kdcyberdude's picture
Training in progress, step 2500, checkpoint
0a02e33 verified
raw
history blame
44.8 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.06509795071651145,
"eval_steps": 500,
"global_step": 2500,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0002603918028660458,
"grad_norm": 0.4500846266746521,
"learning_rate": 5.194805194805195e-06,
"loss": 1.0381,
"step": 10
},
{
"epoch": 0.0005207836057320916,
"grad_norm": 0.35188010334968567,
"learning_rate": 1.038961038961039e-05,
"loss": 1.0108,
"step": 20
},
{
"epoch": 0.0007811754085981374,
"grad_norm": 0.2300374060869217,
"learning_rate": 1.5584415584415583e-05,
"loss": 0.9668,
"step": 30
},
{
"epoch": 0.0010415672114641832,
"grad_norm": 0.16189467906951904,
"learning_rate": 2.077922077922078e-05,
"loss": 0.918,
"step": 40
},
{
"epoch": 0.001301959014330229,
"grad_norm": 0.18843211233615875,
"learning_rate": 2.5974025974025972e-05,
"loss": 0.9265,
"step": 50
},
{
"epoch": 0.0015623508171962747,
"grad_norm": 0.20334510505199432,
"learning_rate": 3.1168831168831166e-05,
"loss": 0.9234,
"step": 60
},
{
"epoch": 0.0018227426200623205,
"grad_norm": 0.1745327115058899,
"learning_rate": 3.6363636363636364e-05,
"loss": 0.881,
"step": 70
},
{
"epoch": 0.0020831344229283663,
"grad_norm": 0.18667331337928772,
"learning_rate": 4.155844155844156e-05,
"loss": 0.8592,
"step": 80
},
{
"epoch": 0.002343526225794412,
"grad_norm": 0.1848158985376358,
"learning_rate": 4.675324675324675e-05,
"loss": 0.8537,
"step": 90
},
{
"epoch": 0.002603918028660458,
"grad_norm": 0.17589879035949707,
"learning_rate": 5.1948051948051944e-05,
"loss": 0.8518,
"step": 100
},
{
"epoch": 0.0028643098315265037,
"grad_norm": 0.2132624089717865,
"learning_rate": 5.714285714285714e-05,
"loss": 0.8511,
"step": 110
},
{
"epoch": 0.0031247016343925495,
"grad_norm": 0.23070092499256134,
"learning_rate": 6.233766233766233e-05,
"loss": 0.7975,
"step": 120
},
{
"epoch": 0.0033850934372585953,
"grad_norm": 0.25368157029151917,
"learning_rate": 6.753246753246754e-05,
"loss": 0.8134,
"step": 130
},
{
"epoch": 0.003645485240124641,
"grad_norm": 0.22897231578826904,
"learning_rate": 7.272727272727273e-05,
"loss": 0.8322,
"step": 140
},
{
"epoch": 0.003905877042990687,
"grad_norm": 0.19932536780834198,
"learning_rate": 7.792207792207793e-05,
"loss": 0.7959,
"step": 150
},
{
"epoch": 0.004166268845856733,
"grad_norm": 0.21011792123317719,
"learning_rate": 8.311688311688312e-05,
"loss": 0.8102,
"step": 160
},
{
"epoch": 0.004426660648722778,
"grad_norm": 0.20594824850559235,
"learning_rate": 8.831168831168831e-05,
"loss": 0.8128,
"step": 170
},
{
"epoch": 0.004687052451588824,
"grad_norm": 0.20465536415576935,
"learning_rate": 9.35064935064935e-05,
"loss": 0.7989,
"step": 180
},
{
"epoch": 0.00494744425445487,
"grad_norm": 0.4109392762184143,
"learning_rate": 9.870129870129871e-05,
"loss": 0.8108,
"step": 190
},
{
"epoch": 0.005207836057320916,
"grad_norm": 0.4293076694011688,
"learning_rate": 0.00010389610389610389,
"loss": 0.8101,
"step": 200
},
{
"epoch": 0.005468227860186962,
"grad_norm": 0.31628963351249695,
"learning_rate": 0.00010909090909090909,
"loss": 0.7989,
"step": 210
},
{
"epoch": 0.005728619663053007,
"grad_norm": 0.24642810225486755,
"learning_rate": 0.00011428571428571428,
"loss": 0.7751,
"step": 220
},
{
"epoch": 0.005989011465919053,
"grad_norm": 0.3599106967449188,
"learning_rate": 0.00011948051948051949,
"loss": 0.8063,
"step": 230
},
{
"epoch": 0.006249403268785099,
"grad_norm": 0.17053447663784027,
"learning_rate": 0.00012467532467532467,
"loss": 0.7751,
"step": 240
},
{
"epoch": 0.006509795071651145,
"grad_norm": 0.17303769290447235,
"learning_rate": 0.00012987012987012987,
"loss": 0.7883,
"step": 250
},
{
"epoch": 0.0067701868745171905,
"grad_norm": 0.1815861016511917,
"learning_rate": 0.00013506493506493507,
"loss": 0.788,
"step": 260
},
{
"epoch": 0.007030578677383236,
"grad_norm": 0.24125365912914276,
"learning_rate": 0.00014025974025974028,
"loss": 0.8018,
"step": 270
},
{
"epoch": 0.007290970480249282,
"grad_norm": 0.19443446397781372,
"learning_rate": 0.00014545454545454546,
"loss": 0.7908,
"step": 280
},
{
"epoch": 0.007551362283115328,
"grad_norm": 0.17829768359661102,
"learning_rate": 0.00015064935064935066,
"loss": 0.8033,
"step": 290
},
{
"epoch": 0.007811754085981374,
"grad_norm": 0.19535653293132782,
"learning_rate": 0.00015584415584415587,
