sedrickkeh's picture
End of training
5cca166 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 2.998551424432641,
"eval_steps": 500,
"global_step": 3105,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.009657170449058426,
"grad_norm": 3.7815811768441914,
"learning_rate": 5e-06,
"loss": 0.6253,
"step": 10
},
{
"epoch": 0.01931434089811685,
"grad_norm": 2.097627838391192,
"learning_rate": 5e-06,
"loss": 0.5439,
"step": 20
},
{
"epoch": 0.028971511347175277,
"grad_norm": 1.991134226246532,
"learning_rate": 5e-06,
"loss": 0.5217,
"step": 30
},
{
"epoch": 0.0386286817962337,
"grad_norm": 1.786626694141357,
"learning_rate": 5e-06,
"loss": 0.5096,
"step": 40
},
{
"epoch": 0.04828585224529213,
"grad_norm": 1.717098828666389,
"learning_rate": 5e-06,
"loss": 0.5039,
"step": 50
},
{
"epoch": 0.05794302269435055,
"grad_norm": 1.8094322954355757,
"learning_rate": 5e-06,
"loss": 0.5015,
"step": 60
},
{
"epoch": 0.06760019314340898,
"grad_norm": 2.0392174555732336,
"learning_rate": 5e-06,
"loss": 0.4883,
"step": 70
},
{
"epoch": 0.0772573635924674,
"grad_norm": 1.9677308677580745,
"learning_rate": 5e-06,
"loss": 0.4874,
"step": 80
},
{
"epoch": 0.08691453404152583,
"grad_norm": 1.7766414325618487,
"learning_rate": 5e-06,
"loss": 0.4874,
"step": 90
},
{
"epoch": 0.09657170449058426,
"grad_norm": 1.6816893104701698,
"learning_rate": 5e-06,
"loss": 0.4803,
"step": 100
},
{
"epoch": 0.10622887493964268,
"grad_norm": 1.4814895014838179,
"learning_rate": 5e-06,
"loss": 0.4781,
"step": 110
},
{
"epoch": 0.1158860453887011,
"grad_norm": 1.809417684888777,
"learning_rate": 5e-06,
"loss": 0.477,
"step": 120
},
{
"epoch": 0.12554321583775954,
"grad_norm": 1.604499406008116,
"learning_rate": 5e-06,
"loss": 0.4745,
"step": 130
},
{
"epoch": 0.13520038628681796,
"grad_norm": 1.5342478528722183,
"learning_rate": 5e-06,
"loss": 0.4733,
"step": 140
},
{
"epoch": 0.14485755673587639,
"grad_norm": 1.7155349659817856,
"learning_rate": 5e-06,
"loss": 0.4733,
"step": 150
},
{
"epoch": 0.1545147271849348,
"grad_norm": 1.4873226511627278,
"learning_rate": 5e-06,
"loss": 0.4717,
"step": 160
},
{
"epoch": 0.16417189763399323,
"grad_norm": 1.5335342617066339,
"learning_rate": 5e-06,
"loss": 0.4703,
"step": 170
},
{
"epoch": 0.17382906808305165,
"grad_norm": 1.692809745357256,
"learning_rate": 5e-06,
"loss": 0.473,
"step": 180
},
{
"epoch": 0.1834862385321101,
"grad_norm": 1.6215225290403987,
"learning_rate": 5e-06,
"loss": 0.4713,
"step": 190
},
{
"epoch": 0.19314340898116852,
"grad_norm": 1.61595338484294,
"learning_rate": 5e-06,
"loss": 0.4666,
"step": 200
},
{
"epoch": 0.20280057943022695,
"grad_norm": 1.535971453026849,
"learning_rate": 5e-06,
"loss": 0.4644,
"step": 210
},
{
"epoch": 0.21245774987928537,
"grad_norm": 1.448430643756855,
"learning_rate": 5e-06,
"loss": 0.4583,
"step": 220
},
{
"epoch": 0.2221149203283438,
"grad_norm": 1.6067011202263324,
"learning_rate": 5e-06,
"loss": 0.4575,
"step": 230
},
{
"epoch": 0.2317720907774022,
"grad_norm": 1.4643615572820308,
"learning_rate": 5e-06,
"loss": 0.4554,
"step": 240
},
{
"epoch": 0.24142926122646063,
"grad_norm": 1.5756879099170888,
"learning_rate": 5e-06,
"loss": 0.4661,
"step": 250
},
{
"epoch": 0.2510864316755191,
"grad_norm": 1.6966284718047921,
"learning_rate": 5e-06,
"loss": 0.4586,
"step": 260
},
{
"epoch": 0.2607436021245775,
"grad_norm": 1.6310274076314688,
"learning_rate": 5e-06,
"loss": 0.4616,
"step": 270
},
{
"epoch": 0.27040077257363593,
"grad_norm": 1.5908628903198843,
"learning_rate": 5e-06,
"loss": 0.456,
"step": 280
},
{
"epoch": 0.2800579430226944,
"grad_norm": 1.5321607540064421,
"learning_rate": 5e-06,
"loss": 0.4632,
"step": 290
},
{
"epoch": 0.28971511347175277,
"grad_norm": 1.5432080707621136,
"learning_rate": 5e-06,
"loss": 0.4498,
"step": 300
},
{
"epoch": 0.2993722839208112,
"grad_norm": 1.5174884163746274,
"learning_rate": 5e-06,
"loss": 0.4547,
"step": 310
},
{
"epoch": 0.3090294543698696,
"grad_norm": 1.4431913116342714,
"learning_rate": 5e-06,
"loss": 0.448,
"step": 320
},
{
"epoch": 0.31868662481892807,
"grad_norm": 1.7071593067951876,
"learning_rate": 5e-06,
"loss": 0.4493,
"step": 330
},
{
"epoch": 0.32834379526798646,
"grad_norm": 1.3857947339153756,
"learning_rate": 5e-06,
"loss": 0.4545,
"step": 340
},
{
"epoch": 0.3380009657170449,
"grad_norm": 1.4688790780164955,
"learning_rate": 5e-06,
"loss": 0.4465,
"step": 350
},
{
"epoch": 0.3476581361661033,
"grad_norm": 1.4620765033414924,
"learning_rate": 5e-06,
"loss": 0.4495,
"step": 360
},
{
"epoch": 0.35731530661516175,
"grad_norm": 1.4806186634505536,
"learning_rate": 5e-06,
"loss": 0.4455,
"step": 370
},
{
"epoch": 0.3669724770642202,
"grad_norm": 1.3726165431422352,
"learning_rate": 5e-06,
"loss": 0.446,
"step": 380
},
{
"epoch": 0.3766296475132786,
