss": 1.9326646226885789,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 44000,
"tokens": 3426626574,
"per_source": {
"fineweb_edu": 3.0232615751378678,
"code_python": 1.6142767186450873,
"finemath_4plus": 1.013934709595747,
"pes2o": 2.0463366508483887,
"pubmed": 2.111333131790161,
"arxiv": 2.0536038875579834,
"pressbooks": 3.1413965225219727,
"libretexts": 2.2818014884758675,
"doab": 1.3004039492017265,
"gutenberg": 2.7241744995117188,
"pre_1929_books": 2.8943052291870117,
"library_of_congress": 2.701125144958496
},
"weighted_loss": 1.9329977954816016,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 44500,
"tokens": 3465401696,
"per_source": {
"fineweb_edu": 2.987875545726103,
"code_python": 1.6178917265834825,
"finemath_4plus": 1.0102886612378674,
"pes2o": 2.045403480529785,
"pubmed": 2.098811388015747,
"arxiv": 2.0463454723358154,
"pressbooks": 3.172196626663208,
"libretexts": 2.2618471193143908,
"doab": 1.2863743341172897,
"gutenberg": 2.706678867340088,
"pre_1929_books": 2.886965751647949,
"library_of_congress": 2.692286968231201
},
"weighted_loss": 1.9273108447087122,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 45000,
"tokens": 3505576750,
"per_source": {
"fineweb_edu": 2.988297662815126,
"code_python": 1.6077501643632497,
"finemath_4plus": 1.0122092034367418,
"pes2o": 2.0385587215423584,
"pubmed": 2.0955381393432617,
"arxiv": 2.0327322483062744,
"pressbooks": 3.1708600521087646,
"libretexts": 2.2772722889095864,
"doab": 1.2915958170518353,
"gutenberg": 2.7220659255981445,
"pre_1929_books": 2.88950777053833,
"library_of_congress": 2.688689947128296
},
"weighted_loss": 1.9251106591225582,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 45500,
"tokens": 3544003975,
"per_source": {
"fineweb_edu": 2.9786802660517333,
"code_python": 1.597408065864201,
"finemath_4plus": 1.006723773675519,
"pes2o": 2.042379856109619,
"pubmed": 2.093881368637085,
"arxiv": 2.038701057434082,
"pressbooks": 3.1330010890960693,
"libretexts": 2.282208534322175,
"doab": 1.293476346431864,
"gutenberg": 2.7033514976501465,
"pre_1929_books": 2.8779959678649902,
"library_of_congress": 2.6925430297851562
},
"weighted_loss": 1.9178625750047267,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 46000,
"tokens": 3582437673,
"per_source": {
"fineweb_edu": 2.9777655080586922,
"code_python": 1.5914234513135073,
"finemath_4plus": 1.0168956634200592,
"pes2o": 2.0407822132110596,
"pubmed": 2.090282678604126,
"arxiv": 2.02995228767395,
"pressbooks": 3.1352667808532715,
"libretexts": 2.267103310581628,
"doab": 1.2943670545853587,
"gutenberg": 2.728991985321045,
"pre_1929_books": 2.8805582523345947,
"library_of_congress": 2.690157890319824
},
"weighted_loss": 1.918607664882172,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 46500,
"tokens": 3620875828,
"per_source": {
"fineweb_edu": 2.9836989971769956,
"code_python": 1.5629991003734893,
"finemath_4plus": 1.0083133536035656,
"pes2o": 2.0496747493743896,
"pubmed": 2.094560146331787,
"arxiv": 2.029087781906128,
"pressbooks": 3.1419410705566406,
"libretexts": 2.273836726395685,
"doab": 1.2975777125062855,
"gutenberg": 2.713489294052124,
"pre_1929_books": 2.89003586769104,
"library_of_congress": 2.6777610778808594
},
