{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.46664999166249793,
"eval_steps": 500,
"global_step": 5597,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008337502084375521,
"grad_norm": 13.566391944885254,
"learning_rate": 1.1061797752808989e-06,
"loss": 2.2566,
"step": 10
},
{
"epoch": 0.0016675004168751042,
"grad_norm": 2.918423652648926,
"learning_rate": 2.2241573033707866e-06,
"loss": 2.04,
"step": 20
},
{
"epoch": 0.0025012506253126563,
"grad_norm": 3.1750669479370117,
"learning_rate": 3.342134831460675e-06,
"loss": 1.8853,
"step": 30
},
{
"epoch": 0.0033350008337502085,
"grad_norm": 1.5451328754425049,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.482,
"step": 40
},
{
"epoch": 0.00416875104218776,
"grad_norm": 0.9934996366500854,
"learning_rate": 5.5780898876404495e-06,
"loss": 1.232,
"step": 50
},
{
"epoch": 0.0050025012506253125,
"grad_norm": 0.6822673082351685,
"learning_rate": 6.6960674157303374e-06,
"loss": 1.1003,
"step": 60
},
{
"epoch": 0.005836251459062865,
"grad_norm": 0.8204601407051086,
"learning_rate": 7.814044943820226e-06,
"loss": 1.0664,
"step": 70
},
{
"epoch": 0.006670001667500417,
"grad_norm": 0.5949751734733582,
"learning_rate": 8.932022471910112e-06,
"loss": 1.0583,
"step": 80
},
{
"epoch": 0.007503751875937969,
"grad_norm": 0.6005659103393555,
"learning_rate": 1.005e-05,
"loss": 0.9972,
"step": 90
},
{
"epoch": 0.00833750208437552,
"grad_norm": 0.5980632305145264,
"learning_rate": 1.1167977528089888e-05,
"loss": 0.9785,
"step": 100
},
{
"epoch": 0.009171252292813074,
"grad_norm": 0.5540244579315186,
"learning_rate": 1.2285955056179776e-05,
"loss": 1.0015,
"step": 110
},
{
"epoch": 0.010005002501250625,
"grad_norm": 0.593195378780365,
"learning_rate": 1.3403932584269664e-05,
"loss": 0.9758,
"step": 120
},
{
"epoch": 0.010838752709688178,
"grad_norm": 0.583214282989502,
"learning_rate": 1.4521910112359552e-05,
"loss": 0.9762,
"step": 130
},
{
"epoch": 0.01167250291812573,
"grad_norm": 1.0294115543365479,
"learning_rate": 1.563988764044944e-05,
"loss": 0.9824,
"step": 140
},
{
"epoch": 0.01250625312656328,
"grad_norm": 0.6010154485702515,
"learning_rate": 1.6757865168539328e-05,
"loss": 0.9845,
"step": 150
},
{
"epoch": 0.013340003335000834,
"grad_norm": 0.5743474960327148,
"learning_rate": 1.7875842696629214e-05,
"loss": 0.9589,
"step": 160
},
{
"epoch": 0.014173753543438385,
"grad_norm": 0.6928213238716125,
"learning_rate": 1.89938202247191e-05,
"loss": 0.9375,
"step": 170
},
{
"epoch": 0.015007503751875938,
"grad_norm": 0.5875935554504395,
"learning_rate": 2e-05,
"loss": 0.9497,
"step": 180
},
{
"epoch": 0.01584125396031349,
"grad_norm": 0.6017818450927734,
"learning_rate": 2e-05,
"loss": 0.9398,
"step": 190
},
{
"epoch": 0.01667500416875104,
"grad_norm": 0.6024709939956665,
"learning_rate": 2e-05,
"loss": 0.9518,
"step": 200
},
{
"epoch": 0.017508754377188594,
"grad_norm": 0.5575109124183655,
"learning_rate": 2e-05,
"loss": 0.9559,
"step": 210
},
{
"epoch": 0.018342504585626147,
"grad_norm": 0.5377241969108582,
"learning_rate": 2e-05,
"loss": 0.9173,
"step": 220
},
{
"epoch": 0.019176254794063697,
"grad_norm": 0.6026791930198669,
"learning_rate": 2e-05,
"loss": 0.9429,
"step": 230
},
{
"epoch": 0.02001000500250125,
"grad_norm": 0.5152384042739868,
"learning_rate": 2e-05,
"loss": 0.9307,
"step": 240
},
{
"epoch": 0.020843755210938803,
"grad_norm": 0.5376507043838501,
"learning_rate": 2e-05,
"loss": 0.9141,
"step": 250
},
{
"epoch": 0.021677505419376356,
"grad_norm": 0.5467250943183899,
"learning_rate": 2e-05,
"loss": 0.9635,
"step": 260
},
{
"epoch": 0.022511255627813906,
"grad_norm": 0.48651859164237976,
"learning_rate": 2e-05,
"loss": 0.9256,
"step": 270
},
{
"epoch": 0.02334500583625146,
"grad_norm": 0.5394302606582642,
"learning_rate": 2e-05,
"loss": 0.9682,
"step": 280
},
{
"epoch": 0.024178756044689012,
"grad_norm": 0.557639479637146,
"learning_rate": 2e-05,
"loss": 0.8902,
"step": 290
},
{
"epoch": 0.02501250625312656,
"grad_norm": 0.5069289207458496,
"learning_rate": 2e-05,
"loss": 0.8967,
"step": 300
},
{
"epoch": 0.025846256461564115,
"grad_norm": 0.5206510424613953,
"learning_rate": 2e-05,
"loss": 0.9144,
"step": 310
},
{
"epoch": 0.026680006670001668,
"grad_norm": 0.6359990835189819,
"learning_rate": 2e-05,
"loss": 0.9147,
"step": 320
},
{
"epoch": 0.02751375687843922,
"grad_norm": 0.5385337471961975,
"learning_rate": 2e-05,
"loss": 0.9343,
"step": 330
},
{
"epoch": 0.02834750708687677,
"grad_norm": 0.9713227152824402,
"learning_rate": 2e-05,
"loss": 0.922,
"step": 340
},
{
"epoch": 0.029181257295314324,
"grad_norm": 0.541314959526062,
"learning_rate": 2e-05,
"loss": 0.8897,
"step": 350
},
{
"epoch": 0.030015007503751877,
"grad_norm": 0.5001296401023865,
"learning_rate": 2e-05,
"loss": 0.935,
"step": 360
},
{
"epoch": 0.030848757712189426,
"grad_norm": 0.5119391083717346,
"learning_rate": 2e-05,
"loss": 0.9041,
"step": 370
},
{
"epoch": 0.03168250792062698,
"grad_norm": 0.4927831292152405,
"learning_rate": 2e-05,
"loss": 0.917,
"step": 380
},
{
"epoch": 0.03251625812906453,
"grad_norm": 0.5068843364715576,
"learning_rate": 2e-05,
"loss": 0.8978,
"step": 390
},
{
"epoch": 0.03335000833750208,
"grad_norm": 0.524895191192627,
"learning_rate": 2e-05,
"loss": 0.9182,
"step": 400
},
{
"epoch": 0.034183758545939635,
"grad_norm": 0.5074824690818787,
"learning_rate": 2e-05,
"loss": 0.9265,
"step": 410
},
{
"epoch": 0.03501750875437719,
"grad_norm": 0.4857582151889801,
"learning_rate": 2e-05,
"loss": 0.9585,
"step": 420
},
{
"epoch": 0.03585125896281474,
"grad_norm": 0.5838627219200134,
"learning_rate": 2e-05,
"loss": 0.9099,
"step": 430
},
{
"epoch": 0.036685009171252295,
"grad_norm": 0.4798157513141632,
"learning_rate": 2e-05,
"loss": 0.8595,
"step": 440
},
{
"epoch": 0.03751875937968985,
"grad_norm": 0.4893852472305298,
"learning_rate": 2e-05,
"loss": 0.9249,
"step": 450
},
{
"epoch": 0.038352509588127394,
"grad_norm": 0.4752409756183624,
"learning_rate": 2e-05,
"loss": 0.8971,
"step": 460
},
{
"epoch": 0.03918625979656495,
"grad_norm": 0.5044603943824768,
"learning_rate": 2e-05,
"loss": 0.9007,
"step": 470
},
{
"epoch": 0.0400200100050025,
"grad_norm": 0.4857725203037262,
"learning_rate": 2e-05,
"loss": 0.8884,
"step": 480
},
{
"epoch": 0.04085376021344005,
"grad_norm": 0.5009463429450989,
"learning_rate": 2e-05,
"loss": 0.897,
"step": 490
},
{
"epoch": 0.041687510421877606,
"grad_norm": 0.5030511617660522,
"learning_rate": 2e-05,
"loss": 0.8975,
"step": 500
},
{
"epoch": 0.04252126063031516,
"grad_norm": 0.4980432689189911,
"learning_rate": 2e-05,
"loss": 0.8826,
"step": 510
},
{
"epoch": 0.04335501083875271,
"grad_norm": 0.503282368183136,
"learning_rate": 2e-05,
"loss": 0.9187,
"step": 520
},
{
"epoch": 0.04418876104719026,
"grad_norm": 0.4999975860118866,
"learning_rate": 2e-05,
"loss": 0.9012,
"step": 530
},
{
"epoch": 0.04502251125562781,
"grad_norm": 0.5200240015983582,
"learning_rate": 2e-05,
"loss": 0.9279,
"step": 540
},
{
"epoch": 0.045856261464065365,
"grad_norm": 0.4858852028846741,
"learning_rate": 2e-05,
"loss": 0.8755,
"step": 550
},
{
"epoch": 0.04669001167250292,
"grad_norm": 0.4801354706287384,
"learning_rate": 2e-05,
"loss": 0.8966,
"step": 560
},
{
"epoch": 0.04752376188094047,
"grad_norm": 0.4935963451862335,
"learning_rate": 2e-05,
"loss": 0.8972,
"step": 570
},
{
"epoch": 0.048357512089378024,
"grad_norm": 0.474505752325058,
"learning_rate": 2e-05,
"loss": 0.9117,
"step": 580
},
{
"epoch": 0.04919126229781558,
"grad_norm": 0.4899780750274658,
"learning_rate": 2e-05,
"loss": 0.9031,
"step": 590
},
{
"epoch": 0.05002501250625312,
"grad_norm": 0.4700799286365509,
"learning_rate": 2e-05,
"loss": 0.8806,
"step": 600
},
{
"epoch": 0.050858762714690676,
"grad_norm": 0.48884260654449463,
"learning_rate": 2e-05,
"loss": 0.9147,
"step": 610
},
{
"epoch": 0.05169251292312823,
"grad_norm": 0.5095788836479187,
"learning_rate": 2e-05,
"loss": 0.913,
"step": 620
},
{
"epoch": 0.05252626313156578,
"grad_norm": 0.4703826904296875,
"learning_rate": 2e-05,
"loss": 0.8676,
"step": 630
},
{
"epoch": 0.053360013340003336,
"grad_norm": 0.47759559750556946,
"learning_rate": 2e-05,
"loss": 0.9071,
"step": 640
},
{
"epoch": 0.05419376354844089,
"grad_norm": 0.4874522387981415,
"learning_rate": 2e-05,
"loss": 0.9025,
"step": 650
},
{
"epoch": 0.05502751375687844,
"grad_norm": 0.5711647272109985,
"learning_rate": 2e-05,
"loss": 0.8959,
"step": 660
},
{
"epoch": 0.05586126396531599,
"grad_norm": 0.467171311378479,
"learning_rate": 2e-05,
"loss": 0.8513,
"step": 670
},
{
"epoch": 0.05669501417375354,
"grad_norm": 0.46761074662208557,
"learning_rate": 2e-05,
"loss": 0.9062,
"step": 680
},
{
"epoch": 0.057528764382191094,
"grad_norm": 0.5580011010169983,
"learning_rate": 2e-05,
"loss": 0.8929,
"step": 690
},
{
"epoch": 0.05836251459062865,
"grad_norm": 0.48909950256347656,
"learning_rate": 2e-05,
"loss": 0.8542,
"step": 700
},
{
"epoch": 0.0591962647990662,