"loss": 0.7997,
"step": 300
},
{
"epoch": 0.008072145888847419,
"grad_norm": 0.19930541515350342,
"learning_rate": 0.00016103896103896104,
"loss": 0.7945,
"step": 310
},
{
"epoch": 0.008332537691713465,
"grad_norm": 0.2156297266483307,
"learning_rate": 0.00016623376623376625,
"loss": 0.8018,
"step": 320
},
{
"epoch": 0.00859292949457951,
"grad_norm": 0.1924206018447876,
"learning_rate": 0.00017142857142857143,
"loss": 0.7746,
"step": 330
},
{
"epoch": 0.008853321297445557,
"grad_norm": 0.2294880747795105,
"learning_rate": 0.00017662337662337663,
"loss": 0.8152,
"step": 340
},
{
"epoch": 0.009113713100311602,
"grad_norm": 0.16817067563533783,
"learning_rate": 0.00018181818181818183,
"loss": 0.7972,
"step": 350
},
{
"epoch": 0.009374104903177648,
"grad_norm": 0.18544812500476837,
"learning_rate": 0.000187012987012987,
"loss": 0.7801,
"step": 360
},
{
"epoch": 0.009634496706043693,
"grad_norm": 0.19597066938877106,
"learning_rate": 0.00019220779220779222,
"loss": 0.7706,
"step": 370
},
{
"epoch": 0.00989488850890974,
"grad_norm": 0.40291881561279297,
"learning_rate": 0.00019740259740259742,
"loss": 0.7911,
"step": 380
},
{
"epoch": 0.010155280311775785,
"grad_norm": 0.23841074109077454,
"learning_rate": 0.00019999996515752773,
"loss": 0.7861,
"step": 390
},
{
"epoch": 0.010415672114641832,
"grad_norm": 0.1675388514995575,
"learning_rate": 0.00019999968641789507,
"loss": 0.788,
"step": 400
},
{
"epoch": 0.010676063917507876,
"grad_norm": 1.8860758543014526,
"learning_rate": 0.0001999991289394067,
"loss": 0.7632,
"step": 410
},
{
"epoch": 0.010936455720373923,
"grad_norm": 0.17022117972373962,
"learning_rate": 0.00019999829272361654,
"loss": 0.784,
"step": 420
},
{
"epoch": 0.011196847523239968,
"grad_norm": 0.21460269391536713,
"learning_rate": 0.00019999717777285545,
"loss": 0.761,
"step": 430
},
{
"epoch": 0.011457239326106015,
"grad_norm": 0.19413785636425018,
"learning_rate": 0.00019999578409023126,
"loss": 0.7772,
"step": 440
},
{
"epoch": 0.01171763112897206,
"grad_norm": 0.20223405957221985,
"learning_rate": 0.00019999411167962868,
"loss": 0.7811,
"step": 450
},
{
"epoch": 0.011978022931838106,
"grad_norm": 0.15166303515434265,
"learning_rate": 0.00019999216054570942,
"loss": 0.7709,
"step": 460
},
{
"epoch": 0.012238414734704151,
"grad_norm": 0.16307081282138824,
"learning_rate": 0.00019998993069391205,
"loss": 0.7811,
"step": 470
},
{
"epoch": 0.012498806537570198,
"grad_norm": 0.15996049344539642,
"learning_rate": 0.00019998742213045206,
"loss": 0.7599,
"step": 480
},
{
"epoch": 0.012759198340436243,
"grad_norm": 0.17560279369354248,
"learning_rate": 0.00019998463486232179,
"loss": 0.7572,
"step": 490
},
{
"epoch": 0.01301959014330229,
"grad_norm": 0.17571642994880676,
"learning_rate": 0.0001999815688972905,
"loss": 0.7643,
"step": 500
},
{
"epoch": 0.013279981946168334,
"grad_norm": 0.17719799280166626,
"learning_rate": 0.00019997822424390422,
"loss": 0.7923,
"step": 510
},
{
"epoch": 0.013540373749034381,
"grad_norm": 0.19846616685390472,
"learning_rate": 0.00019997460091148586,
"loss": 0.7674,
"step": 520
},
{
"epoch": 0.013800765551900426,
"grad_norm": 0.2715558111667633,
"learning_rate": 0.00019997069891013503,
"loss": 0.7421,
"step": 530
},
{
"epoch": 0.014061157354766473,
"grad_norm": 0.1725197583436966,
"learning_rate": 0.00019996651825072826,
"loss": 0.7663,
"step": 540
},
{
"epoch": 0.014321549157632518,
"grad_norm": 0.15060502290725708,
"learning_rate": 0.00019996205894491856,
"loss": 0.7794,
"step": 550
},
{
"epoch": 0.014581940960498564,
"grad_norm": 0.16645808517932892,
"learning_rate": 0.00019995732100513592,
"loss": 0.752,
"step": 560
},
{
"epoch": 0.014842332763364609,
"grad_norm": 0.1736789345741272,
"learning_rate": 0.00019995230444458682,
"loss": 0.7788,
"step": 570
},
{
"epoch": 0.015102724566230656,
"grad_norm": 0.15416319668293,
"learning_rate": 0.0001999470092772544,
"loss": 0.7656,
"step": 580
},
{
"epoch": 0.0153631163690967,
"grad_norm": 0.16610187292099,
"learning_rate": 0.00019994143551789839,
"loss": 0.7676,
"step": 590
},
{
"epoch": 0.015623508171962747,
"grad_norm": 0.15843011438846588,
"learning_rate": 0.00019993558318205507,
"loss": 0.7746,
"step": 600
},
{
"epoch": 0.015883899974828794,
"grad_norm": 0.26837801933288574,
"learning_rate": 0.00019992945228603724,
"loss": 0.7617,
"step": 610
},
{
"epoch": 0.016144291777694837,
"grad_norm": 0.15099173784255981,