"weighted_loss": 1.9100045857022006,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 47000,
"tokens": 3659070217,
"per_source": {
"fineweb_edu": 2.987820665375525,
"code_python": 1.5509768684954117,
"finemath_4plus": 1.0086587971193381,
"pes2o": 2.049764394760132,
"pubmed": 2.0830423831939697,
"arxiv": 2.0287392139434814,
"pressbooks": 3.1325247287750244,
"libretexts": 2.2584825834769795,
"doab": 1.287508364455875,
"gutenberg": 2.7062764167785645,
"pre_1929_books": 2.8719329833984375,
"library_of_congress": 2.6775529384613037
},
"weighted_loss": 1.9037556535371987,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 47500,
"tokens": 3697839703,
"per_source": {
"fineweb_edu": 2.9579313903295694,
"code_python": 1.5530246335049238,
"finemath_4plus": 1.0051965289245754,
"pes2o": 2.036105155944824,
"pubmed": 2.090127468109131,
"arxiv": 2.0306756496429443,
"pressbooks": 3.1469333171844482,
"libretexts": 2.265679084533474,
"doab": 1.2783257960473935,
"gutenberg": 2.714803457260132,
"pre_1929_books": 2.8816757202148438,
"library_of_congress": 2.6825075149536133
},
"weighted_loss": 1.9011117901200518,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 48000,
"tokens": 3736760393,
"per_source": {
"fineweb_edu": 2.967810879234506,
"code_python": 1.5527744822557632,
"finemath_4plus": 1.0088392202665812,
"pes2o": 2.045091152191162,
"pubmed": 2.0803418159484863,
"arxiv": 2.0227174758911133,
"pressbooks": 3.1109724044799805,
"libretexts": 2.2596161866103204,
"doab": 1.2834385901619594,
"gutenberg": 2.7177932262420654,
"pre_1929_books": 2.871385097503662,
"library_of_congress": 2.6750173568725586
},
"weighted_loss": 1.9013473360516127,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 48500,
"tokens": 3776468585,
"per_source": {
"fineweb_edu": 2.9612565240940127,
"code_python": 1.5620835183877015,
"finemath_4plus": 1.004246559256201,
"pes2o": 2.039208173751831,
"pubmed": 2.087571859359741,
"arxiv": 2.0270135402679443,
"pressbooks": 3.100381851196289,
"libretexts": 2.2543339305076735,
"doab": 1.285293502372821,
"gutenberg": 2.7007815837860107,
"pre_1929_books": 2.8757965564727783,
"library_of_congress": 2.6871213912963867
},
"weighted_loss": 1.9016999571656046,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 49000,
"tokens": 3814795559,
"per_source": {
"fineweb_edu": 2.944382098542542,
"code_python": 1.5740049903480304,
"finemath_4plus": 0.999643695550519,
"pes2o": 2.0403778553009033,
"pubmed": 2.084845781326294,
"arxiv": 2.0252697467803955,
"pressbooks": 3.1253771781921387,
"libretexts": 2.2506199086688166,
"doab": 1.2895421057869594,
"gutenberg": 2.7065510749816895,
"pre_1929_books": 2.8710777759552,
"library_of_congress": 2.6717000007629395
},
"weighted_loss": 1.902972594900398,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 49500,
"tokens": 3853419148,
"per_source": {
"fineweb_edu": 2.9590269457392333,
"code_python": 1.5983114080335161,
"finemath_4plus": 1.0006353975338702,
"pes2o": 2.027620792388916,
"pubmed": 2.0766212940216064,
"arxiv": 2.0161662101745605,
"pressbooks": 3.1335315704345703,
"libretexts": 2.2417552581461297,
"doab": 1.285827779945734,
"gutenberg": 2.701399564743042,
"pre_1929_books": 2.8685643672943115,
"library_of_congress": 2.6766157150268555
},
