gsm8k_5k_sft / trainer_state.json
modrill's picture
Add files using upload-large-folder tool
107b537 verified
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 3.0,
"eval_steps": 200,
"global_step": 1782,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.016842105263157894,
"grad_norm": 2.3675968647003174,
"learning_rate": 5.000000000000001e-07,
"loss": 2.3691780090332033,
"step": 10
},
{
"epoch": 0.03368421052631579,
"grad_norm": 2.2398316860198975,
"learning_rate": 1.0555555555555557e-06,
"loss": 2.442026901245117,
"step": 20
},
{
"epoch": 0.05052631578947368,
"grad_norm": 2.4165735244750977,
"learning_rate": 1.6111111111111113e-06,
"loss": 2.4075597763061523,
"step": 30
},
{
"epoch": 0.06736842105263158,
"grad_norm": 2.081270694732666,
"learning_rate": 2.166666666666667e-06,
"loss": 2.509693717956543,
"step": 40
},
{
"epoch": 0.08421052631578947,
"grad_norm": 2.0487782955169678,
"learning_rate": 2.7222222222222224e-06,
"loss": 2.265007209777832,
"step": 50
},
{
"epoch": 0.10105263157894737,
"grad_norm": 2.2293291091918945,
"learning_rate": 3.277777777777778e-06,
"loss": 2.235431671142578,
"step": 60
},
{
"epoch": 0.11789473684210526,
"grad_norm": 1.609149694442749,
"learning_rate": 3.833333333333334e-06,
"loss": 1.9537654876708985,
"step": 70
},
{
"epoch": 0.13473684210526315,
"grad_norm": 1.5908480882644653,
"learning_rate": 4.388888888888889e-06,
"loss": 1.80606689453125,
"step": 80
},
{
"epoch": 0.15157894736842106,
"grad_norm": 1.250032663345337,
"learning_rate": 4.944444444444445e-06,
"loss": 1.5460500717163086,
"step": 90
},
{
"epoch": 0.16842105263157894,
"grad_norm": 0.7745718955993652,
"learning_rate": 4.999650952964643e-06,
"loss": 1.3418588638305664,
"step": 100
},
{
"epoch": 0.18526315789473685,
"grad_norm": 0.786589503288269,
"learning_rate": 4.998444495752662e-06,
"loss": 1.197255802154541,
"step": 110
},
{
"epoch": 0.20210526315789473,
"grad_norm": 0.5270315408706665,
"learning_rate": 4.9963767349515075e-06,
"loss": 1.0972392082214355,
"step": 120
},
{
"epoch": 0.21894736842105264,
"grad_norm": 0.5498689413070679,
"learning_rate": 4.993448383392625e-06,
"loss": 1.0014358520507813,
"step": 130
},
{
"epoch": 0.23578947368421052,
"grad_norm": 0.583773672580719,
"learning_rate": 4.989660450584015e-06,
"loss": 0.9596162796020508,
"step": 140
},
{
"epoch": 0.25263157894736843,
"grad_norm": 0.5195373296737671,
"learning_rate": 4.985014242362221e-06,
"loss": 0.941214656829834,
"step": 150
},
{
"epoch": 0.2694736842105263,
"grad_norm": 0.5280083417892456,
"learning_rate": 4.9795113604421606e-06,
"loss": 0.8085845947265625,
"step": 160
},
{
"epoch": 0.2863157894736842,
"grad_norm": 0.45546460151672363,
"learning_rate": 4.973153701864953e-06,
"loss": 0.8009994506835938,
"step": 170
},
{
"epoch": 0.3031578947368421,
"grad_norm": 0.46576207876205444,
"learning_rate": 4.965943458343949e-06,
"loss": 0.7760515213012695,
"step": 180
},
{
"epoch": 0.32,
"grad_norm": 0.45923057198524475,
"learning_rate": 4.9578831155091585e-06,
"loss": 0.7632324695587158,
"step": 190
},
{
"epoch": 0.3368421052631579,
"grad_norm": 0.4534441828727722,
"learning_rate": 4.9489754520503754e-06,
"loss": 0.7539843082427978,
"step": 200
},
{
"epoch": 0.35368421052631577,
"grad_norm": 0.4716040790081024,
"learning_rate": 4.939223538759253e-06,
"loss": 0.6971303939819335,
"step": 210
},
{
"epoch": 0.3705263157894737,