"learning_rate": 0.0001999230428469341,
"loss": 0.7601,
"step": 620
},
{
"epoch": 0.016404683580560884,
"grad_norm": 0.15511856973171234,
"learning_rate": 0.00019991635488261138,
"loss": 0.7647,
"step": 630
},
{
"epoch": 0.01666507538342693,
"grad_norm": 0.14919579029083252,
"learning_rate": 0.00019990938841171104,
"loss": 0.7692,
"step": 640
},
{
"epoch": 0.016925467186292977,
"grad_norm": 0.15838642418384552,
"learning_rate": 0.0001999021434536514,
"loss": 0.7763,
"step": 650
},
{
"epoch": 0.01718585898915902,
"grad_norm": 0.15956635773181915,
"learning_rate": 0.00019989462002862704,
"loss": 0.7598,
"step": 660
},
{
"epoch": 0.017446250792025067,
"grad_norm": 0.1499069333076477,
"learning_rate": 0.0001998868181576088,
"loss": 0.7626,
"step": 670
},
{
"epoch": 0.017706642594891114,
"grad_norm": 0.2170073390007019,
"learning_rate": 0.00019987873786234348,
"loss": 0.7569,
"step": 680
},
{
"epoch": 0.01796703439775716,
"grad_norm": 0.17841948568820953,
"learning_rate": 0.00019987037916535417,
"loss": 0.7494,
"step": 690
},
{
"epoch": 0.018227426200623204,
"grad_norm": 0.2066909372806549,
"learning_rate": 0.0001998617420899398,
"loss": 0.7609,
"step": 700
},
{
"epoch": 0.01848781800348925,
"grad_norm": 0.17015361785888672,
"learning_rate": 0.0001998528266601754,
"loss": 0.7761,
"step": 710
},
{
"epoch": 0.018748209806355297,
"grad_norm": 0.22166290879249573,
"learning_rate": 0.0001998436329009118,
"loss": 0.7573,
"step": 720
},
{
"epoch": 0.01900860160922134,
"grad_norm": 0.15084640681743622,
"learning_rate": 0.00019983416083777563,
"loss": 0.7775,
"step": 730
},
{
"epoch": 0.019268993412087387,
"grad_norm": 0.17800921201705933,
"learning_rate": 0.0001998244104971693,
"loss": 0.7359,
"step": 740
},
{
"epoch": 0.019529385214953433,
"grad_norm": 0.17354707419872284,
"learning_rate": 0.0001998143819062709,
"loss": 0.7415,
"step": 750
},
{
"epoch": 0.01978977701781948,
"grad_norm": 0.16408118605613708,
"learning_rate": 0.00019980407509303413,
"loss": 0.7708,
"step": 760
},
{
"epoch": 0.020050168820685523,
"grad_norm": 0.16820089519023895,
"learning_rate": 0.00019979349008618808,
"loss": 0.791,
"step": 770
},
{
"epoch": 0.02031056062355157,
"grad_norm": 0.15958388149738312,
"learning_rate": 0.00019978262691523743,
"loss": 0.7412,
"step": 780
},
{
"epoch": 0.020570952426417616,
"grad_norm": 0.1646542251110077,
"learning_rate": 0.00019977148561046217,
"loss": 0.7529,
"step": 790
},
{
"epoch": 0.020831344229283663,
"grad_norm": 0.17032025754451752,
"learning_rate": 0.0001997600662029175,
"loss": 0.7656,
"step": 800
},
{
"epoch": 0.021091736032149706,
"grad_norm": 0.17189227044582367,
"learning_rate": 0.00019974836872443388,
"loss": 0.7433,
"step": 810
},
{
"epoch": 0.021352127835015753,
"grad_norm": 0.16334249079227448,
"learning_rate": 0.0001997363932076168,
"loss": 0.7703,
"step": 820
},
{
"epoch": 0.0216125196378818,
"grad_norm": 0.1676424890756607,
"learning_rate": 0.00019972413968584682,
"loss": 0.7603,
"step": 830
},
{
"epoch": 0.021872911440747846,
"grad_norm": 0.16826209425926208,
"learning_rate": 0.0001997116081932793,
"loss": 0.7569,
"step": 840
},
{
"epoch": 0.02213330324361389,
"grad_norm": 0.1876436173915863,
"learning_rate": 0.0001996987987648446,
"loss": 0.7553,
"step": 850
},
{
"epoch": 0.022393695046479936,
"grad_norm": 0.17252250015735626,
"learning_rate": 0.0001996857114362476,
"loss": 0.7644,
"step": 860
},
{
"epoch": 0.022654086849345983,
"grad_norm": 0.1632252335548401,
"learning_rate": 0.00019967234624396793,
"loss": 0.7568,
"step": 870
},
{
"epoch": 0.02291447865221203,
"grad_norm": 0.1818259060382843,
"learning_rate": 0.00019965870322525965,
"loss": 0.7672,
"step": 880
},
{
"epoch": 0.023174870455078073,
"grad_norm": 0.15418195724487305,
"learning_rate": 0.0001996447824181513,
"loss": 0.7642,
"step": 890
},
{
"epoch": 0.02343526225794412,
"grad_norm": 0.17383505403995514,
"learning_rate": 0.0001996305838614457,
"loss": 0.7607,
"step": 900
},
{
"epoch": 0.023695654060810166,
"grad_norm": 0.17794272303581238,
"learning_rate": 0.00019961610759471984,
"loss": 0.7588,
"step": 910
},
{
"epoch": 0.023956045863676213,
"grad_norm": 0.1909121572971344,
"learning_rate": 0.00019960135365832486,
"loss": 0.7438,
"step": 920
},
{
"epoch": 0.024216437666542256,
"grad_norm": 0.17758873105049133,
"learning_rate": 0.00019958632209338587,
"loss": 0.7323,
"step": 930
},
{
"epoch": 0.024476829469408302,