"grad_norm": 1.902972844618989,
"learning_rate": 5e-06,
"loss": 0.447,
"step": 390
},
{
"epoch": 0.38628681796233705,
"grad_norm": 1.4905365903207408,
"learning_rate": 5e-06,
"loss": 0.4446,
"step": 400
},
{
"epoch": 0.39594398841139544,
"grad_norm": 1.4193622471558158,
"learning_rate": 5e-06,
"loss": 0.4481,
"step": 410
},
{
"epoch": 0.4056011588604539,
"grad_norm": 1.5124518593909522,
"learning_rate": 5e-06,
"loss": 0.4417,
"step": 420
},
{
"epoch": 0.4152583293095123,
"grad_norm": 1.3927026205868633,
"learning_rate": 5e-06,
"loss": 0.4469,
"step": 430
},
{
"epoch": 0.42491549975857074,
"grad_norm": 1.4506580301027323,
"learning_rate": 5e-06,
"loss": 0.442,
"step": 440
},
{
"epoch": 0.4345726702076292,
"grad_norm": 1.3495438486710758,
"learning_rate": 5e-06,
"loss": 0.446,
"step": 450
},
{
"epoch": 0.4442298406566876,
"grad_norm": 1.5206970544390066,
"learning_rate": 5e-06,
"loss": 0.4419,
"step": 460
},
{
"epoch": 0.45388701110574603,
"grad_norm": 1.4858134923328608,
"learning_rate": 5e-06,
"loss": 0.4543,
"step": 470
},
{
"epoch": 0.4635441815548044,
"grad_norm": 1.5043934135687507,
"learning_rate": 5e-06,
"loss": 0.4459,
"step": 480
},
{
"epoch": 0.4732013520038629,
"grad_norm": 2.2482606991957463,
"learning_rate": 5e-06,
"loss": 0.4426,
"step": 490
},
{
"epoch": 0.48285852245292127,
"grad_norm": 1.4045208076303264,
"learning_rate": 5e-06,
"loss": 0.4326,
"step": 500
},
{
"epoch": 0.4925156929019797,
"grad_norm": 1.543363161753652,
"learning_rate": 5e-06,
"loss": 0.4439,
"step": 510
},
{
"epoch": 0.5021728633510382,
"grad_norm": 1.3653299013378564,
"learning_rate": 5e-06,
"loss": 0.436,
"step": 520
},
{
"epoch": 0.5118300338000966,
"grad_norm": 1.4150482204508787,
"learning_rate": 5e-06,
"loss": 0.4378,
"step": 530
},
{
"epoch": 0.521487204249155,
"grad_norm": 1.3973876180346887,
"learning_rate": 5e-06,
"loss": 0.4395,
"step": 540
},
{
"epoch": 0.5311443746982134,
"grad_norm": 1.4601941048467661,
"learning_rate": 5e-06,
"loss": 0.4409,
"step": 550
},
{
"epoch": 0.5408015451472719,
"grad_norm": 1.367282105296493,
"learning_rate": 5e-06,
"loss": 0.4365,
"step": 560
},
{
"epoch": 0.5504587155963303,
"grad_norm": 1.4142842428381743,
"learning_rate": 5e-06,
"loss": 0.4368,
"step": 570
},
{
"epoch": 0.5601158860453888,
"grad_norm": 1.5238374949968105,
"learning_rate": 5e-06,
"loss": 0.4351,
"step": 580
},
{
"epoch": 0.5697730564944471,
"grad_norm": 1.4426020649884985,
"learning_rate": 5e-06,
"loss": 0.4378,
"step": 590
},
{
"epoch": 0.5794302269435055,
"grad_norm": 1.6034191206258377,
"learning_rate": 5e-06,
"loss": 0.4359,
"step": 600
},
{
"epoch": 0.589087397392564,
"grad_norm": 1.3861019948416724,
"learning_rate": 5e-06,
"loss": 0.4366,
"step": 610
},
{
"epoch": 0.5987445678416224,
"grad_norm": 1.5575620851838663,
"learning_rate": 5e-06,
"loss": 0.4293,
"step": 620
},
{
"epoch": 0.6084017382906808,
"grad_norm": 1.4940232627496768,
"learning_rate": 5e-06,
"loss": 0.4308,
"step": 630
},
{
"epoch": 0.6180589087397392,
"grad_norm": 1.3940687230128848,
"learning_rate": 5e-06,
"loss": 0.4344,
"step": 640
},
{
"epoch": 0.6277160791887977,
"grad_norm": 1.4063585473842182,
"learning_rate": 5e-06,
"loss": 0.4312,
"step": 650
},
{
"epoch": 0.6373732496378561,
"grad_norm": 1.4263057370102823,
"learning_rate": 5e-06,
"loss": 0.4288,
"step": 660
},
{
"epoch": 0.6470304200869146,
"grad_norm": 1.359338730182779,
"learning_rate": 5e-06,
"loss": 0.432,
"step": 670
},
{
"epoch": 0.6566875905359729,
"grad_norm": 1.4201113340211817,
"learning_rate": 5e-06,
"loss": 0.4271,
"step": 680
},
{
"epoch": 0.6663447609850314,
"grad_norm": 1.3945845556957837,
"learning_rate": 5e-06,
"loss": 0.4297,
"step": 690
},
{
"epoch": 0.6760019314340898,
"grad_norm": 1.4879889305917073,
"learning_rate": 5e-06,
"loss": 0.4275,
"step": 700
},
{
"epoch": 0.6856591018831483,
"grad_norm": 1.5684295486014674,
"learning_rate": 5e-06,
"loss": 0.4318,
"step": 710
},
{
"epoch": 0.6953162723322066,
"grad_norm": 1.6080556978629539,
"learning_rate": 5e-06,
"loss": 0.4327,
"step": 720
},
{
"epoch": 0.7049734427812651,
"grad_norm": 1.4517662054077567,
"learning_rate": 5e-06,
"loss": 0.4316,
"step": 730
},
{
"epoch": 0.7146306132303235,
"grad_norm": 1.2929610515185452,
"learning_rate": 5e-06,
"loss": 0.4294,
"step": 740
},
{
"epoch": 0.724287783679382,
"grad_norm": 1.4669951814767501,
"learning_rate": 5e-06,
"loss": 0.4295,
"step": 750
},
{
"epoch": 0.7339449541284404,
"grad_norm": 1.3523170842518906,
"learning_rate": 5e-06,
"loss": 0.4323,
"step": 760
},
{
"epoch": 0.7436021245774987,
"grad_norm": 1.4848119403639475,
"learning_rate": 5e-06,
"loss": 0.4307,
"step": 770
},
{
"epoch": 0.7532592950265572,
"grad_norm": 1.2865027479600895,
"learning_rate": 5e-06,
"loss": 0.4302,
"step": 780
},
{
"epoch": 0.7629164654756156,
