legal-led / trainer_state.json
Mwnthai's picture
End of training
9cb9863 verified
Raw
History Blame Contribute Delete
115 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 4.0,
"eval_steps": 30000.0,
"global_step": 324984,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.006154149127341654,
"grad_norm": 2.092341661453247,
"learning_rate": 0.00015,
"loss": 5.0044,
"step": 500
},
{
"epoch": 0.012308298254683308,
"grad_norm": 2.625105619430542,
"learning_rate": 0.0003,
"loss": 3.8336,
"step": 1000
},
{
"epoch": 0.01846244738202496,
"grad_norm": 2.2265453338623047,
"learning_rate": 0.0002995370141735394,
"loss": 3.9081,
"step": 1500
},
{
"epoch": 0.024616596509366616,
"grad_norm": 1.888099193572998,
"learning_rate": 0.00029907402834707884,
"loss": 4.149,
"step": 2000
},
{
"epoch": 0.030770745636708268,
"grad_norm": 2.0151073932647705,
"learning_rate": 0.00029861104252061827,
"loss": 4.1269,
"step": 2500
},
{
"epoch": 0.03692489476404992,
"grad_norm": 1.8050236701965332,
"learning_rate": 0.0002981480566941577,
"loss": 4.1035,
"step": 3000
},
{
"epoch": 0.043079043891391576,
"grad_norm": 1.8458595275878906,
"learning_rate": 0.00029768507086769713,
"loss": 4.128,
"step": 3500
},
{
"epoch": 0.04923319301873323,
"grad_norm": 1.53248929977417,
"learning_rate": 0.00029722208504123657,
"loss": 4.1165,
"step": 4000
},
{
"epoch": 0.05538734214607488,
"grad_norm": 1.5712928771972656,
"learning_rate": 0.000296759099214776,
"loss": 4.1251,
"step": 4500
},
{
"epoch": 0.061541491273416536,
"grad_norm": 1.5576750040054321,
"learning_rate": 0.0002962961133883155,
"loss": 4.1188,
"step": 5000
},
{
"epoch": 0.06769564040075819,
"grad_norm": 1.102683424949646,
"learning_rate": 0.00029583312756185486,
"loss": 4.1077,
"step": 5500
},
{
"epoch": 0.07384978952809984,
"grad_norm": 0.9449716806411743,
"learning_rate": 0.0002953701417353943,
"loss": 4.1365,
"step": 6000
},
{
"epoch": 0.0800039386554415,
"grad_norm": 0.8101568818092346,
"learning_rate": 0.0002949071559089337,
"loss": 4.1129,
"step": 6500
},
{
"epoch": 0.08615808778278315,
"grad_norm": 0.6702257394790649,
"learning_rate": 0.00029444417008247316,
"loss": 4.1243,
"step": 7000
},
{
"epoch": 0.0923122369101248,
"grad_norm": 0.46337786316871643,
"learning_rate": 0.00029398118425601265,
"loss": 4.1169,
"step": 7500
},
{
"epoch": 0.09846638603746646,
"grad_norm": 0.4964500665664673,
"learning_rate": 0.0002935181984295521,
"loss": 4.0984,
"step": 8000
},
{
"epoch": 0.10462053516480811,
"grad_norm": 0.8461629748344421,
"learning_rate": 0.00029305521260309146,
"loss": 4.1145,
"step": 8500
},
{
"epoch": 0.11077468429214976,
"grad_norm": 0.6422436237335205,
"learning_rate": 0.0002925922267766309,
"loss": 4.0772,
"step": 9000
},
{
"epoch": 0.11692883341949142,
"grad_norm": 0.6632367372512817,
"learning_rate": 0.0002921292409501704,
"loss": 4.1215,
"step": 9500
},
{
"epoch": 0.12308298254683307,
"grad_norm": 0.39363622665405273,
"learning_rate": 0.0002916662551237098,
"loss": 4.0933,
"step": 10000
},
{
"epoch": 0.12923713167417472,
"grad_norm": 0.569042980670929,
"learning_rate": 0.00029120326929724924,
"loss": 4.1197,
"step": 10500
},
{
"epoch": 0.13539128080151638,
"grad_norm": 0.2661289572715759,
"learning_rate": 0.00029074028347078867,
"loss": 4.0887,
"step": 11000
},
{
"epoch": 0.14154542992885805,
"grad_norm": 0.297193318605423,
"learning_rate": 0.0002902772976443281,
"loss": 4.0932,
"step": 11500
},
{
"epoch": 0.14769957905619968,
"grad_norm": 0.7171770930290222,
"learning_rate": 0.00028981431181786753,
"loss": 4.0815,
"step": 12000
},
{
"epoch": 0.15385372818354134,
"grad_norm": 0.646996259689331,
"learning_rate": 0.00028935132599140697,
"loss": 4.1041,
"step": 12500
},
{
"epoch": 0.160007877310883,
"grad_norm": 2.0741255283355713,
"learning_rate": 0.0002888883401649464,
"loss": 4.0795,
"step": 13000
},
{
"epoch": 0.16616202643822464,
"grad_norm": 0.49319279193878174,
"learning_rate": 0.00028842535433848583,
"loss": 4.1045,
"step": 13500
},
{
"epoch": 0.1723161755655663,
"grad_norm": 1.0520975589752197,
"learning_rate": 0.00028796236851202526,
"loss": 4.0949,
"step": 14000
},
{
"epoch": 0.17847032469290797,
"grad_norm": 0.2214071899652481,
"learning_rate": 0.0002874993826855647,
"loss": 4.1167,
"step": 14500
},
{
"epoch": 0.1846244738202496,
"grad_norm": 0.3094998896121979,
"learning_rate": 0.0002870363968591041,
"loss": 4.1129,
"step": 15000
},
{
"epoch": 0.19077862294759126,
"grad_norm": 0.34810543060302734,
"learning_rate": 0.00028657341103264356,
"loss": 4.0916,
"step": 15500
},
{
"epoch": 0.19693277207493293,
"grad_norm": 0.418119341135025,
"learning_rate": 0.000286110425206183,
"loss": 4.0734,
"step": 16000
},
{
"epoch": 0.20308692120227456,
"grad_norm": 0.6338772177696228,
"learning_rate": 0.0002856474393797224,
"loss": 4.0812,
"step": 16500
},
{
"epoch": 0.20924107032961622,
"grad_norm": 0.5320194959640503,
"learning_rate": 0.00028518445355326185,
"loss": 4.0927,
"step": 17000
},
{
"epoch": 0.2153952194569579,
"grad_norm": 0.8376117944717407,
"learning_rate": 0.0002847214677268013,
"loss": 4.0998,
"step": 17500
},
{
"epoch": 0.22154936858429952,
"grad_norm": 0.5754292607307434,
"learning_rate": 0.0002842584819003407,
"loss": 4.1012,
"step": 18000
},
{
"epoch": 0.22770351771164118,
"grad_norm": 1.2594908475875854,
"learning_rate": 0.00028379549607388015,
"loss": 4.0926,
"step": 18500
},
{
"epoch": 0.23385766683898285,
"grad_norm": 1.6177163124084473,
"learning_rate": 0.0002833325102474196,
"loss": 4.0948,
"step": 19000
},
{
"epoch": 0.24001181596632448,
"grad_norm": 1.4938915967941284,
"learning_rate": 0.00028286952442095907,
"loss": 4.1028,
"step": 19500
},
{
"epoch": 0.24616596509366614,
"grad_norm": 1.118909239768982,
"learning_rate": 0.00028240653859449845,
"loss": 4.1197,
"step": 20000
},
{
"epoch": 0.2523201142210078,
"grad_norm": 0.4127946197986603,
"learning_rate": 0.0002819435527680379,
"loss": 4.0846,
"step": 20500
},
{
"epoch": 0.25847426334834944,
"grad_norm": 0.30985167622566223,
"learning_rate": 0.0002814805669415773,
"loss": 4.1061,
"step": 21000
},
{
"epoch": 0.26462841247569113,
"grad_norm": 1.9164427518844604,
"learning_rate": 0.0002810175811151168,
"loss": 4.1081,
"step": 21500
},
{
"epoch": 0.27078256160303277,
"grad_norm": 2.2871201038360596,
"learning_rate": 0.00028055459528865623,
"loss": 4.107,
"step": 22000
},
{
"epoch": 0.2769367107303744,
"grad_norm": 1.8674062490463257,
"learning_rate": 0.00028009160946219566,
"loss": 4.0785,
"step": 22500
},
{
"epoch": 0.2830908598577161,
"grad_norm": 1.2295348644256592,
"learning_rate": 0.00027962862363573504,
"loss": 4.0808,
"step": 23000
},
{
"epoch": 0.2892450089850577,
"grad_norm": 1.4836262464523315,
"learning_rate": 0.0002791656378092745,
"loss": 4.0992,
"step": 23500
},
{
"epoch": 0.29539915811239936,
"grad_norm": 0.18524084985256195,
"learning_rate": 0.00027870265198281396,
"loss": 4.0937,
"step": 24000
},
{
"epoch": 0.30155330723974105,
"grad_norm": 2.11242413520813,
"learning_rate": 0.0002782396661563534,
"loss": 4.1074,
"step": 24500
},
{
"epoch": 0.3077074563670827,
"grad_norm": 1.2607438564300537,
"learning_rate": 0.0002777766803298928,
"loss": 4.1116,
"step": 25000
},
{
"epoch": 0.3138616054944243,
"grad_norm": 1.5996503829956055,
"learning_rate": 0.00027731369450343225,
"loss": 4.1001,
"step": 25500
},
{
"epoch": 0.320015754621766,
"grad_norm": 0.8358060717582703,
"learning_rate": 0.0002768507086769717,
"loss": 4.0989,
"step": 26000
},
{
"epoch": 0.32616990374910765,
"grad_norm": 0.48429960012435913,
"learning_rate": 0.0002763877228505111,
"loss": 4.0875,
"step": 26500
},
{
"epoch": 0.3323240528764493,
"grad_norm": 5.845719337463379,
"learning_rate": 0.00027592473702405055,
"loss": 4.0954,
"step": 27000
},
{
"epoch": 0.338478202003791,
"grad_norm": 0.5381409525871277,
"learning_rate": 0.00027546175119759,
"loss": 4.1119,
"step": 27500
},
{
"epoch": 0.3446323511311326,
"grad_norm": 1.4658836126327515,
"learning_rate": 0.0002749987653711294,
"loss": 4.1049,
"step": 28000
},
{
"epoch": 0.35078650025847424,
"grad_norm": 1.774096131324768,
"learning_rate": 0.00027453577954466885,
"loss": 4.0797,
"step": 28500
},
{
"epoch": 0.35694064938581593,
"grad_norm": 0.40620070695877075,
"learning_rate": 0.0002740727937182083,
"loss": 4.089,
"step": 29000
},
{
"epoch": 0.36309479851315757,
"grad_norm": 1.0200700759887695,
"learning_rate": 0.0002736098078917477,
"loss": 4.107,
"step": 29500
},
{
"epoch": 0.3692489476404992,
"grad_norm": 0.9029337763786316,
"learning_rate": 0.00027314682206528714,
"loss": 4.1019,
"step": 30000
},
{
"epoch": 0.3754030967678409,
"grad_norm": 2.974106550216675,
"learning_rate": 0.0002726838362388266,
"loss": 4.1006,
"step": 30500
},
{
"epoch": 0.38155724589518253,
"grad_norm": 1.8245761394500732,
"learning_rate": 0.000272220850412366,
"loss": 4.1021,
"step": 31000
},
{
"epoch": 0.38771139502252416,
"grad_norm": 0.6887871623039246,
"learning_rate": 0.00027175786458590544,
"loss": 4.0841,
"step": 31500
},
{
"epoch": 0.39386554414986585,
"grad_norm": 0.6739060878753662,
"learning_rate": 0.00027129487875944487,
"loss": 4.1031,
"step": 32000
},
{
"epoch": 0.4000196932772075,
"grad_norm": 2.433579921722412,
"learning_rate": 0.0002708318929329843,
"loss": 4.0823,
"step": 32500
},
{
"epoch": 0.4061738424045491,
"grad_norm": 1.9396827220916748,
"learning_rate": 0.00027036890710652374,
"loss": 4.0815,
"step": 33000
},
{
"epoch": 0.4123279915318908,
"grad_norm": 1.4887537956237793,
"learning_rate": 0.0002699059212800632,
"loss": 4.0989,
"step": 33500
},
{
"epoch": 0.41848214065923245,
"grad_norm": 3.702249050140381,
"learning_rate": 0.00026944293545360265,
"loss": 4.1073,
"step": 34000
},
{
"epoch": 0.4246362897865741,
"grad_norm": 3.2793872356414795,
"learning_rate": 0.00026897994962714203,
"loss": 4.0918,
"step": 34500
},
{
"epoch": 0.4307904389139158,
"grad_norm": 2.0356898307800293,
"learning_rate": 0.00026851696380068146,
"loss": 4.1154,
"step": 35000
},
{
"epoch": 0.4369445880412574,
"grad_norm": 1.4987791776657104,
"learning_rate": 0.00026805397797422095,
"loss": 4.0831,
"step": 35500
},
{
"epoch": 0.44309873716859904,
"grad_norm": 2.4620182514190674,
"learning_rate": 0.0002675909921477604,
"loss": 4.0845,
"step": 36000
},
{
"epoch": 0.44925288629594073,
"grad_norm": 3.3095810413360596,
"learning_rate": 0.0002671280063212998,
"loss": 4.11,
"step": 36500
},
{
"epoch": 0.45540703542328237,
"grad_norm": 0.38411280512809753,
"learning_rate": 0.00026666502049483925,
"loss": 4.0833,
"step": 37000
},
{
"epoch": 0.461561184550624,
"grad_norm": 1.105375051498413,
"learning_rate": 0.0002662020346683786,
"loss": 4.1033,
"step": 37500
},
{
"epoch": 0.4677153336779657,
"grad_norm": 2.4970552921295166,
"learning_rate": 0.0002657390488419181,
"loss": 4.0883,
"step": 38000
},
{
"epoch": 0.47386948280530733,
"grad_norm": 0.12203908711671829,
"learning_rate": 0.00026527606301545754,
"loss": 4.1037,
"step": 38500
},
{
"epoch": 0.48002363193264896,
"grad_norm": 2.4065377712249756,
"learning_rate": 0.000264813077188997,
"loss": 4.0982,
"step": 39000
},
{
"epoch": 0.48617778105999065,
"grad_norm": 0.8224688768386841,
"learning_rate": 0.0002643500913625364,
"loss": 4.0929,
"step": 39500
},
{
"epoch": 0.4923319301873323,
"grad_norm": 3.7842533588409424,
"learning_rate": 0.00026388710553607584,