"grad_norm": 0.15553662180900574,
"learning_rate": 0.00019957101294180174,
"loss": 0.7508,
"step": 940
},
{
"epoch": 0.02473722127227435,
"grad_norm": 0.15310749411582947,
"learning_rate": 0.00019955542624624522,
"loss": 0.7563,
"step": 950
},
{
"epoch": 0.024997613075140396,
"grad_norm": 0.1628728210926056,
"learning_rate": 0.00019953956205016256,
"loss": 0.7524,
"step": 960
},
{
"epoch": 0.02525800487800644,
"grad_norm": 0.16211454570293427,
"learning_rate": 0.00019952342039777362,
"loss": 0.7564,
"step": 970
},
{
"epoch": 0.025518396680872486,
"grad_norm": 0.15663012862205505,
"learning_rate": 0.00019950700133407163,
"loss": 0.7395,
"step": 980
},
{
"epoch": 0.025778788483738532,
"grad_norm": 0.1684863567352295,
"learning_rate": 0.00019949030490482296,
"loss": 0.753,
"step": 990
},
{
"epoch": 0.02603918028660458,
"grad_norm": 0.1561436653137207,
"learning_rate": 0.0001994733311565673,
"loss": 0.7409,
"step": 1000
},
{
"epoch": 0.026299572089470622,
"grad_norm": 0.1781485229730606,
"learning_rate": 0.0001994560801366171,
"loss": 0.762,
"step": 1010
},
{
"epoch": 0.02655996389233667,
"grad_norm": 0.15422071516513824,
"learning_rate": 0.00019943855189305792,
"loss": 0.7291,
"step": 1020
},
{
"epoch": 0.026820355695202715,
"grad_norm": 0.17980527877807617,
"learning_rate": 0.00019942074647474786,
"loss": 0.7732,
"step": 1030
},
{
"epoch": 0.027080747498068762,
"grad_norm": 0.15810626745224,
"learning_rate": 0.00019940266393131775,
"loss": 0.7764,
"step": 1040
},
{
"epoch": 0.027341139300934805,
"grad_norm": 0.16385480761528015,
"learning_rate": 0.00019938430431317081,
"loss": 0.7404,
"step": 1050
},
{
"epoch": 0.027601531103800852,
"grad_norm": 0.15134255588054657,
"learning_rate": 0.00019936566767148257,
"loss": 0.7506,
"step": 1060
},
{
"epoch": 0.0278619229066669,
"grad_norm": 0.1592187136411667,
"learning_rate": 0.00019934675405820077,
"loss": 0.73,
"step": 1070
},
{
"epoch": 0.028122314709532945,
"grad_norm": 0.16852422058582306,
"learning_rate": 0.00019932756352604515,
"loss": 0.7443,
"step": 1080
},
{
"epoch": 0.02838270651239899,
"grad_norm": 0.15741507709026337,
"learning_rate": 0.00019930809612850735,
"loss": 0.7377,
"step": 1090
},
{
"epoch": 0.028643098315265035,
"grad_norm": 0.22424879670143127,
"learning_rate": 0.00019928835191985076,
"loss": 0.7544,
"step": 1100
},
{
"epoch": 0.028903490118131082,
"grad_norm": 0.2047310769557953,
"learning_rate": 0.0001992683309551103,
"loss": 0.7441,
"step": 1110
},
{
"epoch": 0.02916388192099713,
"grad_norm": 0.16392463445663452,
"learning_rate": 0.00019924803329009243,
"loss": 0.7606,
"step": 1120
},
{
"epoch": 0.02942427372386317,
"grad_norm": 0.16227149963378906,
"learning_rate": 0.00019922745898137473,
"loss": 0.736,
"step": 1130
},
{
"epoch": 0.029684665526729218,
"grad_norm": 0.15652808547019958,
"learning_rate": 0.00019920660808630598,
"loss": 0.7513,
"step": 1140
},
{
"epoch": 0.029945057329595265,
"grad_norm": 0.15162768959999084,
"learning_rate": 0.00019918548066300592,
"loss": 0.7303,
"step": 1150
},
{
"epoch": 0.03020544913246131,
"grad_norm": 0.17650415003299713,
"learning_rate": 0.0001991640767703651,
"loss": 0.7254,
"step": 1160
},
{
"epoch": 0.030465840935327355,
"grad_norm": 0.1594468355178833,
"learning_rate": 0.00019914239646804462,
"loss": 0.741,
"step": 1170
},
{
"epoch": 0.0307262327381934,
"grad_norm": 0.17928367853164673,
"learning_rate": 0.00019912043981647616,
"loss": 0.7515,
"step": 1180
},
{
"epoch": 0.030986624541059448,
"grad_norm": 0.17009998857975006,
"learning_rate": 0.00019909820687686157,
"loss": 0.7539,
"step": 1190
},
{
"epoch": 0.031247016343925495,
"grad_norm": 0.16556763648986816,
"learning_rate": 0.0001990756977111729,
"loss": 0.7418,
"step": 1200
},
{
"epoch": 0.03150740814679154,
"grad_norm": 0.1561640352010727,
"learning_rate": 0.0001990529123821522,
"loss": 0.7465,
"step": 1210
},
{
"epoch": 0.03176779994965759,
"grad_norm": 0.15182287991046906,
"learning_rate": 0.00019902985095331113,
"loss": 0.7694,
"step": 1220
},
{
"epoch": 0.03202819175252363,
"grad_norm": 0.15173685550689697,
"learning_rate": 0.00019900651348893114,
"loss": 0.7519,
"step": 1230
},
{
"epoch": 0.032288583555389674,
"grad_norm": 0.16535787284374237,
"learning_rate": 0.00019898290005406296,
"loss": 0.7646,
"step": 1240
},
{
"epoch": 0.032548975358255725,
"grad_norm": 0.19272534549236298,
"learning_rate": 0.00019895901071452667,