"grad_norm": 1.3394197026037133,
"learning_rate": 5e-06,
"loss": 0.4274,
"step": 790
},
{
"epoch": 0.7725736359246741,
"grad_norm": 1.4058992660952825,
"learning_rate": 5e-06,
"loss": 0.4315,
"step": 800
},
{
"epoch": 0.7822308063737325,
"grad_norm": 1.4021237990828046,
"learning_rate": 5e-06,
"loss": 0.4258,
"step": 810
},
{
"epoch": 0.7918879768227909,
"grad_norm": 1.4089771533232405,
"learning_rate": 5e-06,
"loss": 0.4334,
"step": 820
},
{
"epoch": 0.8015451472718493,
"grad_norm": 1.3600046812066533,
"learning_rate": 5e-06,
"loss": 0.4225,
"step": 830
},
{
"epoch": 0.8112023177209078,
"grad_norm": 1.4685840247095097,
"learning_rate": 5e-06,
"loss": 0.4251,
"step": 840
},
{
"epoch": 0.8208594881699662,
"grad_norm": 1.3854952044022746,
"learning_rate": 5e-06,
"loss": 0.4305,
"step": 850
},
{
"epoch": 0.8305166586190246,
"grad_norm": 1.3373112968229082,
"learning_rate": 5e-06,
"loss": 0.4266,
"step": 860
},
{
"epoch": 0.840173829068083,
"grad_norm": 1.4141453052618997,
"learning_rate": 5e-06,
"loss": 0.4276,
"step": 870
},
{
"epoch": 0.8498309995171415,
"grad_norm": 1.5086378917784917,
"learning_rate": 5e-06,
"loss": 0.4247,
"step": 880
},
{
"epoch": 0.8594881699661999,
"grad_norm": 7.458182848059056,
"learning_rate": 5e-06,
"loss": 0.4299,
"step": 890
},
{
"epoch": 0.8691453404152584,
"grad_norm": 1.5061946368232628,
"learning_rate": 5e-06,
"loss": 0.4207,
"step": 900
},
{
"epoch": 0.8788025108643167,
"grad_norm": 1.2888259560849804,
"learning_rate": 5e-06,
"loss": 0.4224,
"step": 910
},
{
"epoch": 0.8884596813133752,
"grad_norm": 1.4278585748957382,
"learning_rate": 5e-06,
"loss": 0.4222,
"step": 920
},
{
"epoch": 0.8981168517624336,
"grad_norm": 1.4321653215479198,
"learning_rate": 5e-06,
"loss": 0.4242,
"step": 930
},
{
"epoch": 0.9077740222114921,
"grad_norm": 1.3716154862902383,
"learning_rate": 5e-06,
"loss": 0.4225,
"step": 940
},
{
"epoch": 0.9174311926605505,
"grad_norm": 1.3700235242916874,
"learning_rate": 5e-06,
"loss": 0.421,
"step": 950
},
{
"epoch": 0.9270883631096088,
"grad_norm": 1.3005175365880353,
"learning_rate": 5e-06,
"loss": 0.4191,
"step": 960
},
{
"epoch": 0.9367455335586673,
"grad_norm": 1.3469399837188125,
"learning_rate": 5e-06,
"loss": 0.4215,
"step": 970
},
{
"epoch": 0.9464027040077257,
"grad_norm": 1.3797432696350105,
"learning_rate": 5e-06,
"loss": 0.4265,
"step": 980
},
{
"epoch": 0.9560598744567842,
"grad_norm": 1.2977225244391166,
"learning_rate": 5e-06,
"loss": 0.4215,
"step": 990
},
{
"epoch": 0.9657170449058425,
"grad_norm": 1.2662429869365561,
"learning_rate": 5e-06,
"loss": 0.4227,
"step": 1000
},
{
"epoch": 0.975374215354901,
"grad_norm": 1.3086127516497834,
"learning_rate": 5e-06,
"loss": 0.4178,
"step": 1010
},
{
"epoch": 0.9850313858039594,
"grad_norm": 1.3519105272191883,
"learning_rate": 5e-06,
"loss": 0.4186,
"step": 1020
},
{
"epoch": 0.9946885562530179,
"grad_norm": 1.301344809598359,
"learning_rate": 5e-06,
"loss": 0.417,
"step": 1030
},
{
"epoch": 0.9995171414775471,
"eval_loss": 0.4187374413013458,
"eval_runtime": 182.0762,
"eval_samples_per_second": 153.249,
"eval_steps_per_second": 0.599,
"step": 1035
},
{
"epoch": 1.0043457267020763,
"grad_norm": 2.0938717237725024,
"learning_rate": 5e-06,
"loss": 0.3807,
"step": 1040
},
{
"epoch": 1.0140028971511348,
"grad_norm": 1.6443261926343353,
"learning_rate": 5e-06,
"loss": 0.3165,
"step": 1050
},
{
"epoch": 1.0236600676001932,
"grad_norm": 1.3639427703718043,
"learning_rate": 5e-06,
"loss": 0.3142,
"step": 1060
},
{
"epoch": 1.0333172380492515,
"grad_norm": 1.4375989800345246,
"learning_rate": 5e-06,
"loss": 0.315,
"step": 1070
},
{
"epoch": 1.04297440849831,
"grad_norm": 1.608018512856855,
"learning_rate": 5e-06,
"loss": 0.3105,
"step": 1080
},
{
"epoch": 1.0526315789473684,
"grad_norm": 1.6910926571603153,
"learning_rate": 5e-06,
"loss": 0.3156,
"step": 1090
},
{
"epoch": 1.0622887493964268,
"grad_norm": 1.501323197263165,
"learning_rate": 5e-06,
"loss": 0.3214,
"step": 1100
},
{
"epoch": 1.0719459198454853,
"grad_norm": 1.5198024912737862,
"learning_rate": 5e-06,
"loss": 0.3187,
"step": 1110
},
{
"epoch": 1.0816030902945437,
"grad_norm": 1.3967412194416047,
"learning_rate": 5e-06,
"loss": 0.3177,
"step": 1120
},
{
"epoch": 1.0912602607436022,
"grad_norm": 1.5169020279572174,
"learning_rate": 5e-06,
"loss": 0.3194,
"step": 1130
},
{
"epoch": 1.1009174311926606,
"grad_norm": 1.436092584626518,
"learning_rate": 5e-06,
"loss": 0.3184,
"step": 1140
},
{
"epoch": 1.110574601641719,
"grad_norm": 1.5133593820810858,
"learning_rate": 5e-06,
"loss": 0.3209,
"step": 1150
},
{
"epoch": 1.1202317720907775,
"grad_norm": 1.4358744153476208,
"learning_rate": 5e-06,
"loss": 0.3162,
"step": 1160
},
{
"epoch": 1.1298889425398357,
"grad_norm": 1.550919605032498,
"learning_rate": 5e-06,