"grad_norm": 0.4764370620250702,
"learning_rate": 4.9286307374706985e-06,
"loss": 0.7053776264190674,
"step": 220
},
{
"epoch": 0.3873684210526316,
"grad_norm": 0.48134034872055054,
"learning_rate": 4.917200699903926e-06,
"loss": 0.7123528957366944,
"step": 230
},
{
"epoch": 0.40421052631578946,
"grad_norm": 0.45863306522369385,
"learning_rate": 4.904937366403576e-06,
"loss": 0.6910786628723145,
"step": 240
},
{
"epoch": 0.42105263157894735,
"grad_norm": 0.46483689546585083,
"learning_rate": 4.891844964581339e-06,
"loss": 0.6985108852386475,
"step": 250
},
{
"epoch": 0.4378947368421053,
"grad_norm": 0.5262766480445862,
"learning_rate": 4.8779280078585475e-06,
"loss": 0.6655729293823243,
"step": 260
},
{
"epoch": 0.45473684210526316,
"grad_norm": 0.42967167496681213,
"learning_rate": 4.8631912939102326e-06,
"loss": 0.7196405410766602,
"step": 270
},
{
"epoch": 0.47157894736842104,
"grad_norm": 0.4787631630897522,
"learning_rate": 4.847639903011196e-06,
"loss": 0.6648534297943115,
"step": 280
},
{
"epoch": 0.4884210526315789,
"grad_norm": 0.5099977850914001,
"learning_rate": 4.831279196284656e-06,
"loss": 0.575913381576538,
"step": 290
},
{
"epoch": 0.5052631578947369,
"grad_norm": 0.46509549021720886,
"learning_rate": 4.814114813854078e-06,
"loss": 0.6416436195373535,
"step": 300
},
{
"epoch": 0.5221052631578947,
"grad_norm": 0.432441771030426,
"learning_rate": 4.796152672898818e-06,
"loss": 0.6302789211273193,
"step": 310
},
{
"epoch": 0.5389473684210526,
"grad_norm": 0.4251745939254761,
"learning_rate": 4.777398965614261e-06,
"loss": 0.6588118076324463,
"step": 320
},
{
"epoch": 0.5557894736842105,
"grad_norm": 0.4384589195251465,
"learning_rate": 4.757860157077147e-06,
"loss": 0.6521795272827149,
"step": 330
},
{
"epoch": 0.5726315789473684,
"grad_norm": 0.4723098576068878,
"learning_rate": 4.737542983016824e-06,
"loss": 0.6493458271026611,
"step": 340
},
{
"epoch": 0.5894736842105263,
"grad_norm": 0.42850667238235474,
"learning_rate": 4.716454447493209e-06,
"loss": 0.6356882095336914,
"step": 350
},
{
"epoch": 0.6063157894736843,
"grad_norm": 0.3517947196960449,
"learning_rate": 4.694601820482225e-06,
"loss": 0.6760905265808106,
"step": 360
},
{
"epoch": 0.6231578947368421,
"grad_norm": 0.5018452405929565,
"learning_rate": 4.671992635369592e-06,
"loss": 0.6354838371276855,
"step": 370
},
{
"epoch": 0.64,
"grad_norm": 0.4580940902233124,
"learning_rate": 4.648634686353784e-06,
"loss": 0.6125568866729736,
"step": 380
},
{
"epoch": 0.6568421052631579,
"grad_norm": 0.48389866948127747,
"learning_rate": 4.624536025759103e-06,
"loss": 0.6288070678710938,
"step": 390
},
{
"epoch": 0.6736842105263158,
"grad_norm": 0.5069875717163086,
"learning_rate": 4.599704961259743e-06,
"loss": 0.6024885177612305,
"step": 400
},
{
"epoch": 0.6905263157894737,
"grad_norm": 0.41696321964263916,
"learning_rate": 4.574150053015841e-06,
"loss": 0.5551046848297119,
"step": 410
},
{
"epoch": 0.7073684210526315,
"grad_norm": 0.4543442726135254,
"learning_rate": 4.54788011072248e-06,
"loss": 0.6317256927490235,
"step": 420
},
{
"epoch": 0.7242105263157895,
"grad_norm": 0.5469536781311035,
"learning_rate": 4.5209041905726726e-06,
"loss": 0.6079788208007812,
"step": 430
},
{
"epoch": 0.7410526315789474,
"grad_norm": 0.521289050579071,
"learning_rate": 4.493231592135365e-06,
"loss": 0.6110894203186035,
"step": 440
},
{
"epoch": 0.7578947368421053,