"loss": 0.7655,
"step": 1250
},
{
"epoch": 0.03280936716112177,
"grad_norm": 0.1672705113887787,
"learning_rate": 0.0001989348455369113,
"loss": 0.7486,
"step": 1260
},
{
"epoch": 0.03306975896398781,
"grad_norm": 0.1525493860244751,
"learning_rate": 0.0001989104045885748,
"loss": 0.7546,
"step": 1270
},
{
"epoch": 0.03333015076685386,
"grad_norm": 0.16333037614822388,
"learning_rate": 0.00019888568793764385,
"loss": 0.7299,
"step": 1280
},
{
"epoch": 0.033590542569719904,
"grad_norm": 0.1590205729007721,
"learning_rate": 0.00019886069565301355,
"loss": 0.762,
"step": 1290
},
{
"epoch": 0.033850934372585954,
"grad_norm": 0.15006420016288757,
"learning_rate": 0.00019883542780434733,
"loss": 0.7531,
"step": 1300
},
{
"epoch": 0.034111326175452,
"grad_norm": 0.18390792608261108,
"learning_rate": 0.0001988098844620767,
"loss": 0.7621,
"step": 1310
},
{
"epoch": 0.03437171797831804,
"grad_norm": 0.17046166956424713,
"learning_rate": 0.0001987840656974011,
"loss": 0.7422,
"step": 1320
},
{
"epoch": 0.03463210978118409,
"grad_norm": 0.15121813118457794,
"learning_rate": 0.00019875797158228775,
"loss": 0.7555,
"step": 1330
},
{
"epoch": 0.034892501584050134,
"grad_norm": 0.16219307482242584,
"learning_rate": 0.00019873160218947125,
"loss": 0.7301,
"step": 1340
},
{
"epoch": 0.03515289338691618,
"grad_norm": 0.1779986321926117,
"learning_rate": 0.00019870495759245362,
"loss": 0.7356,
"step": 1350
},
{
"epoch": 0.03541328518978223,
"grad_norm": 0.16951359808444977,
"learning_rate": 0.0001986780378655039,
"loss": 0.7645,
"step": 1360
},
{
"epoch": 0.03567367699264827,
"grad_norm": 0.16620802879333496,
"learning_rate": 0.0001986508430836581,
"loss": 0.7331,
"step": 1370
},
{
"epoch": 0.03593406879551432,
"grad_norm": 0.1577858328819275,
"learning_rate": 0.0001986233733227188,
"loss": 0.7667,
"step": 1380
},
{
"epoch": 0.036194460598380364,
"grad_norm": 0.1637091338634491,
"learning_rate": 0.00019859562865925525,
"loss": 0.7521,
"step": 1390
},
{
"epoch": 0.03645485240124641,
"grad_norm": 0.15061691403388977,
"learning_rate": 0.00019856760917060277,
"loss": 0.744,
"step": 1400
},
{
"epoch": 0.03671524420411246,
"grad_norm": 0.15373477339744568,
"learning_rate": 0.00019853931493486287,
"loss": 0.7677,
"step": 1410
},
{
"epoch": 0.0369756360069785,
"grad_norm": 0.16468606889247894,
"learning_rate": 0.00019851074603090277,
"loss": 0.7179,
"step": 1420
},
{
"epoch": 0.037236027809844544,
"grad_norm": 0.16084876656532288,
"learning_rate": 0.00019848190253835536,
"loss": 0.749,
"step": 1430
},
{
"epoch": 0.037496419612710594,
"grad_norm": 0.16743004322052002,
"learning_rate": 0.00019845278453761896,
"loss": 0.7483,
"step": 1440
},
{
"epoch": 0.03775681141557664,
"grad_norm": 0.17335088551044464,
"learning_rate": 0.00019842339210985696,
"loss": 0.735,
"step": 1450
},
{
"epoch": 0.03801720321844268,
"grad_norm": 0.1546197235584259,
"learning_rate": 0.00019839372533699774,
"loss": 0.7549,
"step": 1460
},
{
"epoch": 0.03827759502130873,
"grad_norm": 0.16218656301498413,
"learning_rate": 0.00019836378430173438,
"loss": 0.7425,
"step": 1470
},
{
"epoch": 0.03853798682417477,
"grad_norm": 0.1712743639945984,
"learning_rate": 0.0001983335690875245,
"loss": 0.733,
"step": 1480
},
{
"epoch": 0.03879837862704082,
"grad_norm": 0.15490613877773285,
"learning_rate": 0.00019830307977858984,
"loss": 0.7265,
"step": 1490
},
{
"epoch": 0.03905877042990687,
"grad_norm": 0.1646670252084732,
"learning_rate": 0.00019827231645991623,
"loss": 0.7315,
"step": 1500
},
{
"epoch": 0.03931916223277291,
"grad_norm": 0.1599082201719284,
"learning_rate": 0.00019824127921725326,
"loss": 0.7293,
"step": 1510
},
{
"epoch": 0.03957955403563896,
"grad_norm": 0.1565747708082199,
"learning_rate": 0.00019820996813711407,
"loss": 0.7396,
"step": 1520
},
{
"epoch": 0.039839945838505,
"grad_norm": 0.154826357960701,
"learning_rate": 0.0001981783833067751,
"loss": 0.7217,
"step": 1530
},
{
"epoch": 0.040100337641371046,
"grad_norm": 0.16705222427845,
"learning_rate": 0.0001981465248142758,
"loss": 0.761,
"step": 1540
},
{
"epoch": 0.040360729444237096,
"grad_norm": 0.15651623904705048,
"learning_rate": 0.00019811439274841842,
"loss": 0.7565,
"step": 1550
},
{
"epoch": 0.04062112124710314,
"grad_norm": 0.16211090981960297,
"learning_rate": 0.00019808198719876782,
"loss": 0.7555,
"step": 1560
},
{
"epoch": 0.04088151304996919,
"grad_norm": 0.16856881976127625,