"loss": 0.3176,
"step": 1170
},
{
"epoch": 1.1395461129888942,
"grad_norm": 1.4353404806567058,
"learning_rate": 5e-06,
"loss": 0.3206,
"step": 1180
},
{
"epoch": 1.1492032834379526,
"grad_norm": 1.6213115971080414,
"learning_rate": 5e-06,
"loss": 0.3189,
"step": 1190
},
{
"epoch": 1.158860453887011,
"grad_norm": 1.4735029754670448,
"learning_rate": 5e-06,
"loss": 0.318,
"step": 1200
},
{
"epoch": 1.1685176243360695,
"grad_norm": 1.4914905722949483,
"learning_rate": 5e-06,
"loss": 0.3259,
"step": 1210
},
{
"epoch": 1.178174794785128,
"grad_norm": 1.4734223688553245,
"learning_rate": 5e-06,
"loss": 0.3197,
"step": 1220
},
{
"epoch": 1.1878319652341864,
"grad_norm": 1.4303986315832913,
"learning_rate": 5e-06,
"loss": 0.3152,
"step": 1230
},
{
"epoch": 1.1974891356832449,
"grad_norm": 1.641460216526965,
"learning_rate": 5e-06,
"loss": 0.3203,
"step": 1240
},
{
"epoch": 1.2071463061323033,
"grad_norm": 1.4854108071397198,
"learning_rate": 5e-06,
"loss": 0.3187,
"step": 1250
},
{
"epoch": 1.2168034765813616,
"grad_norm": 1.5657183004768043,
"learning_rate": 5e-06,
"loss": 0.321,
"step": 1260
},
{
"epoch": 1.22646064703042,
"grad_norm": 1.5392245759709497,
"learning_rate": 5e-06,
"loss": 0.3199,
"step": 1270
},
{
"epoch": 1.2361178174794785,
"grad_norm": 1.4716569015272043,
"learning_rate": 5e-06,
"loss": 0.3167,
"step": 1280
},
{
"epoch": 1.245774987928537,
"grad_norm": 1.4273719929805762,
"learning_rate": 5e-06,
"loss": 0.3203,
"step": 1290
},
{
"epoch": 1.2554321583775954,
"grad_norm": 1.437096297299039,
"learning_rate": 5e-06,
"loss": 0.3211,
"step": 1300
},
{
"epoch": 1.2650893288266538,
"grad_norm": 1.4122099703029305,
"learning_rate": 5e-06,
"loss": 0.3182,
"step": 1310
},
{
"epoch": 1.2747464992757123,
"grad_norm": 1.62630879502805,
"learning_rate": 5e-06,
"loss": 0.3217,
"step": 1320
},
{
"epoch": 1.2844036697247707,
"grad_norm": 1.516391222863939,
"learning_rate": 5e-06,
"loss": 0.319,
"step": 1330
},
{
"epoch": 1.2940608401738292,
"grad_norm": 1.9043021829524946,
"learning_rate": 5e-06,
"loss": 0.3201,
"step": 1340
},
{
"epoch": 1.3037180106228874,
"grad_norm": 1.468668927245736,
"learning_rate": 5e-06,
"loss": 0.3185,
"step": 1350
},
{
"epoch": 1.3133751810719458,
"grad_norm": 1.5192911853076112,
"learning_rate": 5e-06,
"loss": 0.321,
"step": 1360
},
{
"epoch": 1.3230323515210043,
"grad_norm": 1.4775016904206435,
"learning_rate": 5e-06,
"loss": 0.323,
"step": 1370
},
{
"epoch": 1.3326895219700627,
"grad_norm": 1.5738282394014576,
"learning_rate": 5e-06,
"loss": 0.3244,
"step": 1380
},
{
"epoch": 1.3423466924191212,
"grad_norm": 1.451975577099937,
"learning_rate": 5e-06,
"loss": 0.3231,
"step": 1390
},
{
"epoch": 1.3520038628681796,
"grad_norm": 1.509638768808278,
"learning_rate": 5e-06,
"loss": 0.3238,
"step": 1400
},
{
"epoch": 1.361661033317238,
"grad_norm": 1.4711514260625576,
"learning_rate": 5e-06,
"loss": 0.3246,
"step": 1410
},
{
"epoch": 1.3713182037662965,
"grad_norm": 1.5617390029956357,
"learning_rate": 5e-06,
"loss": 0.3224,
"step": 1420
},
{
"epoch": 1.380975374215355,
"grad_norm": 1.5052132010129833,
"learning_rate": 5e-06,
"loss": 0.3225,
"step": 1430
},
{
"epoch": 1.3906325446644132,
"grad_norm": 1.5656411569392583,
"learning_rate": 5e-06,
"loss": 0.3151,
"step": 1440
},
{
"epoch": 1.4002897151134719,
"grad_norm": 1.4546198678024953,
"learning_rate": 5e-06,
"loss": 0.3186,
"step": 1450
},
{
"epoch": 1.4099468855625301,
"grad_norm": 1.4514681189539558,
"learning_rate": 5e-06,
"loss": 0.3252,
"step": 1460
},
{
"epoch": 1.4196040560115886,
"grad_norm": 1.5187373109976763,
"learning_rate": 5e-06,
"loss": 0.3218,
"step": 1470
},
{
"epoch": 1.429261226460647,
"grad_norm": 1.4206099886595174,
"learning_rate": 5e-06,
"loss": 0.3224,
"step": 1480
},
{
"epoch": 1.4389183969097055,
"grad_norm": 1.3933469991291707,
"learning_rate": 5e-06,
"loss": 0.3261,
"step": 1490
},
{
"epoch": 1.448575567358764,
"grad_norm": 1.5275153572741944,
"learning_rate": 5e-06,
"loss": 0.3196,
"step": 1500
},
{
"epoch": 1.4582327378078224,
"grad_norm": 1.502387340983924,
"learning_rate": 5e-06,
"loss": 0.3202,
"step": 1510
},
{
"epoch": 1.4678899082568808,
"grad_norm": 1.4367426017329248,
"learning_rate": 5e-06,
"loss": 0.3246,
"step": 1520
},
{
"epoch": 1.477547078705939,
"grad_norm": 1.50109980877967,
"learning_rate": 5e-06,
"loss": 0.3232,
"step": 1530
},
{
"epoch": 1.4872042491549977,
"grad_norm": 1.6172108349800483,
"learning_rate": 5e-06,
"loss": 0.3261,
"step": 1540
},
{
"epoch": 1.496861419604056,
"grad_norm": 1.44998024463031,
"learning_rate": 5e-06,
"loss": 0.3223,
"step": 1550
},
{
"epoch": 1.5065185900531144,
"grad_norm": 1.4396628484827616,
"learning_rate": 5e-06,
"loss": 0.3207,
"step": 1560
},
{
"epoch": 1.5161757605021728,
"grad_norm": 1.4505846726645737,