"grad_norm": 0.476967990398407,
"learning_rate": 2e-05,
"loss": 0.8883,
"step": 710
},
{
"epoch": 0.060030015007503754,
"grad_norm": 0.465226948261261,
"learning_rate": 2e-05,
"loss": 0.8702,
"step": 720
},
{
"epoch": 0.06086376521594131,
"grad_norm": 0.5059548616409302,
"learning_rate": 2e-05,
"loss": 0.9262,
"step": 730
},
{
"epoch": 0.06169751542437885,
"grad_norm": 0.47689661383628845,
"learning_rate": 2e-05,
"loss": 0.8881,
"step": 740
},
{
"epoch": 0.06253126563281641,
"grad_norm": 0.4785926043987274,
"learning_rate": 2e-05,
"loss": 0.8778,
"step": 750
},
{
"epoch": 0.06336501584125397,
"grad_norm": 0.4779227375984192,
"learning_rate": 2e-05,
"loss": 0.8711,
"step": 760
},
{
"epoch": 0.06419876604969152,
"grad_norm": 0.4782222509384155,
"learning_rate": 2e-05,
"loss": 0.8741,
"step": 770
},
{
"epoch": 0.06503251625812906,
"grad_norm": 0.48066234588623047,
"learning_rate": 2e-05,
"loss": 0.8801,
"step": 780
},
{
"epoch": 0.06586626646656661,
"grad_norm": 0.47301703691482544,
"learning_rate": 2e-05,
"loss": 0.883,
"step": 790
},
{
"epoch": 0.06670001667500416,
"grad_norm": 0.5085282921791077,
"learning_rate": 2e-05,
"loss": 0.8742,
"step": 800
},
{
"epoch": 0.06753376688344172,
"grad_norm": 0.45049068331718445,
"learning_rate": 2e-05,
"loss": 0.8756,
"step": 810
},
{
"epoch": 0.06836751709187927,
"grad_norm": 0.49371621012687683,
"learning_rate": 2e-05,
"loss": 0.8805,
"step": 820
},
{
"epoch": 0.06920126730031682,
"grad_norm": 0.4748493432998657,
"learning_rate": 2e-05,
"loss": 0.8604,
"step": 830
},
{
"epoch": 0.07003501750875438,
"grad_norm": 0.4948427081108093,
"learning_rate": 2e-05,
"loss": 0.9014,
"step": 840
},
{
"epoch": 0.07086876771719193,
"grad_norm": 0.4881714880466461,
"learning_rate": 2e-05,
"loss": 0.8926,
"step": 850
},
{
"epoch": 0.07170251792562948,
"grad_norm": 0.48637422919273376,
"learning_rate": 2e-05,
"loss": 0.8852,
"step": 860
},
{
"epoch": 0.07253626813406704,
"grad_norm": 0.47452136874198914,
"learning_rate": 2e-05,
"loss": 0.8837,
"step": 870
},
{
"epoch": 0.07337001834250459,
"grad_norm": 0.5064214468002319,
"learning_rate": 2e-05,
"loss": 0.8451,
"step": 880
},
{
"epoch": 0.07420376855094214,
"grad_norm": 0.5455189943313599,
"learning_rate": 2e-05,
"loss": 0.8783,
"step": 890
},
{
"epoch": 0.0750375187593797,
"grad_norm": 0.4725022315979004,
"learning_rate": 2e-05,
"loss": 0.8772,
"step": 900
},
{
"epoch": 0.07587126896781725,
"grad_norm": 0.49021732807159424,
"learning_rate": 2e-05,
"loss": 0.863,
"step": 910
},
{
"epoch": 0.07670501917625479,
"grad_norm": 0.4547465145587921,
"learning_rate": 2e-05,
"loss": 0.8704,
"step": 920
},
{
"epoch": 0.07753876938469234,
"grad_norm": 0.4670726954936981,
"learning_rate": 2e-05,
"loss": 0.8707,
"step": 930
},
{
"epoch": 0.0783725195931299,
"grad_norm": 0.4348442852497101,
"learning_rate": 2e-05,
"loss": 0.8489,
"step": 940
},
{
"epoch": 0.07920626980156745,
"grad_norm": 0.49067702889442444,
"learning_rate": 2e-05,
"loss": 0.8632,
"step": 950
},
{
"epoch": 0.080040020010005,
"grad_norm": 0.46889927983283997,
"learning_rate": 2e-05,
"loss": 0.8597,
"step": 960
},
{
"epoch": 0.08087377021844255,
"grad_norm": 0.4586699903011322,
"learning_rate": 2e-05,
"loss": 0.8419,
"step": 970
},
{
"epoch": 0.0817075204268801,
"grad_norm": 0.49893268942832947,
"learning_rate": 2e-05,
"loss": 0.895,
"step": 980
},
{
"epoch": 0.08254127063531766,
"grad_norm": 0.4792695939540863,
"learning_rate": 2e-05,
"loss": 0.8723,
"step": 990
},
{
"epoch": 0.08337502084375521,
"grad_norm": 0.4571530818939209,
"learning_rate": 2e-05,
"loss": 0.8824,
"step": 1000
},
{
"epoch": 0.08420877105219277,
"grad_norm": 0.46045640110969543,
"learning_rate": 2e-05,
"loss": 0.872,
"step": 1010
},
{
"epoch": 0.08504252126063032,
"grad_norm": 0.45626309514045715,
"learning_rate": 2e-05,
"loss": 0.8686,
"step": 1020
},
{
"epoch": 0.08587627146906787,
"grad_norm": 0.45131054520606995,
"learning_rate": 2e-05,
"loss": 0.8719,
"step": 1030
},
{
"epoch": 0.08671002167750542,
"grad_norm": 0.48775601387023926,
"learning_rate": 2e-05,
"loss": 0.8844,
"step": 1040
},
{
"epoch": 0.08754377188594298,
"grad_norm": 0.45046332478523254,
"learning_rate": 2e-05,
"loss": 0.8626,
"step": 1050
},
{
"epoch": 0.08837752209438052,
"grad_norm": 0.47383394837379456,
"learning_rate": 2e-05,
"loss": 0.8636,
"step": 1060
},
{
"epoch": 0.08921127230281807,
"grad_norm": 0.4502175450325012,
"learning_rate": 2e-05,
"loss": 0.8932,
"step": 1070
},
{
"epoch": 0.09004502251125562,
"grad_norm": 0.4500514566898346,
"learning_rate": 2e-05,
"loss": 0.8616,
"step": 1080
},
{
"epoch": 0.09087877271969318,
"grad_norm": 0.4716588854789734,
"learning_rate": 2e-05,
"loss": 0.889,
"step": 1090
},
{
"epoch": 0.09171252292813073,
"grad_norm": 0.46128395199775696,
"learning_rate": 2e-05,
"loss": 0.8749,
"step": 1100
},
{
"epoch": 0.09254627313656828,
"grad_norm": 0.45671573281288147,
"learning_rate": 2e-05,
"loss": 0.8675,
"step": 1110
},
{
"epoch": 0.09338002334500584,
"grad_norm": 0.4433386027812958,
"learning_rate": 2e-05,
"loss": 0.8851,
"step": 1120
},
{
"epoch": 0.09421377355344339,
"grad_norm": 0.47851717472076416,
"learning_rate": 2e-05,
"loss": 0.8543,
"step": 1130
},
{
"epoch": 0.09504752376188094,
"grad_norm": 0.45275554060935974,
"learning_rate": 2e-05,
"loss": 0.8557,
"step": 1140
},
{
"epoch": 0.0958812739703185,
"grad_norm": 0.4398982524871826,
"learning_rate": 2e-05,
"loss": 0.8765,
"step": 1150
},
{
"epoch": 0.09671502417875605,
"grad_norm": 0.47268056869506836,
"learning_rate": 2e-05,
"loss": 0.8504,
"step": 1160
},
{
"epoch": 0.0975487743871936,
"grad_norm": 0.5026320219039917,
"learning_rate": 2e-05,
"loss": 0.8582,
"step": 1170
},
{
"epoch": 0.09838252459563115,
"grad_norm": 0.47815778851509094,
"learning_rate": 2e-05,
"loss": 0.8824,
"step": 1180
},
{
"epoch": 0.09921627480406871,
"grad_norm": 0.4754660129547119,
"learning_rate": 2e-05,
"loss": 0.8418,
"step": 1190
},
{
"epoch": 0.10005002501250625,
"grad_norm": 0.4670088589191437,
"learning_rate": 2e-05,
"loss": 0.8685,
"step": 1200
},
{
"epoch": 0.1008837752209438,
"grad_norm": 0.445632666349411,
"learning_rate": 2e-05,
"loss": 0.9002,
"step": 1210
},
{
"epoch": 0.10171752542938135,
"grad_norm": 0.4594423472881317,
"learning_rate": 2e-05,
"loss": 0.8335,
"step": 1220
},
{
"epoch": 0.1025512756378189,
"grad_norm": 0.46774882078170776,
"learning_rate": 2e-05,
"loss": 0.8707,
"step": 1230
},
{
"epoch": 0.10338502584625646,
"grad_norm": 0.4260616898536682,
"learning_rate": 2e-05,
"loss": 0.8438,
"step": 1240
},
{
"epoch": 0.10421877605469401,
"grad_norm": 0.455828994512558,
"learning_rate": 2e-05,
"loss": 0.8826,
"step": 1250
},
{
"epoch": 0.10505252626313157,
"grad_norm": 0.4610627293586731,
"learning_rate": 2e-05,
"loss": 0.8514,
"step": 1260
},
{
"epoch": 0.10588627647156912,
"grad_norm": 0.44051027297973633,
"learning_rate": 2e-05,
"loss": 0.8328,
"step": 1270
},
{
"epoch": 0.10672002668000667,
"grad_norm": 0.43709734082221985,
"learning_rate": 2e-05,
"loss": 0.8399,
"step": 1280
},
{
"epoch": 0.10755377688844422,
"grad_norm": 0.4435420334339142,
"learning_rate": 2e-05,
"loss": 0.8651,
"step": 1290
},
{
"epoch": 0.10838752709688178,
"grad_norm": 0.4506440758705139,
"learning_rate": 2e-05,
"loss": 0.8647,
"step": 1300
},
{
"epoch": 0.10922127730531933,
"grad_norm": 0.4587005376815796,
"learning_rate": 2e-05,
"loss": 0.8565,
"step": 1310
},
{
"epoch": 0.11005502751375688,
"grad_norm": 0.4504447281360626,
"learning_rate": 2e-05,
"loss": 0.8265,
"step": 1320
},
{
"epoch": 0.11088877772219444,
"grad_norm": 0.4566003978252411,
"learning_rate": 2e-05,
"loss": 0.8727,
"step": 1330
},
{
"epoch": 0.11172252793063198,
"grad_norm": 0.4230361580848694,
"learning_rate": 2e-05,
"loss": 0.8721,
"step": 1340
},
{
"epoch": 0.11255627813906953,
"grad_norm": 0.43980881571769714,
"learning_rate": 2e-05,
"loss": 0.8323,
"step": 1350
},
{
"epoch": 0.11339002834750708,
"grad_norm": 0.4772922396659851,
"learning_rate": 2e-05,
"loss": 0.8312,
"step": 1360
},
{
"epoch": 0.11422377855594464,
"grad_norm": 0.44763606786727905,
"learning_rate": 2e-05,
"loss": 0.8666,
"step": 1370
},
{
"epoch": 0.11505752876438219,
"grad_norm": 0.4610816538333893,
"learning_rate": 2e-05,
"loss": 0.824,
"step": 1380
},
{
"epoch": 0.11589127897281974,
"grad_norm": 0.46850505471229553,
"learning_rate": 2e-05,
"loss": 0.8562,
"step": 1390
},
{
"epoch": 0.1167250291812573,
"grad_norm": 0.44208332896232605,
"learning_rate": 2e-05,
"loss": 0.8283,
"step": 1400
},
{
"epoch": 0.11755877938969485,
"grad_norm": 0.4290333390235901,
"learning_rate": 2e-05,
"loss": 0.8678,
"step": 1410
},
{
"epoch": 0.1183925295981324,
"grad_norm": 0.4428878128528595,
"learning_rate": 2e-05,
"loss": 0.8617,
"step": 1420
},
{
"epoch": 0.11922627980656995,
"grad_norm": 0.4282263219356537,
"learning_rate": 2e-05,
"loss": 0.8685,
"step": 1430
},
{
"epoch": 0.12006003001500751,
"grad_norm": 0.45656654238700867,
"learning_rate": 2e-05,
"loss": 0.8432,