"learning_rate": 0.00019804930825565112,
"loss": 0.7567,
"step": 1570
},
{
"epoch": 0.04114190485283523,
"grad_norm": 0.1588718593120575,
"learning_rate": 0.00019801635601015752,
"loss": 0.729,
"step": 1580
},
{
"epoch": 0.041402296655701276,
"grad_norm": 0.17078711092472076,
"learning_rate": 0.00019798313055413808,
"loss": 0.7418,
"step": 1590
},
{
"epoch": 0.041662688458567326,
"grad_norm": 0.16652734577655792,
"learning_rate": 0.00019794963198020525,
"loss": 0.7341,
"step": 1600
},
{
"epoch": 0.04192308026143337,
"grad_norm": 0.15535488724708557,
"learning_rate": 0.00019791586038173296,
"loss": 0.7396,
"step": 1610
},
{
"epoch": 0.04218347206429941,
"grad_norm": 0.3506317734718323,
"learning_rate": 0.00019788181585285602,
"loss": 0.7345,
"step": 1620
},
{
"epoch": 0.04244386386716546,
"grad_norm": 0.16875872015953064,
"learning_rate": 0.00019784749848847003,
"loss": 0.7214,
"step": 1630
},
{
"epoch": 0.042704255670031506,
"grad_norm": 0.17675861716270447,
"learning_rate": 0.0001978129083842312,
"loss": 0.7431,
"step": 1640
},
{
"epoch": 0.042964647472897556,
"grad_norm": 0.15601837635040283,
"learning_rate": 0.00019777804563655583,
"loss": 0.7215,
"step": 1650
},
{
"epoch": 0.0432250392757636,
"grad_norm": 0.1874823123216629,
"learning_rate": 0.00019774291034262026,
"loss": 0.727,
"step": 1660
},
{
"epoch": 0.04348543107862964,
"grad_norm": 0.17005637288093567,
"learning_rate": 0.00019770750260036054,
"loss": 0.7446,
"step": 1670
},
{
"epoch": 0.04374582288149569,
"grad_norm": 0.17069579660892487,
"learning_rate": 0.00019767182250847207,
"loss": 0.7266,
"step": 1680
},
{
"epoch": 0.044006214684361736,
"grad_norm": 0.16133156418800354,
"learning_rate": 0.00019763587016640948,
"loss": 0.7568,
"step": 1690
},
{
"epoch": 0.04426660648722778,
"grad_norm": 0.16229428350925446,
"learning_rate": 0.00019759964567438623,
"loss": 0.7402,
"step": 1700
},
{
"epoch": 0.04452699829009383,
"grad_norm": 0.1622512936592102,
"learning_rate": 0.00019756314913337432,
"loss": 0.7536,
"step": 1710
},
{
"epoch": 0.04478739009295987,
"grad_norm": 0.2161218672990799,
"learning_rate": 0.00019752638064510415,
"loss": 0.723,
"step": 1720
},
{
"epoch": 0.04504778189582592,
"grad_norm": 0.154169961810112,
"learning_rate": 0.00019748934031206414,
"loss": 0.7441,
"step": 1730
},
{
"epoch": 0.045308173698691966,
"grad_norm": 0.15468057990074158,
"learning_rate": 0.00019745202823750034,
"loss": 0.7349,
"step": 1740
},
{
"epoch": 0.04556856550155801,
"grad_norm": 0.2015281468629837,
"learning_rate": 0.0001974144445254164,
"loss": 0.726,
"step": 1750
},
{
"epoch": 0.04582895730442406,
"grad_norm": 0.1931644082069397,
"learning_rate": 0.00019737658928057302,
"loss": 0.7604,
"step": 1760
},
{
"epoch": 0.0460893491072901,
"grad_norm": 0.1528482288122177,
"learning_rate": 0.00019733846260848776,
"loss": 0.7408,
"step": 1770
},
{
"epoch": 0.046349740910156145,
"grad_norm": 0.16370061039924622,
"learning_rate": 0.0001973000646154349,
"loss": 0.7647,
"step": 1780
},
{
"epoch": 0.046610132713022195,
"grad_norm": 0.16271348297595978,
"learning_rate": 0.00019726139540844484,
"loss": 0.7212,
"step": 1790
},
{
"epoch": 0.04687052451588824,
"grad_norm": 0.16218173503875732,
"learning_rate": 0.00019722245509530401,
"loss": 0.735,
"step": 1800
},
{
"epoch": 0.04713091631875429,
"grad_norm": 0.17063820362091064,
"learning_rate": 0.00019718324378455458,
"loss": 0.7311,
"step": 1810
},
{
"epoch": 0.04739130812162033,
"grad_norm": 0.1678459346294403,
"learning_rate": 0.00019714376158549404,
"loss": 0.7486,
"step": 1820
},
{
"epoch": 0.047651699924486375,
"grad_norm": 0.15926459431648254,
"learning_rate": 0.00019710400860817494,
"loss": 0.743,
"step": 1830
},
{
"epoch": 0.047912091727352425,
"grad_norm": 0.1775251179933548,
"learning_rate": 0.00019706398496340463,
"loss": 0.7512,
"step": 1840
},
{
"epoch": 0.04817248353021847,
"grad_norm": 0.1572408229112625,
"learning_rate": 0.00019702369076274494,
"loss": 0.733,
"step": 1850
},
{
"epoch": 0.04843287533308451,
"grad_norm": 0.29658186435699463,
"learning_rate": 0.0001969831261185118,
"loss": 0.7297,
"step": 1860
},
{
"epoch": 0.04869326713595056,
"grad_norm": 0.16520118713378906,
"learning_rate": 0.00019694229114377494,
"loss": 0.721,
"step": 1870
},
{
"epoch": 0.048953658938816605,
"grad_norm": 0.17762574553489685,
"learning_rate": 0.00019690118595235774,
"loss": 0.7304,
"step": 1880
},
{