"grad_norm": 0.4019668698310852,
"learning_rate": 4.4648718551495414e-06,
"loss": 0.6034395217895507,
"step": 450
},
{
"epoch": 0.7747368421052632,
"grad_norm": 0.41849735379219055,
"learning_rate": 4.435834756235534e-06,
"loss": 0.584140682220459,
"step": 460
},
{
"epoch": 0.791578947368421,
"grad_norm": 0.40643349289894104,
"learning_rate": 4.406130305524668e-06,
"loss": 0.5806079864501953,
"step": 470
},
{
"epoch": 0.8084210526315789,
"grad_norm": 0.3704324960708618,
"learning_rate": 4.375768743208413e-06,
"loss": 0.5913614749908447,
"step": 480
},
{
"epoch": 0.8252631578947368,
"grad_norm": 0.5236285328865051,
"learning_rate": 4.344760536008218e-06,
"loss": 0.6399223327636718,
"step": 490
},
{
"epoch": 0.8421052631578947,
"grad_norm": 0.464455783367157,
"learning_rate": 4.313116373567262e-06,
"loss": 0.593417739868164,
"step": 500
},
{
"epoch": 0.8589473684210527,
"grad_norm": 0.42120617628097534,
"learning_rate": 4.28084716476534e-06,
"loss": 0.6142099857330322,
"step": 510
},
{
"epoch": 0.8757894736842106,
"grad_norm": 0.5095754861831665,
"learning_rate": 4.247964033958192e-06,
"loss": 0.5817235469818115,
"step": 520
},
{
"epoch": 0.8926315789473684,
"grad_norm": 0.4550492465496063,
"learning_rate": 4.214478317142529e-06,
"loss": 0.5919324874877929,
"step": 530
},
{
"epoch": 0.9094736842105263,
"grad_norm": 0.4662947654724121,
"learning_rate": 4.1804015580481095e-06,
"loss": 0.5827170848846436,
"step": 540
},
{
"epoch": 0.9263157894736842,
"grad_norm": 0.5098485350608826,
"learning_rate": 4.1457455041582044e-06,
"loss": 0.6532581806182861,
"step": 550
},
{
"epoch": 0.9431578947368421,
"grad_norm": 0.4516877233982086,
"learning_rate": 4.110522102659816e-06,
"loss": 0.5680957317352295,
"step": 560
},
{
"epoch": 0.96,
"grad_norm": 0.48152726888656616,
"learning_rate": 4.074743496325048e-06,
"loss": 0.5398642539978027,
"step": 570
},
{
"epoch": 0.9768421052631578,
"grad_norm": 0.45088857412338257,
"learning_rate": 4.038422019325066e-06,
"loss": 0.567262077331543,
"step": 580
},
{
"epoch": 0.9936842105263158,
"grad_norm": 0.44439584016799927,
"learning_rate": 4.001570192978057e-06,
"loss": 0.5635426998138428,
"step": 590
},
{
"epoch": 1.0101052631578948,
"grad_norm": 0.44740575551986694,
"learning_rate": 3.964200721432683e-06,
"loss": 0.5941667079925537,
"step": 600
},
{
"epoch": 1.0269473684210526,
"grad_norm": 0.44090500473976135,
"learning_rate": 3.926326487288506e-06,
"loss": 0.5816664695739746,
"step": 610
},
{
"epoch": 1.0437894736842106,
"grad_norm": 0.41892901062965393,
"learning_rate": 3.887960547154894e-06,
"loss": 0.5755373954772949,
"step": 620
},
{
"epoch": 1.0606315789473684,
"grad_norm": 0.46069079637527466,
"learning_rate": 3.849116127149936e-06,
"loss": 0.5655642032623291,
"step": 630
},
{
"epoch": 1.0774736842105264,
"grad_norm": 0.5407482385635376,
"learning_rate": 3.8098066183409223e-06,
"loss": 0.5383800983428955,
"step": 640
},
{
"epoch": 1.0943157894736841,
"grad_norm": 0.4630482494831085,
"learning_rate": 3.7700455721279694e-06,
"loss": 0.5431939125061035,
"step": 650
},
{
"epoch": 1.1111578947368421,
"grad_norm": 0.43207013607025146,
"learning_rate": 3.7298466955723587e-06,
"loss": 0.6164653778076172,
"step": 660
},
{
"epoch": 1.1280000000000001,
"grad_norm": 0.44431108236312866,
"learning_rate": 3.6892238466712233e-06,
"loss": 0.5817042350769043,
"step": 670
},
{