"weighted_loss": 1.9097669102075931,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 50000,
"tokens": 3891887182,
"per_source": {
"fineweb_edu": 2.9664596429392067,
"code_python": 1.603377380644304,
"finemath_4plus": 0.9981175698048665,
"pes2o": 2.0287020206451416,
"pubmed": 2.0748515129089355,
"arxiv": 2.0193557739257812,
"pressbooks": 3.1396472454071045,
"libretexts": 2.2261104923126114,
"doab": 1.2807917554946782,
"gutenberg": 2.68536376953125,
"pre_1929_books": 2.859271764755249,
"library_of_congress": 2.66851544380188
},
"weighted_loss": 1.909462633053348,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 50403,
"tokens": 3923645749,
"per_source": {
"fineweb_edu": 2.949349796070772,
"code_python": 1.5737558226555506,
"finemath_4plus": 0.9995966315044487,
"pes2o": 2.027310371398926,
"pubmed": 2.0710272789001465,
"arxiv": 2.0190863609313965,
"pressbooks": 3.1382837295532227,
"libretexts": 2.230359494898243,
"doab": 1.2815076448835065,
"gutenberg": 2.69559907913208,
"pre_1929_books": 2.8595340251922607,
"library_of_congress": 2.6590516567230225
},
"weighted_loss": 1.8992631233807942,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 50500,
"tokens": 3931044166,
"per_source": {
"fineweb_edu": 2.960360486968225,
"code_python": 1.5783419288901634,
"finemath_4plus": 0.9942097400326908,
"pes2o": 2.0286741256713867,
"pubmed": 2.072269916534424,
"arxiv": 2.0118539333343506,
"pressbooks": 3.144930601119995,
"libretexts": 2.2429859527913703,
"doab": 1.2818791347584226,
"gutenberg": 2.6898574829101562,
"pre_1929_books": 2.870680093765259,
"library_of_congress": 2.6617014408111572
},
"weighted_loss": 1.9018573500413565,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 51000,
"tokens": 3969319072,
"per_source": {
"fineweb_edu": 2.943423487559086,
"code_python": 1.5982723936185095,
"finemath_4plus": 0.9961785311067674,
"pes2o": 2.0270535945892334,
"pubmed": 2.074352264404297,
"arxiv": 2.019926071166992,
"pressbooks": 3.154388427734375,
"libretexts": 2.2336990519350532,
"doab": 1.2784105045780254,
"gutenberg": 2.6948399543762207,
"pre_1929_books": 2.856677532196045,
"library_of_congress": 2.6683900356292725
},
"weighted_loss": 1.9059343924918233,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 51500,
"tokens": 4007872075,
"per_source": {
"fineweb_edu": 2.946484734030331,
"code_python": 1.615453271003525,
"finemath_4plus": 0.9946329873281208,
"pes2o": 2.0195069313049316,
"pubmed": 2.0804672241210938,
"arxiv": 2.0148000717163086,
"pressbooks": 3.1001694202423096,
"libretexts": 2.2315365394239324,
"doab": 1.283014883820818,
"gutenberg": 2.687328815460205,
"pre_1929_books": 2.8493192195892334,
"library_of_congress": 2.656096935272217
},
"weighted_loss": 1.90764523180341,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 52000,
"tokens": 4047916378,
"per_source": {
"fineweb_edu": 2.943156009962579,
"code_python": 1.5815723661663497,
"finemath_4plus": 0.9956445022875101,
"pes2o": 2.0164499282836914,
"pubmed": 2.066169261932373,
"arxiv": 2.018613576889038,
"pressbooks": 3.109703540802002,
"libretexts": 2.2327913440419263,
"doab": 1.2733683418276482,
"gutenberg": 2.6883111000061035,
"pre_1929_books": 2.8471858501434326,
"library_of_congress": 2.6604878902435303
},