"loss": 4.0931,
"step": 40000
},
{
"epoch": 0.498486079314674,
"grad_norm": 3.7798380851745605,
"learning_rate": 0.00026342411970961527,
"loss": 4.0889,
"step": 40500
},
{
"epoch": 0.5046402284420156,
"grad_norm": 1.76235032081604,
"learning_rate": 0.0002629611338831547,
"loss": 4.086,
"step": 41000
},
{
"epoch": 0.5107943775693573,
"grad_norm": 2.1387345790863037,
"learning_rate": 0.00026249814805669414,
"loss": 4.0871,
"step": 41500
},
{
"epoch": 0.5169485266966989,
"grad_norm": 3.1453747749328613,
"learning_rate": 0.00026203516223023357,
"loss": 4.1148,
"step": 42000
},
{
"epoch": 0.5231026758240406,
"grad_norm": 3.683594226837158,
"learning_rate": 0.000261572176403773,
"loss": 4.0974,
"step": 42500
},
{
"epoch": 0.5292568249513823,
"grad_norm": 2.171173334121704,
"learning_rate": 0.00026110919057731243,
"loss": 4.1,
"step": 43000
},
{
"epoch": 0.5354109740787238,
"grad_norm": 0.12354115396738052,
"learning_rate": 0.00026064620475085186,
"loss": 4.1038,
"step": 43500
},
{
"epoch": 0.5415651232060655,
"grad_norm": 3.5541982650756836,
"learning_rate": 0.0002601832189243913,
"loss": 4.1057,
"step": 44000
},
{
"epoch": 0.5477192723334072,
"grad_norm": 4.4840874671936035,
"learning_rate": 0.00025972023309793073,
"loss": 4.0899,
"step": 44500
},
{
"epoch": 0.5538734214607488,
"grad_norm": 3.817657947540283,
"learning_rate": 0.00025925724727147016,
"loss": 4.0998,
"step": 45000
},
{
"epoch": 0.5600275705880905,
"grad_norm": 1.6138055324554443,
"learning_rate": 0.00025879426144500965,
"loss": 4.1029,
"step": 45500
},
{
"epoch": 0.5661817197154322,
"grad_norm": 2.5960400104522705,
"learning_rate": 0.000258331275618549,
"loss": 4.089,
"step": 46000
},
{
"epoch": 0.5723358688427738,
"grad_norm": 4.017026901245117,
"learning_rate": 0.00025786828979208846,
"loss": 4.0955,
"step": 46500
},
{
"epoch": 0.5784900179701155,
"grad_norm": 8.38429069519043,
"learning_rate": 0.0002574053039656279,
"loss": 4.0986,
"step": 47000
},
{
"epoch": 0.5846441670974571,
"grad_norm": 2.181142568588257,
"learning_rate": 0.0002569423181391673,
"loss": 4.0983,
"step": 47500
},
{
"epoch": 0.5907983162247987,
"grad_norm": 1.965347170829773,
"learning_rate": 0.0002564793323127068,
"loss": 4.0878,
"step": 48000
},
{
"epoch": 0.5969524653521404,
"grad_norm": 9.256057739257812,
"learning_rate": 0.00025601634648624624,
"loss": 4.1051,
"step": 48500
},
{
"epoch": 0.6031066144794821,
"grad_norm": 0.9311700463294983,
"learning_rate": 0.0002555533606597856,
"loss": 4.097,
"step": 49000
},
{
"epoch": 0.6092607636068237,
"grad_norm": 0.9691674709320068,
"learning_rate": 0.00025509037483332505,
"loss": 4.0928,
"step": 49500
},
{
"epoch": 0.6154149127341654,
"grad_norm": 3.4853315353393555,
"learning_rate": 0.00025462738900686454,
"loss": 4.0946,
"step": 50000
},
{
"epoch": 0.6215690618615071,
"grad_norm": 2.781506299972534,
"learning_rate": 0.00025416440318040397,
"loss": 4.0732,
"step": 50500
},
{
"epoch": 0.6277232109888486,
"grad_norm": 1.5784199237823486,
"learning_rate": 0.0002537014173539434,
"loss": 4.1129,
"step": 51000
},
{
"epoch": 0.6338773601161903,
"grad_norm": 3.7334139347076416,
"learning_rate": 0.00025323843152748283,
"loss": 4.1002,
"step": 51500
},
{
"epoch": 0.640031509243532,
"grad_norm": 5.097366809844971,
"learning_rate": 0.00025277544570102226,
"loss": 4.0966,
"step": 52000
},
{
"epoch": 0.6461856583708736,
"grad_norm": 0.38809725642204285,
"learning_rate": 0.0002523124598745617,
"loss": 4.1146,
"step": 52500
},
{
"epoch": 0.6523398074982153,
"grad_norm": 1.1312806606292725,
"learning_rate": 0.00025184947404810113,
"loss": 4.0986,
"step": 53000
},
{
"epoch": 0.658493956625557,
"grad_norm": 2.7945168018341064,
"learning_rate": 0.00025138648822164056,
"loss": 4.0655,
"step": 53500
},
{
"epoch": 0.6646481057528986,
"grad_norm": 3.515511989593506,
"learning_rate": 0.00025092350239518,
"loss": 4.1085,
"step": 54000
},
{
"epoch": 0.6708022548802403,
"grad_norm": 3.6539127826690674,
"learning_rate": 0.0002504605165687194,
"loss": 4.0879,
"step": 54500
},
{
"epoch": 0.676956404007582,
"grad_norm": 1.3498042821884155,
"learning_rate": 0.00024999753074225886,
"loss": 4.1058,
"step": 55000
},
{
"epoch": 0.6831105531349235,
"grad_norm": 0.7177558541297913,
"learning_rate": 0.0002495345449157983,
"loss": 4.0873,
"step": 55500
},
{
"epoch": 0.6892647022622652,
"grad_norm": 0.4013034999370575,
"learning_rate": 0.0002490715590893377,
"loss": 4.0982,
"step": 56000
},
{
"epoch": 0.6954188513896069,
"grad_norm": 1.7527958154678345,
"learning_rate": 0.00024860857326287715,
"loss": 4.1044,
"step": 56500
},
{
"epoch": 0.7015730005169485,
"grad_norm": 6.336050510406494,
"learning_rate": 0.0002481455874364166,
"loss": 4.0944,
"step": 57000
},
{
"epoch": 0.7077271496442902,
"grad_norm": 3.1961464881896973,
"learning_rate": 0.000247682601609956,
"loss": 4.0779,
"step": 57500
},
{
"epoch": 0.7138812987716319,
"grad_norm": 1.864181399345398,
"learning_rate": 0.00024721961578349545,
"loss": 4.0959,
"step": 58000
},
{
"epoch": 0.7200354478989734,
"grad_norm": 2.878396987915039,
"learning_rate": 0.0002467566299570349,
"loss": 4.0959,
"step": 58500
},
{
"epoch": 0.7261895970263151,
"grad_norm": 1.3051272630691528,
"learning_rate": 0.0002462936441305743,
"loss": 4.1082,
"step": 59000
},
{
"epoch": 0.7323437461536568,
"grad_norm": 1.0373369455337524,
"learning_rate": 0.00024583065830411375,
"loss": 4.0909,
"step": 59500
},
{
"epoch": 0.7384978952809984,
"grad_norm": 0.7805006504058838,
"learning_rate": 0.00024536767247765323,
"loss": 4.0922,
"step": 60000
},
{
"epoch": 0.7446520444083401,
"grad_norm": 1.5807021856307983,
"learning_rate": 0.0002449046866511926,
"loss": 4.0988,
"step": 60500
},
{
"epoch": 0.7508061935356818,
"grad_norm": 2.8410210609436035,
"learning_rate": 0.00024444170082473204,
"loss": 4.0952,
"step": 61000
},
{
"epoch": 0.7569603426630234,
"grad_norm": 3.121964454650879,
"learning_rate": 0.0002439787149982715,
"loss": 4.0938,
"step": 61500
},
{
"epoch": 0.7631144917903651,
"grad_norm": 4.728808879852295,
"learning_rate": 0.00024351572917181093,
"loss": 4.0817,
"step": 62000
},
{
"epoch": 0.7692686409177067,
"grad_norm": 1.653712511062622,
"learning_rate": 0.00024305274334535036,
"loss": 4.0992,
"step": 62500
},
{
"epoch": 0.7754227900450483,
"grad_norm": 4.432304859161377,
"learning_rate": 0.00024258975751888982,
"loss": 4.095,
"step": 63000
},
{
"epoch": 0.78157693917239,
"grad_norm": 0.7322250008583069,
"learning_rate": 0.00024212677169242923,
"loss": 4.084,
"step": 63500
},
{
"epoch": 0.7877310882997317,
"grad_norm": 0.9135098457336426,
"learning_rate": 0.00024166378586596866,
"loss": 4.1022,
"step": 64000
},
{
"epoch": 0.7938852374270733,
"grad_norm": 0.8668899536132812,
"learning_rate": 0.0002412008000395081,
"loss": 4.0746,
"step": 64500
},
{
"epoch": 0.800039386554415,
"grad_norm": 2.584885835647583,
"learning_rate": 0.00024073781421304755,
"loss": 4.0923,
"step": 65000
},
{
"epoch": 0.8061935356817567,
"grad_norm": 4.204476833343506,
"learning_rate": 0.00024027482838658698,
"loss": 4.0962,
"step": 65500
},
{
"epoch": 0.8123476848090982,
"grad_norm": 2.48603892326355,
"learning_rate": 0.00023981184256012642,
"loss": 4.0898,
"step": 66000
},
{
"epoch": 0.8185018339364399,
"grad_norm": 8.403986930847168,
"learning_rate": 0.00023934885673366582,
"loss": 4.1102,
"step": 66500
},
{
"epoch": 0.8246559830637816,
"grad_norm": 2.5791406631469727,
"learning_rate": 0.00023888587090720528,
"loss": 4.1114,
"step": 67000
},
{
"epoch": 0.8308101321911232,
"grad_norm": 2.5820565223693848,
"learning_rate": 0.0002384228850807447,
"loss": 4.0991,
"step": 67500
},
{
"epoch": 0.8369642813184649,
"grad_norm": 3.1282472610473633,
"learning_rate": 0.00023795989925428414,
"loss": 4.0976,
"step": 68000
},
{
"epoch": 0.8431184304458066,
"grad_norm": 2.349026679992676,
"learning_rate": 0.00023749691342782358,
"loss": 4.0896,
"step": 68500
},
{
"epoch": 0.8492725795731482,
"grad_norm": 0.8069925904273987,
"learning_rate": 0.00023703392760136298,
"loss": 4.0983,
"step": 69000
},
{
"epoch": 0.8554267287004899,
"grad_norm": 1.1102579832077026,
"learning_rate": 0.00023657094177490244,
"loss": 4.1028,
"step": 69500
},
{
"epoch": 0.8615808778278315,
"grad_norm": 0.3178214132785797,
"learning_rate": 0.00023610795594844187,
"loss": 4.0822,
"step": 70000
},
{
"epoch": 0.8677350269551731,
"grad_norm": 1.18157160282135,
"learning_rate": 0.0002356449701219813,
"loss": 4.1023,
"step": 70500
},
{
"epoch": 0.8738891760825148,
"grad_norm": 4.670410633087158,
"learning_rate": 0.00023518198429552076,
"loss": 4.0942,
"step": 71000
},
{
"epoch": 0.8800433252098565,
"grad_norm": 2.3747074604034424,
"learning_rate": 0.0002347189984690602,
"loss": 4.0722,
"step": 71500
},
{
"epoch": 0.8861974743371981,
"grad_norm": 4.259999752044678,
"learning_rate": 0.0002342560126425996,
"loss": 4.0931,
"step": 72000
},
{
"epoch": 0.8923516234645398,
"grad_norm": 2.4184932708740234,
"learning_rate": 0.00023379302681613903,
"loss": 4.0914,
"step": 72500
},
{
"epoch": 0.8985057725918815,
"grad_norm": 0.9239826202392578,
"learning_rate": 0.0002333300409896785,
"loss": 4.0937,
"step": 73000
},
{
"epoch": 0.904659921719223,
"grad_norm": 2.7900195121765137,
"learning_rate": 0.00023286705516321792,
"loss": 4.0877,
"step": 73500
},
{
"epoch": 0.9108140708465647,
"grad_norm": 1.7842776775360107,
"learning_rate": 0.00023240406933675736,
"loss": 4.1047,
"step": 74000
},
{
"epoch": 0.9169682199739064,
"grad_norm": 1.1505067348480225,
"learning_rate": 0.0002319410835102968,
"loss": 4.0947,
"step": 74500
},
{
"epoch": 0.923122369101248,
"grad_norm": 1.2708269357681274,
"learning_rate": 0.0002314780976838362,
"loss": 4.1042,
"step": 75000
},
{
"epoch": 0.9292765182285897,
"grad_norm": 1.7025552988052368,
"learning_rate": 0.00023101511185737565,
"loss": 4.1106,
"step": 75500
},
{
"epoch": 0.9354306673559314,
"grad_norm": 3.4087588787078857,
"learning_rate": 0.00023055212603091509,
"loss": 4.0969,
"step": 76000
},
{
"epoch": 0.941584816483273,
"grad_norm": 5.700456619262695,
"learning_rate": 0.00023008914020445452,
"loss": 4.0831,
"step": 76500
},
{
"epoch": 0.9477389656106147,
"grad_norm": 2.284078598022461,
"learning_rate": 0.00022962615437799398,
"loss": 4.0884,
"step": 77000
},
{
"epoch": 0.9538931147379563,
"grad_norm": 4.581364154815674,
"learning_rate": 0.0002291631685515334,
"loss": 4.0984,
"step": 77500
},
{
"epoch": 0.9600472638652979,
"grad_norm": 1.655754566192627,
"learning_rate": 0.00022870018272507281,
"loss": 4.1103,
"step": 78000
},
{
"epoch": 0.9662014129926396,
"grad_norm": 1.3334680795669556,
"learning_rate": 0.00022823719689861225,
"loss": 4.0984,
"step": 78500
},
{
"epoch": 0.9723555621199813,
"grad_norm": 0.851294219493866,
"learning_rate": 0.00022777421107215168,
"loss": 4.1095,
"step": 79000
},
{
"epoch": 0.978509711247323,
"grad_norm": 2.8952951431274414,
"learning_rate": 0.00022731122524569114,
"loss": 4.1064,
"step": 79500
},
{
"epoch": 0.9846638603746646,
"grad_norm": 5.8795013427734375,
"learning_rate": 0.00022684823941923057,
"loss": 4.0916,
"step": 80000
},
{
"epoch": 0.9908180095020063,
"grad_norm": 0.7731097936630249,
"learning_rate": 0.00022638525359276997,
"loss": 4.1022,
"step": 80500
},
{
"epoch": 0.996972158629348,
"grad_norm": 0.7958303689956665,
"learning_rate": 0.0002259222677663094,