"epoch": 1.1448421052631579,
"grad_norm": 0.4709595739841461,
"learning_rate": 3.6481910295801964e-06,
"loss": 0.5780113220214844,
"step": 680
},
{
"epoch": 1.1616842105263159,
"grad_norm": 0.3738909363746643,
"learning_rate": 3.606762389785677e-06,
"loss": 0.5264674663543701,
"step": 690
},
{
"epoch": 1.1785263157894736,
"grad_norm": 0.353249728679657,
"learning_rate": 3.5649522092283727e-06,
"loss": 0.5763276576995849,
"step": 700
},
{
"epoch": 1.1953684210526316,
"grad_norm": 0.43097689747810364,
"learning_rate": 3.522774901379803e-06,
"loss": 0.5881312847137451,
"step": 710
},
{
"epoch": 1.2122105263157894,
"grad_norm": 0.34989133477211,
"learning_rate": 3.4802450062734516e-06,
"loss": 0.5387351989746094,
"step": 720
},
{
"epoch": 1.2290526315789474,
"grad_norm": 0.4101610779762268,
"learning_rate": 3.4373771854923032e-06,
"loss": 0.5462720394134521,
"step": 730
},
{
"epoch": 1.2458947368421052,
"grad_norm": 0.4284352958202362,
"learning_rate": 3.394186217114461e-06,
"loss": 0.5075682640075684,
"step": 740
},
{
"epoch": 1.2627368421052632,
"grad_norm": 0.46738967299461365,
"learning_rate": 3.350686990618619e-06,
"loss": 0.56449875831604,
"step": 750
},
{
"epoch": 1.279578947368421,
"grad_norm": 0.3971182107925415,
"learning_rate": 3.306894501751118e-06,
"loss": 0.5791185379028321,
"step": 760
},
{
"epoch": 1.296421052631579,
"grad_norm": 0.4265970289707184,
"learning_rate": 3.262823847356376e-06,
"loss": 0.5642617225646973,
"step": 770
},
{
"epoch": 1.313263157894737,
"grad_norm": 0.4123178720474243,
"learning_rate": 3.218490220172464e-06,
"loss": 0.58898024559021,
"step": 780
},
{
"epoch": 1.3301052631578947,
"grad_norm": 0.4736369848251343,
"learning_rate": 3.173908903593621e-06,
"loss": 0.5553134441375732,
"step": 790
},
{
"epoch": 1.3469473684210527,
"grad_norm": 0.6982717514038086,
"learning_rate": 3.1290952664015226e-06,
"loss": 0.5672073841094971,
"step": 800
},
{
"epoch": 1.3637894736842107,
"grad_norm": 0.5104728937149048,
"learning_rate": 3.0840647574671046e-06,
"loss": 0.5513389110565186,
"step": 810
},
{
"epoch": 1.3806315789473684,
"grad_norm": 0.43303966522216797,
"learning_rate": 3.038832900424784e-06,
"loss": 0.5767755031585693,
"step": 820
},
{
"epoch": 1.3974736842105262,
"grad_norm": 0.3601587414741516,
"learning_rate": 2.99341528832091e-06,
"loss": 0.5640051364898682,
"step": 830
},
{
"epoch": 1.4143157894736842,
"grad_norm": 0.4812554121017456,
"learning_rate": 2.9478275782382698e-06,
"loss": 0.5934456825256348,
"step": 840
},
{
"epoch": 1.4311578947368422,
"grad_norm": 0.41394785046577454,
"learning_rate": 2.9020854858985405e-06,
"loss": 0.5351485252380371,
"step": 850
},
{
"epoch": 1.448,
"grad_norm": 0.488293319940567,
"learning_rate": 2.856204780244508e-06,
"loss": 0.5578882217407226,
"step": 860
},
{
"epoch": 1.464842105263158,
"grad_norm": 0.43654918670654297,
"learning_rate": 2.810201278003949e-06,
"loss": 0.5997494697570801,
"step": 870
},
{
"epoch": 1.4816842105263157,
"grad_norm": 0.47475796937942505,
"learning_rate": 2.7640908382370353e-06,
"loss": 0.6016314506530762,
"step": 880
},
{
"epoch": 1.4985263157894737,
"grad_norm": 0.4382602870464325,
"learning_rate": 2.717889356869146e-06,
"loss": 0.5398138046264649,
"step": 890
},
{
"epoch": 1.5153684210526315,
"grad_norm": 0.5595154762268066,
"learning_rate": 2.671612761210972e-06,
"loss": 0.5806910037994385,
"step": 900