"learning_rate": 5e-06,
"loss": 0.3238,
"step": 1570
},
{
"epoch": 1.5258329309512313,
"grad_norm": 1.3991156805400873,
"learning_rate": 5e-06,
"loss": 0.3205,
"step": 1580
},
{
"epoch": 1.5354901014002897,
"grad_norm": 1.8677762783077632,
"learning_rate": 5e-06,
"loss": 0.3258,
"step": 1590
},
{
"epoch": 1.5451472718493482,
"grad_norm": 1.5966624238860196,
"learning_rate": 5e-06,
"loss": 0.3253,
"step": 1600
},
{
"epoch": 1.5548044422984066,
"grad_norm": 1.4666709592985163,
"learning_rate": 5e-06,
"loss": 0.3197,
"step": 1610
},
{
"epoch": 1.5644616127474649,
"grad_norm": 1.5429686092632175,
"learning_rate": 5e-06,
"loss": 0.3243,
"step": 1620
},
{
"epoch": 1.5741187831965235,
"grad_norm": 1.6197267190074782,
"learning_rate": 5e-06,
"loss": 0.3194,
"step": 1630
},
{
"epoch": 1.5837759536455818,
"grad_norm": 1.5284451091184315,
"learning_rate": 5e-06,
"loss": 0.3195,
"step": 1640
},
{
"epoch": 1.5934331240946402,
"grad_norm": 1.4818015371419853,
"learning_rate": 5e-06,
"loss": 0.3252,
"step": 1650
},
{
"epoch": 1.6030902945436987,
"grad_norm": 1.5230446062018719,
"learning_rate": 5e-06,
"loss": 0.3256,
"step": 1660
},
{
"epoch": 1.6127474649927571,
"grad_norm": 1.3984458497949286,
"learning_rate": 5e-06,
"loss": 0.3251,
"step": 1670
},
{
"epoch": 1.6224046354418156,
"grad_norm": 1.3753762689022815,
"learning_rate": 5e-06,
"loss": 0.318,
"step": 1680
},
{
"epoch": 1.632061805890874,
"grad_norm": 1.4229134627752649,
"learning_rate": 5e-06,
"loss": 0.3206,
"step": 1690
},
{
"epoch": 1.6417189763399325,
"grad_norm": 1.6325248655032423,
"learning_rate": 5e-06,
"loss": 0.3254,
"step": 1700
},
{
"epoch": 1.6513761467889907,
"grad_norm": 1.460452232456223,
"learning_rate": 5e-06,
"loss": 0.3256,
"step": 1710
},
{
"epoch": 1.6610333172380494,
"grad_norm": 1.4967322575333943,
"learning_rate": 5e-06,
"loss": 0.3221,
"step": 1720
},
{
"epoch": 1.6706904876871076,
"grad_norm": 1.4589595336063315,
"learning_rate": 5e-06,
"loss": 0.3247,
"step": 1730
},
{
"epoch": 1.6803476581361663,
"grad_norm": 1.535858835340216,
"learning_rate": 5e-06,
"loss": 0.3218,
"step": 1740
},
{
"epoch": 1.6900048285852245,
"grad_norm": 1.5876620484010096,
"learning_rate": 5e-06,
"loss": 0.3232,
"step": 1750
},
{
"epoch": 1.699661999034283,
"grad_norm": 1.4347951889442994,
"learning_rate": 5e-06,
"loss": 0.3223,
"step": 1760
},
{
"epoch": 1.7093191694833414,
"grad_norm": 1.462429783459939,
"learning_rate": 5e-06,
"loss": 0.321,
"step": 1770
},
{
"epoch": 1.7189763399323998,
"grad_norm": 1.4922559510321622,
"learning_rate": 5e-06,
"loss": 0.3231,
"step": 1780
},
{
"epoch": 1.7286335103814583,
"grad_norm": 1.467959135285837,
"learning_rate": 5e-06,
"loss": 0.328,
"step": 1790
},
{
"epoch": 1.7382906808305165,
"grad_norm": 1.49130361205012,
"learning_rate": 5e-06,
"loss": 0.3266,
"step": 1800
},
{
"epoch": 1.7479478512795752,
"grad_norm": 2.106032317323986,
"learning_rate": 5e-06,
"loss": 0.3251,
"step": 1810
},
{
"epoch": 1.7576050217286334,
"grad_norm": 1.543093994781833,
"learning_rate": 5e-06,
"loss": 0.3243,
"step": 1820
},
{
"epoch": 1.767262192177692,
"grad_norm": 1.4767806762226672,
"learning_rate": 5e-06,
"loss": 0.3222,
"step": 1830
},
{
"epoch": 1.7769193626267503,
"grad_norm": 1.6074675928640145,
"learning_rate": 5e-06,
"loss": 0.3243,
"step": 1840
},
{
"epoch": 1.7865765330758088,
"grad_norm": 1.586893521300227,
"learning_rate": 5e-06,
"loss": 0.3271,
"step": 1850
},
{
"epoch": 1.7962337035248672,
"grad_norm": 1.5199781278405553,
"learning_rate": 5e-06,
"loss": 0.3226,
"step": 1860
},
{
"epoch": 1.8058908739739257,
"grad_norm": 1.7072009333034235,
"learning_rate": 5e-06,
"loss": 0.3251,
"step": 1870
},
{
"epoch": 1.8155480444229841,
"grad_norm": 1.4657197536244577,
"learning_rate": 5e-06,
"loss": 0.3232,
"step": 1880
},
{
"epoch": 1.8252052148720423,
"grad_norm": 1.5502462503355572,
"learning_rate": 5e-06,
"loss": 0.3241,
"step": 1890
},
{
"epoch": 1.834862385321101,
"grad_norm": 1.4268551559294822,
"learning_rate": 5e-06,
"loss": 0.3233,
"step": 1900
},
{
"epoch": 1.8445195557701592,
"grad_norm": 1.5487349032646411,
"learning_rate": 5e-06,
"loss": 0.3248,
"step": 1910
},
{
"epoch": 1.854176726219218,
"grad_norm": 1.5587365739097951,
"learning_rate": 5e-06,
"loss": 0.3262,
"step": 1920
},
{
"epoch": 1.8638338966682761,
"grad_norm": 1.6410211222118756,
"learning_rate": 5e-06,
"loss": 0.3243,
"step": 1930
},
{
"epoch": 1.8734910671173346,
"grad_norm": 1.4412258241860316,
"learning_rate": 5e-06,
"loss": 0.3242,
"step": 1940
},
{
"epoch": 1.883148237566393,
"grad_norm": 1.408887524672963,
"learning_rate": 5e-06,
"loss": 0.3207,
"step": 1950
},
{
"epoch": 1.8928054080154515,
"grad_norm": 1.709744732252996,
"learning_rate": 5e-06,
"loss": 0.3192,
"step": 1960
},
{
"epoch": 1.90246257846451,