"loss": 4.0818,
"step": 81000
},
{
"epoch": 1.0031263077566897,
"grad_norm": 2.979816198348999,
"learning_rate": 0.00022545928193984887,
"loss": 4.1006,
"step": 81500
},
{
"epoch": 1.0092804568840312,
"grad_norm": 0.7593286633491516,
"learning_rate": 0.0002249962961133883,
"loss": 4.0989,
"step": 82000
},
{
"epoch": 1.0154346060113728,
"grad_norm": 1.7182486057281494,
"learning_rate": 0.00022453331028692773,
"loss": 4.088,
"step": 82500
},
{
"epoch": 1.0215887551387146,
"grad_norm": 4.9435601234436035,
"learning_rate": 0.0002240703244604672,
"loss": 4.0891,
"step": 83000
},
{
"epoch": 1.0277429042660562,
"grad_norm": 0.6826997995376587,
"learning_rate": 0.0002236073386340066,
"loss": 4.0786,
"step": 83500
},
{
"epoch": 1.0338970533933978,
"grad_norm": 0.27785202860832214,
"learning_rate": 0.00022314435280754603,
"loss": 4.1007,
"step": 84000
},
{
"epoch": 1.0400512025207396,
"grad_norm": 5.7929606437683105,
"learning_rate": 0.00022268136698108546,
"loss": 4.0802,
"step": 84500
},
{
"epoch": 1.0462053516480811,
"grad_norm": 1.5252392292022705,
"learning_rate": 0.0002222183811546249,
"loss": 4.1036,
"step": 85000
},
{
"epoch": 1.0523595007754227,
"grad_norm": 1.1192035675048828,
"learning_rate": 0.00022175539532816435,
"loss": 4.1267,
"step": 85500
},
{
"epoch": 1.0585136499027645,
"grad_norm": 4.278738498687744,
"learning_rate": 0.00022129240950170378,
"loss": 4.1023,
"step": 86000
},
{
"epoch": 1.064667799030106,
"grad_norm": 1.0558756589889526,
"learning_rate": 0.00022082942367524319,
"loss": 4.0999,
"step": 86500
},
{
"epoch": 1.0708219481574477,
"grad_norm": 0.3059670627117157,
"learning_rate": 0.00022036643784878262,
"loss": 4.0979,
"step": 87000
},
{
"epoch": 1.0769760972847895,
"grad_norm": 1.7485718727111816,
"learning_rate": 0.00021990345202232208,
"loss": 4.0948,
"step": 87500
},
{
"epoch": 1.083130246412131,
"grad_norm": 1.7698047161102295,
"learning_rate": 0.0002194404661958615,
"loss": 4.099,
"step": 88000
},
{
"epoch": 1.0892843955394726,
"grad_norm": 1.0428645610809326,
"learning_rate": 0.00021897748036940094,
"loss": 4.1021,
"step": 88500
},
{
"epoch": 1.0954385446668145,
"grad_norm": 1.9697622060775757,
"learning_rate": 0.0002185144945429404,
"loss": 4.1033,
"step": 89000
},
{
"epoch": 1.101592693794156,
"grad_norm": 3.6831917762756348,
"learning_rate": 0.0002180515087164798,
"loss": 4.0934,
"step": 89500
},
{
"epoch": 1.1077468429214976,
"grad_norm": 1.3112094402313232,
"learning_rate": 0.00021758852289001924,
"loss": 4.0986,
"step": 90000
},
{
"epoch": 1.1139009920488394,
"grad_norm": 1.110479712486267,
"learning_rate": 0.00021712553706355867,
"loss": 4.0934,
"step": 90500
},
{
"epoch": 1.120055141176181,
"grad_norm": 2.9965875148773193,
"learning_rate": 0.0002166625512370981,
"loss": 4.083,
"step": 91000
},
{
"epoch": 1.1262092903035226,
"grad_norm": 4.021323204040527,
"learning_rate": 0.00021619956541063756,
"loss": 4.0998,
"step": 91500
},
{
"epoch": 1.1323634394308644,
"grad_norm": 1.4921329021453857,
"learning_rate": 0.000215736579584177,
"loss": 4.0892,
"step": 92000
},
{
"epoch": 1.138517588558206,
"grad_norm": 0.5872803330421448,
"learning_rate": 0.0002152735937577164,
"loss": 4.0977,
"step": 92500
},
{
"epoch": 1.1446717376855475,
"grad_norm": 1.0161774158477783,
"learning_rate": 0.00021481060793125583,
"loss": 4.1057,
"step": 93000
},
{
"epoch": 1.1508258868128893,
"grad_norm": 0.779848039150238,
"learning_rate": 0.0002143476221047953,
"loss": 4.1045,
"step": 93500
},
{
"epoch": 1.156980035940231,
"grad_norm": 0.45371928811073303,
"learning_rate": 0.00021388463627833472,
"loss": 4.1195,
"step": 94000
},
{
"epoch": 1.1631341850675725,
"grad_norm": 2.4952192306518555,
"learning_rate": 0.00021342165045187415,
"loss": 4.1148,
"step": 94500
},
{
"epoch": 1.1692883341949143,
"grad_norm": 2.1651134490966797,
"learning_rate": 0.00021295866462541356,
"loss": 4.0884,
"step": 95000
},
{
"epoch": 1.1754424833222559,
"grad_norm": 1.2217682600021362,
"learning_rate": 0.00021249567879895302,
"loss": 4.0999,
"step": 95500
},
{
"epoch": 1.1815966324495975,
"grad_norm": 0.47837311029434204,
"learning_rate": 0.00021203269297249245,
"loss": 4.0965,
"step": 96000
},
{
"epoch": 1.1877507815769393,
"grad_norm": 5.905663013458252,
"learning_rate": 0.00021156970714603188,
"loss": 4.1012,
"step": 96500
},
{
"epoch": 1.1939049307042808,
"grad_norm": 0.5790697932243347,
"learning_rate": 0.00021110672131957131,
"loss": 4.1098,
"step": 97000
},
{
"epoch": 1.2000590798316224,
"grad_norm": 0.6411845684051514,
"learning_rate": 0.00021064373549311077,
"loss": 4.0918,
"step": 97500
},
{
"epoch": 1.2062132289589642,
"grad_norm": 0.6363158822059631,
"learning_rate": 0.00021018074966665018,
"loss": 4.0948,
"step": 98000
},
{
"epoch": 1.2123673780863058,
"grad_norm": 0.35349979996681213,
"learning_rate": 0.0002097177638401896,
"loss": 4.0999,
"step": 98500
},
{
"epoch": 1.2185215272136474,
"grad_norm": 4.329227447509766,
"learning_rate": 0.00020925477801372904,
"loss": 4.0939,
"step": 99000
},
{
"epoch": 1.2246756763409892,
"grad_norm": 3.660310983657837,
"learning_rate": 0.0002087917921872685,
"loss": 4.0942,
"step": 99500
},
{
"epoch": 1.2308298254683308,
"grad_norm": 2.401116371154785,
"learning_rate": 0.00020832880636080793,
"loss": 4.098,
"step": 100000
},
{
"epoch": 1.2369839745956723,
"grad_norm": 0.6453625559806824,
"learning_rate": 0.00020786582053434737,
"loss": 4.1028,
"step": 100500
},
{
"epoch": 1.2431381237230141,
"grad_norm": 1.2233339548110962,
"learning_rate": 0.00020740283470788677,
"loss": 4.0887,
"step": 101000
},
{
"epoch": 1.2492922728503557,
"grad_norm": 4.921336650848389,
"learning_rate": 0.00020693984888142623,
"loss": 4.1008,
"step": 101500
},
{
"epoch": 1.2554464219776973,
"grad_norm": 0.9309550523757935,
"learning_rate": 0.00020647686305496566,
"loss": 4.1094,
"step": 102000
},
{
"epoch": 1.261600571105039,
"grad_norm": 2.209359645843506,
"learning_rate": 0.0002060138772285051,
"loss": 4.1101,
"step": 102500
},
{
"epoch": 1.2677547202323807,
"grad_norm": 0.7697844505310059,
"learning_rate": 0.00020555089140204453,
"loss": 4.1151,
"step": 103000
},
{
"epoch": 1.2739088693597223,
"grad_norm": 4.606212139129639,
"learning_rate": 0.00020508790557558399,
"loss": 4.1015,
"step": 103500
},
{
"epoch": 1.280063018487064,
"grad_norm": 1.7386395931243896,
"learning_rate": 0.0002046249197491234,
"loss": 4.1138,
"step": 104000
},
{
"epoch": 1.2862171676144056,
"grad_norm": 2.085214376449585,
"learning_rate": 0.00020416193392266282,
"loss": 4.1088,
"step": 104500
},
{
"epoch": 1.2923713167417472,
"grad_norm": 1.9936320781707764,
"learning_rate": 0.00020369894809620226,
"loss": 4.083,
"step": 105000
},
{
"epoch": 1.298525465869089,
"grad_norm": 0.9798199534416199,
"learning_rate": 0.00020323596226974171,
"loss": 4.1052,
"step": 105500
},
{
"epoch": 1.3046796149964306,
"grad_norm": 0.899678647518158,
"learning_rate": 0.00020277297644328115,
"loss": 4.1147,
"step": 106000
},
{
"epoch": 1.3108337641237722,
"grad_norm": 0.7392956018447876,
"learning_rate": 0.00020230999061682055,
"loss": 4.1112,
"step": 106500
},
{
"epoch": 1.316987913251114,
"grad_norm": 2.128492832183838,
"learning_rate": 0.00020184700479035998,
"loss": 4.1251,
"step": 107000
},
{
"epoch": 1.3231420623784556,
"grad_norm": 5.049408435821533,
"learning_rate": 0.00020138401896389944,
"loss": 4.0949,
"step": 107500
},
{
"epoch": 1.3292962115057971,
"grad_norm": 4.644421577453613,
"learning_rate": 0.00020092103313743887,
"loss": 4.1139,
"step": 108000
},
{
"epoch": 1.335450360633139,
"grad_norm": 2.6653685569763184,
"learning_rate": 0.0002004580473109783,
"loss": 4.1244,
"step": 108500
},
{
"epoch": 1.3416045097604805,
"grad_norm": 1.0980528593063354,
"learning_rate": 0.00019999506148451774,
"loss": 4.1208,
"step": 109000
},
{
"epoch": 1.347758658887822,
"grad_norm": 4.797991752624512,
"learning_rate": 0.00019953207565805714,
"loss": 4.126,
"step": 109500
},
{
"epoch": 1.353912808015164,
"grad_norm": 2.24348783493042,
"learning_rate": 0.0001990690898315966,
"loss": 4.1393,
"step": 110000
},
{
"epoch": 1.3600669571425055,
"grad_norm": 1.1769734621047974,
"learning_rate": 0.00019860610400513604,
"loss": 4.1478,
"step": 110500
},
{
"epoch": 1.366221106269847,
"grad_norm": 1.0057837963104248,
"learning_rate": 0.00019814311817867547,
"loss": 4.1229,
"step": 111000
},
{
"epoch": 1.3723752553971889,
"grad_norm": 5.748145580291748,
"learning_rate": 0.00019768013235221493,
"loss": 4.1302,
"step": 111500
},
{
"epoch": 1.3785294045245304,
"grad_norm": 1.36845862865448,
"learning_rate": 0.00019721714652575436,
"loss": 4.1217,
"step": 112000
},
{
"epoch": 1.384683553651872,
"grad_norm": 0.9179917573928833,
"learning_rate": 0.00019675416069929376,
"loss": 4.1465,
"step": 112500
},
{
"epoch": 1.3908377027792138,
"grad_norm": 2.5272738933563232,
"learning_rate": 0.0001962911748728332,
"loss": 4.1631,
"step": 113000
},
{
"epoch": 1.3969918519065554,
"grad_norm": 5.107125759124756,
"learning_rate": 0.00019582818904637263,
"loss": 4.1356,
"step": 113500
},
{
"epoch": 1.403146001033897,
"grad_norm": 5.968631744384766,
"learning_rate": 0.0001953652032199121,
"loss": 4.148,
"step": 114000
},
{
"epoch": 1.4093001501612388,
"grad_norm": 2.8107075691223145,
"learning_rate": 0.00019490221739345152,
"loss": 4.1626,
"step": 114500
},
{
"epoch": 1.4154542992885804,
"grad_norm": 3.8864150047302246,
"learning_rate": 0.00019443923156699095,
"loss": 4.1605,
"step": 115000
},
{
"epoch": 1.421608448415922,
"grad_norm": 0.7238738536834717,
"learning_rate": 0.00019397624574053036,
"loss": 4.1501,
"step": 115500
},
{
"epoch": 1.4277625975432637,
"grad_norm": 4.19093656539917,
"learning_rate": 0.00019351325991406982,
"loss": 4.1422,
"step": 116000
},
{
"epoch": 1.4339167466706053,
"grad_norm": 0.5995033979415894,
"learning_rate": 0.00019305027408760925,
"loss": 4.1496,
"step": 116500
},
{
"epoch": 1.440070895797947,
"grad_norm": 1.2837109565734863,
"learning_rate": 0.00019258728826114868,
"loss": 4.1257,
"step": 117000
},
{
"epoch": 1.4462250449252887,
"grad_norm": 4.454913139343262,
"learning_rate": 0.00019212430243468814,
"loss": 4.1268,
"step": 117500
},
{
"epoch": 1.4523791940526303,
"grad_norm": 0.16046346724033356,
"learning_rate": 0.00019166131660822757,
"loss": 4.1364,
"step": 118000
},
{
"epoch": 1.458533343179972,
"grad_norm": 0.5446693897247314,
"learning_rate": 0.00019119833078176698,
"loss": 4.1251,
"step": 118500
},
{
"epoch": 1.4646874923073137,
"grad_norm": 0.7152977585792542,
"learning_rate": 0.0001907353449553064,
"loss": 4.1346,
"step": 119000
},
{
"epoch": 1.4708416414346552,
"grad_norm": 2.160975933074951,
"learning_rate": 0.00019027235912884584,
"loss": 4.1215,
"step": 119500
},
{
"epoch": 1.4769957905619968,
"grad_norm": 4.624399662017822,
"learning_rate": 0.0001898093733023853,
"loss": 4.1152,
"step": 120000
},
{
"epoch": 1.4831499396893386,
"grad_norm": 3.8192062377929688,
"learning_rate": 0.00018934638747592473,
"loss": 4.107,
"step": 120500
},
{
"epoch": 1.4893040888166802,
"grad_norm": 1.5222162008285522,
"learning_rate": 0.00018888340164946414,
"loss": 4.1267,
"step": 121000
},
{
"epoch": 1.495458237944022,
"grad_norm": 0.45535144209861755,
"learning_rate": 0.00018842041582300357,
"loss": 4.1246,
"step": 121500
},
{
"epoch": 1.5016123870713636,