"weighted_loss": 1.896661334963861,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 52500,
"tokens": 4085799363,
"per_source": {
"fineweb_edu": 2.93925950507156,
"code_python": 1.5939723930939458,
"finemath_4plus": 0.9923327732163318,
"pes2o": 2.0171456336975098,
"pubmed": 2.075166940689087,
"arxiv": 2.00490403175354,
"pressbooks": 3.1086196899414062,
"libretexts": 2.2390529863350754,
"doab": 1.267857458541108,
"gutenberg": 2.6819143295288086,
"pre_1929_books": 2.8509654998779297,
"library_of_congress": 2.6598076820373535
},
"weighted_loss": 1.8992538858630552,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 53000,
"tokens": 4125025171,
"per_source": {
"fineweb_edu": 2.922544078666623,
"code_python": 1.5664358659845008,
"finemath_4plus": 0.9905642182655365,
"pes2o": 2.01765775680542,
"pubmed": 2.0689287185668945,
"arxiv": 1.9952750205993652,
"pressbooks": 3.128915548324585,
"libretexts": 2.2437101208018237,
"doab": 1.2674399723432785,
"gutenberg": 2.683368444442749,
"pre_1929_books": 2.8387534618377686,
"library_of_congress": 2.6462442874908447
},
"weighted_loss": 1.888182011107686,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 53500,
"tokens": 4163956427,
"per_source": {
"fineweb_edu": 2.935108345095851,
"code_python": 1.589088269185038,
"finemath_4plus": 0.9837558609547722,
"pes2o": 2.006471872329712,
"pubmed": 2.0647568702697754,
"arxiv": 2.003195285797119,
"pressbooks": 3.097538471221924,
"libretexts": 2.2415884431995106,
"doab": 1.268671069655129,
"gutenberg": 2.6978330612182617,
"pre_1929_books": 2.8474364280700684,
"library_of_congress": 2.658670663833618
},
"weighted_loss": 1.8945352596727325,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 54000,
"tokens": 4202252839,
"per_source": {
"fineweb_edu": 2.930043965828519,
"code_python": 1.5926141013177038,
"finemath_4plus": 0.9919394757684011,
"pes2o": 2.0054235458374023,
"pubmed": 2.0572168827056885,
"arxiv": 2.0032174587249756,
"pressbooks": 3.1442461013793945,
"libretexts": 2.2326466842054047,
"doab": 1.2727536934556236,
"gutenberg": 2.674293279647827,
"pre_1929_books": 2.849240779876709,
"library_of_congress": 2.6435861587524414
},
"weighted_loss": 1.8961857670133568,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 54500,
"tokens": 4241217001,
"per_source": {
"fineweb_edu": 2.9333721769957983,
"code_python": 1.5780594295546106,
"finemath_4plus": 0.9915933081903815,
"pes2o": 2.003685474395752,
"pubmed": 2.056598663330078,
"arxiv": 1.9997072219848633,
"pressbooks": 3.1203930377960205,
"libretexts": 2.2314329317031807,
"doab": 1.2719412281574758,
"gutenberg": 2.668272018432617,
"pre_1929_books": 2.836702346801758,
"library_of_congress": 2.642357587814331
},
"weighted_loss": 1.889820281026673,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 55000,
"tokens": 4281063644,
"per_source": {
"fineweb_edu": 2.949059750853466,
"code_python": 1.5654797396066473,
"finemath_4plus": 0.988482473480891,
"pes2o": 2.012335777282715,
"pubmed": 2.0489635467529297,
"arxiv": 2.0005264282226562,
"pressbooks": 3.1427664756774902,
"libretexts": 2.246391975158474,
"doab": 1.2726517158429014,
"gutenberg": 2.667894124984741,
"pre_1929_books": 2.8502907752990723,
"library_of_congress": 2.651327133178711
},