"grad_norm": 1.53624861095146,
"learning_rate": 5e-06,
"loss": 0.3234,
"step": 1970
},
{
"epoch": 1.9121197489135682,
"grad_norm": 1.4790016911744388,
"learning_rate": 5e-06,
"loss": 0.3239,
"step": 1980
},
{
"epoch": 1.9217769193626268,
"grad_norm": 1.4505596932174116,
"learning_rate": 5e-06,
"loss": 0.3226,
"step": 1990
},
{
"epoch": 1.931434089811685,
"grad_norm": 1.3770134690086049,
"learning_rate": 5e-06,
"loss": 0.3253,
"step": 2000
},
{
"epoch": 1.9410912602607437,
"grad_norm": 1.6550530625579105,
"learning_rate": 5e-06,
"loss": 0.3255,
"step": 2010
},
{
"epoch": 1.950748430709802,
"grad_norm": 1.5935808137814957,
"learning_rate": 5e-06,
"loss": 0.3236,
"step": 2020
},
{
"epoch": 1.9604056011588604,
"grad_norm": 1.5070382250631085,
"learning_rate": 5e-06,
"loss": 0.3314,
"step": 2030
},
{
"epoch": 1.9700627716079189,
"grad_norm": 1.3793762943653258,
"learning_rate": 5e-06,
"loss": 0.3231,
"step": 2040
},
{
"epoch": 1.9797199420569773,
"grad_norm": 1.4658674183812177,
"learning_rate": 5e-06,
"loss": 0.3247,
"step": 2050
},
{
"epoch": 1.9893771125060358,
"grad_norm": 1.5804425363669086,
"learning_rate": 5e-06,
"loss": 0.3286,
"step": 2060
},
{
"epoch": 1.999034282955094,
"grad_norm": 1.550360674186604,
"learning_rate": 5e-06,
"loss": 0.3265,
"step": 2070
},
{
"epoch": 2.0,
"eval_loss": 0.4136686325073242,
"eval_runtime": 178.6997,
"eval_samples_per_second": 156.145,
"eval_steps_per_second": 0.61,
"step": 2071
},
{
"epoch": 2.0086914534041527,
"grad_norm": 1.9820970989127087,
"learning_rate": 5e-06,
"loss": 0.2226,
"step": 2080
},
{
"epoch": 2.018348623853211,
"grad_norm": 1.746604108675904,
"learning_rate": 5e-06,
"loss": 0.2022,
"step": 2090
},
{
"epoch": 2.0280057943022696,
"grad_norm": 1.738922693622109,
"learning_rate": 5e-06,
"loss": 0.2034,
"step": 2100
},
{
"epoch": 2.037662964751328,
"grad_norm": 1.842908561465572,
"learning_rate": 5e-06,
"loss": 0.1987,
"step": 2110
},
{
"epoch": 2.0473201352003865,
"grad_norm": 1.555963693945732,
"learning_rate": 5e-06,
"loss": 0.1998,
"step": 2120
},
{
"epoch": 2.0569773056494447,
"grad_norm": 1.6105373644152785,
"learning_rate": 5e-06,
"loss": 0.1977,
"step": 2130
},
{
"epoch": 2.066634476098503,
"grad_norm": 1.7277918775624639,
"learning_rate": 5e-06,
"loss": 0.1997,
"step": 2140
},
{
"epoch": 2.0762916465475616,
"grad_norm": 1.7710659996843952,
"learning_rate": 5e-06,
"loss": 0.2002,
"step": 2150
},
{
"epoch": 2.08594881699662,
"grad_norm": 1.6510171974053387,
"learning_rate": 5e-06,
"loss": 0.2025,
"step": 2160
},
{
"epoch": 2.0956059874456785,
"grad_norm": 1.7020580751172847,
"learning_rate": 5e-06,
"loss": 0.2005,
"step": 2170
},
{
"epoch": 2.1052631578947367,
"grad_norm": 2.0101369980825474,
"learning_rate": 5e-06,
"loss": 0.2076,
"step": 2180
},
{
"epoch": 2.1149203283437954,
"grad_norm": 1.6487612820560622,
"learning_rate": 5e-06,
"loss": 0.2031,
"step": 2190
},
{
"epoch": 2.1245774987928536,
"grad_norm": 1.6667015280913091,
"learning_rate": 5e-06,
"loss": 0.2042,
"step": 2200
},
{
"epoch": 2.1342346692419123,
"grad_norm": 1.6702800446638546,
"learning_rate": 5e-06,
"loss": 0.2016,
"step": 2210
},
{
"epoch": 2.1438918396909705,
"grad_norm": 1.5921726575950466,
"learning_rate": 5e-06,
"loss": 0.2017,
"step": 2220
},
{
"epoch": 2.153549010140029,
"grad_norm": 1.6461690389920633,
"learning_rate": 5e-06,
"loss": 0.2015,
"step": 2230
},
{
"epoch": 2.1632061805890874,
"grad_norm": 1.7782309168905173,
"learning_rate": 5e-06,
"loss": 0.2012,
"step": 2240
},
{
"epoch": 2.1728633510381457,
"grad_norm": 1.768405330134614,
"learning_rate": 5e-06,
"loss": 0.2058,
"step": 2250
},
{
"epoch": 2.1825205214872043,
"grad_norm": 1.8294577091973667,
"learning_rate": 5e-06,
"loss": 0.2039,
"step": 2260
},
{
"epoch": 2.1921776919362626,
"grad_norm": 1.6757794760632077,
"learning_rate": 5e-06,
"loss": 0.206,
"step": 2270
},
{
"epoch": 2.2018348623853212,
"grad_norm": 1.674322596519805,
"learning_rate": 5e-06,
"loss": 0.2073,
"step": 2280
},
{
"epoch": 2.2114920328343795,
"grad_norm": 1.729559352602187,
"learning_rate": 5e-06,
"loss": 0.2082,
"step": 2290
},
{
"epoch": 2.221149203283438,
"grad_norm": 1.7521877519603215,
"learning_rate": 5e-06,
"loss": 0.206,
"step": 2300
},
{
"epoch": 2.2308063737324964,
"grad_norm": 1.6806851822041886,
"learning_rate": 5e-06,
"loss": 0.2022,
"step": 2310
},
{
"epoch": 2.240463544181555,
"grad_norm": 1.7855843714445576,
"learning_rate": 5e-06,
"loss": 0.2092,
"step": 2320
},
{
"epoch": 2.2501207146306133,
"grad_norm": 1.6890806520431167,
"learning_rate": 5e-06,
"loss": 0.2089,
"step": 2330
},
{
"epoch": 2.2597778850796715,
"grad_norm": 1.6876559538674738,
"learning_rate": 5e-06,
"loss": 0.2076,
"step": 2340
},
{
"epoch": 2.26943505552873,
"grad_norm": 1.866952527448764,
"learning_rate": 5e-06,
"loss": 0.2101,