"grad_norm": 3.5713419914245605,
"learning_rate": 0.00018795742999654303,
"loss": 4.1589,
"step": 122000
},
{
"epoch": 1.5077665361987052,
"grad_norm": 3.76360821723938,
"learning_rate": 0.00018749444417008246,
"loss": 4.1279,
"step": 122500
},
{
"epoch": 1.5139206853260467,
"grad_norm": 0.7985491752624512,
"learning_rate": 0.0001870314583436219,
"loss": 4.1329,
"step": 123000
},
{
"epoch": 1.5200748344533883,
"grad_norm": 5.686063289642334,
"learning_rate": 0.00018656847251716135,
"loss": 4.1241,
"step": 123500
},
{
"epoch": 1.5262289835807301,
"grad_norm": 2.424764394760132,
"learning_rate": 0.00018610548669070076,
"loss": 4.1231,
"step": 124000
},
{
"epoch": 1.532383132708072,
"grad_norm": 3.832352638244629,
"learning_rate": 0.0001856425008642402,
"loss": 4.1149,
"step": 124500
},
{
"epoch": 1.5385372818354135,
"grad_norm": 0.7271844744682312,
"learning_rate": 0.00018517951503777962,
"loss": 4.129,
"step": 125000
},
{
"epoch": 1.544691430962755,
"grad_norm": 4.204314708709717,
"learning_rate": 0.00018471652921131905,
"loss": 4.1446,
"step": 125500
},
{
"epoch": 1.5508455800900967,
"grad_norm": 1.8513261079788208,
"learning_rate": 0.0001842535433848585,
"loss": 4.1465,
"step": 126000
},
{
"epoch": 1.5569997292174382,
"grad_norm": 2.9440431594848633,
"learning_rate": 0.00018379055755839794,
"loss": 4.1283,
"step": 126500
},
{
"epoch": 1.56315387834478,
"grad_norm": 3.142031192779541,
"learning_rate": 0.00018332757173193735,
"loss": 4.1237,
"step": 127000
},
{
"epoch": 1.5693080274721218,
"grad_norm": 1.904176115989685,
"learning_rate": 0.00018286458590547678,
"loss": 4.1101,
"step": 127500
},
{
"epoch": 1.5754621765994634,
"grad_norm": 2.4365878105163574,
"learning_rate": 0.00018240160007901624,
"loss": 4.1247,
"step": 128000
},
{
"epoch": 1.581616325726805,
"grad_norm": 1.5106476545333862,
"learning_rate": 0.00018193861425255567,
"loss": 4.1243,
"step": 128500
},
{
"epoch": 1.5877704748541466,
"grad_norm": 1.3250341415405273,
"learning_rate": 0.0001814756284260951,
"loss": 4.1309,
"step": 129000
},
{
"epoch": 1.5939246239814882,
"grad_norm": 5.156502723693848,
"learning_rate": 0.00018101264259963456,
"loss": 4.1307,
"step": 129500
},
{
"epoch": 1.60007877310883,
"grad_norm": 0.4731999933719635,
"learning_rate": 0.00018054965677317397,
"loss": 4.1197,
"step": 130000
},
{
"epoch": 1.6062329222361718,
"grad_norm": 2.638735294342041,
"learning_rate": 0.0001800866709467134,
"loss": 4.1237,
"step": 130500
},
{
"epoch": 1.6123870713635133,
"grad_norm": 3.110156297683716,
"learning_rate": 0.00017962368512025283,
"loss": 4.1235,
"step": 131000
},
{
"epoch": 1.618541220490855,
"grad_norm": 0.2362884283065796,
"learning_rate": 0.00017916069929379226,
"loss": 4.1447,
"step": 131500
},
{
"epoch": 1.6246953696181965,
"grad_norm": 5.515174388885498,
"learning_rate": 0.00017869771346733172,
"loss": 4.1368,
"step": 132000
},
{
"epoch": 1.6308495187455383,
"grad_norm": 5.211053848266602,
"learning_rate": 0.00017823472764087113,
"loss": 4.1277,
"step": 132500
},
{
"epoch": 1.6370036678728799,
"grad_norm": 6.04197359085083,
"learning_rate": 0.00017777174181441056,
"loss": 4.106,
"step": 133000
},
{
"epoch": 1.6431578170002217,
"grad_norm": 0.6410980224609375,
"learning_rate": 0.00017730875598795,
"loss": 4.1593,
"step": 133500
},
{
"epoch": 1.6493119661275633,
"grad_norm": 2.109435558319092,
"learning_rate": 0.00017684577016148945,
"loss": 4.1151,
"step": 134000
},
{
"epoch": 1.6554661152549048,
"grad_norm": 2.0466954708099365,
"learning_rate": 0.00017638278433502888,
"loss": 4.1223,
"step": 134500
},
{
"epoch": 1.6616202643822464,
"grad_norm": 1.3198188543319702,
"learning_rate": 0.00017591979850856832,
"loss": 4.1271,
"step": 135000
},
{
"epoch": 1.6677744135095882,
"grad_norm": 3.2391276359558105,
"learning_rate": 0.00017545681268210772,
"loss": 4.1302,
"step": 135500
},
{
"epoch": 1.6739285626369298,
"grad_norm": 1.2362720966339111,
"learning_rate": 0.00017499382685564718,
"loss": 4.1337,
"step": 136000
},
{
"epoch": 1.6800827117642716,
"grad_norm": 1.9433321952819824,
"learning_rate": 0.0001745308410291866,
"loss": 4.1375,
"step": 136500
},
{
"epoch": 1.6862368608916132,
"grad_norm": 6.300889015197754,
"learning_rate": 0.00017406785520272604,
"loss": 4.1247,
"step": 137000
},
{
"epoch": 1.6923910100189548,
"grad_norm": 0.326621949672699,
"learning_rate": 0.00017360486937626548,
"loss": 4.1305,
"step": 137500
},
{
"epoch": 1.6985451591462963,
"grad_norm": 1.1014314889907837,
"learning_rate": 0.00017314188354980494,
"loss": 4.1142,
"step": 138000
},
{
"epoch": 1.7046993082736381,
"grad_norm": 0.41776031255722046,
"learning_rate": 0.00017267889772334434,
"loss": 4.1421,
"step": 138500
},
{
"epoch": 1.7108534574009797,
"grad_norm": 4.244435787200928,
"learning_rate": 0.00017221591189688377,
"loss": 4.121,
"step": 139000
},
{
"epoch": 1.7170076065283215,
"grad_norm": 2.942218542098999,
"learning_rate": 0.0001717529260704232,
"loss": 4.129,
"step": 139500
},
{
"epoch": 1.723161755655663,
"grad_norm": 1.3000593185424805,
"learning_rate": 0.00017128994024396266,
"loss": 4.124,
"step": 140000
},
{
"epoch": 1.7293159047830047,
"grad_norm": 1.2166913747787476,
"learning_rate": 0.0001708269544175021,
"loss": 4.1413,
"step": 140500
},
{
"epoch": 1.7354700539103463,
"grad_norm": 4.335798740386963,
"learning_rate": 0.00017036396859104153,
"loss": 4.1295,
"step": 141000
},
{
"epoch": 1.741624203037688,
"grad_norm": 3.6867549419403076,
"learning_rate": 0.00016990098276458093,
"loss": 4.1303,
"step": 141500
},
{
"epoch": 1.7477783521650296,
"grad_norm": 1.952437162399292,
"learning_rate": 0.0001694379969381204,
"loss": 4.1277,
"step": 142000
},
{
"epoch": 1.7539325012923714,
"grad_norm": 0.4589731693267822,
"learning_rate": 0.00016897501111165982,
"loss": 4.1431,
"step": 142500
},
{
"epoch": 1.760086650419713,
"grad_norm": 1.9184387922286987,
"learning_rate": 0.00016851202528519926,
"loss": 4.1176,
"step": 143000
},
{
"epoch": 1.7662407995470546,
"grad_norm": 2.446629524230957,
"learning_rate": 0.0001680490394587387,
"loss": 4.1236,
"step": 143500
},
{
"epoch": 1.7723949486743962,
"grad_norm": 2.49019718170166,
"learning_rate": 0.00016758605363227815,
"loss": 4.1375,
"step": 144000
},
{
"epoch": 1.778549097801738,
"grad_norm": 0.5399507880210876,
"learning_rate": 0.00016712306780581755,
"loss": 4.1248,
"step": 144500
},
{
"epoch": 1.7847032469290796,
"grad_norm": 1.3562763929367065,
"learning_rate": 0.00016666008197935698,
"loss": 4.1209,
"step": 145000
},
{
"epoch": 1.7908573960564214,
"grad_norm": 4.684988975524902,
"learning_rate": 0.00016619709615289642,
"loss": 4.1258,
"step": 145500
},
{
"epoch": 1.797011545183763,
"grad_norm": 1.0172507762908936,
"learning_rate": 0.00016573411032643588,
"loss": 4.144,
"step": 146000
},
{
"epoch": 1.8031656943111045,
"grad_norm": 7.56387186050415,
"learning_rate": 0.0001652711244999753,
"loss": 4.1282,
"step": 146500
},
{
"epoch": 1.809319843438446,
"grad_norm": 0.6657699942588806,
"learning_rate": 0.0001648081386735147,
"loss": 4.1405,
"step": 147000
},
{
"epoch": 1.815473992565788,
"grad_norm": 2.632422685623169,
"learning_rate": 0.00016434515284705415,
"loss": 4.1306,
"step": 147500
},
{
"epoch": 1.8216281416931295,
"grad_norm": 5.751383304595947,
"learning_rate": 0.0001638821670205936,
"loss": 4.1268,
"step": 148000
},
{
"epoch": 1.8277822908204713,
"grad_norm": 1.0454890727996826,
"learning_rate": 0.00016341918119413304,
"loss": 4.1175,
"step": 148500
},
{
"epoch": 1.8339364399478129,
"grad_norm": 1.7634836435317993,
"learning_rate": 0.00016295619536767247,
"loss": 4.1171,
"step": 149000
},
{
"epoch": 1.8400905890751544,
"grad_norm": 1.0641893148422241,
"learning_rate": 0.0001624932095412119,
"loss": 4.1161,
"step": 149500
},
{
"epoch": 1.846244738202496,
"grad_norm": 1.7824281454086304,
"learning_rate": 0.0001620302237147513,
"loss": 4.1095,
"step": 150000
},
{
"epoch": 1.8523988873298378,
"grad_norm": 9.278116226196289,
"learning_rate": 0.00016156723788829076,
"loss": 4.1653,
"step": 150500
},
{
"epoch": 1.8585530364571794,
"grad_norm": 1.2916337251663208,
"learning_rate": 0.0001611042520618302,
"loss": 4.1275,
"step": 151000
},
{
"epoch": 1.8647071855845212,
"grad_norm": 3.0669305324554443,
"learning_rate": 0.00016064126623536963,
"loss": 4.1339,
"step": 151500
},
{
"epoch": 1.8708613347118628,
"grad_norm": 0.4204738736152649,
"learning_rate": 0.0001601782804089091,
"loss": 4.1175,
"step": 152000
},
{
"epoch": 1.8770154838392044,
"grad_norm": 0.8279763460159302,
"learning_rate": 0.00015971529458244852,
"loss": 4.133,
"step": 152500
},
{
"epoch": 1.883169632966546,
"grad_norm": 0.5505543947219849,
"learning_rate": 0.00015925230875598793,
"loss": 4.1334,
"step": 153000
},
{
"epoch": 1.8893237820938877,
"grad_norm": 1.1535730361938477,
"learning_rate": 0.00015878932292952736,
"loss": 4.1408,
"step": 153500
},
{
"epoch": 1.8954779312212293,
"grad_norm": 4.983729362487793,
"learning_rate": 0.0001583263371030668,
"loss": 4.1483,
"step": 154000
},
{
"epoch": 1.9016320803485711,
"grad_norm": 3.520394802093506,
"learning_rate": 0.00015786335127660625,
"loss": 4.1483,
"step": 154500
},
{
"epoch": 1.9077862294759127,
"grad_norm": 6.582132816314697,
"learning_rate": 0.00015740036545014568,
"loss": 4.133,
"step": 155000
},
{
"epoch": 1.9139403786032543,
"grad_norm": 6.116377353668213,
"learning_rate": 0.0001569373796236851,
"loss": 4.1181,
"step": 155500
},
{
"epoch": 1.9200945277305959,
"grad_norm": 3.6372199058532715,
"learning_rate": 0.00015647439379722452,
"loss": 4.1265,
"step": 156000
},
{
"epoch": 1.9262486768579377,
"grad_norm": 2.3151426315307617,
"learning_rate": 0.00015601140797076398,
"loss": 4.1245,
"step": 156500
},
{
"epoch": 1.9324028259852792,
"grad_norm": 4.454445838928223,
"learning_rate": 0.0001555484221443034,
"loss": 4.1375,
"step": 157000
},
{
"epoch": 1.938556975112621,
"grad_norm": 4.774474620819092,
"learning_rate": 0.00015508543631784284,
"loss": 4.144,
"step": 157500
},
{
"epoch": 1.9447111242399626,
"grad_norm": 6.174612998962402,
"learning_rate": 0.0001546224504913823,
"loss": 4.1267,
"step": 158000
},
{
"epoch": 1.9508652733673042,
"grad_norm": 1.683795690536499,
"learning_rate": 0.0001541594646649217,
"loss": 4.1375,
"step": 158500
},
{
"epoch": 1.9570194224946458,
"grad_norm": 4.973104000091553,
"learning_rate": 0.00015369647883846114,
"loss": 4.1462,
"step": 159000
},
{
"epoch": 1.9631735716219876,
"grad_norm": 1.2062525749206543,
"learning_rate": 0.00015323349301200057,
"loss": 4.1228,
"step": 159500
},
{
"epoch": 1.9693277207493292,
"grad_norm": 4.831448078155518,
"learning_rate": 0.00015277050718554,
"loss": 4.138,
"step": 160000
},
{
"epoch": 1.975481869876671,
"grad_norm": 5.075714588165283,
"learning_rate": 0.00015230752135907946,
"loss": 4.1435,
"step": 160500
},
{
"epoch": 1.9816360190040125,
"grad_norm": 2.948014497756958,
"learning_rate": 0.0001518445355326189,
"loss": 4.1467,
"step": 161000
},
{
"epoch": 1.9877901681313541,
"grad_norm": 1.2960885763168335,
"learning_rate": 0.0001513815497061583,
"loss": 4.1326,
"step": 161500
},
{
"epoch": 1.9939443172586957,
"grad_norm": 0.545448362827301,
"learning_rate": 0.00015091856387969773,
"loss": 4.1452,
"step": 162000
},
{
"epoch": 2.0000984663860373,
"grad_norm": 2.841965436935425,
"learning_rate": 0.0001504555780532372,