"weighted_loss": 1.88999510103316,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 55500,
"tokens": 4320074786,
"per_source": {
"fineweb_edu": 2.9429003290769433,
"code_python": 1.5557220923441697,
"finemath_4plus": 0.9852103703617889,
"pes2o": 2.0085551738739014,
"pubmed": 2.0513741970062256,
"arxiv": 1.996988296508789,
"pressbooks": 3.1293859481811523,
"libretexts": 2.2275179934247107,
"doab": 1.2674847410063275,
"gutenberg": 2.6694235801696777,
"pre_1929_books": 2.845364570617676,
"library_of_congress": 2.6472034454345703
},
"weighted_loss": 1.883854554114243,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 56000,
"tokens": 4358314767,
"per_source": {
"fineweb_edu": 2.928751713087579,
"code_python": 1.5439454217840756,
"finemath_4plus": 0.9881705343000134,
"pes2o": 2.013885021209717,
"pubmed": 2.0513722896575928,
"arxiv": 1.9993882179260254,
"pressbooks": 3.1122119426727295,
"libretexts": 2.2190169473559833,
"doab": 1.2707864094451895,
"gutenberg": 2.6691343784332275,
"pre_1929_books": 2.842271566390991,
"library_of_congress": 2.649552345275879
},
"weighted_loss": 1.8792809618791793,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 56500,
"tokens": 4397961347,
"per_source": {
"fineweb_edu": 2.9451647846638656,
"code_python": 1.5550242042370748,
"finemath_4plus": 0.9863063373087423,
"pes2o": 2.0087850093841553,
"pubmed": 2.044990301132202,
"arxiv": 1.9970510005950928,
"pressbooks": 3.102025270462036,
"libretexts": 2.212477931772687,
"doab": 1.2642253040667952,
"gutenberg": 2.6712806224823,
"pre_1929_books": 2.854702949523926,
"library_of_congress": 2.650137424468994
},
"weighted_loss": 1.883355705738114,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 57000,
"tokens": 4436712815,
"per_source": {
"fineweb_edu": 2.9350878290769433,
"code_python": 1.5484022449571957,
"finemath_4plus": 0.9842350585147613,
"pes2o": 2.0058093070983887,
"pubmed": 2.041165828704834,
"arxiv": 1.998108983039856,
"pressbooks": 3.1159861087799072,
"libretexts": 2.2184122431744884,
"doab": 1.2683512233385015,
"gutenberg": 2.659032106399536,
"pre_1929_books": 2.8430590629577637,
"library_of_congress": 2.6393845081329346
},
"weighted_loss": 1.8785678277927664,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 57500,
"tokens": 4475614611,
"per_source": {
"fineweb_edu": 2.9366434562106094,
"code_python": 1.5590341648248658,
"finemath_4plus": 0.9867276098889526,
"pes2o": 2.0104308128356934,
"pubmed": 2.0450375080108643,
"arxiv": 1.997819185256958,
"pressbooks": 3.111299514770508,
"libretexts": 2.220621672389346,
"doab": 1.2658234716780505,
"gutenberg": 2.661203384399414,
"pre_1929_books": 2.843355178833008,
"library_of_congress": 2.6397907733917236
},
"weighted_loss": 1.8829500366972962,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 58000,
"tokens": 4514528500,
"per_source": {
"fineweb_edu": 2.9339245708048844,
"code_python": 1.5445807993998992,
"finemath_4plus": 0.9856700182411027,
"pes2o": 2.008680582046509,
"pubmed": 2.0447473526000977,
"arxiv": 1.994388222694397,
"pressbooks": 3.102419853210449,
"libretexts": 2.2108480107317616,
"doab": 1.266800688929978,
"gutenberg": 2.668614387512207,
"pre_1929_books": 2.8355906009674072,
"library_of_congress": 2.6415798664093018
},
"weighted_loss": 1.8772384646962939,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 58500,