"step": 2350
},
{
"epoch": 2.2790922259777884,
"grad_norm": 1.7778130347386727,
"learning_rate": 5e-06,
"loss": 0.2092,
"step": 2360
},
{
"epoch": 2.288749396426847,
"grad_norm": 1.7573632813881142,
"learning_rate": 5e-06,
"loss": 0.2092,
"step": 2370
},
{
"epoch": 2.2984065668759053,
"grad_norm": 1.670588490011592,
"learning_rate": 5e-06,
"loss": 0.21,
"step": 2380
},
{
"epoch": 2.308063737324964,
"grad_norm": 2.0244107541981857,
"learning_rate": 5e-06,
"loss": 0.2121,
"step": 2390
},
{
"epoch": 2.317720907774022,
"grad_norm": 1.7228769196960538,
"learning_rate": 5e-06,
"loss": 0.2065,
"step": 2400
},
{
"epoch": 2.327378078223081,
"grad_norm": 1.7316110503319007,
"learning_rate": 5e-06,
"loss": 0.2079,
"step": 2410
},
{
"epoch": 2.337035248672139,
"grad_norm": 1.7859669994070049,
"learning_rate": 5e-06,
"loss": 0.2106,
"step": 2420
},
{
"epoch": 2.3466924191211973,
"grad_norm": 1.6790885546872112,
"learning_rate": 5e-06,
"loss": 0.2134,
"step": 2430
},
{
"epoch": 2.356349589570256,
"grad_norm": 1.658832098468064,
"learning_rate": 5e-06,
"loss": 0.209,
"step": 2440
},
{
"epoch": 2.366006760019314,
"grad_norm": 1.737362445041373,
"learning_rate": 5e-06,
"loss": 0.2086,
"step": 2450
},
{
"epoch": 2.375663930468373,
"grad_norm": 1.627103813908181,
"learning_rate": 5e-06,
"loss": 0.214,
"step": 2460
},
{
"epoch": 2.385321100917431,
"grad_norm": 1.7557722068636354,
"learning_rate": 5e-06,
"loss": 0.2119,
"step": 2470
},
{
"epoch": 2.3949782713664898,
"grad_norm": 1.676762758309891,
"learning_rate": 5e-06,
"loss": 0.2143,
"step": 2480
},
{
"epoch": 2.404635441815548,
"grad_norm": 1.8055582761883138,
"learning_rate": 5e-06,
"loss": 0.2138,
"step": 2490
},
{
"epoch": 2.4142926122646067,
"grad_norm": 1.8126267211804017,
"learning_rate": 5e-06,
"loss": 0.213,
"step": 2500
},
{
"epoch": 2.423949782713665,
"grad_norm": 1.737365446135157,
"learning_rate": 5e-06,
"loss": 0.2101,
"step": 2510
},
{
"epoch": 2.433606953162723,
"grad_norm": 1.8601108967097126,
"learning_rate": 5e-06,
"loss": 0.2113,
"step": 2520
},
{
"epoch": 2.443264123611782,
"grad_norm": 1.7975172388473801,
"learning_rate": 5e-06,
"loss": 0.2121,
"step": 2530
},
{
"epoch": 2.45292129406084,
"grad_norm": 1.6548943065520165,
"learning_rate": 5e-06,
"loss": 0.213,
"step": 2540
},
{
"epoch": 2.4625784645098987,
"grad_norm": 1.6142344009099507,
"learning_rate": 5e-06,
"loss": 0.2101,
"step": 2550
},
{
"epoch": 2.472235634958957,
"grad_norm": 1.7136093491402586,
"learning_rate": 5e-06,
"loss": 0.2132,
"step": 2560
},
{
"epoch": 2.4818928054080156,
"grad_norm": 1.6928112777667244,
"learning_rate": 5e-06,
"loss": 0.214,
"step": 2570
},
{
"epoch": 2.491549975857074,
"grad_norm": 1.7487627188812938,
"learning_rate": 5e-06,
"loss": 0.2121,
"step": 2580
},
{
"epoch": 2.5012071463061325,
"grad_norm": 1.7611973606308302,
"learning_rate": 5e-06,
"loss": 0.2146,
"step": 2590
},
{
"epoch": 2.5108643167551907,
"grad_norm": 1.7432835398393358,
"learning_rate": 5e-06,
"loss": 0.2131,
"step": 2600
},
{
"epoch": 2.520521487204249,
"grad_norm": 1.914665414646886,
"learning_rate": 5e-06,
"loss": 0.2135,
"step": 2610
},
{
"epoch": 2.5301786576533076,
"grad_norm": 1.7235392993581606,
"learning_rate": 5e-06,
"loss": 0.2139,
"step": 2620
},
{
"epoch": 2.539835828102366,
"grad_norm": 1.8401761899916762,
"learning_rate": 5e-06,
"loss": 0.216,
"step": 2630
},
{
"epoch": 2.5494929985514245,
"grad_norm": 1.7238390715314391,
"learning_rate": 5e-06,
"loss": 0.2136,
"step": 2640
},
{
"epoch": 2.5591501690004828,
"grad_norm": 1.6967163269012748,
"learning_rate": 5e-06,
"loss": 0.2135,
"step": 2650
},
{
"epoch": 2.5688073394495414,
"grad_norm": 1.6547200950158283,
"learning_rate": 5e-06,
"loss": 0.2154,
"step": 2660
},
{
"epoch": 2.5784645098985997,
"grad_norm": 1.7345144961212824,
"learning_rate": 5e-06,
"loss": 0.2194,
"step": 2670
},
{
"epoch": 2.5881216803476583,
"grad_norm": 1.695025030426855,
"learning_rate": 5e-06,
"loss": 0.2148,
"step": 2680
},
{
"epoch": 2.5977788507967166,
"grad_norm": 1.6586909849777336,
"learning_rate": 5e-06,
"loss": 0.2177,
"step": 2690
},
{
"epoch": 2.607436021245775,
"grad_norm": 1.6450495177327662,
"learning_rate": 5e-06,
"loss": 0.217,
"step": 2700
},
{
"epoch": 2.6170931916948335,
"grad_norm": 1.75951484894314,
"learning_rate": 5e-06,
"loss": 0.2161,
"step": 2710
},
{
"epoch": 2.6267503621438917,
"grad_norm": 1.6771766744486507,
"learning_rate": 5e-06,
"loss": 0.216,
"step": 2720
},
{
"epoch": 2.6364075325929504,
"grad_norm": 1.6522749567618924,
"learning_rate": 5e-06,
"loss": 0.2164,
"step": 2730
},
{
"epoch": 2.6460647030420086,
"grad_norm": 1.6904676125685896,
"learning_rate": 5e-06,
"loss": 0.2183,
"step": 2740
},
{
"epoch": 2.6557218734910673,
"grad_norm": 1.9074890209165016,
"learning_rate": 5e-06,
"loss": 0.2185,