"epoch": 0.049214050741682655,
"grad_norm": 0.16636615991592407,
"learning_rate": 0.00019685981065883663,
"loss": 0.7257,
"step": 1890
},
{
"epoch": 0.0494744425445487,
"grad_norm": 0.1622323989868164,
"learning_rate": 0.00019681816537854102,
"loss": 0.7353,
"step": 1900
},
{
"epoch": 0.04973483434741474,
"grad_norm": 0.17419832944869995,
"learning_rate": 0.00019677625022755289,
"loss": 0.7452,
"step": 1910
},
{
"epoch": 0.04999522615028079,
"grad_norm": 0.17460434138774872,
"learning_rate": 0.00019673406532270634,
"loss": 0.7391,
"step": 1920
},
{
"epoch": 0.050255617953146835,
"grad_norm": 0.15844550728797913,
"learning_rate": 0.00019669161078158753,
"loss": 0.7327,
"step": 1930
},
{
"epoch": 0.05051600975601288,
"grad_norm": 0.1638839989900589,
"learning_rate": 0.0001966488867225341,
"loss": 0.745,
"step": 1940
},
{
"epoch": 0.05077640155887893,
"grad_norm": 0.1587786227464676,
"learning_rate": 0.00019660589326463498,
"loss": 0.7476,
"step": 1950
},
{
"epoch": 0.05103679336174497,
"grad_norm": 0.15708380937576294,
"learning_rate": 0.00019656263052773002,
"loss": 0.7208,
"step": 1960
},
{
"epoch": 0.05129718516461102,
"grad_norm": 0.15816234052181244,
"learning_rate": 0.00019651909863240965,
"loss": 0.7262,
"step": 1970
},
{
"epoch": 0.051557576967477065,
"grad_norm": 0.16749270260334015,
"learning_rate": 0.00019647529770001456,
"loss": 0.7284,
"step": 1980
},
{
"epoch": 0.05181796877034311,
"grad_norm": 0.16943767666816711,
"learning_rate": 0.00019643122785263536,
"loss": 0.7225,
"step": 1990
},
{
"epoch": 0.05207836057320916,
"grad_norm": 0.42929205298423767,
"learning_rate": 0.00019638688921311224,
"loss": 0.7305,
"step": 2000
},
{
"epoch": 0.0523387523760752,
"grad_norm": 0.15851692855358124,
"learning_rate": 0.00019634228190503454,
"loss": 0.7344,
"step": 2010
},
{
"epoch": 0.052599144178941244,
"grad_norm": 0.16053883731365204,
"learning_rate": 0.00019629740605274062,
"loss": 0.7468,
"step": 2020
},
{
"epoch": 0.052859535981807294,
"grad_norm": 0.16504009068012238,
"learning_rate": 0.00019625226178131728,
"loss": 0.7375,
"step": 2030
},
{
"epoch": 0.05311992778467334,
"grad_norm": 0.1618044674396515,
"learning_rate": 0.00019620684921659953,
"loss": 0.7201,
"step": 2040
},
{
"epoch": 0.05338031958753939,
"grad_norm": 0.15512776374816895,
"learning_rate": 0.00019616116848517027,
"loss": 0.7355,
"step": 2050
},
{
"epoch": 0.05364071139040543,
"grad_norm": 0.17377036809921265,
"learning_rate": 0.00019611521971435979,
"loss": 0.7226,
"step": 2060
},
{
"epoch": 0.053901103193271474,
"grad_norm": 0.1685250997543335,
"learning_rate": 0.0001960690030322456,
"loss": 0.7483,
"step": 2070
},
{
"epoch": 0.054161494996137524,
"grad_norm": 0.18394522368907928,
"learning_rate": 0.00019602251856765194,
"loss": 0.7385,
"step": 2080
},
{
"epoch": 0.05442188679900357,
"grad_norm": 0.1753673106431961,
"learning_rate": 0.0001959757664501495,
"loss": 0.7378,
"step": 2090
},
{
"epoch": 0.05468227860186961,
"grad_norm": 0.1795465052127838,
"learning_rate": 0.000195928746810055,
"loss": 0.748,
"step": 2100
},
{
"epoch": 0.05494267040473566,
"grad_norm": 0.16327305138111115,
"learning_rate": 0.0001958814597784309,
"loss": 0.7306,
"step": 2110
},
{
"epoch": 0.055203062207601704,
"grad_norm": 0.15880291163921356,
"learning_rate": 0.00019583390548708486,
"loss": 0.7281,
"step": 2120
},
{
"epoch": 0.05546345401046775,
"grad_norm": 0.1702323853969574,
"learning_rate": 0.0001957860840685696,
"loss": 0.7407,
"step": 2130
},
{
"epoch": 0.0557238458133338,
"grad_norm": 0.16931670904159546,
"learning_rate": 0.0001957379956561825,
"loss": 0.7272,
"step": 2140
},
{
"epoch": 0.05598423761619984,
"grad_norm": 0.15455976128578186,
"learning_rate": 0.000195689640383965,
"loss": 0.7398,
"step": 2150
},
{
"epoch": 0.05624462941906589,
"grad_norm": 0.16061417758464813,
"learning_rate": 0.0001956410183867024,
"loss": 0.749,
"step": 2160
},
{
"epoch": 0.056505021221931934,
"grad_norm": 0.14933143556118011,
"learning_rate": 0.00019559212979992365,
"loss": 0.7418,
"step": 2170
},
{
"epoch": 0.05676541302479798,
"grad_norm": 0.1592816412448883,
"learning_rate": 0.00019554297475990058,
"loss": 0.7423,
"step": 2180
},
{
"epoch": 0.05702580482766403,
"grad_norm": 0.1677238792181015,
"learning_rate": 0.00019549355340364787,
"loss": 0.7101,
"step": 2190
},
{
"epoch": 0.05728619663053007,
"grad_norm": 0.3558599054813385,
"learning_rate": 0.00019544386586892238,