},
{
"epoch": 1.5322105263157895,
"grad_norm": 0.43729111552238464,
"learning_rate": 2.625277004467798e-06,
"loss": 0.5106444358825684,
"step": 910
},
{
"epoch": 1.5490526315789475,
"grad_norm": 0.493868887424469,
"learning_rate": 2.578898060239864e-06,
"loss": 0.5604496479034424,
"step": 920
},
{
"epoch": 1.5658947368421052,
"grad_norm": 0.5986487865447998,
"learning_rate": 2.5324919170156812e-06,
"loss": 0.6156312465667725,
"step": 930
},
{
"epoch": 1.582736842105263,
"grad_norm": 0.532580554485321,
"learning_rate": 2.4860745726602388e-06,
"loss": 0.6126661777496338,
"step": 940
},
{
"epoch": 1.5995789473684212,
"grad_norm": 0.45284345746040344,
"learning_rate": 2.4396620288999535e-06,
"loss": 0.5442125797271729,
"step": 950
},
{
"epoch": 1.616421052631579,
"grad_norm": 0.471273809671402,
"learning_rate": 2.3932702858063077e-06,
"loss": 0.5386880874633789,
"step": 960
},
{
"epoch": 1.6332631578947368,
"grad_norm": 0.4507131576538086,
"learning_rate": 2.3469153362800444e-06,
"loss": 0.5528570175170898,
"step": 970
},
{
"epoch": 1.6501052631578947,
"grad_norm": 0.3987991213798523,
"learning_rate": 2.300613160537842e-06,
"loss": 0.5685427188873291,
"step": 980
},
{
"epoch": 1.6669473684210527,
"grad_norm": 0.3747977316379547,
"learning_rate": 2.2543797206033624e-06,
"loss": 0.5286425113677978,
"step": 990
},
{
"epoch": 1.6837894736842105,
"grad_norm": 0.4136403203010559,
"learning_rate": 2.2082309548045595e-06,
"loss": 0.5814678192138671,
"step": 1000
},
{
"epoch": 1.7006315789473683,
"grad_norm": 0.687925398349762,
"learning_rate": 2.1621827722791766e-06,
"loss": 0.5451530933380127,
"step": 1010
},
{
"epoch": 1.7174736842105263,
"grad_norm": 0.45145687460899353,
"learning_rate": 2.1162510474902817e-06,
"loss": 0.5333961963653564,
"step": 1020
},
{
"epoch": 1.7343157894736843,
"grad_norm": 0.42507562041282654,
"learning_rate": 2.070451614753783e-06,
"loss": 0.5521537780761718,
"step": 1030
},
{
"epoch": 1.751157894736842,
"grad_norm": 0.4860495626926422,
"learning_rate": 2.0248002627797603e-06,
"loss": 0.5086616992950439,
"step": 1040
},
{
"epoch": 1.768,
"grad_norm": 0.37300288677215576,
"learning_rate": 1.9793127292295355e-06,
"loss": 0.5284741401672364,
"step": 1050
},
{
"epoch": 1.784842105263158,
"grad_norm": 0.6154864430427551,
"learning_rate": 1.9340046952903347e-06,
"loss": 0.5843222141265869,
"step": 1060
},
{
"epoch": 1.8016842105263158,
"grad_norm": 0.40758585929870605,
"learning_rate": 1.8888917802694163e-06,
"loss": 0.5341190814971923,
"step": 1070
},
{
"epoch": 1.8185263157894735,
"grad_norm": 0.6138201951980591,
"learning_rate": 1.8439895362095392e-06,
"loss": 0.5368884563446045,
"step": 1080
},
{
"epoch": 1.8353684210526315,
"grad_norm": 0.4472939968109131,
"learning_rate": 1.7993134425276095e-06,
"loss": 0.5785743236541748,
"step": 1090
},
{
"epoch": 1.8522105263157895,
"grad_norm": 0.5062076449394226,
"learning_rate": 1.7548789006783767e-06,
"loss": 0.5302117347717286,
"step": 1100
},
{
"epoch": 1.8690526315789473,
"grad_norm": 0.4329136610031128,
"learning_rate": 1.7107012288449893e-06,
"loss": 0.5525520324707032,
"step": 1110
},
{
"epoch": 1.8858947368421053,
"grad_norm": 0.48740825057029724,
"learning_rate": 1.6667956566582733e-06,
"loss": 0.5427632331848145,
"step": 1120
},
{
"epoch": 1.9027368421052633,
"grad_norm": 0.4774317741394043,
"learning_rate": 1.6231773199465328e-06,