"tokens": 4552849091,
"per_source": {
"fineweb_edu": 2.9356894613314077,
"code_python": 1.5485936013736572,
"finemath_4plus": 0.984946021817707,
"pes2o": 2.001271963119507,
"pubmed": 2.044247627258301,
"arxiv": 1.9952765703201294,
"pressbooks": 3.0883216857910156,
"libretexts": 2.198041271060387,
"doab": 1.2685744119018187,
"gutenberg": 2.6679489612579346,
"pre_1929_books": 2.8303987979888916,
"library_of_congress": 2.636129856109619
},
"weighted_loss": 1.8764395122319042,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 59000,
"tokens": 4591589393,
"per_source": {
"fineweb_edu": 2.934203845112264,
"code_python": 1.5596745695081693,
"finemath_4plus": 0.984537189943381,
"pes2o": 2.0044071674346924,
"pubmed": 2.040489912033081,
"arxiv": 1.9907217025756836,
"pressbooks": 3.1076765060424805,
"libretexts": 2.212436228036032,
"doab": 1.2645768240079198,
"gutenberg": 2.6521592140197754,
"pre_1929_books": 2.821898937225342,
"library_of_congress": 2.6311306953430176
},
"weighted_loss": 1.8789613036580541,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 59500,
"tokens": 4630683709,
"per_source": {
"fineweb_edu": 2.919700814896271,
"code_python": 1.555321784775067,
"finemath_4plus": 0.9839543856581963,
"pes2o": 2.0014615058898926,
"pubmed": 2.036778450012207,
"arxiv": 1.98920738697052,
"pressbooks": 3.113809585571289,
"libretexts": 2.2066196428074956,
"doab": 1.2595607694906554,
"gutenberg": 2.6603782176971436,
"pre_1929_books": 2.8247132301330566,
"library_of_congress": 2.6271607875823975
},
"weighted_loss": 1.875950114135185,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 60000,
"tokens": 4669735636,
"per_source": {
"fineweb_edu": 2.9216349625787816,
"code_python": 1.5571375396919762,
"finemath_4plus": 0.9818498658246833,
"pes2o": 2.0047519207000732,
"pubmed": 2.0341224670410156,
"arxiv": 1.9845623970031738,
"pressbooks": 3.1188762187957764,
"libretexts": 2.2073944200400355,
"doab": 1.2667731893490195,
"gutenberg": 2.6631383895874023,
"pre_1929_books": 2.817103624343872,
"library_of_congress": 2.6247668266296387
},
"weighted_loss": 1.8764210700730743,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 60500,
"tokens": 4709137391,
"per_source": {
"fineweb_edu": 2.9261954171316966,
"code_python": 1.5422623377350044,
"finemath_4plus": 0.9836645632877797,
"pes2o": 2.005618095397949,
"pubmed": 2.04032564163208,
"arxiv": 1.9868124723434448,
"pressbooks": 3.104785442352295,
"libretexts": 2.202401049196508,
"doab": 1.264988171906428,
"gutenberg": 2.6542341709136963,
"pre_1929_books": 2.8210315704345703,
"library_of_congress": 2.6225693225860596
},
"weighted_loss": 1.8722151037032608,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 61000,
"tokens": 4747919581,
"per_source": {
"fineweb_edu": 2.9111328125,
"code_python": 1.553325164712959,
"finemath_4plus": 0.9841929970805811,
"pes2o": 1.9972466230392456,
"pubmed": 2.0361483097076416,
"arxiv": 1.984036922454834,
"pressbooks": 3.1018166542053223,
"libretexts": 2.2111038805326957,
"doab": 1.2601409615424908,
"gutenberg": 2.6556344032287598,
"pre_1929_books": 2.815495252609253,
"library_of_congress": 2.623640298843384
},
"weighted_loss": 1.8728081314374818,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 61500,