"loss": 4.1429,
"step": 162500
},
{
"epoch": 2.0062526155133793,
"grad_norm": 4.865884304046631,
"learning_rate": 0.00014999259222677662,
"loss": 4.1464,
"step": 163000
},
{
"epoch": 2.012406764640721,
"grad_norm": 1.21327543258667,
"learning_rate": 0.00014952960640031605,
"loss": 4.1507,
"step": 163500
},
{
"epoch": 2.0185609137680625,
"grad_norm": 0.4554235339164734,
"learning_rate": 0.00014906662057385549,
"loss": 4.1378,
"step": 164000
},
{
"epoch": 2.024715062895404,
"grad_norm": 0.5327489972114563,
"learning_rate": 0.00014860363474739492,
"loss": 4.1454,
"step": 164500
},
{
"epoch": 2.0308692120227456,
"grad_norm": 0.8064332604408264,
"learning_rate": 0.00014814064892093435,
"loss": 4.1386,
"step": 165000
},
{
"epoch": 2.037023361150087,
"grad_norm": 2.2158634662628174,
"learning_rate": 0.00014767766309447378,
"loss": 4.1502,
"step": 165500
},
{
"epoch": 2.043177510277429,
"grad_norm": 2.3383662700653076,
"learning_rate": 0.00014721467726801321,
"loss": 4.1394,
"step": 166000
},
{
"epoch": 2.049331659404771,
"grad_norm": 4.575577735900879,
"learning_rate": 0.00014675169144155265,
"loss": 4.1393,
"step": 166500
},
{
"epoch": 2.0554858085321124,
"grad_norm": 0.4294615685939789,
"learning_rate": 0.00014628870561509208,
"loss": 4.1482,
"step": 167000
},
{
"epoch": 2.061639957659454,
"grad_norm": 1.2794427871704102,
"learning_rate": 0.00014582571978863154,
"loss": 4.1286,
"step": 167500
},
{
"epoch": 2.0677941067867955,
"grad_norm": 6.330613613128662,
"learning_rate": 0.00014536273396217094,
"loss": 4.1431,
"step": 168000
},
{
"epoch": 2.073948255914137,
"grad_norm": 3.15324330329895,
"learning_rate": 0.0001448997481357104,
"loss": 4.1252,
"step": 168500
},
{
"epoch": 2.080102405041479,
"grad_norm": 2.5174105167388916,
"learning_rate": 0.00014443676230924983,
"loss": 4.143,
"step": 169000
},
{
"epoch": 2.0862565541688207,
"grad_norm": 3.220691680908203,
"learning_rate": 0.00014397377648278927,
"loss": 4.1513,
"step": 169500
},
{
"epoch": 2.0924107032961623,
"grad_norm": 0.6489084959030151,
"learning_rate": 0.0001435107906563287,
"loss": 4.1353,
"step": 170000
},
{
"epoch": 2.098564852423504,
"grad_norm": 1.4879485368728638,
"learning_rate": 0.00014304780482986813,
"loss": 4.1631,
"step": 170500
},
{
"epoch": 2.1047190015508455,
"grad_norm": 0.5198183059692383,
"learning_rate": 0.00014258481900340756,
"loss": 4.1342,
"step": 171000
},
{
"epoch": 2.110873150678187,
"grad_norm": 4.062627792358398,
"learning_rate": 0.000142121833176947,
"loss": 4.1526,
"step": 171500
},
{
"epoch": 2.117027299805529,
"grad_norm": 2.0375592708587646,
"learning_rate": 0.00014165884735048643,
"loss": 4.1403,
"step": 172000
},
{
"epoch": 2.1231814489328706,
"grad_norm": 8.87256908416748,
"learning_rate": 0.00014119586152402586,
"loss": 4.1414,
"step": 172500
},
{
"epoch": 2.129335598060212,
"grad_norm": 4.595679759979248,
"learning_rate": 0.0001407328756975653,
"loss": 4.157,
"step": 173000
},
{
"epoch": 2.135489747187554,
"grad_norm": 2.625487804412842,
"learning_rate": 0.00014026988987110475,
"loss": 4.1325,
"step": 173500
},
{
"epoch": 2.1416438963148954,
"grad_norm": 2.112154483795166,
"learning_rate": 0.00013980690404464415,
"loss": 4.1426,
"step": 174000
},
{
"epoch": 2.147798045442237,
"grad_norm": 5.883920669555664,
"learning_rate": 0.00013934391821818361,
"loss": 4.1357,
"step": 174500
},
{
"epoch": 2.153952194569579,
"grad_norm": 3.2005159854888916,
"learning_rate": 0.00013888093239172305,
"loss": 4.1152,
"step": 175000
},
{
"epoch": 2.1601063436969206,
"grad_norm": 0.8658522963523865,
"learning_rate": 0.00013841794656526248,
"loss": 4.1435,
"step": 175500
},
{
"epoch": 2.166260492824262,
"grad_norm": 2.876591682434082,
"learning_rate": 0.0001379549607388019,
"loss": 4.1167,
"step": 176000
},
{
"epoch": 2.1724146419516037,
"grad_norm": 4.943939685821533,
"learning_rate": 0.00013749197491234134,
"loss": 4.1367,
"step": 176500
},
{
"epoch": 2.1785687910789453,
"grad_norm": 4.762856483459473,
"learning_rate": 0.00013702898908588077,
"loss": 4.1349,
"step": 177000
},
{
"epoch": 2.184722940206287,
"grad_norm": 2.7978150844573975,
"learning_rate": 0.0001365660032594202,
"loss": 4.1265,
"step": 177500
},
{
"epoch": 2.190877089333629,
"grad_norm": 4.108112335205078,
"learning_rate": 0.00013610301743295964,
"loss": 4.1314,
"step": 178000
},
{
"epoch": 2.1970312384609705,
"grad_norm": 2.733691930770874,
"learning_rate": 0.00013564003160649907,
"loss": 4.1482,
"step": 178500
},
{
"epoch": 2.203185387588312,
"grad_norm": 6.319185256958008,
"learning_rate": 0.0001351770457800385,
"loss": 4.1477,
"step": 179000
},
{
"epoch": 2.2093395367156536,
"grad_norm": 2.4234657287597656,
"learning_rate": 0.00013471405995357793,
"loss": 4.1333,
"step": 179500
},
{
"epoch": 2.215493685842995,
"grad_norm": 0.6562241911888123,
"learning_rate": 0.00013425107412711737,
"loss": 4.1358,
"step": 180000
},
{
"epoch": 2.221647834970337,
"grad_norm": 1.6722023487091064,
"learning_rate": 0.00013378808830065683,
"loss": 4.1337,
"step": 180500
},
{
"epoch": 2.227801984097679,
"grad_norm": 1.162979245185852,
"learning_rate": 0.00013332510247419623,
"loss": 4.1283,
"step": 181000
},
{
"epoch": 2.2339561332250204,
"grad_norm": 5.3414835929870605,
"learning_rate": 0.0001328621166477357,
"loss": 4.1555,
"step": 181500
},
{
"epoch": 2.240110282352362,
"grad_norm": 3.4271726608276367,
"learning_rate": 0.00013239913082127512,
"loss": 4.1365,
"step": 182000
},
{
"epoch": 2.2462644314797036,
"grad_norm": 2.4515178203582764,
"learning_rate": 0.00013193614499481455,
"loss": 4.1484,
"step": 182500
},
{
"epoch": 2.252418580607045,
"grad_norm": 0.9025920033454895,
"learning_rate": 0.00013147315916835399,
"loss": 4.1164,
"step": 183000
},
{
"epoch": 2.2585727297343867,
"grad_norm": 1.4333921670913696,
"learning_rate": 0.00013101017334189342,
"loss": 4.1434,
"step": 183500
},
{
"epoch": 2.2647268788617287,
"grad_norm": 15.7656831741333,
"learning_rate": 0.00013054718751543285,
"loss": 4.1305,
"step": 184000
},
{
"epoch": 2.2708810279890703,
"grad_norm": 5.036754608154297,
"learning_rate": 0.00013008420168897228,
"loss": 4.1562,
"step": 184500
},
{
"epoch": 2.277035177116412,
"grad_norm": 4.341217041015625,
"learning_rate": 0.00012962121586251171,
"loss": 4.1384,
"step": 185000
},
{
"epoch": 2.2831893262437535,
"grad_norm": 12.635770797729492,
"learning_rate": 0.00012915823003605115,
"loss": 4.1381,
"step": 185500
},
{
"epoch": 2.289343475371095,
"grad_norm": 14.095486640930176,
"learning_rate": 0.00012869524420959058,
"loss": 4.1316,
"step": 186000
},
{
"epoch": 2.295497624498437,
"grad_norm": 1.3120825290679932,
"learning_rate": 0.00012823225838313004,
"loss": 4.1333,
"step": 186500
},
{
"epoch": 2.3016517736257787,
"grad_norm": 4.015687942504883,
"learning_rate": 0.00012776927255666944,
"loss": 4.1433,
"step": 187000
},
{
"epoch": 2.3078059227531202,
"grad_norm": 1.5111069679260254,
"learning_rate": 0.0001273062867302089,
"loss": 4.1437,
"step": 187500
},
{
"epoch": 2.313960071880462,
"grad_norm": 17.275177001953125,
"learning_rate": 0.00012684330090374833,
"loss": 4.1352,
"step": 188000
},
{
"epoch": 2.3201142210078034,
"grad_norm": 24.972490310668945,
"learning_rate": 0.00012638031507728774,
"loss": 4.1578,
"step": 188500
},
{
"epoch": 2.326268370135145,
"grad_norm": 6.434344291687012,
"learning_rate": 0.0001259173292508272,
"loss": 4.146,
"step": 189000
},
{
"epoch": 2.3324225192624866,
"grad_norm": 5.063055515289307,
"learning_rate": 0.00012545434342436663,
"loss": 4.1491,
"step": 189500
},
{
"epoch": 2.3385766683898286,
"grad_norm": 13.573065757751465,
"learning_rate": 0.00012499135759790606,
"loss": 4.1432,
"step": 190000
},
{
"epoch": 2.34473081751717,
"grad_norm": 3.9898264408111572,
"learning_rate": 0.0001245283717714455,
"loss": 4.1346,
"step": 190500
},
{
"epoch": 2.3508849666445117,
"grad_norm": 38.64807891845703,
"learning_rate": 0.00012406538594498493,
"loss": 4.1382,
"step": 191000
},
{
"epoch": 2.3570391157718533,
"grad_norm": 4.317899227142334,
"learning_rate": 0.00012360240011852436,
"loss": 4.1202,
"step": 191500
},
{
"epoch": 2.363193264899195,
"grad_norm": 3.524425745010376,
"learning_rate": 0.0001231394142920638,
"loss": 4.1428,
"step": 192000
},
{
"epoch": 2.369347414026537,
"grad_norm": 9.885839462280273,
"learning_rate": 0.00012267642846560322,
"loss": 4.1369,
"step": 192500
},
{
"epoch": 2.3755015631538785,
"grad_norm": 6.044156074523926,
"learning_rate": 0.00012221344263914266,
"loss": 4.1477,
"step": 193000
},
{
"epoch": 2.38165571228122,
"grad_norm": 2.5400869846343994,
"learning_rate": 0.0001217504568126821,
"loss": 4.1401,
"step": 193500
},
{
"epoch": 2.3878098614085617,
"grad_norm": 7.136928081512451,
"learning_rate": 0.00012128747098622152,
"loss": 4.1432,
"step": 194000
},
{
"epoch": 2.3939640105359032,
"grad_norm": 2.3224997520446777,
"learning_rate": 0.00012082448515976097,
"loss": 4.1423,
"step": 194500
},
{
"epoch": 2.400118159663245,
"grad_norm": 2.5237538814544678,
"learning_rate": 0.00012036149933330041,
"loss": 4.1099,
"step": 195000
},
{
"epoch": 2.4062723087905864,
"grad_norm": 18.10267448425293,
"learning_rate": 0.00011989851350683983,
"loss": 4.1211,
"step": 195500
},
{
"epoch": 2.4124264579179284,
"grad_norm": 7.731093406677246,
"learning_rate": 0.00011943552768037926,
"loss": 4.1425,
"step": 196000
},
{
"epoch": 2.41858060704527,
"grad_norm": 9.18722915649414,
"learning_rate": 0.00011897254185391871,
"loss": 4.2406,
"step": 196500
},
{
"epoch": 2.4247347561726116,
"grad_norm": 1.7126137018203735,
"learning_rate": 0.00011850955602745813,
"loss": 4.1401,
"step": 197000
},
{
"epoch": 2.430888905299953,
"grad_norm": 3.3530025482177734,
"learning_rate": 0.00011804657020099757,
"loss": 4.1476,
"step": 197500
},
{
"epoch": 2.4370430544272947,
"grad_norm": 2.5332510471343994,
"learning_rate": 0.000117583584374537,
"loss": 4.139,
"step": 198000
},
{
"epoch": 2.4431972035546368,
"grad_norm": 3.647127628326416,
"learning_rate": 0.00011712059854807644,
"loss": 4.1263,
"step": 198500
},
{
"epoch": 2.4493513526819783,
"grad_norm": 3.8709239959716797,
"learning_rate": 0.00011665761272161587,
"loss": 4.1227,
"step": 199000
},
{
"epoch": 2.45550550180932,
"grad_norm": 1.679821252822876,
"learning_rate": 0.00011619462689515531,
"loss": 4.144,
"step": 199500
},
{
"epoch": 2.4616596509366615,
"grad_norm": 2.7724051475524902,
"learning_rate": 0.00011573164106869473,
"loss": 4.1547,
"step": 200000
},
{
"epoch": 2.467813800064003,
"grad_norm": 4.430192470550537,
"learning_rate": 0.00011526865524223418,
"loss": 4.1369,
"step": 200500
},
{
"epoch": 2.4739679491913447,
"grad_norm": 2.663402795791626,
"learning_rate": 0.00011480566941577361,
"loss": 4.126,
"step": 201000
},
{
"epoch": 2.4801220983186862,
"grad_norm": 5.047146320343018,
"learning_rate": 0.00011434268358931304,
"loss": 4.1518,
"step": 201500
},
{
"epoch": 2.4862762474460283,
"grad_norm": 11.797883987426758,
"learning_rate": 0.00011387969776285247,
"loss": 4.17,
"step": 202000
},
{
"epoch": 2.49243039657337,
"grad_norm": 4.274112224578857,
"learning_rate": 0.00011341671193639192,
"loss": 4.1372,
"step": 202500
},
{
"epoch": 2.4985845457007114,
"grad_norm": 1.7666431665420532,
"learning_rate": 0.00011295372610993134,
"loss": 4.1447,
"step": 203000
},
{
"epoch": 2.504738694828053,
"grad_norm": 4.489656925201416,