"loss": 0.5031283855438232,
"step": 1130
},
{
"epoch": 1.919578947368421,
"grad_norm": 0.5567426085472107,
"learning_rate": 1.579861255517679e-06,
"loss": 0.5639900207519531,
"step": 1140
},
{
"epoch": 1.9364210526315788,
"grad_norm": 0.418606698513031,
"learning_rate": 1.5368623959755091e-06,
"loss": 0.5398945331573486,
"step": 1150
},
{
"epoch": 1.9532631578947368,
"grad_norm": 0.41494137048721313,
"learning_rate": 1.494195564571896e-06,
"loss": 0.5497087001800537,
"step": 1160
},
{
"epoch": 1.9701052631578948,
"grad_norm": 0.43794137239456177,
"learning_rate": 1.4518754700966852e-06,
"loss": 0.5589231967926025,
"step": 1170
},
{
"epoch": 1.9869473684210526,
"grad_norm": 0.4637230634689331,
"learning_rate": 1.4099167018070436e-06,
"loss": 0.5796440601348877,
"step": 1180
},
{
"epoch": 2.0033684210526315,
"grad_norm": 0.4874701499938965,
"learning_rate": 1.368333724398018e-06,
"loss": 0.5948200225830078,
"step": 1190
},
{
"epoch": 2.0202105263157897,
"grad_norm": 0.4159238934516907,
"learning_rate": 1.3271408730160387e-06,
"loss": 0.5691422462463379,
"step": 1200
},
{
"epoch": 2.0370526315789474,
"grad_norm": 0.5367531180381775,
"learning_rate": 1.2863523483170747e-06,
"loss": 0.49358205795288085,
"step": 1210
},
{
"epoch": 2.053894736842105,
"grad_norm": 0.3846629858016968,
"learning_rate": 1.2459822115711604e-06,
"loss": 0.5058943748474121,
"step": 1220
},
{
"epoch": 2.070736842105263,
"grad_norm": 0.5145422220230103,
"learning_rate": 1.206044379814969e-06,
"loss": 0.5441148757934571,
"step": 1230
},
{
"epoch": 2.087578947368421,
"grad_norm": 0.48207297921180725,
"learning_rate": 1.166552621054111e-06,
"loss": 0.5424808025360107,
"step": 1240
},
{
"epoch": 2.104421052631579,
"grad_norm": 0.5606981515884399,
"learning_rate": 1.1275205495168088e-06,
"loss": 0.5733020305633545,
"step": 1250
},
{
"epoch": 2.1212631578947367,
"grad_norm": 0.6228098273277283,
"learning_rate": 1.0889616209605792e-06,
"loss": 0.5328383922576905,
"step": 1260
},
{
"epoch": 2.138105263157895,
"grad_norm": 0.4159585237503052,
"learning_rate": 1.0508891280335562e-06,
"loss": 0.5331964015960693,
"step": 1270
},
{
"epoch": 2.1549473684210527,
"grad_norm": 0.461050808429718,
"learning_rate": 1.0133161956920324e-06,
"loss": 0.5633898735046386,
"step": 1280
},
{
"epoch": 2.1717894736842105,
"grad_norm": 0.45412588119506836,
"learning_rate": 9.762557766758162e-07,
"loss": 0.5189047813415527,
"step": 1290
},
{
"epoch": 2.1886315789473683,
"grad_norm": 0.47112417221069336,
"learning_rate": 9.397206470429593e-07,
"loss": 0.5841322422027588,
"step": 1300
},
{
"epoch": 2.2054736842105265,
"grad_norm": 0.5289595127105713,
"learning_rate": 9.037234017653868e-07,
"loss": 0.5423564910888672,
"step": 1310
},
{
"epoch": 2.2223157894736842,
"grad_norm": 0.5475178956985474,
"learning_rate": 8.682764503869628e-07,
"loss": 0.5551994323730469,
"step": 1320
},
{
"epoch": 2.239157894736842,
"grad_norm": 0.38113123178482056,
"learning_rate": 8.333920127454697e-07,
"loss": 0.5250718116760253,
"step": 1330
},
{
"epoch": 2.2560000000000002,
"grad_norm": 0.49941059947013855,
"learning_rate": 7.990821147599933e-07,
"loss": 0.5366021633148194,
"step": 1340
},
{
"epoch": 2.272842105263158,
"grad_norm": 0.6488338112831116,
"learning_rate": 7.653585842851555e-07,
"loss": 0.5126526832580567,
"step": 1350
},
{
"epoch": 2.2896842105263158,
"grad_norm": 0.442120224237442,