"step": 2750
},
{
"epoch": 2.6653790439401255,
"grad_norm": 1.7817515462190572,
"learning_rate": 5e-06,
"loss": 0.2166,
"step": 2760
},
{
"epoch": 2.675036214389184,
"grad_norm": 1.7562563485880531,
"learning_rate": 5e-06,
"loss": 0.2184,
"step": 2770
},
{
"epoch": 2.6846933848382424,
"grad_norm": 1.998249733627222,
"learning_rate": 5e-06,
"loss": 0.2207,
"step": 2780
},
{
"epoch": 2.6943505552873006,
"grad_norm": 1.7695683095416619,
"learning_rate": 5e-06,
"loss": 0.2154,
"step": 2790
},
{
"epoch": 2.7040077257363593,
"grad_norm": 1.8078600319718185,
"learning_rate": 5e-06,
"loss": 0.2194,
"step": 2800
},
{
"epoch": 2.7136648961854175,
"grad_norm": 1.8027624003524778,
"learning_rate": 5e-06,
"loss": 0.216,
"step": 2810
},
{
"epoch": 2.723322066634476,
"grad_norm": 1.6742700740217098,
"learning_rate": 5e-06,
"loss": 0.2208,
"step": 2820
},
{
"epoch": 2.7329792370835344,
"grad_norm": 1.773334112408393,
"learning_rate": 5e-06,
"loss": 0.2188,
"step": 2830
},
{
"epoch": 2.742636407532593,
"grad_norm": 1.6731213070854867,
"learning_rate": 5e-06,
"loss": 0.222,
"step": 2840
},
{
"epoch": 2.7522935779816513,
"grad_norm": 1.7120912589030635,
"learning_rate": 5e-06,
"loss": 0.2174,
"step": 2850
},
{
"epoch": 2.76195074843071,
"grad_norm": 1.7123222485174125,
"learning_rate": 5e-06,
"loss": 0.2177,
"step": 2860
},
{
"epoch": 2.771607918879768,
"grad_norm": 1.6545568282400362,
"learning_rate": 5e-06,
"loss": 0.2176,
"step": 2870
},
{
"epoch": 2.7812650893288264,
"grad_norm": 2.0273088669056385,
"learning_rate": 5e-06,
"loss": 0.2177,
"step": 2880
},
{
"epoch": 2.790922259777885,
"grad_norm": 1.6066656179070626,
"learning_rate": 5e-06,
"loss": 0.219,
"step": 2890
},
{
"epoch": 2.8005794302269438,
"grad_norm": 1.8053174623133685,
"learning_rate": 5e-06,
"loss": 0.2176,
"step": 2900
},
{
"epoch": 2.810236600676002,
"grad_norm": 1.70700256545585,
"learning_rate": 5e-06,
"loss": 0.2196,
"step": 2910
},
{
"epoch": 2.8198937711250602,
"grad_norm": 1.8175496500932709,
"learning_rate": 5e-06,
"loss": 0.2207,
"step": 2920
},
{
"epoch": 2.829550941574119,
"grad_norm": 1.7332734928998839,
"learning_rate": 5e-06,
"loss": 0.2192,
"step": 2930
},
{
"epoch": 2.839208112023177,
"grad_norm": 1.6737893973481872,
"learning_rate": 5e-06,
"loss": 0.2198,
"step": 2940
},
{
"epoch": 2.848865282472236,
"grad_norm": 1.861536272319189,
"learning_rate": 5e-06,
"loss": 0.2211,
"step": 2950
},
{
"epoch": 2.858522452921294,
"grad_norm": 1.7745633627018984,
"learning_rate": 5e-06,
"loss": 0.2242,
"step": 2960
},
{
"epoch": 2.8681796233703523,
"grad_norm": 1.7269651603359077,
"learning_rate": 5e-06,
"loss": 0.221,
"step": 2970
},
{
"epoch": 2.877836793819411,
"grad_norm": 1.8445740625163256,
"learning_rate": 5e-06,
"loss": 0.2205,
"step": 2980
},
{
"epoch": 2.8874939642684696,
"grad_norm": 1.7256657735965188,
"learning_rate": 5e-06,
"loss": 0.2187,
"step": 2990
},
{
"epoch": 2.897151134717528,
"grad_norm": 1.7947034947358826,
"learning_rate": 5e-06,
"loss": 0.2217,
"step": 3000
},
{
"epoch": 2.906808305166586,
"grad_norm": 1.7396418325368443,
"learning_rate": 5e-06,
"loss": 0.2183,
"step": 3010
},
{
"epoch": 2.9164654756156447,
"grad_norm": 1.6566041516835608,
"learning_rate": 5e-06,
"loss": 0.224,
"step": 3020
},
{
"epoch": 2.926122646064703,
"grad_norm": 1.7285392977136116,
"learning_rate": 5e-06,
"loss": 0.2209,
"step": 3030
},
{
"epoch": 2.9357798165137616,
"grad_norm": 1.6972125749702298,
"learning_rate": 5e-06,
"loss": 0.2222,
"step": 3040
},
{
"epoch": 2.94543698696282,
"grad_norm": 1.7429187695624144,
"learning_rate": 5e-06,
"loss": 0.2197,
"step": 3050
},
{
"epoch": 2.955094157411878,
"grad_norm": 1.7068313963220236,
"learning_rate": 5e-06,
"loss": 0.2219,
"step": 3060
},
{
"epoch": 2.9647513278609368,
"grad_norm": 1.6955378543746138,
"learning_rate": 5e-06,
"loss": 0.2212,
"step": 3070
},
{
"epoch": 2.9744084983099954,
"grad_norm": 1.685143060439258,
"learning_rate": 5e-06,
"loss": 0.2233,
"step": 3080
},
{
"epoch": 2.9840656687590537,
"grad_norm": 1.7308667414857535,
"learning_rate": 5e-06,
"loss": 0.2226,
"step": 3090
},
{
"epoch": 2.993722839208112,
"grad_norm": 1.7145293308716394,
"learning_rate": 5e-06,
"loss": 0.2217,
"step": 3100
},
{
"epoch": 2.998551424432641,
"eval_loss": 0.44667962193489075,
"eval_runtime": 176.8031,
"eval_samples_per_second": 157.82,
"eval_steps_per_second": 0.617,
"step": 3105
},
{
"epoch": 2.998551424432641,
"step": 3105,
"total_flos": 5200153128468480.0,
"train_loss": 0.3276555372321087,
"train_runtime": 26364.0416,
"train_samples_per_second": 60.326,
"train_steps_per_second": 0.118
}
],
"logging_steps": 10,
"max_steps": 3105,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 5200153128468480.0,
"train_batch_size": 8,
"trial_name": null,
"trial_params": null
}