"learning_rate": 0.00011249074028347078,
"loss": 4.1383,
"step": 203500
},
{
"epoch": 2.5108928439553946,
"grad_norm": 9.751529693603516,
"learning_rate": 0.0001120277544570102,
"loss": 4.1486,
"step": 204000
},
{
"epoch": 2.5170469930827366,
"grad_norm": 22.9904842376709,
"learning_rate": 0.00011156476863054965,
"loss": 4.1537,
"step": 204500
},
{
"epoch": 2.523201142210078,
"grad_norm": 15.45181941986084,
"learning_rate": 0.00011110178280408908,
"loss": 4.1344,
"step": 205000
},
{
"epoch": 2.5293552913374198,
"grad_norm": 16.877206802368164,
"learning_rate": 0.00011063879697762851,
"loss": 4.1238,
"step": 205500
},
{
"epoch": 2.5355094404647613,
"grad_norm": 17.026702880859375,
"learning_rate": 0.00011017581115116794,
"loss": 4.1526,
"step": 206000
},
{
"epoch": 2.541663589592103,
"grad_norm": 2.4947428703308105,
"learning_rate": 0.00010971282532470739,
"loss": 4.1337,
"step": 206500
},
{
"epoch": 2.5478177387194445,
"grad_norm": 5.502418041229248,
"learning_rate": 0.00010924983949824681,
"loss": 4.1273,
"step": 207000
},
{
"epoch": 2.553971887846786,
"grad_norm": 5.675118446350098,
"learning_rate": 0.00010878685367178625,
"loss": 4.1494,
"step": 207500
},
{
"epoch": 2.560126036974128,
"grad_norm": 19.652507781982422,
"learning_rate": 0.00010832386784532569,
"loss": 4.1407,
"step": 208000
},
{
"epoch": 2.5662801861014697,
"grad_norm": 12.558784484863281,
"learning_rate": 0.00010786088201886512,
"loss": 4.1343,
"step": 208500
},
{
"epoch": 2.5724343352288113,
"grad_norm": 4.799954414367676,
"learning_rate": 0.00010739789619240455,
"loss": 4.1427,
"step": 209000
},
{
"epoch": 2.578588484356153,
"grad_norm": 10.397370338439941,
"learning_rate": 0.000106934910365944,
"loss": 4.1357,
"step": 209500
},
{
"epoch": 2.5847426334834944,
"grad_norm": 5.0170745849609375,
"learning_rate": 0.00010647192453948341,
"loss": 4.152,
"step": 210000
},
{
"epoch": 2.5908967826108364,
"grad_norm": 12.359256744384766,
"learning_rate": 0.00010600893871302286,
"loss": 4.1598,
"step": 210500
},
{
"epoch": 2.597050931738178,
"grad_norm": 6.895079135894775,
"learning_rate": 0.00010554595288656229,
"loss": 4.1502,
"step": 211000
},
{
"epoch": 2.6032050808655196,
"grad_norm": 7.364566326141357,
"learning_rate": 0.00010508296706010172,
"loss": 4.1419,
"step": 211500
},
{
"epoch": 2.609359229992861,
"grad_norm": 5.654910087585449,
"learning_rate": 0.00010461998123364116,
"loss": 4.1357,
"step": 212000
},
{
"epoch": 2.6155133791202028,
"grad_norm": 12.257036209106445,
"learning_rate": 0.0001041569954071806,
"loss": 4.1534,
"step": 212500
},
{
"epoch": 2.6216675282475443,
"grad_norm": 12.89324951171875,
"learning_rate": 0.00010369400958072002,
"loss": 4.1299,
"step": 213000
},
{
"epoch": 2.627821677374886,
"grad_norm": 17.213781356811523,
"learning_rate": 0.00010323102375425947,
"loss": 4.1258,
"step": 213500
},
{
"epoch": 2.633975826502228,
"grad_norm": 11.56577205657959,
"learning_rate": 0.0001027680379277989,
"loss": 4.18,
"step": 214000
},
{
"epoch": 2.6401299756295695,
"grad_norm": 9.175166130065918,
"learning_rate": 0.00010230505210133833,
"loss": 4.1434,
"step": 214500
},
{
"epoch": 2.646284124756911,
"grad_norm": 7.084720611572266,
"learning_rate": 0.00010184206627487776,
"loss": 4.1455,
"step": 215000
},
{
"epoch": 2.6524382738842527,
"grad_norm": 1.4853074550628662,
"learning_rate": 0.00010137908044841721,
"loss": 4.1458,
"step": 215500
},
{
"epoch": 2.6585924230115943,
"grad_norm": 22.556468963623047,
"learning_rate": 0.00010091609462195663,
"loss": 4.1484,
"step": 216000
},
{
"epoch": 2.6647465721389363,
"grad_norm": 6.518449306488037,
"learning_rate": 0.00010045310879549607,
"loss": 4.1385,
"step": 216500
},
{
"epoch": 2.670900721266278,
"grad_norm": 10.592835426330566,
"learning_rate": 9.999012296903549e-05,
"loss": 4.1438,
"step": 217000
},
{
"epoch": 2.6770548703936194,
"grad_norm": 6.5668158531188965,
"learning_rate": 9.952713714257494e-05,
"loss": 4.1346,
"step": 217500
},
{
"epoch": 2.683209019520961,
"grad_norm": 7.547019958496094,
"learning_rate": 9.906415131611437e-05,
"loss": 4.1452,
"step": 218000
},
{
"epoch": 2.6893631686483026,
"grad_norm": 7.282440185546875,
"learning_rate": 9.86011654896538e-05,
"loss": 4.1175,
"step": 218500
},
{
"epoch": 2.695517317775644,
"grad_norm": 30.473175048828125,
"learning_rate": 9.813817966319323e-05,
"loss": 4.1407,
"step": 219000
},
{
"epoch": 2.7016714669029858,
"grad_norm": 47.161136627197266,
"learning_rate": 9.767519383673268e-05,
"loss": 4.1475,
"step": 219500
},
{
"epoch": 2.707825616030328,
"grad_norm": 9.303009986877441,
"learning_rate": 9.72122080102721e-05,
"loss": 4.1313,
"step": 220000
},
{
"epoch": 2.7139797651576694,
"grad_norm": 6.46337366104126,
"learning_rate": 9.674922218381154e-05,
"loss": 4.1337,
"step": 220500
},
{
"epoch": 2.720133914285011,
"grad_norm": 3.8435237407684326,
"learning_rate": 9.628623635735097e-05,
"loss": 4.1531,
"step": 221000
},
{
"epoch": 2.7262880634123525,
"grad_norm": 9.514744758605957,
"learning_rate": 9.58232505308904e-05,
"loss": 4.138,
"step": 221500
},
{
"epoch": 2.732442212539694,
"grad_norm": 6.541099548339844,
"learning_rate": 9.536026470442984e-05,
"loss": 4.1288,
"step": 222000
},
{
"epoch": 2.738596361667036,
"grad_norm": 9.796896934509277,
"learning_rate": 9.489727887796928e-05,
"loss": 4.1421,
"step": 222500
},
{
"epoch": 2.7447505107943777,
"grad_norm": 2.1440978050231934,
"learning_rate": 9.44342930515087e-05,
"loss": 4.1381,
"step": 223000
},
{
"epoch": 2.7509046599217193,
"grad_norm": 6.687036991119385,
"learning_rate": 9.397130722504815e-05,
"loss": 4.1154,
"step": 223500
},
{
"epoch": 2.757058809049061,
"grad_norm": 72.82162475585938,
"learning_rate": 9.350832139858758e-05,
"loss": 4.125,
"step": 224000
},
{
"epoch": 2.7632129581764024,
"grad_norm": 4.186785697937012,
"learning_rate": 9.3045335572127e-05,
"loss": 4.1243,
"step": 224500
},
{
"epoch": 2.769367107303744,
"grad_norm": 10.238506317138672,
"learning_rate": 9.258234974566644e-05,
"loss": 4.1305,
"step": 225000
},
{
"epoch": 2.7755212564310856,
"grad_norm": 42.393123626708984,
"learning_rate": 9.211936391920589e-05,
"loss": 4.1494,
"step": 225500
},
{
"epoch": 2.7816754055584276,
"grad_norm": 31.10955238342285,
"learning_rate": 9.165637809274531e-05,
"loss": 4.1262,
"step": 226000
},
{
"epoch": 2.787829554685769,
"grad_norm": 3.7543489933013916,
"learning_rate": 9.119339226628475e-05,
"loss": 4.1335,
"step": 226500
},
{
"epoch": 2.793983703813111,
"grad_norm": 4.825121879577637,
"learning_rate": 9.073040643982419e-05,
"loss": 4.1296,
"step": 227000
},
{
"epoch": 2.8001378529404524,
"grad_norm": 40.39415740966797,
"learning_rate": 9.02674206133636e-05,
"loss": 4.1487,
"step": 227500
},
{
"epoch": 2.806292002067794,
"grad_norm": 27.26569938659668,
"learning_rate": 8.980443478690305e-05,
"loss": 4.1219,
"step": 228000
},
{
"epoch": 2.812446151195136,
"grad_norm": 6.383996486663818,
"learning_rate": 8.93414489604425e-05,
"loss": 4.1262,
"step": 228500
},
{
"epoch": 2.8186003003224775,
"grad_norm": 21.24449920654297,
"learning_rate": 8.887846313398191e-05,
"loss": 4.1475,
"step": 229000
},
{
"epoch": 2.824754449449819,
"grad_norm": 25.860145568847656,
"learning_rate": 8.841547730752136e-05,
"loss": 4.1353,
"step": 229500
},
{
"epoch": 2.8309085985771607,
"grad_norm": 18.35698890686035,
"learning_rate": 8.795249148106078e-05,
"loss": 4.1307,
"step": 230000
},
{
"epoch": 2.8370627477045023,
"grad_norm": 5.2866973876953125,
"learning_rate": 8.748950565460021e-05,
"loss": 4.1428,
"step": 230500
},
{
"epoch": 2.843216896831844,
"grad_norm": 5.111605644226074,
"learning_rate": 8.702651982813966e-05,
"loss": 4.1216,
"step": 231000
},
{
"epoch": 2.8493710459591854,
"grad_norm": 6.656818866729736,
"learning_rate": 8.656353400167908e-05,
"loss": 4.1582,
"step": 231500
},
{
"epoch": 2.8555251950865275,
"grad_norm": 6.107633590698242,
"learning_rate": 8.610054817521852e-05,
"loss": 4.135,
"step": 232000
},
{
"epoch": 2.861679344213869,
"grad_norm": 14.607207298278809,
"learning_rate": 8.563756234875797e-05,
"loss": 4.1361,
"step": 232500
},
{
"epoch": 2.8678334933412106,
"grad_norm": 20.888408660888672,
"learning_rate": 8.517457652229739e-05,
"loss": 4.1407,
"step": 233000
},
{
"epoch": 2.873987642468552,
"grad_norm": 6.468882083892822,
"learning_rate": 8.471159069583682e-05,
"loss": 4.1299,
"step": 233500
},
{
"epoch": 2.880141791595894,
"grad_norm": 2.9903552532196045,
"learning_rate": 8.424860486937626e-05,
"loss": 4.1495,
"step": 234000
},
{
"epoch": 2.886295940723236,
"grad_norm": 3.253113269805908,
"learning_rate": 8.378561904291568e-05,
"loss": 4.1359,
"step": 234500
},
{
"epoch": 2.8924500898505774,
"grad_norm": 31.159034729003906,
"learning_rate": 8.332263321645513e-05,
"loss": 4.1463,
"step": 235000
},
{
"epoch": 2.898604238977919,
"grad_norm": 6.632800579071045,
"learning_rate": 8.285964738999456e-05,
"loss": 4.1544,
"step": 235500
},
{
"epoch": 2.9047583881052605,
"grad_norm": 3.6069889068603516,
"learning_rate": 8.239666156353399e-05,
"loss": 4.1521,
"step": 236000
},
{
"epoch": 2.910912537232602,
"grad_norm": 18.797504425048828,
"learning_rate": 8.193367573707342e-05,
"loss": 4.1577,
"step": 236500
},
{
"epoch": 2.917066686359944,
"grad_norm": 25.01851463317871,
"learning_rate": 8.147068991061287e-05,
"loss": 4.1195,
"step": 237000
},
{
"epoch": 2.9232208354872853,
"grad_norm": 7.6719136238098145,
"learning_rate": 8.100770408415229e-05,
"loss": 4.1405,
"step": 237500
},
{
"epoch": 2.9293749846146273,
"grad_norm": 23.961761474609375,
"learning_rate": 8.054471825769173e-05,
"loss": 4.15,
"step": 238000
},
{
"epoch": 2.935529133741969,
"grad_norm": 17.680160522460938,
"learning_rate": 8.008173243123117e-05,
"loss": 4.1475,
"step": 238500
},
{
"epoch": 2.9416832828693105,
"grad_norm": 16.601022720336914,
"learning_rate": 7.96187466047706e-05,
"loss": 4.1527,
"step": 239000
},
{
"epoch": 2.947837431996652,
"grad_norm": 33.24941635131836,
"learning_rate": 7.915576077831003e-05,
"loss": 4.149,
"step": 239500
},
{
"epoch": 2.9539915811239936,
"grad_norm": 13.79638671875,
"learning_rate": 7.869277495184948e-05,
"loss": 4.1326,
"step": 240000
},
{
"epoch": 2.9601457302513356,
"grad_norm": 3.769580602645874,
"learning_rate": 7.82297891253889e-05,
"loss": 4.1594,
"step": 240500
},
{
"epoch": 2.9662998793786772,
"grad_norm": 10.10777759552002,
"learning_rate": 7.776680329892834e-05,
"loss": 4.1557,
"step": 241000
},
{
"epoch": 2.972454028506019,
"grad_norm": 5.826690673828125,
"learning_rate": 7.730381747246777e-05,
"loss": 4.1378,
"step": 241500
},
{
"epoch": 2.9786081776333604,
"grad_norm": 10.416824340820312,
"learning_rate": 7.68408316460072e-05,
"loss": 4.1536,
"step": 242000
},
{
"epoch": 2.984762326760702,
"grad_norm": 11.075167655944824,
"learning_rate": 7.637784581954664e-05,
"loss": 4.1511,
"step": 242500
},
{
"epoch": 2.990916475888044,
"grad_norm": 6.712924480438232,
"learning_rate": 7.591485999308607e-05,
"loss": 4.1801,
"step": 243000
},
{
"epoch": 2.997070625015385,
"grad_norm": 4.74166202545166,
"learning_rate": 7.54518741666255e-05,
"loss": 4.1374,
"step": 243500
},
{
"epoch": 3.003224774142727,
"grad_norm": 2.3096487522125244,
"learning_rate": 7.498888834016495e-05,
"loss": 4.1398,
"step": 244000
},
{
"epoch": 3.0093789232700687,