"step": 1440
},
{
"epoch": 0.12089378022344506,
"grad_norm": 0.44715428352355957,
"learning_rate": 2e-05,
"loss": 0.8511,
"step": 1450
},
{
"epoch": 0.12172753043188261,
"grad_norm": 0.4341605603694916,
"learning_rate": 2e-05,
"loss": 0.8541,
"step": 1460
},
{
"epoch": 0.12256128064032017,
"grad_norm": 0.4401302933692932,
"learning_rate": 2e-05,
"loss": 0.8299,
"step": 1470
},
{
"epoch": 0.1233950308487577,
"grad_norm": 0.4861335754394531,
"learning_rate": 2e-05,
"loss": 0.8838,
"step": 1480
},
{
"epoch": 0.12422878105719526,
"grad_norm": 0.5418664813041687,
"learning_rate": 2e-05,
"loss": 0.8731,
"step": 1490
},
{
"epoch": 0.12506253126563283,
"grad_norm": 0.43481454253196716,
"learning_rate": 2e-05,
"loss": 0.834,
"step": 1500
},
{
"epoch": 0.12589628147407037,
"grad_norm": 0.4351367652416229,
"learning_rate": 2e-05,
"loss": 0.823,
"step": 1510
},
{
"epoch": 0.12673003168250793,
"grad_norm": 0.42949992418289185,
"learning_rate": 2e-05,
"loss": 0.8313,
"step": 1520
},
{
"epoch": 0.12756378189094547,
"grad_norm": 0.47757044434547424,
"learning_rate": 2e-05,
"loss": 0.8467,
"step": 1530
},
{
"epoch": 0.12839753209938304,
"grad_norm": 0.44212520122528076,
"learning_rate": 2e-05,
"loss": 0.8179,
"step": 1540
},
{
"epoch": 0.12923128230782058,
"grad_norm": 0.46180012822151184,
"learning_rate": 2e-05,
"loss": 0.8594,
"step": 1550
},
{
"epoch": 0.13006503251625812,
"grad_norm": 0.4632825553417206,
"learning_rate": 2e-05,
"loss": 0.8523,
"step": 1560
},
{
"epoch": 0.13089878272469568,
"grad_norm": 0.45442265272140503,
"learning_rate": 2e-05,
"loss": 0.8682,
"step": 1570
},
{
"epoch": 0.13173253293313322,
"grad_norm": 0.42941489815711975,
"learning_rate": 2e-05,
"loss": 0.8648,
"step": 1580
},
{
"epoch": 0.1325662831415708,
"grad_norm": 0.4399435520172119,
"learning_rate": 2e-05,
"loss": 0.8374,
"step": 1590
},
{
"epoch": 0.13340003335000833,
"grad_norm": 0.4403332769870758,
"learning_rate": 2e-05,
"loss": 0.8397,
"step": 1600
},
{
"epoch": 0.1342337835584459,
"grad_norm": 0.4336073100566864,
"learning_rate": 2e-05,
"loss": 0.8274,
"step": 1610
},
{
"epoch": 0.13506753376688344,
"grad_norm": 0.4528632164001465,
"learning_rate": 2e-05,
"loss": 0.856,
"step": 1620
},
{
"epoch": 0.135901283975321,
"grad_norm": 0.4432793855667114,
"learning_rate": 2e-05,
"loss": 0.8504,
"step": 1630
},
{
"epoch": 0.13673503418375854,
"grad_norm": 0.41927823424339294,
"learning_rate": 2e-05,
"loss": 0.8275,
"step": 1640
},
{
"epoch": 0.1375687843921961,
"grad_norm": 0.4702625274658203,
"learning_rate": 2e-05,
"loss": 0.8484,
"step": 1650
},
{
"epoch": 0.13840253460063365,
"grad_norm": 0.44438639283180237,
"learning_rate": 2e-05,
"loss": 0.8615,
"step": 1660
},
{
"epoch": 0.13923628480907121,
"grad_norm": 0.41862818598747253,
"learning_rate": 2e-05,
"loss": 0.7987,
"step": 1670
},
{
"epoch": 0.14007003501750875,
"grad_norm": 0.4880077540874481,
"learning_rate": 2e-05,
"loss": 0.882,
"step": 1680
},
{
"epoch": 0.1409037852259463,
"grad_norm": 0.4247034192085266,
"learning_rate": 2e-05,
"loss": 0.8713,
"step": 1690
},
{
"epoch": 0.14173753543438386,
"grad_norm": 0.48232707381248474,
"learning_rate": 2e-05,
"loss": 0.8157,
"step": 1700
},
{
"epoch": 0.1425712856428214,
"grad_norm": 0.4385620653629303,
"learning_rate": 2e-05,
"loss": 0.8653,
"step": 1710
},
{
"epoch": 0.14340503585125897,
"grad_norm": 0.40841519832611084,
"learning_rate": 2e-05,
"loss": 0.8421,
"step": 1720
},
{
"epoch": 0.1442387860596965,
"grad_norm": 0.4390290379524231,
"learning_rate": 2e-05,
"loss": 0.8325,
"step": 1730
},
{
"epoch": 0.14507253626813407,
"grad_norm": 0.43640732765197754,
"learning_rate": 2e-05,
"loss": 0.8035,
"step": 1740
},
{
"epoch": 0.1459062864765716,
"grad_norm": 0.4441671073436737,
"learning_rate": 2e-05,
"loss": 0.8573,
"step": 1750
},
{
"epoch": 0.14674003668500918,
"grad_norm": 0.5069043040275574,
"learning_rate": 2e-05,
"loss": 0.8239,
"step": 1760
},
{
"epoch": 0.14757378689344672,
"grad_norm": 0.4640333950519562,
"learning_rate": 2e-05,
"loss": 0.8502,
"step": 1770
},
{
"epoch": 0.14840753710188428,
"grad_norm": 0.4455471634864807,
"learning_rate": 2e-05,
"loss": 0.8146,
"step": 1780
},
{
"epoch": 0.14924128731032182,
"grad_norm": 0.4304905831813812,
"learning_rate": 2e-05,
"loss": 0.8315,
"step": 1790
},
{
"epoch": 0.1500750375187594,
"grad_norm": 0.4412347376346588,
"learning_rate": 2e-05,
"loss": 0.848,
"step": 1800
},
{
"epoch": 0.15090878772719693,
"grad_norm": 0.47276702523231506,
"learning_rate": 2e-05,
"loss": 0.8394,
"step": 1810
},
{
"epoch": 0.1517425379356345,
"grad_norm": 0.4487875998020172,
"learning_rate": 2e-05,
"loss": 0.8238,
"step": 1820
},
{
"epoch": 0.15257628814407204,
"grad_norm": 0.4340097904205322,
"learning_rate": 2e-05,
"loss": 0.8331,
"step": 1830
},
{
"epoch": 0.15341003835250958,
"grad_norm": 0.47058507800102234,
"learning_rate": 2e-05,
"loss": 0.8841,
"step": 1840
},
{
"epoch": 0.15424378856094714,
"grad_norm": 0.44329574704170227,
"learning_rate": 2e-05,
"loss": 0.8383,
"step": 1850
},
{
"epoch": 0.15507753876938468,
"grad_norm": 0.4418177604675293,
"learning_rate": 2e-05,
"loss": 0.8502,
"step": 1860
},
{
"epoch": 0.15591128897782225,
"grad_norm": 0.428423136472702,
"learning_rate": 2e-05,
"loss": 0.8119,
"step": 1870
},
{
"epoch": 0.1567450391862598,
"grad_norm": 0.440356969833374,
"learning_rate": 2e-05,
"loss": 0.8329,
"step": 1880
},
{
"epoch": 0.15757878939469736,
"grad_norm": 0.42486879229545593,
"learning_rate": 2e-05,
"loss": 0.8544,
"step": 1890
},
{
"epoch": 0.1584125396031349,
"grad_norm": 0.4485068917274475,
"learning_rate": 2e-05,
"loss": 0.8636,
"step": 1900
},
{
"epoch": 0.15924628981157246,
"grad_norm": 0.40998324751853943,
"learning_rate": 2e-05,
"loss": 0.8147,
"step": 1910
},
{
"epoch": 0.16008004002001,
"grad_norm": 0.42555490136146545,
"learning_rate": 2e-05,
"loss": 0.8372,
"step": 1920
},
{
"epoch": 0.16091379022844757,
"grad_norm": 0.4394669830799103,
"learning_rate": 2e-05,
"loss": 0.8044,
"step": 1930
},
{
"epoch": 0.1617475404368851,
"grad_norm": 0.45242002606391907,
"learning_rate": 2e-05,
"loss": 0.846,
"step": 1940
},
{
"epoch": 0.16258129064532267,
"grad_norm": 0.5341451168060303,
"learning_rate": 2e-05,
"loss": 0.819,
"step": 1950
},
{
"epoch": 0.1634150408537602,
"grad_norm": 0.429604172706604,
"learning_rate": 2e-05,
"loss": 0.8567,
"step": 1960
},
{
"epoch": 0.16424879106219775,
"grad_norm": 0.46033960580825806,
"learning_rate": 2e-05,
"loss": 0.8622,
"step": 1970
},
{
"epoch": 0.16508254127063532,
"grad_norm": 0.461689293384552,
"learning_rate": 2e-05,
"loss": 0.8663,
"step": 1980
},
{
"epoch": 0.16591629147907286,
"grad_norm": 0.42240920662879944,
"learning_rate": 2e-05,
"loss": 0.8422,
"step": 1990
},
{
"epoch": 0.16675004168751043,
"grad_norm": 0.4205416440963745,
"learning_rate": 2e-05,
"loss": 0.8178,
"step": 2000
},
{
"epoch": 0.16758379189594796,
"grad_norm": 0.46915921568870544,
"learning_rate": 2e-05,
"loss": 0.8677,
"step": 2010
},
{
"epoch": 0.16841754210438553,
"grad_norm": 0.44211524724960327,
"learning_rate": 2e-05,
"loss": 0.8183,
"step": 2020
},
{
"epoch": 0.16925129231282307,
"grad_norm": 0.4337581694126129,
"learning_rate": 2e-05,
"loss": 0.8405,
"step": 2030
},
{
"epoch": 0.17008504252126064,
"grad_norm": 0.463716596364975,
"learning_rate": 2e-05,
"loss": 0.8798,
"step": 2040
},
{
"epoch": 0.17091879272969818,
"grad_norm": 0.44323939085006714,
"learning_rate": 2e-05,
"loss": 0.8193,
"step": 2050
},
{
"epoch": 0.17175254293813574,
"grad_norm": 0.46792158484458923,
"learning_rate": 2e-05,
"loss": 0.8516,
"step": 2060
},
{
"epoch": 0.17258629314657328,
"grad_norm": 0.4367827773094177,
"learning_rate": 2e-05,
"loss": 0.8503,
"step": 2070
},
{
"epoch": 0.17342004335501085,
"grad_norm": 0.45662805438041687,
"learning_rate": 2e-05,
"loss": 0.8479,
"step": 2080
},
{
"epoch": 0.1742537935634484,
"grad_norm": 0.44357606768608093,
"learning_rate": 2e-05,
"loss": 0.8517,
"step": 2090
},
{
"epoch": 0.17508754377188596,
"grad_norm": 0.4385230243206024,
"learning_rate": 2e-05,
"loss": 0.8418,
"step": 2100
},
{
"epoch": 0.1759212939803235,
"grad_norm": 0.4620836079120636,
"learning_rate": 2e-05,
"loss": 0.8237,
"step": 2110
},
{
"epoch": 0.17675504418876103,
"grad_norm": 0.41884246468544006,
"learning_rate": 2e-05,
"loss": 0.8155,
"step": 2120
},
{
"epoch": 0.1775887943971986,
"grad_norm": 0.4452560842037201,
"learning_rate": 2e-05,
"loss": 0.85,
"step": 2130
},
{
"epoch": 0.17842254460563614,
"grad_norm": 0.43115249276161194,
"learning_rate": 2e-05,
"loss": 0.8247,
"step": 2140
},
{
"epoch": 0.1792562948140737,
"grad_norm": 0.41687360405921936,
"learning_rate": 2e-05,
"loss": 0.8233,
"step": 2150
},
{
"epoch": 0.18009004502251125,
"grad_norm": 0.4290129542350769,
"learning_rate": 2e-05,
"loss": 0.8496,
"step": 2160
},
{
"epoch": 0.18092379523094881,
"grad_norm": 0.4227672517299652,
"learning_rate": 2e-05,
"loss": 0.8286,
"step": 2170
},
{
"epoch": 0.18175754543938635,