"learning_rate": 7.322330470336314e-07,
"loss": 0.5691324234008789,
"step": 1360
},
{
"epoch": 2.3065263157894735,
"grad_norm": 0.41539308428764343,
"learning_rate": 6.997169225683428e-07,
"loss": 0.5692724704742431,
"step": 1370
},
{
"epoch": 2.3233684210526317,
"grad_norm": 0.487481027841568,
"learning_rate": 6.678214203657271e-07,
"loss": 0.49768476486206054,
"step": 1380
},
{
"epoch": 2.3402105263157895,
"grad_norm": 0.4554758071899414,
"learning_rate": 6.365575359514311e-07,
"loss": 0.5807519435882569,
"step": 1390
},
{
"epoch": 2.3570526315789473,
"grad_norm": 0.43024933338165283,
"learning_rate": 6.059360471097528e-07,
"loss": 0.5478704452514649,
"step": 1400
},
{
"epoch": 2.3738947368421055,
"grad_norm": 0.4391016960144043,
"learning_rate": 5.759675101681547e-07,
"loss": 0.5237262725830079,
"step": 1410
},
{
"epoch": 2.3907368421052633,
"grad_norm": 0.48355668783187866,
"learning_rate": 5.466622563581186e-07,
"loss": 0.5412522792816162,
"step": 1420
},
{
"epoch": 2.407578947368421,
"grad_norm": 0.4674224853515625,
"learning_rate": 5.180303882535992e-07,
"loss": 0.5138509273529053,
"step": 1430
},
{
"epoch": 2.424421052631579,
"grad_norm": 0.49533811211586,
"learning_rate": 4.90081776288302e-07,
"loss": 0.5057380676269532,
"step": 1440
},
{
"epoch": 2.441263157894737,
"grad_norm": 0.3906404376029968,
"learning_rate": 4.628260553529917e-07,
"loss": 0.5184959888458252,
"step": 1450
},
{
"epoch": 2.458105263157895,
"grad_norm": 0.49051445722579956,
"learning_rate": 4.362726214739985e-07,
"loss": 0.5473256587982178,
"step": 1460
},
{
"epoch": 2.4749473684210526,
"grad_norm": 0.5990830659866333,
"learning_rate": 4.104306285740703e-07,
"loss": 0.54063720703125,
"step": 1470
},
{
"epoch": 2.4917894736842103,
"grad_norm": 0.5474934577941895,
"learning_rate": 3.8530898531668775e-07,
"loss": 0.5649588584899903,
"step": 1480
},
{
"epoch": 2.5086315789473685,
"grad_norm": 0.47150352597236633,
"learning_rate": 3.609163520349254e-07,
"loss": 0.617987585067749,
"step": 1490
},
{
"epoch": 2.5254736842105263,
"grad_norm": 0.43933191895484924,
"learning_rate": 3.3726113774592727e-07,
"loss": 0.5586119651794433,
"step": 1500
},
{
"epoch": 2.542315789473684,
"grad_norm": 0.41653919219970703,
"learning_rate": 3.1435149725201256e-07,
"loss": 0.5318275451660156,
"step": 1510
},
{
"epoch": 2.559157894736842,
"grad_norm": 0.4257458448410034,
"learning_rate": 2.921953283294243e-07,
"loss": 0.5267440795898437,
"step": 1520
},
{
"epoch": 2.576,
"grad_norm": 0.5163229703903198,
"learning_rate": 2.708002690056824e-07,
"loss": 0.5639180183410645,
"step": 1530
},
{
"epoch": 2.592842105263158,
"grad_norm": 0.32207292318344116,
"learning_rate": 2.501736949264805e-07,
"loss": 0.5227752208709717,
"step": 1540
},
{
"epoch": 2.609684210526316,
"grad_norm": 0.49159786105155945,
"learning_rate": 2.3032271681303674e-07,
"loss": 0.508394718170166,
"step": 1550
},
{
"epoch": 2.626526315789474,
"grad_norm": 0.5257501602172852,
"learning_rate": 2.1125417801077103e-07,
"loss": 0.5707829475402832,
"step": 1560
},
{
"epoch": 2.6433684210526316,
"grad_norm": 0.46089208126068115,
"learning_rate": 1.929746521301587e-07,
"loss": 0.5277367115020752,
"step": 1570
},
{
"epoch": 2.6602105263157894,
"grad_norm": 0.34436914324760437,
"learning_rate": 1.754904407805727e-07,
"loss": 0.5176792621612549,
"step": 1580
},
{
"epoch": 2.677052631578947,