"grad_norm": 7.170060634613037,
"learning_rate": 7.452590251370438e-05,
"loss": 4.1576,
"step": 244500
},
{
"epoch": 3.0155330723974103,
"grad_norm": 2.7017977237701416,
"learning_rate": 7.406291668724381e-05,
"loss": 4.1622,
"step": 245000
},
{
"epoch": 3.021687221524752,
"grad_norm": 7.089437007904053,
"learning_rate": 7.359993086078324e-05,
"loss": 4.1567,
"step": 245500
},
{
"epoch": 3.0278413706520935,
"grad_norm": 3.3189284801483154,
"learning_rate": 7.313694503432267e-05,
"loss": 4.1419,
"step": 246000
},
{
"epoch": 3.0339955197794355,
"grad_norm": 2.4991772174835205,
"learning_rate": 7.26739592078621e-05,
"loss": 4.1527,
"step": 246500
},
{
"epoch": 3.040149668906777,
"grad_norm": 3.2394919395446777,
"learning_rate": 7.221097338140154e-05,
"loss": 4.1424,
"step": 247000
},
{
"epoch": 3.0463038180341186,
"grad_norm": 4.59478759765625,
"learning_rate": 7.174798755494098e-05,
"loss": 4.1296,
"step": 247500
},
{
"epoch": 3.0524579671614602,
"grad_norm": 3.0080718994140625,
"learning_rate": 7.128500172848042e-05,
"loss": 4.1562,
"step": 248000
},
{
"epoch": 3.058612116288802,
"grad_norm": 4.77623176574707,
"learning_rate": 7.082201590201985e-05,
"loss": 4.1415,
"step": 248500
},
{
"epoch": 3.0647662654161434,
"grad_norm": 15.261367797851562,
"learning_rate": 7.035903007555928e-05,
"loss": 4.1434,
"step": 249000
},
{
"epoch": 3.0709204145434854,
"grad_norm": 4.615048408508301,
"learning_rate": 6.989604424909871e-05,
"loss": 4.1386,
"step": 249500
},
{
"epoch": 3.077074563670827,
"grad_norm": 3.0708060264587402,
"learning_rate": 6.943305842263814e-05,
"loss": 4.1538,
"step": 250000
},
{
"epoch": 3.0832287127981686,
"grad_norm": 9.329169273376465,
"learning_rate": 6.897007259617759e-05,
"loss": 4.1636,
"step": 250500
},
{
"epoch": 3.08938286192551,
"grad_norm": 4.104388236999512,
"learning_rate": 6.850708676971702e-05,
"loss": 4.1389,
"step": 251000
},
{
"epoch": 3.0955370110528517,
"grad_norm": 2.5644283294677734,
"learning_rate": 6.804410094325645e-05,
"loss": 4.1386,
"step": 251500
},
{
"epoch": 3.1016911601801933,
"grad_norm": 5.874880790710449,
"learning_rate": 6.758111511679589e-05,
"loss": 4.1554,
"step": 252000
},
{
"epoch": 3.1078453093075353,
"grad_norm": 1.9047770500183105,
"learning_rate": 6.711812929033532e-05,
"loss": 4.1461,
"step": 252500
},
{
"epoch": 3.113999458434877,
"grad_norm": 2.8584365844726562,
"learning_rate": 6.665514346387475e-05,
"loss": 4.1204,
"step": 253000
},
{
"epoch": 3.1201536075622185,
"grad_norm": 7.893682956695557,
"learning_rate": 6.619215763741418e-05,
"loss": 4.1396,
"step": 253500
},
{
"epoch": 3.12630775668956,
"grad_norm": 3.6255972385406494,
"learning_rate": 6.572917181095363e-05,
"loss": 4.1631,
"step": 254000
},
{
"epoch": 3.1324619058169016,
"grad_norm": 4.607624530792236,
"learning_rate": 6.526618598449306e-05,
"loss": 4.1377,
"step": 254500
},
{
"epoch": 3.1386160549442432,
"grad_norm": 7.349343299865723,
"learning_rate": 6.480320015803249e-05,
"loss": 4.1411,
"step": 255000
},
{
"epoch": 3.1447702040715853,
"grad_norm": 19.699459075927734,
"learning_rate": 6.434021433157192e-05,
"loss": 4.1371,
"step": 255500
},
{
"epoch": 3.150924353198927,
"grad_norm": 6.568043231964111,
"learning_rate": 6.387722850511136e-05,
"loss": 4.1439,
"step": 256000
},
{
"epoch": 3.1570785023262684,
"grad_norm": 2.4748892784118652,
"learning_rate": 6.341424267865079e-05,
"loss": 4.1399,
"step": 256500
},
{
"epoch": 3.16323265145361,
"grad_norm": 32.743019104003906,
"learning_rate": 6.295125685219023e-05,
"loss": 4.1464,
"step": 257000
},
{
"epoch": 3.1693868005809516,
"grad_norm": 36.00674819946289,
"learning_rate": 6.248827102572967e-05,
"loss": 4.1453,
"step": 257500
},
{
"epoch": 3.175540949708293,
"grad_norm": 50.27063751220703,
"learning_rate": 6.20252851992691e-05,
"loss": 4.1363,
"step": 258000
},
{
"epoch": 3.181695098835635,
"grad_norm": 43.25789260864258,
"learning_rate": 6.156229937280853e-05,
"loss": 4.1319,
"step": 258500
},
{
"epoch": 3.1878492479629768,
"grad_norm": 36.427085876464844,
"learning_rate": 6.109931354634796e-05,
"loss": 4.1415,
"step": 259000
},
{
"epoch": 3.1940033970903183,
"grad_norm": 57.88483428955078,
"learning_rate": 6.0636327719887394e-05,
"loss": 4.1313,
"step": 259500
},
{
"epoch": 3.20015754621766,
"grad_norm": 32.543067932128906,
"learning_rate": 6.0173341893426826e-05,
"loss": 4.1335,
"step": 260000
},
{
"epoch": 3.2063116953450015,
"grad_norm": 59.16879653930664,
"learning_rate": 5.9710356066966265e-05,
"loss": 4.1542,
"step": 260500
},
{
"epoch": 3.212465844472343,
"grad_norm": 30.83115577697754,
"learning_rate": 5.92473702405057e-05,
"loss": 4.1528,
"step": 261000
},
{
"epoch": 3.218619993599685,
"grad_norm": 6.640603542327881,
"learning_rate": 5.878438441404513e-05,
"loss": 4.134,
"step": 261500
},
{
"epoch": 3.2247741427270267,
"grad_norm": 7.389746189117432,
"learning_rate": 5.832139858758457e-05,
"loss": 4.1371,
"step": 262000
},
{
"epoch": 3.2309282918543683,
"grad_norm": 6.286543369293213,
"learning_rate": 5.7858412761124e-05,
"loss": 4.1585,
"step": 262500
},
{
"epoch": 3.23708244098171,
"grad_norm": 7.098686218261719,
"learning_rate": 5.739542693466343e-05,
"loss": 4.1471,
"step": 263000
},
{
"epoch": 3.2432365901090514,
"grad_norm": 21.91095542907715,
"learning_rate": 5.693244110820287e-05,
"loss": 4.1447,
"step": 263500
},
{
"epoch": 3.249390739236393,
"grad_norm": 14.315342903137207,
"learning_rate": 5.6469455281742303e-05,
"loss": 4.1268,
"step": 264000
},
{
"epoch": 3.255544888363735,
"grad_norm": 34.134361267089844,
"learning_rate": 5.6006469455281736e-05,
"loss": 4.1342,
"step": 264500
},
{
"epoch": 3.2616990374910766,
"grad_norm": 17.96697425842285,
"learning_rate": 5.5543483628821174e-05,
"loss": 4.1258,
"step": 265000
},
{
"epoch": 3.267853186618418,
"grad_norm": 16.088926315307617,
"learning_rate": 5.5080497802360607e-05,
"loss": 4.1428,
"step": 265500
},
{
"epoch": 3.2740073357457598,
"grad_norm": 24.062644958496094,
"learning_rate": 5.461751197590004e-05,
"loss": 4.1309,
"step": 266000
},
{
"epoch": 3.2801614848731013,
"grad_norm": 8.451128959655762,
"learning_rate": 5.415452614943947e-05,
"loss": 4.175,
"step": 266500
},
{
"epoch": 3.286315634000443,
"grad_norm": 9.664407730102539,
"learning_rate": 5.369154032297891e-05,
"loss": 4.1464,
"step": 267000
},
{
"epoch": 3.292469783127785,
"grad_norm": 4.8509955406188965,
"learning_rate": 5.322855449651834e-05,
"loss": 4.144,
"step": 267500
},
{
"epoch": 3.2986239322551265,
"grad_norm": 13.462193489074707,
"learning_rate": 5.2765568670057774e-05,
"loss": 4.1379,
"step": 268000
},
{
"epoch": 3.304778081382468,
"grad_norm": 20.66737937927246,
"learning_rate": 5.230258284359721e-05,
"loss": 4.1384,
"step": 268500
},
{
"epoch": 3.3109322305098097,
"grad_norm": 4.091955184936523,
"learning_rate": 5.1839597017136645e-05,
"loss": 4.1507,
"step": 269000
},
{
"epoch": 3.3170863796371512,
"grad_norm": 12.628284454345703,
"learning_rate": 5.137661119067608e-05,
"loss": 4.1513,
"step": 269500
},
{
"epoch": 3.323240528764493,
"grad_norm": 18.36392593383789,
"learning_rate": 5.0913625364215516e-05,
"loss": 4.1305,
"step": 270000
},
{
"epoch": 3.329394677891835,
"grad_norm": 16.12276268005371,
"learning_rate": 5.045063953775495e-05,
"loss": 4.1323,
"step": 270500
},
{
"epoch": 3.3355488270191764,
"grad_norm": 9.975174903869629,
"learning_rate": 4.998765371129438e-05,
"loss": 4.1586,
"step": 271000
},
{
"epoch": 3.341702976146518,
"grad_norm": 4.008594512939453,
"learning_rate": 4.952466788483382e-05,
"loss": 4.1279,
"step": 271500
},
{
"epoch": 3.3478571252738596,
"grad_norm": 41.02973175048828,
"learning_rate": 4.906168205837325e-05,
"loss": 4.1597,
"step": 272000
},
{
"epoch": 3.354011274401201,
"grad_norm": 3.381009101867676,
"learning_rate": 4.859869623191268e-05,
"loss": 4.1549,
"step": 272500
},
{
"epoch": 3.3601654235285427,
"grad_norm": 15.301918983459473,
"learning_rate": 4.8135710405452115e-05,
"loss": 4.1481,
"step": 273000
},
{
"epoch": 3.3663195726558848,
"grad_norm": 5.128480911254883,
"learning_rate": 4.7672724578991554e-05,
"loss": 4.1275,
"step": 273500
},
{
"epoch": 3.3724737217832264,
"grad_norm": 20.987468719482422,
"learning_rate": 4.7209738752530986e-05,
"loss": 4.1357,
"step": 274000
},
{
"epoch": 3.378627870910568,
"grad_norm": 3.4314842224121094,
"learning_rate": 4.674675292607042e-05,
"loss": 4.145,
"step": 274500
},
{
"epoch": 3.3847820200379095,
"grad_norm": 8.336324691772461,
"learning_rate": 4.628376709960986e-05,
"loss": 4.1515,
"step": 275000
},
{
"epoch": 3.390936169165251,
"grad_norm": 15.702668190002441,
"learning_rate": 4.582078127314929e-05,
"loss": 4.1458,
"step": 275500
},
{
"epoch": 3.3970903182925927,
"grad_norm": 20.334640502929688,
"learning_rate": 4.535779544668872e-05,
"loss": 4.13,
"step": 276000
},
{
"epoch": 3.4032444674199347,
"grad_norm": 18.100238800048828,
"learning_rate": 4.489480962022816e-05,
"loss": 4.1493,
"step": 276500
},
{
"epoch": 3.4093986165472763,
"grad_norm": 7.6444172859191895,
"learning_rate": 4.443182379376759e-05,
"loss": 4.1494,
"step": 277000
},
{
"epoch": 3.415552765674618,
"grad_norm": 14.355319023132324,
"learning_rate": 4.3968837967307024e-05,
"loss": 4.1523,
"step": 277500
},
{
"epoch": 3.4217069148019594,
"grad_norm": 5.769527435302734,
"learning_rate": 4.350585214084646e-05,
"loss": 4.139,
"step": 278000
},
{
"epoch": 3.427861063929301,
"grad_norm": 11.69207763671875,
"learning_rate": 4.3042866314385895e-05,
"loss": 4.1531,
"step": 278500
},
{
"epoch": 3.434015213056643,
"grad_norm": 12.014427185058594,
"learning_rate": 4.257988048792533e-05,
"loss": 4.1428,
"step": 279000
},
{
"epoch": 3.4401693621839846,
"grad_norm": 26.5164852142334,
"learning_rate": 4.211689466146476e-05,
"loss": 4.1524,
"step": 279500
},
{
"epoch": 3.446323511311326,
"grad_norm": 17.82427978515625,
"learning_rate": 4.16539088350042e-05,
"loss": 4.1536,
"step": 280000
},
{
"epoch": 3.4524776604386678,
"grad_norm": 4.162466526031494,
"learning_rate": 4.119092300854363e-05,
"loss": 4.1365,
"step": 280500
},
{
"epoch": 3.4586318095660094,
"grad_norm": 13.737496376037598,
"learning_rate": 4.072793718208306e-05,
"loss": 4.1334,
"step": 281000
},
{
"epoch": 3.464785958693351,
"grad_norm": 12.105280876159668,
"learning_rate": 4.02649513556225e-05,
"loss": 4.1327,
"step": 281500
},
{
"epoch": 3.4709401078206925,
"grad_norm": 13.839010238647461,
"learning_rate": 3.980196552916193e-05,
"loss": 4.1465,
"step": 282000
},
{
"epoch": 3.4770942569480345,
"grad_norm": 6.681400775909424,
"learning_rate": 3.9338979702701365e-05,
"loss": 4.1341,
"step": 282500
},
{
"epoch": 3.483248406075376,
"grad_norm": 20.491016387939453,
"learning_rate": 3.8875993876240804e-05,
"loss": 4.1413,
"step": 283000
},
{
"epoch": 3.4894025552027177,
"grad_norm": 49.7690544128418,
"learning_rate": 3.8413008049780236e-05,
"loss": 4.1293,
"step": 283500
},
{
"epoch": 3.4955567043300593,
"grad_norm": 11.641499519348145,
"learning_rate": 3.795002222331966e-05,
"loss": 4.1541,
"step": 284000
},
{
"epoch": 3.501710853457401,
"grad_norm": 5.631669044494629,
"learning_rate": 3.74870363968591e-05,
"loss": 4.1292,
"step": 284500
},
{
"epoch": 3.507865002584743,
"grad_norm": 6.93706750869751,
"learning_rate": 3.702405057039854e-05,
"loss": 4.1545,
"step": 285000
},
{
"epoch": 3.514019151712084,