"grad_norm": 0.4615258574485779,
"learning_rate": 2e-05,
"loss": 0.8535,
"step": 2180
},
{
"epoch": 0.18259129564782392,
"grad_norm": 0.40805891156196594,
"learning_rate": 2e-05,
"loss": 0.8636,
"step": 2190
},
{
"epoch": 0.18342504585626146,
"grad_norm": 0.44394758343696594,
"learning_rate": 2e-05,
"loss": 0.8477,
"step": 2200
},
{
"epoch": 0.18425879606469903,
"grad_norm": 0.446467787027359,
"learning_rate": 2e-05,
"loss": 0.868,
"step": 2210
},
{
"epoch": 0.18509254627313657,
"grad_norm": 0.43390893936157227,
"learning_rate": 2e-05,
"loss": 0.8099,
"step": 2220
},
{
"epoch": 0.18592629648157413,
"grad_norm": 0.4239795207977295,
"learning_rate": 2e-05,
"loss": 0.8365,
"step": 2230
},
{
"epoch": 0.18676004669001167,
"grad_norm": 0.44403794407844543,
"learning_rate": 2e-05,
"loss": 0.8241,
"step": 2240
},
{
"epoch": 0.1875937968984492,
"grad_norm": 0.44895854592323303,
"learning_rate": 2e-05,
"loss": 0.8658,
"step": 2250
},
{
"epoch": 0.18842754710688678,
"grad_norm": 0.44715580344200134,
"learning_rate": 2e-05,
"loss": 0.8144,
"step": 2260
},
{
"epoch": 0.18926129731532432,
"grad_norm": 0.43580275774002075,
"learning_rate": 2e-05,
"loss": 0.8347,
"step": 2270
},
{
"epoch": 0.19009504752376188,
"grad_norm": 0.4666694700717926,
"learning_rate": 2e-05,
"loss": 0.8474,
"step": 2280
},
{
"epoch": 0.19092879773219942,
"grad_norm": 0.4219069182872772,
"learning_rate": 2e-05,
"loss": 0.8425,
"step": 2290
},
{
"epoch": 0.191762547940637,
"grad_norm": 0.43905431032180786,
"learning_rate": 2e-05,
"loss": 0.8549,
"step": 2300
},
{
"epoch": 0.19259629814907453,
"grad_norm": 0.4393678307533264,
"learning_rate": 2e-05,
"loss": 0.8291,
"step": 2310
},
{
"epoch": 0.1934300483575121,
"grad_norm": 0.4422663450241089,
"learning_rate": 2e-05,
"loss": 0.8187,
"step": 2320
},
{
"epoch": 0.19426379856594964,
"grad_norm": 0.4156511723995209,
"learning_rate": 2e-05,
"loss": 0.8291,
"step": 2330
},
{
"epoch": 0.1950975487743872,
"grad_norm": 0.4404476284980774,
"learning_rate": 2e-05,
"loss": 0.8287,
"step": 2340
},
{
"epoch": 0.19593129898282474,
"grad_norm": 0.447643905878067,
"learning_rate": 2e-05,
"loss": 0.82,
"step": 2350
},
{
"epoch": 0.1967650491912623,
"grad_norm": 0.4360268712043762,
"learning_rate": 2e-05,
"loss": 0.8253,
"step": 2360
},
{
"epoch": 0.19759879939969985,
"grad_norm": 0.43036919832229614,
"learning_rate": 2e-05,
"loss": 0.7905,
"step": 2370
},
{
"epoch": 0.19843254960813742,
"grad_norm": 0.4261600375175476,
"learning_rate": 2e-05,
"loss": 0.8079,
"step": 2380
},
{
"epoch": 0.19926629981657495,
"grad_norm": 0.43624958395957947,
"learning_rate": 2e-05,
"loss": 0.8271,
"step": 2390
},
{
"epoch": 0.2001000500250125,
"grad_norm": 0.44643980264663696,
"learning_rate": 2e-05,
"loss": 0.8472,
"step": 2400
},
{
"epoch": 0.20093380023345006,
"grad_norm": 0.4306788146495819,
"learning_rate": 2e-05,
"loss": 0.8481,
"step": 2410
},
{
"epoch": 0.2017675504418876,
"grad_norm": 0.4344717562198639,
"learning_rate": 2e-05,
"loss": 0.8361,
"step": 2420
},
{
"epoch": 0.20260130065032517,
"grad_norm": 0.4240482747554779,
"learning_rate": 2e-05,
"loss": 0.8419,
"step": 2430
},
{
"epoch": 0.2034350508587627,
"grad_norm": 0.43387749791145325,
"learning_rate": 2e-05,
"loss": 0.8388,
"step": 2440
},
{
"epoch": 0.20426880106720027,
"grad_norm": 0.42623400688171387,
"learning_rate": 2e-05,
"loss": 0.8509,
"step": 2450
},
{
"epoch": 0.2051025512756378,
"grad_norm": 0.42098426818847656,
"learning_rate": 2e-05,
"loss": 0.8254,
"step": 2460
},
{
"epoch": 0.20593630148407538,
"grad_norm": 0.4316154420375824,
"learning_rate": 2e-05,
"loss": 0.836,
"step": 2470
},
{
"epoch": 0.20677005169251292,
"grad_norm": 0.43836063146591187,
"learning_rate": 2e-05,
"loss": 0.8161,
"step": 2480
},
{
"epoch": 0.20760380190095049,
"grad_norm": 0.4331987202167511,
"learning_rate": 2e-05,
"loss": 0.8358,
"step": 2490
},
{
"epoch": 0.20843755210938802,
"grad_norm": 0.43718579411506653,
"learning_rate": 2e-05,
"loss": 0.8002,
"step": 2500
},
{
"epoch": 0.2092713023178256,
"grad_norm": 0.42872241139411926,
"learning_rate": 2e-05,
"loss": 0.8273,
"step": 2510
},
{
"epoch": 0.21010505252626313,
"grad_norm": 0.4349031448364258,
"learning_rate": 2e-05,
"loss": 0.8494,
"step": 2520
},
{
"epoch": 0.21093880273470067,
"grad_norm": 0.4240064322948456,
"learning_rate": 2e-05,
"loss": 0.7908,
"step": 2530
},
{
"epoch": 0.21177255294313824,
"grad_norm": 0.4284305274486542,
"learning_rate": 2e-05,
"loss": 0.838,
"step": 2540
},
{
"epoch": 0.21260630315157578,
"grad_norm": 0.44868648052215576,
"learning_rate": 2e-05,
"loss": 0.8282,
"step": 2550
},
{
"epoch": 0.21344005336001334,
"grad_norm": 0.4279681444168091,
"learning_rate": 2e-05,
"loss": 0.7917,
"step": 2560
},
{
"epoch": 0.21427380356845088,
"grad_norm": 0.43642657995224,
"learning_rate": 2e-05,
"loss": 0.8473,
"step": 2570
},
{
"epoch": 0.21510755377688845,
"grad_norm": 0.4385351538658142,
"learning_rate": 2e-05,
"loss": 0.799,
"step": 2580
},
{
"epoch": 0.215941303985326,
"grad_norm": 0.42047759890556335,
"learning_rate": 2e-05,
"loss": 0.8383,
"step": 2590
},
{
"epoch": 0.21677505419376356,
"grad_norm": 0.42801105976104736,
"learning_rate": 2e-05,
"loss": 0.8172,
"step": 2600
},
{
"epoch": 0.2176088044022011,
"grad_norm": 0.44474488496780396,
"learning_rate": 2e-05,
"loss": 0.846,
"step": 2610
},
{
"epoch": 0.21844255461063866,
"grad_norm": 0.4707760512828827,
"learning_rate": 2e-05,
"loss": 0.8341,
"step": 2620
},
{
"epoch": 0.2192763048190762,
"grad_norm": 0.45037761330604553,
"learning_rate": 2e-05,
"loss": 0.8213,
"step": 2630
},
{
"epoch": 0.22011005502751377,
"grad_norm": 0.42427247762680054,
"learning_rate": 2e-05,
"loss": 0.7758,
"step": 2640
},
{
"epoch": 0.2209438052359513,
"grad_norm": 0.42834150791168213,
"learning_rate": 2e-05,
"loss": 0.8356,
"step": 2650
},
{
"epoch": 0.22177755544438887,
"grad_norm": 0.44776657223701477,
"learning_rate": 2e-05,
"loss": 0.8138,
"step": 2660
},
{
"epoch": 0.2226113056528264,
"grad_norm": 0.43263503909111023,
"learning_rate": 2e-05,
"loss": 0.8536,
"step": 2670
},
{
"epoch": 0.22344505586126395,
"grad_norm": 0.4363694489002228,
"learning_rate": 2e-05,
"loss": 0.8267,
"step": 2680
},
{
"epoch": 0.22427880606970152,
"grad_norm": 0.4155452251434326,
"learning_rate": 2e-05,
"loss": 0.8212,
"step": 2690
},
{
"epoch": 0.22511255627813906,
"grad_norm": 0.43567293882369995,
"learning_rate": 2e-05,
"loss": 0.8007,
"step": 2700
},
{
"epoch": 0.22594630648657663,
"grad_norm": 0.41281309723854065,
"learning_rate": 2e-05,
"loss": 0.8288,
"step": 2710
},
{
"epoch": 0.22678005669501416,
"grad_norm": 0.42122575640678406,
"learning_rate": 2e-05,
"loss": 0.846,
"step": 2720
},
{
"epoch": 0.22761380690345173,
"grad_norm": 0.41850346326828003,
"learning_rate": 2e-05,
"loss": 0.8045,
"step": 2730
},
{
"epoch": 0.22844755711188927,
"grad_norm": 0.4028671979904175,
"learning_rate": 2e-05,
"loss": 0.8108,
"step": 2740
},
{
"epoch": 0.22928130732032684,
"grad_norm": 0.7664421796798706,
"learning_rate": 2e-05,
"loss": 0.819,
"step": 2750
},
{
"epoch": 0.23011505752876438,
"grad_norm": 0.42035794258117676,
"learning_rate": 2e-05,
"loss": 0.82,
"step": 2760
},
{
"epoch": 0.23094880773720194,
"grad_norm": 0.42169997096061707,
"learning_rate": 2e-05,
"loss": 0.8185,
"step": 2770
},
{
"epoch": 0.23178255794563948,
"grad_norm": 0.4262278974056244,
"learning_rate": 2e-05,
"loss": 0.7964,
"step": 2780
},
{
"epoch": 0.23261630815407705,
"grad_norm": 0.40541335940361023,
"learning_rate": 2e-05,
"loss": 0.8198,
"step": 2790
},
{
"epoch": 0.2334500583625146,
"grad_norm": 0.4138868749141693,
"learning_rate": 2e-05,
"loss": 0.8052,
"step": 2800
},
{
"epoch": 0.23428380857095213,
"grad_norm": 0.4195197522640228,
"learning_rate": 2e-05,
"loss": 0.8637,
"step": 2810
},
{
"epoch": 0.2351175587793897,
"grad_norm": 0.4476122260093689,
"learning_rate": 2e-05,
"loss": 0.8224,
"step": 2820
},
{
"epoch": 0.23595130898782724,
"grad_norm": 0.4849603772163391,
"learning_rate": 2e-05,
"loss": 0.8139,
"step": 2830
},
{
"epoch": 0.2367850591962648,
"grad_norm": 0.4237458407878876,
"learning_rate": 2e-05,
"loss": 0.7895,
"step": 2840
},
{
"epoch": 0.23761880940470234,
"grad_norm": 0.42281076312065125,
"learning_rate": 2e-05,
"loss": 0.8041,
"step": 2850
},
{
"epoch": 0.2384525596131399,
"grad_norm": 0.4377175569534302,
"learning_rate": 2e-05,
"loss": 0.8244,
"step": 2860
},
{
"epoch": 0.23928630982157745,
"grad_norm": 0.40337878465652466,
"learning_rate": 2e-05,
"loss": 0.7897,
"step": 2870
},
{
"epoch": 0.24012006003001501,
"grad_norm": 0.4314129948616028,
"learning_rate": 2e-05,
"loss": 0.8608,
"step": 2880
},
{
"epoch": 0.24095381023845255,
"grad_norm": 0.4147445261478424,
"learning_rate": 2e-05,
"loss": 0.7804,
"step": 2890
},
{
"epoch": 0.24178756044689012,
"grad_norm": 0.41954874992370605,
"learning_rate": 2e-05,
"loss": 0.8237,
"step": 2900
},
{
"epoch": 0.24262131065532766,
"grad_norm": 0.4387779235839844,