"grad_norm": 0.38178616762161255,
"learning_rate": 1.5880757139788844e-07,
"loss": 0.5936840057373047,
"step": 1590
},
{
"epoch": 2.6938947368421053,
"grad_norm": 0.46855390071868896,
"learning_rate": 1.42931795166614e-07,
"loss": 0.535886573791504,
"step": 1600
},
{
"epoch": 2.710736842105263,
"grad_norm": 0.46840333938598633,
"learning_rate": 1.2786858503724769e-07,
"loss": 0.5586328983306885,
"step": 1610
},
{
"epoch": 2.7275789473684213,
"grad_norm": 0.37853482365608215,
"learning_rate": 1.1362313383955742e-07,
"loss": 0.5618060111999512,
"step": 1620
},
{
"epoch": 2.744421052631579,
"grad_norm": 0.4498389661312103,
"learning_rate": 1.0020035249242304e-07,
"loss": 0.5269010543823243,
"step": 1630
},
{
"epoch": 2.761263157894737,
"grad_norm": 0.40865084528923035,
"learning_rate": 8.760486831086823e-08,
"loss": 0.577173900604248,
"step": 1640
},
{
"epoch": 2.7781052631578946,
"grad_norm": 0.4958624243736267,
"learning_rate": 7.584102341085808e-08,
"loss": 0.5220235824584961,
"step": 1650
},
{
"epoch": 2.7949473684210524,
"grad_norm": 0.5125174522399902,
"learning_rate": 6.491287321241574e-08,
"loss": 0.5500850200653076,
"step": 1660
},
{
"epoch": 2.8117894736842106,
"grad_norm": 0.5046398043632507,
"learning_rate": 5.482418504157372e-08,
"loss": 0.587200117111206,
"step": 1670
},
{
"epoch": 2.8286315789473684,
"grad_norm": 0.45359060168266296,
"learning_rate": 4.5578436831640035e-08,
"loss": 0.5316465377807618,
"step": 1680
},
{
"epoch": 2.845473684210526,
"grad_norm": 0.4397830367088318,
"learning_rate": 3.7178815924232e-08,
"loss": 0.5368952274322509,
"step": 1690
},
{
"epoch": 2.8623157894736844,
"grad_norm": 0.423321008682251,
"learning_rate": 2.9628217970482377e-08,
"loss": 0.5311310768127442,
"step": 1700
},
{
"epoch": 2.879157894736842,
"grad_norm": 0.4652172327041626,
"learning_rate": 2.292924593280621e-08,
"loss": 0.545475435256958,
"step": 1710
},
{
"epoch": 2.896,
"grad_norm": 0.43478888273239136,
"learning_rate": 1.708420918756476e-08,
"loss": 0.5385183334350586,
"step": 1720
},
{
"epoch": 2.9128421052631577,
"grad_norm": 0.4868566691875458,
"learning_rate": 1.2095122728942032e-08,
"loss": 0.5762796401977539,
"step": 1730
},
{
"epoch": 2.929684210526316,
"grad_norm": 0.46321260929107666,
"learning_rate": 7.9637064743035e-09,
"loss": 0.5364442825317383,
"step": 1740
},
{
"epoch": 2.9465263157894737,
"grad_norm": 0.5065796971321106,
"learning_rate": 4.691384671277055e-09,
"loss": 0.548289442062378,
"step": 1750
},
{
"epoch": 2.9633684210526314,
"grad_norm": 0.4855494499206543,
"learning_rate": 2.279285406766585e-09,
"loss": 0.5444241523742676,
"step": 1760
},
{
"epoch": 2.9802105263157896,
"grad_norm": 0.5797643661499023,
"learning_rate": 7.282402180569525e-10,
"loss": 0.5320149421691894,
"step": 1770
},
{
"epoch": 2.9970526315789474,
"grad_norm": 0.4781881272792816,
"learning_rate": 3.878380615579547e-11,
"loss": 0.5637479305267334,
"step": 1780
},
{
"epoch": 3.0,
"step": 1782,
"total_flos": 1.423601283446784e+16,
"train_loss": 0.6745078128529451,
"train_runtime": 1708.5057,
"train_samples_per_second": 8.341,
"train_steps_per_second": 1.043
}
],
"logging_steps": 10,
"max_steps": 1782,
"num_input_tokens_seen": 0,
"num_train_epochs": 3,
"save_steps": 200,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 1.423601283446784e+16,
"train_batch_size": 2,
"trial_name": null,
"trial_params": null
}