"tokens": 4786499880,
"per_source": {
"fineweb_edu": 2.9316116461232933,
"code_python": 1.5386350899801364,
"finemath_4plus": 0.9810316096614654,
"pes2o": 1.9951753616333008,
"pubmed": 2.038236618041992,
"arxiv": 1.9865037202835083,
"pressbooks": 3.1156978607177734,
"libretexts": 2.2306935592054047,
"doab": 1.2616806107002179,
"gutenberg": 2.655083417892456,
"pre_1929_books": 2.819335460662842,
"library_of_congress": 2.624812602996826
},
"weighted_loss": 1.8710637209055538,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 62000,
"tokens": 4825829325,
"per_source": {
"fineweb_edu": 2.927432276621586,
"code_python": 1.550826384323243,
"finemath_4plus": 0.9849801843910083,
"pes2o": 1.994505524635315,
"pubmed": 2.0372862815856934,
"arxiv": 1.98847234249115,
"pressbooks": 3.1064300537109375,
"libretexts": 2.2117863448064945,
"doab": 1.2648246476125127,
"gutenberg": 2.649616003036499,
"pre_1929_books": 2.818669080734253,
"library_of_congress": 2.6153526306152344
},
"weighted_loss": 1.8737134601799617,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 62500,
"tokens": 4865116783,
"per_source": {
"fineweb_edu": 2.9309271804424895,
"code_python": 1.5528878098422112,
"finemath_4plus": 0.9801978848956929,
"pes2o": 1.9985626935958862,
"pubmed": 2.033087730407715,
"arxiv": 1.985505223274231,
"pressbooks": 3.111314296722412,
"libretexts": 2.207998472600645,
"doab": 1.2600739313139038,
"gutenberg": 2.6560091972351074,
"pre_1929_books": 2.817943572998047,
"library_of_congress": 2.6253323554992676
},
"weighted_loss": 1.8743564646822002,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 63000,
"tokens": 4903585750,
"per_source": {
"fineweb_edu": 2.921711897649685,
"code_python": 1.5481201827579454,
"finemath_4plus": 0.9792793131993125,
"pes2o": 1.995309829711914,
"pubmed": 2.0359373092651367,
"arxiv": 1.986189603805542,
"pressbooks": 3.0952982902526855,
"libretexts": 2.2161663231900577,
"doab": 1.26186713315559,
"gutenberg": 2.659075975418091,
"pre_1929_books": 2.819981575012207,
"library_of_congress": 2.621986150741577
},
"weighted_loss": 1.8716267188309832,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 63500,
"tokens": 4942445032,
"per_source": {
"fineweb_edu": 2.9171370818835345,
"code_python": 1.555663734647773,
"finemath_4plus": 0.976485551930271,
"pes2o": 1.9950882196426392,
"pubmed": 2.0371034145355225,
"arxiv": 1.9892115592956543,
"pressbooks": 3.1143569946289062,
"libretexts": 2.2098156260425936,
"doab": 1.2554183995767683,
"gutenberg": 2.6655731201171875,
"pre_1929_books": 2.8155829906463623,
"library_of_congress": 2.625032901763916
},
"weighted_loss": 1.8731784615622202,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 64000,
"tokens": 4981948450,
"per_source": {
"fineweb_edu": 2.9206860967043067,
"code_python": 1.5578440612410474,
"finemath_4plus": 0.985456419878168,
"pes2o": 1.9944257736206055,
"pubmed": 2.039682388305664,
"arxiv": 1.98636794090271,
"pressbooks": 3.1151371002197266,
"libretexts": 2.208468074051935,
"doab": 1.261005643306864,
"gutenberg": 2.6607327461242676,
"pre_1929_books": 2.823298454284668,
"library_of_congress": 2.628213882446289
},
"weighted_loss": 1.8765358463876165,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