"learning_rate": 2e-05,
"loss": 0.812,
"step": 2910
},
{
"epoch": 0.24345506086376523,
"grad_norm": 0.41750842332839966,
"learning_rate": 2e-05,
"loss": 0.8328,
"step": 2920
},
{
"epoch": 0.24428881107220277,
"grad_norm": 0.41714218258857727,
"learning_rate": 2e-05,
"loss": 0.8223,
"step": 2930
},
{
"epoch": 0.24512256128064033,
"grad_norm": 0.3931734263896942,
"learning_rate": 2e-05,
"loss": 0.8135,
"step": 2940
},
{
"epoch": 0.24595631148907787,
"grad_norm": 0.4289018213748932,
"learning_rate": 2e-05,
"loss": 0.8309,
"step": 2950
},
{
"epoch": 0.2467900616975154,
"grad_norm": 0.4370642900466919,
"learning_rate": 2e-05,
"loss": 0.816,
"step": 2960
},
{
"epoch": 0.24762381190595298,
"grad_norm": 0.4377880096435547,
"learning_rate": 2e-05,
"loss": 0.8186,
"step": 2970
},
{
"epoch": 0.24845756211439052,
"grad_norm": 0.4115336835384369,
"learning_rate": 2e-05,
"loss": 0.8148,
"step": 2980
},
{
"epoch": 0.24929131232282808,
"grad_norm": 0.8987250328063965,
"learning_rate": 2e-05,
"loss": 0.8527,
"step": 2990
},
{
"epoch": 0.25012506253126565,
"grad_norm": 0.44562411308288574,
"learning_rate": 2e-05,
"loss": 0.8018,
"step": 3000
},
{
"epoch": 0.25095881273970316,
"grad_norm": 0.4264613389968872,
"learning_rate": 2e-05,
"loss": 0.8095,
"step": 3010
},
{
"epoch": 0.25179256294814073,
"grad_norm": 0.5419912338256836,
"learning_rate": 2e-05,
"loss": 0.8268,
"step": 3020
},
{
"epoch": 0.2526263131565783,
"grad_norm": 0.4279841184616089,
"learning_rate": 2e-05,
"loss": 0.8033,
"step": 3030
},
{
"epoch": 0.25346006336501586,
"grad_norm": 0.4485812783241272,
"learning_rate": 2e-05,
"loss": 0.8474,
"step": 3040
},
{
"epoch": 0.2542938135734534,
"grad_norm": 0.44027024507522583,
"learning_rate": 2e-05,
"loss": 0.8239,
"step": 3050
},
{
"epoch": 0.25512756378189094,
"grad_norm": 0.41620147228240967,
"learning_rate": 2e-05,
"loss": 0.7959,
"step": 3060
},
{
"epoch": 0.2559613139903285,
"grad_norm": 0.4188208281993866,
"learning_rate": 2e-05,
"loss": 0.8071,
"step": 3070
},
{
"epoch": 0.2567950641987661,
"grad_norm": 0.4468199610710144,
"learning_rate": 2e-05,
"loss": 0.8024,
"step": 3080
},
{
"epoch": 0.2576288144072036,
"grad_norm": 0.41432344913482666,
"learning_rate": 2e-05,
"loss": 0.8322,
"step": 3090
},
{
"epoch": 0.25846256461564115,
"grad_norm": 0.5648444890975952,
"learning_rate": 2e-05,
"loss": 0.8143,
"step": 3100
},
{
"epoch": 0.2592963148240787,
"grad_norm": 0.40376046299934387,
"learning_rate": 2e-05,
"loss": 0.8087,
"step": 3110
},
{
"epoch": 0.26013006503251623,
"grad_norm": 0.4495043158531189,
"learning_rate": 2e-05,
"loss": 0.8386,
"step": 3120
},
{
"epoch": 0.2609638152409538,
"grad_norm": 0.44088467955589294,
"learning_rate": 2e-05,
"loss": 0.8364,
"step": 3130
},
{
"epoch": 0.26179756544939137,
"grad_norm": 0.4208716154098511,
"learning_rate": 2e-05,
"loss": 0.8017,
"step": 3140
},
{
"epoch": 0.26263131565782893,
"grad_norm": 0.4128001034259796,
"learning_rate": 2e-05,
"loss": 0.802,
"step": 3150
},
{
"epoch": 0.26346506586626645,
"grad_norm": 0.4371351897716522,
"learning_rate": 2e-05,
"loss": 0.8327,
"step": 3160
},
{
"epoch": 0.264298816074704,
"grad_norm": 0.45394638180732727,
"learning_rate": 2e-05,
"loss": 0.8203,
"step": 3170
},
{
"epoch": 0.2651325662831416,
"grad_norm": 0.3899805545806885,
"learning_rate": 2e-05,
"loss": 0.8305,
"step": 3180
},
{
"epoch": 0.26596631649157915,
"grad_norm": 0.4152947664260864,
"learning_rate": 2e-05,
"loss": 0.8574,
"step": 3190
},
{
"epoch": 0.26680006670001666,
"grad_norm": 0.4249829649925232,
"learning_rate": 2e-05,
"loss": 0.8,
"step": 3200
},
{
"epoch": 0.2676338169084542,
"grad_norm": 0.43881216645240784,
"learning_rate": 2e-05,
"loss": 0.8335,
"step": 3210
},
{
"epoch": 0.2684675671168918,
"grad_norm": 0.4557602107524872,
"learning_rate": 2e-05,
"loss": 0.7953,
"step": 3220
},
{
"epoch": 0.26930131732532936,
"grad_norm": 0.4189995527267456,
"learning_rate": 2e-05,
"loss": 0.7893,
"step": 3230
},
{
"epoch": 0.27013506753376687,
"grad_norm": 0.4260282814502716,
"learning_rate": 2e-05,
"loss": 0.8279,
"step": 3240
},
{
"epoch": 0.27096881774220444,
"grad_norm": 0.41926705837249756,
"learning_rate": 2e-05,
"loss": 0.8458,
"step": 3250
},
{
"epoch": 0.271802567950642,
"grad_norm": 0.5304961204528809,
"learning_rate": 2e-05,
"loss": 0.8286,
"step": 3260
},
{
"epoch": 0.2726363181590795,
"grad_norm": 0.4510481655597687,
"learning_rate": 2e-05,
"loss": 0.8013,
"step": 3270
},
{
"epoch": 0.2734700683675171,
"grad_norm": 0.41141632199287415,
"learning_rate": 2e-05,
"loss": 0.8222,
"step": 3280
},
{
"epoch": 0.27430381857595465,
"grad_norm": 0.4243338704109192,
"learning_rate": 2e-05,
"loss": 0.789,
"step": 3290
},
{
"epoch": 0.2751375687843922,
"grad_norm": 0.4182097315788269,
"learning_rate": 2e-05,
"loss": 0.8332,
"step": 3300
},
{
"epoch": 0.27597131899282973,
"grad_norm": 0.41882482171058655,
"learning_rate": 2e-05,
"loss": 0.7694,
"step": 3310
},
{
"epoch": 0.2768050692012673,
"grad_norm": 0.43145978450775146,
"learning_rate": 2e-05,
"loss": 0.8111,
"step": 3320
},
{
"epoch": 0.27763881940970486,
"grad_norm": 0.42188000679016113,
"learning_rate": 2e-05,
"loss": 0.82,
"step": 3330
},
{
"epoch": 0.27847256961814243,
"grad_norm": 1.5640748739242554,
"learning_rate": 2e-05,
"loss": 0.8658,
"step": 3340
},
{
"epoch": 0.27930631982657994,
"grad_norm": 0.4104529023170471,
"learning_rate": 2e-05,
"loss": 0.8065,
"step": 3350
},
{
"epoch": 0.2801400700350175,
"grad_norm": 0.41686469316482544,
"learning_rate": 2e-05,
"loss": 0.8328,
"step": 3360
},
{
"epoch": 0.2809738202434551,
"grad_norm": 0.4163873791694641,
"learning_rate": 2e-05,
"loss": 0.7863,
"step": 3370
},
{
"epoch": 0.2818075704518926,
"grad_norm": 0.4275286793708801,
"learning_rate": 2e-05,
"loss": 0.8215,
"step": 3380
},
{
"epoch": 0.28264132066033015,
"grad_norm": 0.4476993978023529,
"learning_rate": 2e-05,
"loss": 0.8086,
"step": 3390
},
{
"epoch": 0.2834750708687677,
"grad_norm": 0.42699599266052246,
"learning_rate": 2e-05,
"loss": 0.8503,
"step": 3400
},
{
"epoch": 0.2843088210772053,
"grad_norm": 0.6670398712158203,
"learning_rate": 2e-05,
"loss": 0.8284,
"step": 3410
},
{
"epoch": 0.2851425712856428,
"grad_norm": 0.4280049800872803,
"learning_rate": 2e-05,
"loss": 0.8214,
"step": 3420
},
{
"epoch": 0.28597632149408037,
"grad_norm": 0.4108944237232208,
"learning_rate": 2e-05,
"loss": 0.8071,
"step": 3430
},
{
"epoch": 0.28681007170251793,
"grad_norm": 0.43111374974250793,
"learning_rate": 2e-05,
"loss": 0.8154,
"step": 3440
},
{
"epoch": 0.2876438219109555,
"grad_norm": 0.4291673004627228,
"learning_rate": 2e-05,
"loss": 0.8129,
"step": 3450
},
{
"epoch": 0.288477572119393,
"grad_norm": 0.4143984913825989,
"learning_rate": 2e-05,
"loss": 0.8222,
"step": 3460
},
{
"epoch": 0.2893113223278306,
"grad_norm": 0.3991544842720032,
"learning_rate": 2e-05,
"loss": 0.8178,
"step": 3470
},
{
"epoch": 0.29014507253626814,
"grad_norm": 0.4332132339477539,
"learning_rate": 2e-05,
"loss": 0.8298,
"step": 3480
},
{
"epoch": 0.2909788227447057,
"grad_norm": 0.40459883213043213,
"learning_rate": 2e-05,
"loss": 0.8057,
"step": 3490
},
{
"epoch": 0.2918125729531432,
"grad_norm": 0.4890405535697937,
"learning_rate": 2e-05,
"loss": 0.8296,
"step": 3500
},
{
"epoch": 0.2926463231615808,
"grad_norm": 0.40339693427085876,
"learning_rate": 2e-05,
"loss": 0.8195,
"step": 3510
},
{
"epoch": 0.29348007337001836,
"grad_norm": 0.41147148609161377,
"learning_rate": 2e-05,
"loss": 0.8057,
"step": 3520
},
{
"epoch": 0.29431382357845587,
"grad_norm": 0.44654861092567444,
"learning_rate": 2e-05,
"loss": 0.819,
"step": 3530
},
{
"epoch": 0.29514757378689344,
"grad_norm": 0.3993259370326996,
"learning_rate": 2e-05,
"loss": 0.8049,
"step": 3540
},
{
"epoch": 0.295981323995331,
"grad_norm": 0.4208177924156189,
"learning_rate": 2e-05,
"loss": 0.7985,
"step": 3550
},
{
"epoch": 0.29681507420376857,
"grad_norm": 0.4575837254524231,
"learning_rate": 2e-05,
"loss": 0.8348,
"step": 3560
},
{
"epoch": 0.2976488244122061,
"grad_norm": 0.4357958734035492,
"learning_rate": 2e-05,
"loss": 0.8059,
"step": 3570
},
{
"epoch": 0.29848257462064365,
"grad_norm": 0.3863260746002197,
"learning_rate": 2e-05,
"loss": 0.8167,
"step": 3580
},
{
"epoch": 0.2993163248290812,
"grad_norm": 0.4312741160392761,
"learning_rate": 2e-05,
"loss": 0.8176,
"step": 3590
},
{
"epoch": 0.3001500750375188,
"grad_norm": 0.3873898684978485,
"learning_rate": 2e-05,
"loss": 0.8151,
"step": 3600
},
{
"epoch": 0.3009838252459563,
"grad_norm": 0.39404091238975525,
"learning_rate": 2e-05,
"loss": 0.7637,
"step": 3610
},
{
"epoch": 0.30181757545439386,
"grad_norm": 0.42365387082099915,
"learning_rate": 2e-05,
"loss": 0.7999,
"step": 3620
},
{
"epoch": 0.3026513256628314,
"grad_norm": 0.44868624210357666,
"learning_rate": 2e-05,
"loss": 0.8334,
"step": 3630
},
{
"epoch": 0.303485075871269,
"grad_norm": 0.40937134623527527,
"learning_rate": 2e-05,
"loss": 0.8103,
"step": 3640
},
{
"epoch": 0.3043188260797065,