"loss": 0.725,
"step": 2200
},
{
"epoch": 0.05754658843339611,
"grad_norm": 0.1746376007795334,
"learning_rate": 0.00019539391229422313,
"loss": 0.7479,
"step": 2210
},
{
"epoch": 0.057806980236262163,
"grad_norm": 0.15979182720184326,
"learning_rate": 0.00019534369281879049,
"loss": 0.7352,
"step": 2220
},
{
"epoch": 0.05806737203912821,
"grad_norm": 0.16173166036605835,
"learning_rate": 0.0001952932075826061,
"loss": 0.7364,
"step": 2230
},
{
"epoch": 0.05832776384199426,
"grad_norm": 0.1514744907617569,
"learning_rate": 0.00019524245672639245,
"loss": 0.734,
"step": 2240
},
{
"epoch": 0.0585881556448603,
"grad_norm": 0.16860373318195343,
"learning_rate": 0.00019519144039161222,
"loss": 0.7098,
"step": 2250
},
{
"epoch": 0.05884854744772634,
"grad_norm": 0.16847743093967438,
"learning_rate": 0.00019514015872046833,
"loss": 0.7103,
"step": 2260
},
{
"epoch": 0.05910893925059239,
"grad_norm": 0.16181516647338867,
"learning_rate": 0.00019508861185590307,
"loss": 0.7561,
"step": 2270
},
{
"epoch": 0.059369331053458436,
"grad_norm": 0.16594484448432922,
"learning_rate": 0.0001950367999415981,
"loss": 0.7308,
"step": 2280
},
{
"epoch": 0.05962972285632448,
"grad_norm": 0.166441410779953,
"learning_rate": 0.00019498472312197375,
"loss": 0.735,
"step": 2290
},
{
"epoch": 0.05989011465919053,
"grad_norm": 0.16273920238018036,
"learning_rate": 0.00019493238154218886,
"loss": 0.7458,
"step": 2300
},
{
"epoch": 0.06015050646205657,
"grad_norm": 0.16227276623249054,
"learning_rate": 0.00019487977534814012,
"loss": 0.7143,
"step": 2310
},
{
"epoch": 0.06041089826492262,
"grad_norm": 0.1619606912136078,
"learning_rate": 0.000194826904686462,
"loss": 0.7285,
"step": 2320
},
{
"epoch": 0.060671290067788666,
"grad_norm": 0.1596045345067978,
"learning_rate": 0.00019477376970452603,
"loss": 0.7513,
"step": 2330
},
{
"epoch": 0.06093168187065471,
"grad_norm": 0.17504757642745972,
"learning_rate": 0.00019472037055044044,
"loss": 0.7376,
"step": 2340
},
{
"epoch": 0.06119207367352076,
"grad_norm": 0.1559167355298996,
"learning_rate": 0.00019466670737304992,
"loss": 0.7339,
"step": 2350
},
{
"epoch": 0.0614524654763868,
"grad_norm": 0.1624836027622223,
"learning_rate": 0.0001946127803219351,
"loss": 0.7258,
"step": 2360
},
{
"epoch": 0.061712857279252846,
"grad_norm": 0.17907138168811798,
"learning_rate": 0.00019455858954741206,
"loss": 0.72,
"step": 2370
},
{
"epoch": 0.061973249082118896,
"grad_norm": 0.15922705829143524,
"learning_rate": 0.00019450413520053202,
"loss": 0.7187,
"step": 2380
},
{
"epoch": 0.06223364088498494,
"grad_norm": 0.1552513986825943,
"learning_rate": 0.0001944494174330809,
"loss": 0.7183,
"step": 2390
},
{
"epoch": 0.06249403268785099,
"grad_norm": 0.16838514804840088,
"learning_rate": 0.00019439443639757885,
"loss": 0.7286,
"step": 2400
},
{
"epoch": 0.06275442449071703,
"grad_norm": 0.17352423071861267,
"learning_rate": 0.00019433919224727986,
"loss": 0.7436,
"step": 2410
},
{
"epoch": 0.06301481629358308,
"grad_norm": 0.17366603016853333,
"learning_rate": 0.0001942836851361713,
"loss": 0.7265,
"step": 2420
},
{
"epoch": 0.06327520809644913,
"grad_norm": 0.14833413064479828,
"learning_rate": 0.00019422791521897357,
"loss": 0.7234,
"step": 2430
},
{
"epoch": 0.06353559989931518,
"grad_norm": 0.16602723300457,
"learning_rate": 0.00019417188265113958,
"loss": 0.725,
"step": 2440
},
{
"epoch": 0.06379599170218121,
"grad_norm": 0.17290353775024414,
"learning_rate": 0.00019411558758885438,
"loss": 0.7174,
"step": 2450
},
{
"epoch": 0.06405638350504726,
"grad_norm": 0.16486665606498718,
"learning_rate": 0.0001940590301890346,
"loss": 0.7301,
"step": 2460
},
{
"epoch": 0.06431677530791331,
"grad_norm": 0.16255232691764832,
"learning_rate": 0.00019400221060932827,
"loss": 0.7462,
"step": 2470
},
{
"epoch": 0.06457716711077935,
"grad_norm": 0.16139757633209229,
"learning_rate": 0.0001939451290081141,
"loss": 0.7424,
"step": 2480
},
{
"epoch": 0.0648375589136454,
"grad_norm": 0.165597602725029,
"learning_rate": 0.00019388778554450117,
"loss": 0.7426,
"step": 2490
},
{
"epoch": 0.06509795071651145,
"grad_norm": 0.19819000363349915,
"learning_rate": 0.00019383018037832854,
"loss": 0.7356,
"step": 2500
}
],
"logging_steps": 10,
"max_steps": 19202,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.1729183440896e+18,
"train_batch_size": 5,
"trial_name": null,
"trial_params": null
}