},
{
"step": 64227,
"tokens": 4999981176,
"per_source": {
"fineweb_edu": 2.9148877568605567,
"code_python": 1.551377941053044,
"finemath_4plus": 0.9781413506420195,
"pes2o": 1.9863625764846802,
"pubmed": 2.0357589721679688,
"arxiv": 1.984279990196228,
"pressbooks": 3.1151490211486816,
"libretexts": 2.2148055215747333,
"doab": 1.2587231780872863,
"gutenberg": 2.655519723892212,
"pre_1929_books": 2.815484046936035,
"library_of_congress": 2.6251580715179443
},
"weighted_loss": 1.8707872297786696,
"segment": "simple-llm-124m-8k-5b-20261018-s03"
}
]
[
{
"step": 0,
"tokens": 0,
"per_source": {
"fineweb_edu": 10.519629726890756,
"code_python": 10.525794538943599,
"finemath_4plus": 10.32566055540577,
"pes2o": 10.462692260742188,
"pubmed": 10.545242309570312,
"arxiv": 10.553985595703125,
"pressbooks": 10.5458984375,
"libretexts": 10.647798042704625,
"doab": 10.522146329198794,
"gutenberg": 10.600608825683594,
"pre_1929_books": 10.588775634765625,
"library_of_congress": 10.568008422851562
},
"weighted_loss": 10.49352138870611,
"segment": "simple-llm-124m-8k-5b-20261018-s00"
},
{
"step": 2,
"tokens": 131039,
"per_source": {
"fineweb_edu": 10.509191176470589,
"code_python": 10.508337063563115,
"finemath_4plus": 10.308657994068483,
"pes2o": 10.448966979980469,
"pubmed": 10.531173706054688,
"arxiv": 10.537490844726562,
"pressbooks": 10.53515625,
"libretexts": 10.631728202846976,
"doab": 10.502660911833724,
"gutenberg": 10.584503173828125,
"pre_1929_books": 10.552055358886719,
"library_of_congress": 10.53436279296875
},
"weighted_loss": 10.475746449265205,
"segment": "simple-llm-124m-8k-5b-20261018-s01"
},
{
"step": 4,
"tokens": 257384,
"per_source": {
"fineweb_edu": 10.488314075630251,
"code_python": 10.474317367949865,
"finemath_4plus": 10.143755055270962,
"pes2o": 10.422088623046875,
"pubmed": 10.506561279296875,
"arxiv": 10.510971069335938,
"pressbooks": 10.5135498046875,
"libretexts": 10.60442615658363,
"doab": 10.470530925243043,
"gutenberg": 10.556404113769531,
"pre_1929_books": 10.490371704101562,
"library_of_congress": 10.477531433105469
},
"weighted_loss": 10.416335434889096,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 500,
"tokens": 38433207,
"per_source": {
"fineweb_edu": 5.349017487854517,
"code_python": 4.60803474009624,
"finemath_4plus": 2.7968560427338907,
"pes2o": 5.143681049346924,
"pubmed": 5.251229763031006,
"arxiv": 4.909776210784912,
"pressbooks": 5.0997161865234375,
"libretexts": 5.201687089913256,
"doab": 4.936758166066041,
"gutenberg": 5.204975128173828,
"pre_1929_books": 5.021296501159668,
"library_of_congress": 4.880281925201416
},
"weighted_loss": 4.5114442955840754,
"segment": "simple-llm-124m-8k-5b-20261018-s02"
},
{
"step": 1000,
"tokens": 77303045,
"per_source": {
"fineweb_edu": 4.551280815060399,
"code_python": 3.3144417594561326,
"finemath_4plus": 1.9642102613575088,
"pes2o": 3.749763011932373,
"pubmed": 3.8531785011291504,
"arxiv": 3.771294355392456,
"pressbooks": 4.586516380310059,
"libretexts": 4.046084366659253,
"doab": 3.476931125335233,
"gutenberg": 4.285614967346191,
"pre_1929_books": 4.3287787437438965,
"library_of_congress": 4.175426006317139
},
"weighted_loss": 3.4489135129907273,
"segment": "simple-llm-124m-8k-5b-20261018-s02"