"grad_norm": 0.39073848724365234,
"learning_rate": 2e-05,
"loss": 0.7997,
"step": 3650
},
{
"epoch": 0.3051525762881441,
"grad_norm": 0.41548940539360046,
"learning_rate": 2e-05,
"loss": 0.8499,
"step": 3660
},
{
"epoch": 0.30598632649658164,
"grad_norm": 0.4142826795578003,
"learning_rate": 2e-05,
"loss": 0.794,
"step": 3670
},
{
"epoch": 0.30682007670501915,
"grad_norm": 0.40233612060546875,
"learning_rate": 2e-05,
"loss": 0.8047,
"step": 3680
},
{
"epoch": 0.3076538269134567,
"grad_norm": 0.4200495779514313,
"learning_rate": 2e-05,
"loss": 0.8153,
"step": 3690
},
{
"epoch": 0.3084875771218943,
"grad_norm": 0.40950807929039,
"learning_rate": 2e-05,
"loss": 0.8166,
"step": 3700
},
{
"epoch": 0.30932132733033185,
"grad_norm": 0.41378214955329895,
"learning_rate": 2e-05,
"loss": 0.7738,
"step": 3710
},
{
"epoch": 0.31015507753876936,
"grad_norm": 0.4448857307434082,
"learning_rate": 2e-05,
"loss": 0.7823,
"step": 3720
},
{
"epoch": 0.31098882774720693,
"grad_norm": 0.4356268346309662,
"learning_rate": 2e-05,
"loss": 0.84,
"step": 3730
},
{
"epoch": 0.3118225779556445,
"grad_norm": 0.41766834259033203,
"learning_rate": 2e-05,
"loss": 0.8024,
"step": 3740
},
{
"epoch": 0.31265632816408206,
"grad_norm": 0.41468915343284607,
"learning_rate": 2e-05,
"loss": 0.7987,
"step": 3750
},
{
"epoch": 0.3134900783725196,
"grad_norm": 0.4448278844356537,
"learning_rate": 2e-05,
"loss": 0.8245,
"step": 3760
},
{
"epoch": 0.31432382858095714,
"grad_norm": 0.5258402824401855,
"learning_rate": 2e-05,
"loss": 0.8146,
"step": 3770
},
{
"epoch": 0.3151575787893947,
"grad_norm": 0.3887770175933838,
"learning_rate": 2e-05,
"loss": 0.8234,
"step": 3780
},
{
"epoch": 0.3159913289978323,
"grad_norm": 0.4393872320652008,
"learning_rate": 2e-05,
"loss": 0.8034,
"step": 3790
},
{
"epoch": 0.3168250792062698,
"grad_norm": 0.4026564955711365,
"learning_rate": 2e-05,
"loss": 0.7712,
"step": 3800
},
{
"epoch": 0.31765882941470736,
"grad_norm": 0.44776251912117004,
"learning_rate": 2e-05,
"loss": 0.8117,
"step": 3810
},
{
"epoch": 0.3184925796231449,
"grad_norm": 0.42479491233825684,
"learning_rate": 2e-05,
"loss": 0.7879,
"step": 3820
},
{
"epoch": 0.31932632983158243,
"grad_norm": 0.39487627148628235,
"learning_rate": 2e-05,
"loss": 0.7889,
"step": 3830
},
{
"epoch": 0.32016008004002,
"grad_norm": 0.45354771614074707,
"learning_rate": 2e-05,
"loss": 0.8065,
"step": 3840
},
{
"epoch": 0.32099383024845757,
"grad_norm": 0.41155821084976196,
"learning_rate": 2e-05,
"loss": 0.798,
"step": 3850
},
{
"epoch": 0.32182758045689513,
"grad_norm": 0.3985389769077301,
"learning_rate": 2e-05,
"loss": 0.804,
"step": 3860
},
{
"epoch": 0.32266133066533265,
"grad_norm": 0.4311758875846863,
"learning_rate": 2e-05,
"loss": 0.7741,
"step": 3870
},
{
"epoch": 0.3234950808737702,
"grad_norm": 0.45199352502822876,
"learning_rate": 2e-05,
"loss": 0.829,
"step": 3880
},
{
"epoch": 0.3243288310822078,
"grad_norm": 0.4198897182941437,
"learning_rate": 2e-05,
"loss": 0.8175,
"step": 3890
},
{
"epoch": 0.32516258129064535,
"grad_norm": 0.40902382135391235,
"learning_rate": 2e-05,
"loss": 0.7979,
"step": 3900
},
{
"epoch": 0.32599633149908286,
"grad_norm": 0.4060145616531372,
"learning_rate": 2e-05,
"loss": 0.8076,
"step": 3910
},
{
"epoch": 0.3268300817075204,
"grad_norm": 0.4076564610004425,
"learning_rate": 2e-05,
"loss": 0.7875,
"step": 3920
},
{
"epoch": 0.327663831915958,
"grad_norm": 0.4184042513370514,
"learning_rate": 2e-05,
"loss": 0.8031,
"step": 3930
},
{
"epoch": 0.3284975821243955,
"grad_norm": 0.40736356377601624,
"learning_rate": 2e-05,
"loss": 0.8302,
"step": 3940
},
{
"epoch": 0.32933133233283307,
"grad_norm": 0.4287526607513428,
"learning_rate": 2e-05,
"loss": 0.8292,
"step": 3950
},
{
"epoch": 0.33016508254127064,
"grad_norm": 0.42028382420539856,
"learning_rate": 2e-05,
"loss": 0.8529,
"step": 3960
},
{
"epoch": 0.3309988327497082,
"grad_norm": 0.43208184838294983,
"learning_rate": 2e-05,
"loss": 0.7999,
"step": 3970
},
{
"epoch": 0.3318325829581457,
"grad_norm": 0.4172027111053467,
"learning_rate": 2e-05,
"loss": 0.8075,
"step": 3980
},
{
"epoch": 0.3326663331665833,
"grad_norm": 0.5087682604789734,
"learning_rate": 2e-05,
"loss": 0.8211,
"step": 3990
},
{
"epoch": 0.33350008337502085,
"grad_norm": 0.4194720387458801,
"learning_rate": 2e-05,
"loss": 0.7951,
"step": 4000
},
{
"epoch": 0.3343338335834584,
"grad_norm": 0.40966758131980896,
"learning_rate": 2e-05,
"loss": 0.7612,
"step": 4010
},
{
"epoch": 0.33516758379189593,
"grad_norm": 0.4449123442173004,
"learning_rate": 2e-05,
"loss": 0.8368,
"step": 4020
},
{
"epoch": 0.3360013340003335,
"grad_norm": 0.43533018231391907,
"learning_rate": 2e-05,
"loss": 0.7813,
"step": 4030
},
{
"epoch": 0.33683508420877106,
"grad_norm": 0.424989253282547,
"learning_rate": 2e-05,
"loss": 0.8334,
"step": 4040
},
{
"epoch": 0.33766883441720863,
"grad_norm": 0.40560266375541687,
"learning_rate": 2e-05,
"loss": 0.8012,
"step": 4050
},
{
"epoch": 0.33850258462564614,
"grad_norm": 0.44729718565940857,
"learning_rate": 2e-05,
"loss": 0.7949,
"step": 4060
},
{
"epoch": 0.3393363348340837,
"grad_norm": 0.4175632894039154,
"learning_rate": 2e-05,
"loss": 0.7527,
"step": 4070
},
{
"epoch": 0.3401700850425213,
"grad_norm": 0.4429507851600647,
"learning_rate": 2e-05,
"loss": 0.8266,
"step": 4080
},
{
"epoch": 0.3410038352509588,
"grad_norm": 0.4307044446468353,
"learning_rate": 2e-05,
"loss": 0.8095,
"step": 4090
},
{
"epoch": 0.34183758545939635,
"grad_norm": 0.3998664915561676,
"learning_rate": 2e-05,
"loss": 0.8023,
"step": 4100
},
{
"epoch": 0.3426713356678339,
"grad_norm": 0.41406020522117615,
"learning_rate": 2e-05,
"loss": 0.81,
"step": 4110
},
{
"epoch": 0.3435050858762715,
"grad_norm": 0.4210001826286316,
"learning_rate": 2e-05,
"loss": 0.8162,
"step": 4120
},
{
"epoch": 0.344338836084709,
"grad_norm": 0.4319205582141876,
"learning_rate": 2e-05,
"loss": 0.8229,
"step": 4130
},
{
"epoch": 0.34517258629314657,
"grad_norm": 0.39437636733055115,
"learning_rate": 2e-05,
"loss": 0.7749,
"step": 4140
},
{
"epoch": 0.34600633650158413,
"grad_norm": 0.42068132758140564,
"learning_rate": 2e-05,
"loss": 0.8135,
"step": 4150
},
{
"epoch": 0.3468400867100217,
"grad_norm": 0.37786853313446045,
"learning_rate": 2e-05,
"loss": 0.8126,
"step": 4160
},
{
"epoch": 0.3476738369184592,
"grad_norm": 0.4334181547164917,
"learning_rate": 2e-05,
"loss": 0.8131,
"step": 4170
},
{
"epoch": 0.3485075871268968,
"grad_norm": 0.42665985226631165,
"learning_rate": 2e-05,
"loss": 0.8107,
"step": 4180
},
{
"epoch": 0.34934133733533435,
"grad_norm": 0.4009602963924408,
"learning_rate": 2e-05,
"loss": 0.7691,
"step": 4190
},
{
"epoch": 0.3501750875437719,
"grad_norm": 0.40056467056274414,
"learning_rate": 2e-05,
"loss": 0.8098,
"step": 4200
},
{
"epoch": 0.3510088377522094,
"grad_norm": 0.38842320442199707,
"learning_rate": 2e-05,
"loss": 0.7859,
"step": 4210
},
{
"epoch": 0.351842587960647,
"grad_norm": 0.4109112322330475,
"learning_rate": 2e-05,
"loss": 0.7934,
"step": 4220
},
{
"epoch": 0.35267633816908456,
"grad_norm": 0.43121665716171265,
"learning_rate": 2e-05,
"loss": 0.7934,
"step": 4230
},
{
"epoch": 0.35351008837752207,
"grad_norm": 0.4145316481590271,
"learning_rate": 2e-05,
"loss": 0.7859,
"step": 4240
},
{
"epoch": 0.35434383858595964,
"grad_norm": 0.4063599407672882,
"learning_rate": 2e-05,
"loss": 0.8002,
"step": 4250
},
{
"epoch": 0.3551775887943972,
"grad_norm": 0.41173651814460754,
"learning_rate": 2e-05,
"loss": 0.7831,
"step": 4260
},
{
"epoch": 0.35601133900283477,
"grad_norm": 0.5056709051132202,
"learning_rate": 2e-05,
"loss": 0.8065,
"step": 4270
},
{
"epoch": 0.3568450892112723,
"grad_norm": 0.40177083015441895,
"learning_rate": 2e-05,
"loss": 0.7979,
"step": 4280
},
{
"epoch": 0.35767883941970985,
"grad_norm": 0.419994980096817,
"learning_rate": 2e-05,
"loss": 0.8124,
"step": 4290
},
{
"epoch": 0.3585125896281474,
"grad_norm": 0.4538871943950653,
"learning_rate": 2e-05,
"loss": 0.8096,
"step": 4300
},
{
"epoch": 0.359346339836585,
"grad_norm": 0.42847737669944763,
"learning_rate": 2e-05,
"loss": 0.8158,
"step": 4310
},
{
"epoch": 0.3601800900450225,
"grad_norm": 0.42587223649024963,
"learning_rate": 2e-05,
"loss": 0.782,
"step": 4320
},
{
"epoch": 0.36101384025346006,
"grad_norm": 0.37175020575523376,
"learning_rate": 2e-05,
"loss": 0.7799,
"step": 4330
},
{
"epoch": 0.36184759046189763,
"grad_norm": 0.4170229732990265,
"learning_rate": 2e-05,
"loss": 0.8076,
"step": 4340
},
{
"epoch": 0.3626813406703352,
"grad_norm": 0.41324084997177124,
"learning_rate": 2e-05,
"loss": 0.8046,
"step": 4350
},
{
"epoch": 0.3635150908787727,
"grad_norm": 0.41819754242897034,
"learning_rate": 2e-05,
"loss": 0.8051,
"step": 4360
},
{
"epoch": 0.3643488410872103,
"grad_norm": 0.40531429648399353,
"learning_rate": 2e-05,
"loss": 0.7843,
"step": 4370
},
{
"epoch": 0.36518259129564784,
"grad_norm": 0.421154648065567,
"learning_rate": 2e-05,