"grad_norm": 6.901698112487793,
"learning_rate": 3.6561064743937965e-05,
"loss": 4.1384,
"step": 285500
},
{
"epoch": 3.520173300839426,
"grad_norm": 14.877540588378906,
"learning_rate": 3.6098078917477404e-05,
"loss": 4.1288,
"step": 286000
},
{
"epoch": 3.5263274499667676,
"grad_norm": 25.724044799804688,
"learning_rate": 3.563509309101684e-05,
"loss": 4.1377,
"step": 286500
},
{
"epoch": 3.532481599094109,
"grad_norm": 7.148214817047119,
"learning_rate": 3.517210726455627e-05,
"loss": 4.1338,
"step": 287000
},
{
"epoch": 3.5386357482214508,
"grad_norm": 7.705902099609375,
"learning_rate": 3.4709121438095707e-05,
"loss": 4.1361,
"step": 287500
},
{
"epoch": 3.5447898973487924,
"grad_norm": 8.448748588562012,
"learning_rate": 3.424613561163514e-05,
"loss": 4.1321,
"step": 288000
},
{
"epoch": 3.5509440464761344,
"grad_norm": 7.869440078735352,
"learning_rate": 3.378314978517457e-05,
"loss": 4.135,
"step": 288500
},
{
"epoch": 3.557098195603476,
"grad_norm": 6.765024662017822,
"learning_rate": 3.332016395871401e-05,
"loss": 4.1529,
"step": 289000
},
{
"epoch": 3.5632523447308175,
"grad_norm": 5.701638698577881,
"learning_rate": 3.285717813225344e-05,
"loss": 4.1436,
"step": 289500
},
{
"epoch": 3.569406493858159,
"grad_norm": 16.283222198486328,
"learning_rate": 3.2394192305792874e-05,
"loss": 4.1355,
"step": 290000
},
{
"epoch": 3.5755606429855007,
"grad_norm": 7.628239154815674,
"learning_rate": 3.1931206479332306e-05,
"loss": 4.1418,
"step": 290500
},
{
"epoch": 3.5817147921128427,
"grad_norm": 15.502190589904785,
"learning_rate": 3.1468220652871745e-05,
"loss": 4.1568,
"step": 291000
},
{
"epoch": 3.5878689412401843,
"grad_norm": 14.92800235748291,
"learning_rate": 3.100523482641118e-05,
"loss": 4.1519,
"step": 291500
},
{
"epoch": 3.594023090367526,
"grad_norm": 8.27001953125,
"learning_rate": 3.054224899995061e-05,
"loss": 4.1441,
"step": 292000
},
{
"epoch": 3.6001772394948675,
"grad_norm": 6.130892753601074,
"learning_rate": 3.0079263173490048e-05,
"loss": 4.1709,
"step": 292500
},
{
"epoch": 3.606331388622209,
"grad_norm": 3.230942726135254,
"learning_rate": 2.9616277347029483e-05,
"loss": 4.1408,
"step": 293000
},
{
"epoch": 3.6124855377495506,
"grad_norm": 11.593179702758789,
"learning_rate": 2.9153291520568915e-05,
"loss": 4.1307,
"step": 293500
},
{
"epoch": 3.618639686876892,
"grad_norm": 16.46498680114746,
"learning_rate": 2.869030569410835e-05,
"loss": 4.1226,
"step": 294000
},
{
"epoch": 3.624793836004234,
"grad_norm": 27.56407928466797,
"learning_rate": 2.822731986764778e-05,
"loss": 4.1413,
"step": 294500
},
{
"epoch": 3.630947985131576,
"grad_norm": 3.463226795196533,
"learning_rate": 2.7764334041187215e-05,
"loss": 4.1454,
"step": 295000
},
{
"epoch": 3.6371021342589174,
"grad_norm": 33.3383674621582,
"learning_rate": 2.7301348214726654e-05,
"loss": 4.1589,
"step": 295500
},
{
"epoch": 3.643256283386259,
"grad_norm": 8.906983375549316,
"learning_rate": 2.6838362388266083e-05,
"loss": 4.1318,
"step": 296000
},
{
"epoch": 3.6494104325136005,
"grad_norm": 5.860848903656006,
"learning_rate": 2.6375376561805518e-05,
"loss": 4.147,
"step": 296500
},
{
"epoch": 3.6555645816409426,
"grad_norm": 9.394577980041504,
"learning_rate": 2.591239073534495e-05,
"loss": 4.1531,
"step": 297000
},
{
"epoch": 3.661718730768284,
"grad_norm": 20.086591720581055,
"learning_rate": 2.5449404908884386e-05,
"loss": 4.1384,
"step": 297500
},
{
"epoch": 3.6678728798956257,
"grad_norm": 4.57155704498291,
"learning_rate": 2.498641908242382e-05,
"loss": 4.129,
"step": 298000
},
{
"epoch": 3.6740270290229673,
"grad_norm": 6.570335865020752,
"learning_rate": 2.4523433255963253e-05,
"loss": 4.1603,
"step": 298500
},
{
"epoch": 3.680181178150309,
"grad_norm": 20.765857696533203,
"learning_rate": 2.406044742950269e-05,
"loss": 4.1105,
"step": 299000
},
{
"epoch": 3.6863353272776505,
"grad_norm": 37.50503921508789,
"learning_rate": 2.3597461603042124e-05,
"loss": 4.1244,
"step": 299500
},
{
"epoch": 3.692489476404992,
"grad_norm": 5.822895050048828,
"learning_rate": 2.3134475776581556e-05,
"loss": 4.1546,
"step": 300000
},
{
"epoch": 3.698643625532334,
"grad_norm": 5.0966291427612305,
"learning_rate": 2.2671489950120992e-05,
"loss": 4.15,
"step": 300500
},
{
"epoch": 3.7047977746596756,
"grad_norm": 4.635249614715576,
"learning_rate": 2.2208504123660424e-05,
"loss": 4.1261,
"step": 301000
},
{
"epoch": 3.710951923787017,
"grad_norm": 12.714454650878906,
"learning_rate": 2.174551829719986e-05,
"loss": 4.145,
"step": 301500
},
{
"epoch": 3.717106072914359,
"grad_norm": 9.874136924743652,
"learning_rate": 2.1282532470739295e-05,
"loss": 4.1263,
"step": 302000
},
{
"epoch": 3.7232602220417004,
"grad_norm": 23.380413055419922,
"learning_rate": 2.0819546644278727e-05,
"loss": 4.1546,
"step": 302500
},
{
"epoch": 3.7294143711690424,
"grad_norm": 9.796693801879883,
"learning_rate": 2.0356560817818162e-05,
"loss": 4.1218,
"step": 303000
},
{
"epoch": 3.735568520296384,
"grad_norm": 8.322081565856934,
"learning_rate": 1.9893574991357594e-05,
"loss": 4.1292,
"step": 303500
},
{
"epoch": 3.7417226694237256,
"grad_norm": 25.19244384765625,
"learning_rate": 1.943058916489703e-05,
"loss": 4.137,
"step": 304000
},
{
"epoch": 3.747876818551067,
"grad_norm": 37.70656967163086,
"learning_rate": 1.8967603338436465e-05,
"loss": 4.1459,
"step": 304500
},
{
"epoch": 3.7540309676784087,
"grad_norm": 10.57068157196045,
"learning_rate": 1.85046175119759e-05,
"loss": 4.136,
"step": 305000
},
{
"epoch": 3.7601851168057503,
"grad_norm": 47.34375,
"learning_rate": 1.8041631685515333e-05,
"loss": 4.1207,
"step": 305500
},
{
"epoch": 3.766339265933092,
"grad_norm": 19.72435760498047,
"learning_rate": 1.7578645859054765e-05,
"loss": 4.1429,
"step": 306000
},
{
"epoch": 3.772493415060434,
"grad_norm": 44.27298355102539,
"learning_rate": 1.71156600325942e-05,
"loss": 4.1357,
"step": 306500
},
{
"epoch": 3.7786475641877755,
"grad_norm": 36.92619705200195,
"learning_rate": 1.6652674206133636e-05,
"loss": 4.1361,
"step": 307000
},
{
"epoch": 3.784801713315117,
"grad_norm": 27.54575538635254,
"learning_rate": 1.6189688379673068e-05,
"loss": 4.1266,
"step": 307500
},
{
"epoch": 3.7909558624424586,
"grad_norm": 34.02424621582031,
"learning_rate": 1.5726702553212504e-05,
"loss": 4.118,
"step": 308000
},
{
"epoch": 3.7971100115698,
"grad_norm": 7.273593425750732,
"learning_rate": 1.5263716726751936e-05,
"loss": 4.1343,
"step": 308500
},
{
"epoch": 3.8032641606971422,
"grad_norm": 9.610830307006836,
"learning_rate": 1.480073090029137e-05,
"loss": 4.1206,
"step": 309000
},
{
"epoch": 3.809418309824484,
"grad_norm": 39.2562255859375,
"learning_rate": 1.4337745073830807e-05,
"loss": 4.1296,
"step": 309500
},
{
"epoch": 3.8155724589518254,
"grad_norm": 46.356842041015625,
"learning_rate": 1.3874759247370239e-05,
"loss": 4.1158,
"step": 310000
},
{
"epoch": 3.821726608079167,
"grad_norm": 33.597740173339844,
"learning_rate": 1.3411773420909673e-05,
"loss": 4.1253,
"step": 310500
},
{
"epoch": 3.8278807572065086,
"grad_norm": 56.68779373168945,
"learning_rate": 1.2948787594449106e-05,
"loss": 4.1105,
"step": 311000
},
{
"epoch": 3.83403490633385,
"grad_norm": 22.97879981994629,
"learning_rate": 1.2485801767988542e-05,
"loss": 4.121,
"step": 311500
},
{
"epoch": 3.8401890554611917,
"grad_norm": 47.771976470947266,
"learning_rate": 1.2022815941527976e-05,
"loss": 4.1247,
"step": 312000
},
{
"epoch": 3.8463432045885337,
"grad_norm": 17.196557998657227,
"learning_rate": 1.155983011506741e-05,
"loss": 4.122,
"step": 312500
},
{
"epoch": 3.8524973537158753,
"grad_norm": 19.346046447753906,
"learning_rate": 1.1096844288606843e-05,
"loss": 4.1442,
"step": 313000
},
{
"epoch": 3.858651502843217,
"grad_norm": 11.184770584106445,
"learning_rate": 1.0633858462146279e-05,
"loss": 4.1482,
"step": 313500
},
{
"epoch": 3.8648056519705585,
"grad_norm": 12.078618049621582,
"learning_rate": 1.0170872635685712e-05,
"loss": 4.1121,
"step": 314000
},
{
"epoch": 3.8709598010979,
"grad_norm": 9.159948348999023,
"learning_rate": 9.707886809225146e-06,
"loss": 4.1098,
"step": 314500
},
{
"epoch": 3.877113950225242,
"grad_norm": 11.605913162231445,
"learning_rate": 9.24490098276458e-06,
"loss": 4.1135,
"step": 315000
},
{
"epoch": 3.8832680993525837,
"grad_norm": 25.581920623779297,
"learning_rate": 8.781915156304014e-06,
"loss": 4.1317,
"step": 315500
},
{
"epoch": 3.8894222484799252,
"grad_norm": 7.528061389923096,
"learning_rate": 8.318929329843448e-06,
"loss": 4.1247,
"step": 316000
},
{
"epoch": 3.895576397607267,
"grad_norm": 13.743077278137207,
"learning_rate": 7.855943503382883e-06,
"loss": 4.1222,
"step": 316500
},
{
"epoch": 3.9017305467346084,
"grad_norm": 8.61697769165039,
"learning_rate": 7.392957676922316e-06,
"loss": 4.1163,
"step": 317000
},
{
"epoch": 3.90788469586195,
"grad_norm": 27.41314697265625,
"learning_rate": 6.929971850461751e-06,
"loss": 4.1533,
"step": 317500
},
{
"epoch": 3.9140388449892916,
"grad_norm": 45.38865280151367,
"learning_rate": 6.466986024001184e-06,
"loss": 4.1138,
"step": 318000
},
{
"epoch": 3.9201929941166336,
"grad_norm": 16.720979690551758,
"learning_rate": 6.004000197540619e-06,
"loss": 4.1209,
"step": 318500
},
{
"epoch": 3.926347143243975,
"grad_norm": 10.842707633972168,
"learning_rate": 5.541014371080053e-06,
"loss": 4.1334,
"step": 319000
},
{
"epoch": 3.9325012923713167,
"grad_norm": 6.323044300079346,
"learning_rate": 5.078028544619487e-06,
"loss": 4.1398,
"step": 319500
},
{
"epoch": 3.9386554414986583,
"grad_norm": 49.76858901977539,
"learning_rate": 4.615042718158921e-06,
"loss": 4.1362,
"step": 320000
},
{
"epoch": 3.944809590626,
"grad_norm": 8.20909595489502,
"learning_rate": 4.152056891698355e-06,
"loss": 4.1095,
"step": 320500
},
{
"epoch": 3.950963739753342,
"grad_norm": 12.263701438903809,
"learning_rate": 3.689071065237789e-06,
"loss": 4.1332,
"step": 321000
},
{
"epoch": 3.9571178888806835,
"grad_norm": 15.455554962158203,
"learning_rate": 3.2260852387772234e-06,
"loss": 4.1342,
"step": 321500
},
{
"epoch": 3.963272038008025,
"grad_norm": 35.89369201660156,
"learning_rate": 2.7630994123166576e-06,
"loss": 4.1269,
"step": 322000
},
{
"epoch": 3.9694261871353667,
"grad_norm": 12.723758697509766,
"learning_rate": 2.3001135858560914e-06,
"loss": 4.1417,
"step": 322500
},
{
"epoch": 3.9755803362627082,
"grad_norm": 9.713438034057617,
"learning_rate": 1.8371277593955256e-06,
"loss": 4.1068,
"step": 323000
},
{
"epoch": 3.98173448539005,
"grad_norm": 24.07921600341797,
"learning_rate": 1.3741419329349596e-06,
"loss": 4.1194,
"step": 323500
},
{
"epoch": 3.9878886345173914,
"grad_norm": 27.489330291748047,
"learning_rate": 9.111561064743937e-07,
"loss": 4.1321,
"step": 324000
},
{
"epoch": 3.9940427836447334,
"grad_norm": 13.5571928024292,
"learning_rate": 4.481702800138278e-07,
"loss": 4.1075,
"step": 324500
},
{
"epoch": 4.0,
"step": 324984,
"total_flos": 1.7111307358572134e+17,
"train_loss": 4.1254700603259264,
"train_runtime": 48035.7406,
"train_samples_per_second": 54.123,
"train_steps_per_second": 6.765
}
],
"logging_steps": 500,
"max_steps": 324984,
"num_input_tokens_seen": 0,
"num_train_epochs": 4,
"save_steps": 30000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.7111307358572134e+17,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}