"loss": 0.8061,
"step": 4380
},
{
"epoch": 0.36601634150408535,
"grad_norm": 0.5506669282913208,
"learning_rate": 2e-05,
"loss": 0.8335,
"step": 4390
},
{
"epoch": 0.3668500917125229,
"grad_norm": 0.42062658071517944,
"learning_rate": 2e-05,
"loss": 0.7924,
"step": 4400
},
{
"epoch": 0.3676838419209605,
"grad_norm": 0.4221999943256378,
"learning_rate": 2e-05,
"loss": 0.7886,
"step": 4410
},
{
"epoch": 0.36851759212939805,
"grad_norm": 0.4072527289390564,
"learning_rate": 2e-05,
"loss": 0.7991,
"step": 4420
},
{
"epoch": 0.36935134233783556,
"grad_norm": 0.41719478368759155,
"learning_rate": 2e-05,
"loss": 0.7963,
"step": 4430
},
{
"epoch": 0.37018509254627313,
"grad_norm": 0.4121597111225128,
"learning_rate": 2e-05,
"loss": 0.8007,
"step": 4440
},
{
"epoch": 0.3710188427547107,
"grad_norm": 0.409883052110672,
"learning_rate": 2e-05,
"loss": 0.7888,
"step": 4450
},
{
"epoch": 0.37185259296314827,
"grad_norm": 0.42768505215644836,
"learning_rate": 2e-05,
"loss": 0.779,
"step": 4460
},
{
"epoch": 0.3726863431715858,
"grad_norm": 0.41129279136657715,
"learning_rate": 2e-05,
"loss": 0.8126,
"step": 4470
},
{
"epoch": 0.37352009338002334,
"grad_norm": 0.38922542333602905,
"learning_rate": 2e-05,
"loss": 0.7817,
"step": 4480
},
{
"epoch": 0.3743538435884609,
"grad_norm": 0.4301270842552185,
"learning_rate": 2e-05,
"loss": 0.7869,
"step": 4490
},
{
"epoch": 0.3751875937968984,
"grad_norm": 0.3859865069389343,
"learning_rate": 2e-05,
"loss": 0.7882,
"step": 4500
},
{
"epoch": 0.376021344005336,
"grad_norm": 0.3825930655002594,
"learning_rate": 2e-05,
"loss": 0.8151,
"step": 4510
},
{
"epoch": 0.37685509421377356,
"grad_norm": 0.44355669617652893,
"learning_rate": 2e-05,
"loss": 0.7992,
"step": 4520
},
{
"epoch": 0.3776888444222111,
"grad_norm": 0.3892509639263153,
"learning_rate": 2e-05,
"loss": 0.8019,
"step": 4530
},
{
"epoch": 0.37852259463064863,
"grad_norm": 0.39480897784233093,
"learning_rate": 2e-05,
"loss": 0.7835,
"step": 4540
},
{
"epoch": 0.3793563448390862,
"grad_norm": 0.4017105996608734,
"learning_rate": 2e-05,
"loss": 0.7968,
"step": 4550
},
{
"epoch": 0.38019009504752377,
"grad_norm": 0.4092944860458374,
"learning_rate": 2e-05,
"loss": 0.8003,
"step": 4560
},
{
"epoch": 0.38102384525596134,
"grad_norm": 0.5043903589248657,
"learning_rate": 2e-05,
"loss": 0.7906,
"step": 4570
},
{
"epoch": 0.38185759546439885,
"grad_norm": 0.41720426082611084,
"learning_rate": 2e-05,
"loss": 0.8031,
"step": 4580
},
{
"epoch": 0.3826913456728364,
"grad_norm": 0.4069463014602661,
"learning_rate": 2e-05,
"loss": 0.7942,
"step": 4590
},
{
"epoch": 0.383525095881274,
"grad_norm": 0.4088110327720642,
"learning_rate": 2e-05,
"loss": 0.7842,
"step": 4600
},
{
"epoch": 0.38435884608971155,
"grad_norm": 0.42584243416786194,
"learning_rate": 2e-05,
"loss": 0.7752,
"step": 4610
},
{
"epoch": 0.38519259629814906,
"grad_norm": 0.4071617126464844,
"learning_rate": 2e-05,
"loss": 0.802,
"step": 4620
},
{
"epoch": 0.3860263465065866,
"grad_norm": 0.42505118250846863,
"learning_rate": 2e-05,
"loss": 0.8447,
"step": 4630
},
{
"epoch": 0.3868600967150242,
"grad_norm": 0.4184128940105438,
"learning_rate": 2e-05,
"loss": 0.8024,
"step": 4640
},
{
"epoch": 0.3876938469234617,
"grad_norm": 0.4117748439311981,
"learning_rate": 2e-05,
"loss": 0.7946,
"step": 4650
},
{
"epoch": 0.38852759713189927,
"grad_norm": 0.6045395135879517,
"learning_rate": 2e-05,
"loss": 0.7753,
"step": 4660
},
{
"epoch": 0.38936134734033684,
"grad_norm": 0.4164401590824127,
"learning_rate": 2e-05,
"loss": 0.7964,
"step": 4670
},
{
"epoch": 0.3901950975487744,
"grad_norm": 0.42233720421791077,
"learning_rate": 2e-05,
"loss": 0.8034,
"step": 4680
},
{
"epoch": 0.3910288477572119,
"grad_norm": 0.420411616563797,
"learning_rate": 2e-05,
"loss": 0.7758,
"step": 4690
},
{
"epoch": 0.3918625979656495,
"grad_norm": 0.4246000349521637,
"learning_rate": 2e-05,
"loss": 0.7691,
"step": 4700
},
{
"epoch": 0.39269634817408705,
"grad_norm": 0.3850994408130646,
"learning_rate": 2e-05,
"loss": 0.8001,
"step": 4710
},
{
"epoch": 0.3935300983825246,
"grad_norm": 0.4714173674583435,
"learning_rate": 2e-05,
"loss": 0.7937,
"step": 4720
},
{
"epoch": 0.39436384859096213,
"grad_norm": 0.46886536478996277,
"learning_rate": 2e-05,
"loss": 0.7873,
"step": 4730
},
{
"epoch": 0.3951975987993997,
"grad_norm": 0.39866867661476135,
"learning_rate": 2e-05,
"loss": 0.7996,
"step": 4740
},
{
"epoch": 0.39603134900783726,
"grad_norm": 0.4189933240413666,
"learning_rate": 2e-05,
"loss": 0.7955,
"step": 4750
},
{
"epoch": 0.39686509921627483,
"grad_norm": 0.4220077097415924,
"learning_rate": 2e-05,
"loss": 0.7877,
"step": 4760
},
{
"epoch": 0.39769884942471234,
"grad_norm": 0.4490271806716919,
"learning_rate": 2e-05,
"loss": 0.7971,
"step": 4770
},
{
"epoch": 0.3985325996331499,
"grad_norm": 0.41312161087989807,
"learning_rate": 2e-05,
"loss": 0.7998,
"step": 4780
},
{
"epoch": 0.3993663498415875,
"grad_norm": 0.43245819211006165,
"learning_rate": 2e-05,
"loss": 0.7894,
"step": 4790
},
{
"epoch": 0.400200100050025,
"grad_norm": 0.41577789187431335,
"learning_rate": 2e-05,
"loss": 0.7741,
"step": 4800
},
{
"epoch": 0.40103385025846255,
"grad_norm": 0.4054262042045593,
"learning_rate": 2e-05,
"loss": 0.7886,
"step": 4810
},
{
"epoch": 0.4018676004669001,
"grad_norm": 0.3879670798778534,
"learning_rate": 2e-05,
"loss": 0.7934,
"step": 4820
},
{
"epoch": 0.4027013506753377,
"grad_norm": 0.4422363340854645,
"learning_rate": 2e-05,
"loss": 0.805,
"step": 4830
},
{
"epoch": 0.4035351008837752,
"grad_norm": 0.40869560837745667,
"learning_rate": 2e-05,
"loss": 0.829,
"step": 4840
},
{
"epoch": 0.40436885109221277,
"grad_norm": 0.4227999746799469,
"learning_rate": 2e-05,
"loss": 0.8118,
"step": 4850
},
{
"epoch": 0.40520260130065033,
"grad_norm": 0.388187974691391,
"learning_rate": 2e-05,
"loss": 0.7899,
"step": 4860
},
{
"epoch": 0.4060363515090879,
"grad_norm": 0.4188007116317749,
"learning_rate": 2e-05,
"loss": 0.7863,
"step": 4870
},
{
"epoch": 0.4068701017175254,
"grad_norm": 0.39539822936058044,
"learning_rate": 2e-05,
"loss": 0.8058,
"step": 4880
},
{
"epoch": 0.407703851925963,
"grad_norm": 0.45797550678253174,
"learning_rate": 2e-05,
"loss": 0.7806,
"step": 4890
},
{
"epoch": 0.40853760213440055,
"grad_norm": 0.4156181812286377,
"learning_rate": 2e-05,
"loss": 0.7985,
"step": 4900
},
{
"epoch": 0.4093713523428381,
"grad_norm": 0.41822877526283264,
"learning_rate": 2e-05,
"loss": 0.8097,
"step": 4910
},
{
"epoch": 0.4102051025512756,
"grad_norm": 0.4561269283294678,
"learning_rate": 2e-05,
"loss": 0.8211,
"step": 4920
},
{
"epoch": 0.4110388527597132,
"grad_norm": 0.4573151171207428,
"learning_rate": 2e-05,
"loss": 0.7814,
"step": 4930
},
{
"epoch": 0.41187260296815076,
"grad_norm": 0.3992522358894348,
"learning_rate": 2e-05,
"loss": 0.7733,
"step": 4940
},
{
"epoch": 0.41270635317658827,
"grad_norm": 0.4074111580848694,
"learning_rate": 2e-05,
"loss": 0.7974,
"step": 4950
},
{
"epoch": 0.41354010338502584,
"grad_norm": 0.4169853925704956,
"learning_rate": 2e-05,
"loss": 0.7795,
"step": 4960
},
{
"epoch": 0.4143738535934634,
"grad_norm": 0.3988161087036133,
"learning_rate": 2e-05,
"loss": 0.7951,
"step": 4970
},
{
"epoch": 0.41520760380190097,
"grad_norm": 0.47434523701667786,
"learning_rate": 2e-05,
"loss": 0.7893,
"step": 4980
},
{
"epoch": 0.4160413540103385,
"grad_norm": 0.4816352427005768,
"learning_rate": 2e-05,
"loss": 0.8012,
"step": 4990
},
{
"epoch": 0.41687510421877605,
"grad_norm": 0.4109174609184265,
"learning_rate": 2e-05,
"loss": 0.7851,
"step": 5000
},
{
"epoch": 0.4177088544272136,
"grad_norm": 0.414851576089859,
"learning_rate": 2e-05,
"loss": 0.7948,
"step": 5010
},
{
"epoch": 0.4185426046356512,
"grad_norm": 0.4128541350364685,
"learning_rate": 2e-05,
"loss": 0.8287,
"step": 5020
},
{
"epoch": 0.4193763548440887,
"grad_norm": 0.4099479615688324,
"learning_rate": 2e-05,
"loss": 0.8114,
"step": 5030
},
{
"epoch": 0.42021010505252626,
"grad_norm": 0.3901870548725128,
"learning_rate": 2e-05,
"loss": 0.7929,
"step": 5040
},
{
"epoch": 0.42104385526096383,
"grad_norm": 0.3896540105342865,
"learning_rate": 2e-05,
"loss": 0.787,
"step": 5050
},
{
"epoch": 0.42187760546940134,
"grad_norm": 0.40145042538642883,
"learning_rate": 2e-05,
"loss": 0.7749,
"step": 5060
},
{
"epoch": 0.4227113556778389,
"grad_norm": 0.4008077085018158,
"learning_rate": 2e-05,
"loss": 0.7757,
"step": 5070
},
{
"epoch": 0.4235451058862765,
"grad_norm": 0.4295864701271057,
"learning_rate": 2e-05,
"loss": 0.7852,
"step": 5080
},
{
"epoch": 0.42437885609471404,
"grad_norm": 0.4775094985961914,
"learning_rate": 1.9999810479633703e-05,
"loss": 0.7607,
"step": 5090
},
{
"epoch": 0.42521260630315155,
"grad_norm": 0.40330934524536133,
"learning_rate": 1.997707677020786e-05,
"loss": 0.7472,
"step": 5100
},
{
"epoch": 0.4260463565115891,
"grad_norm": 0.40920719504356384,
"learning_rate": 1.9916538196124637e-05,
"loss": 0.7866,
"step": 5110
},
{
"epoch": 0.4268801067200267,
"grad_norm": 0.4409664571285248,
"learning_rate": 1.9818425303863402e-05,
"loss": 0.8046,
"step": 5120
},
{
"epoch": 0.42771385692846425,
"grad_norm": 0.4337279796600342,
"learning_rate": 1.9683111732582887e-05,
"loss": 0.7605,
"step": 5130
},
{
"epoch": 0.42854760713690176,
"grad_norm": 0.4220025837421417,
"learning_rate": 1.951111279120706e-05,
"loss": 0.8061,
"step": 5140
},
{
"epoch": 0.42938135734533933,
"grad_norm": 0.4126664102077484,
"learning_rate": 1.9303083495996028e-05,
"loss": 0.7973,
"step": 5150
},
{
"epoch": 0.4302151075537769,
"grad_norm": 0.39226582646369934,
"learning_rate": 1.9059816076075482e-05,
"loss": 0.7748,
"step": 5160
},
{
"epoch": 0.43104885776221447,
"grad_norm": 0.43882039189338684,
"learning_rate": 1.8782236956424142e-05,
"loss": 0.8029,
"step": 5170
},
{
"epoch": 0.431882607970652,
"grad_norm": 0.3844985365867615,
"learning_rate": 1.8471403229808897e-05,
"loss": 0.8002,
"step": 5180
},
{
"epoch": 0.43271635817908954,
"grad_norm": 0.42616450786590576,
"learning_rate": 1.8128498631103333e-05,
"loss": 0.817,
"step": 5190
},
{
"epoch": 0.4335501083875271,
"grad_norm": 0.41214361786842346,
"learning_rate": 1.7754829029320507e-05,
"loss": 0.7944,
"step": 5200
},
{
"epoch": 0.4343838585959646,
"grad_norm": 0.5948476195335388,
"learning_rate": 1.7351817454527473e-05,
"loss": 0.8135,
"step": 5210
},
{
"epoch": 0.4352176088044022,
"grad_norm": 0.5493759512901306,
"learning_rate": 1.6920998678580345e-05,
"loss": 0.8289,
"step": 5220
},
{
"epoch": 0.43605135901283976,
"grad_norm": 0.4823123514652252,
"learning_rate": 1.6464013370317854e-05,
"loss": 0.7966,
"step": 5230
},
{
"epoch": 0.4368851092212773,
"grad_norm": 0.4415777027606964,
"learning_rate": 1.5982601847471915e-05,
"loss": 0.7589,
"step": 5240
},
{
"epoch": 0.43771885942971483,
"grad_norm": 0.44551271200180054,
"learning_rate": 1.5478597449089553e-05,
"loss": 0.8122,
"step": 5250
},
{
"epoch": 0.4385526096381524,
"grad_norm": 0.3945777714252472,
"learning_rate": 1.4953919553705725e-05,
"loss": 0.7946,
"step": 5260
},
{
"epoch": 0.43938635984658997,
"grad_norm": 0.3924645781517029,
"learning_rate": 1.441056626985559e-05,
"loss": 0.7818,
"step": 5270
},
{
"epoch": 0.44022011005502754,
"grad_norm": 0.4626287519931793,
"learning_rate": 1.3850606826762668e-05,
"loss": 0.7971,
"step": 5280
},
{
"epoch": 0.44105386026346505,
"grad_norm": 0.41017770767211914,
"learning_rate": 1.3276173694181128e-05,
"loss": 0.7843,
"step": 5290
},
{
"epoch": 0.4418876104719026,
"grad_norm": 0.40494775772094727,
"learning_rate": 1.2689454461401822e-05,
"loss": 0.7998,
"step": 5300
},
{
"epoch": 0.4427213606803402,
"grad_norm": 0.412063330411911,
"learning_rate": 1.2092683506348939e-05,
"loss": 0.7861,
"step": 5310
},
{
"epoch": 0.44355511088877775,
"grad_norm": 0.44939616322517395,
"learning_rate": 1.14881334864935e-05,
"loss": 0.7927,
"step": 5320
},
{
"epoch": 0.44438886109721526,
"grad_norm": 0.4089047610759735,
"learning_rate": 1.0878106683988481e-05,
"loss": 0.7698,
"step": 5330
},
{
"epoch": 0.4452226113056528,
"grad_norm": 0.41851571202278137,
"learning_rate": 1.026492623798551e-05,
"loss": 0.7719,
"step": 5340
},
{
"epoch": 0.4460563615140904,
"grad_norm": 0.40026187896728516,
"learning_rate": 9.650927297522743e-06,
"loss": 0.7653,
"step": 5350
},
{
"epoch": 0.4468901117225279,
"grad_norm": 0.4251845180988312,
"learning_rate": 9.038448128676012e-06,
"loss": 0.7853,
"step": 5360
},
{
"epoch": 0.44772386193096547,
"grad_norm": 0.38127291202545166,
"learning_rate": 8.42982120983949e-06,
"loss": 0.7725,
"step": 5370
},
{
"epoch": 0.44855761213940304,
"grad_norm": 0.4067787230014801,
"learning_rate": 7.827364349047303e-06,
"loss": 0.7864,
"step": 5380
},
{
"epoch": 0.4493913623478406,
"grad_norm": 0.432085245847702,
"learning_rate": 7.233371857163706e-06,
"loss": 0.7802,
"step": 5390
},
{
"epoch": 0.4502251125562781,
"grad_norm": 0.3860446810722351,
"learning_rate": 6.650105810556492e-06,
"loss": 0.7656,
"step": 5400
},
{
"epoch": 0.4510588627647157,
"grad_norm": 0.37864622473716736,
"learning_rate": 6.079787436527681e-06,
"loss": 0.7651,
"step": 5410
},
{
"epoch": 0.45189261297315325,
"grad_norm": 0.40164732933044434,
"learning_rate": 5.524588654307961e-06,
"loss": 0.7804,
"step": 5420
},
{
"epoch": 0.4527263631815908,
"grad_norm": 0.41856294870376587,
"learning_rate": 4.986623803828985e-06,
"loss": 0.7931,
"step": 5430
},
{
"epoch": 0.45356011339002833,
"grad_norm": 0.3843195140361786,
"learning_rate": 4.467941593772423e-06,
"loss": 0.7592,
"step": 5440
},
{
"epoch": 0.4543938635984659,
"grad_norm": 0.38011473417282104,
"learning_rate": 3.9705172995597606e-06,
"loss": 0.7721,
"step": 5450
},
{
"epoch": 0.45522761380690346,
"grad_norm": 0.3981033265590668,
"learning_rate": 3.4962452409948346e-06,
"loss": 0.778,
"step": 5460
},
{
"epoch": 0.45606136401534103,
"grad_norm": 0.4012771546840668,
"learning_rate": 3.046931568206211e-06,
"loss": 0.7325,
"step": 5470
},
{
"epoch": 0.45689511422377854,
"grad_norm": 0.38696593046188354,
"learning_rate": 2.624287383362404e-06,
"loss": 0.7703,
"step": 5480
},
{
"epoch": 0.4577288644322161,
"grad_norm": 0.43060189485549927,
"learning_rate": 2.2299222243541845e-06,
"loss": 0.7613,
"step": 5490
},
{
"epoch": 0.4585626146406537,
"grad_norm": 0.5072455406188965,
"learning_rate": 1.8653379352598246e-06,
"loss": 0.7491,
"step": 5500
},
{
"epoch": 0.4593963648490912,
"grad_norm": 0.38514477014541626,
"learning_rate": 1.5319229469361075e-06,
"loss": 0.7685,
"step": 5510
},
{
"epoch": 0.46023011505752875,
"grad_norm": 0.3709384500980377,
"learning_rate": 1.2309469895160917e-06,
"loss": 0.7863,
"step": 5520
},
{
"epoch": 0.4610638652659663,
"grad_norm": 0.38419803977012634,
"learning_rate": 9.635562569497974e-07,
"loss": 0.7591,
"step": 5530
},
{
"epoch": 0.4618976154744039,
"grad_norm": 0.4152466654777527,
"learning_rate": 7.307690420024867e-07,
"loss": 0.7783,
"step": 5540
},
{
"epoch": 0.4627313656828414,
"grad_norm": 0.38992732763290405,
"learning_rate": 5.334718583335942e-07,
"loss": 0.7792,
"step": 5550
},
{
"epoch": 0.46356511589127897,
"grad_norm": 0.3993775248527527,
"learning_rate": 3.7241606442442763e-07,
"loss": 0.7646,
"step": 5560
},
{
"epoch": 0.46439886609971653,
"grad_norm": 0.523891031742096,
"learning_rate": 2.482150022115879e-07,
"loss": 0.7886,
"step": 5570
},
{
"epoch": 0.4652326163081541,
"grad_norm": 0.3977406620979309,
"learning_rate": 1.6134166132293174e-07,
"loss": 0.7656,
"step": 5580
},
{
"epoch": 0.4660663665165916,
"grad_norm": 0.41963762044906616,
"learning_rate": 1.1212687781127357e-07,
"loss": 0.76,
"step": 5590
},
{
"epoch": 0.46664999166249793,
"step": 5597,
"total_flos": 2.2737574718397743e+19,
"train_loss": 0.026235760802432045,
"train_runtime": 1805.4939,
"train_samples_per_second": 37.2,
"train_steps_per_second": 3.1
}
],
"logging_steps": 10,
"max_steps": 5597,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 159,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 2.2737574718397743e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.46664999166249793,
"eval_steps": 500,
"global_step": 5597,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0008337502084375521,
"grad_norm": 13.566391944885254,
"learning_rate": 1.1061797752808989e-06,
"loss": 2.2566,
"step": 10
},
{
"epoch": 0.0016675004168751042,
"grad_norm": 2.918423652648926,
"learning_rate": 2.2241573033707866e-06,
"loss": 2.04,
"step": 20
},
{
"epoch": 0.0025012506253126563,
"grad_norm": 3.1750669479370117,
"learning_rate": 3.342134831460675e-06,
"loss": 1.8853,
"step": 30
},
{
"epoch": 0.0033350008337502085,
"grad_norm": 1.5451328754425049,
"learning_rate": 4.4601123595505624e-06,
"loss": 1.482,
"step": 40
},
{
"epoch": 0.00416875104218776,
"grad_norm": 0.9934996366500854,
"learning_rate": 5.5780898876404495e-06,
"loss": 1.232,
"step": 50
},
{
"epoch": 0.0050025012506253125,
"grad_norm": 0.6822673082351685,
"learning_rate": 6.6960674157303374e-06,
"loss": 1.1003,
"step": 60
},
{
"epoch": 0.005836251459062865,
"grad_norm": 0.8204601407051086,
"learning_rate": 7.814044943820226e-06,
"loss": 1.0664,
"step": 70
},
{
"epoch": 0.006670001667500417,
"grad_norm": 0.5949751734733582,
"learning_rate": 8.932022471910112e-06,
"loss": 1.0583,
"step": 80
},
{
"epoch": 0.007503751875937969,
"grad_norm": 0.6005659103393555,
"learning_rate": 1.005e-05,
"loss": 0.9972,
"step": 90
},
{
"epoch": 0.00833750208437552,
"grad_norm": 0.5980632305145264,
"learning_rate": 1.1167977528089888e-05,
"loss": 0.9785,
"step": 100
},
{
"epoch": 0.009171252292813074,
"grad_norm": 0.5540244579315186,
"learning_rate": 1.2285955056179776e-05,
"loss": 1.0015,
"step": 110
},
{
"epoch": 0.010005002501250625,
"grad_norm": 0.593195378780365,
"learning_rate": 1.3403932584269664e-05,
"loss": 0.9758,
"step": 120
},
{
"epoch": 0.010838752709688178,
"grad_norm": 0.583214282989502,
"learning_rate": 1.4521910112359552e-05,
"loss": 0.9762,