{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9332999833249959,
"eval_steps": 500,
"global_step": 11194,
"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": 0.47911542654037476,
"learning_rate": 2e-05,
"loss": 0.7934,
"step": 5090
},
{
"epoch": 0.42521260630315155,
"grad_norm": 0.4033006429672241,
"learning_rate": 2e-05,
"loss": 0.7473,
"step": 5100
},
{
"epoch": 0.4260463565115891,
"grad_norm": 0.42802944779396057,
"learning_rate": 2e-05,
"loss": 0.7866,
"step": 5110
},
{
"epoch": 0.4268801067200267,
"grad_norm": 0.452494353055954,
"learning_rate": 2e-05,
"loss": 0.8045,
"step": 5120
},
{
"epoch": 0.42771385692846425,
"grad_norm": 0.4347948133945465,
"learning_rate": 2e-05,
"loss": 0.7606,
"step": 5130
},
{
"epoch": 0.42854760713690176,
"grad_norm": 0.42910927534103394,
"learning_rate": 2e-05,
"loss": 0.8063,
"step": 5140
},
{
"epoch": 0.42938135734533933,
"grad_norm": 0.5524507164955139,
"learning_rate": 2e-05,
"loss": 0.7975,
"step": 5150
},
{
"epoch": 0.4302151075537769,
"grad_norm": 0.3964111804962158,
"learning_rate": 2e-05,
"loss": 0.7754,
"step": 5160
},
{
"epoch": 0.43104885776221447,
"grad_norm": 0.43679943680763245,
"learning_rate": 2e-05,
"loss": 0.8034,
"step": 5170
},
{
"epoch": 0.431882607970652,
"grad_norm": 0.3903455436229706,
"learning_rate": 2e-05,
"loss": 0.8009,
"step": 5180
},
{
"epoch": 0.43271635817908954,
"grad_norm": 0.43742433190345764,
"learning_rate": 2e-05,
"loss": 0.8179,
"step": 5190
},
{
"epoch": 0.4335501083875271,
"grad_norm": 0.41472327709198,
"learning_rate": 2e-05,
"loss": 0.7955,
"step": 5200
},
{
"epoch": 0.4343838585959646,
"grad_norm": 0.6227070093154907,
"learning_rate": 2e-05,
"loss": 0.815,
"step": 5210
},
{
"epoch": 0.4352176088044022,
"grad_norm": 0.5606524348258972,
"learning_rate": 2e-05,
"loss": 0.8309,
"step": 5220
},
{
"epoch": 0.43605135901283976,
"grad_norm": 0.4135671854019165,
"learning_rate": 2e-05,
"loss": 0.8005,
"step": 5230
},
{
"epoch": 0.4368851092212773,
"grad_norm": 0.5373715162277222,
"learning_rate": 2e-05,
"loss": 0.7633,
"step": 5240
},
{
"epoch": 0.43771885942971483,
"grad_norm": 0.4400574862957001,
"learning_rate": 2e-05,
"loss": 0.8088,
"step": 5250
},
{
"epoch": 0.4385526096381524,
"grad_norm": 0.41376492381095886,
"learning_rate": 2e-05,
"loss": 0.7985,
"step": 5260
},
{
"epoch": 0.43938635984658997,
"grad_norm": 0.40862569212913513,
"learning_rate": 2e-05,
"loss": 0.7859,
"step": 5270
},
{
"epoch": 0.44022011005502754,
"grad_norm": 0.4316557049751282,
"learning_rate": 2e-05,
"loss": 0.8021,
"step": 5280
},
{
"epoch": 0.44105386026346505,
"grad_norm": 0.4101763367652893,
"learning_rate": 2e-05,
"loss": 0.7897,
"step": 5290
},
{
"epoch": 0.4418876104719026,
"grad_norm": 0.404323935508728,
"learning_rate": 2e-05,
"loss": 0.8058,
"step": 5300
},
{
"epoch": 0.4427213606803402,
"grad_norm": 0.43842482566833496,
"learning_rate": 2e-05,
"loss": 0.793,
"step": 5310
},
{
"epoch": 0.44355511088877775,
"grad_norm": 0.4295407235622406,
"learning_rate": 2e-05,
"loss": 0.7999,
"step": 5320
},
{
"epoch": 0.44438886109721526,
"grad_norm": 0.4546605348587036,
"learning_rate": 2e-05,
"loss": 0.7772,
"step": 5330
},
{
"epoch": 0.4452226113056528,
"grad_norm": 0.4212942123413086,
"learning_rate": 2e-05,
"loss": 0.7801,
"step": 5340
},
{
"epoch": 0.4460563615140904,
"grad_norm": 0.4185762405395508,
"learning_rate": 2e-05,
"loss": 0.7741,
"step": 5350
},
{
"epoch": 0.4468901117225279,
"grad_norm": 0.4719997048377991,
"learning_rate": 2e-05,
"loss": 0.7947,
"step": 5360
},
{
"epoch": 0.44772386193096547,
"grad_norm": 0.5614922642707825,
"learning_rate": 2e-05,
"loss": 0.7827,
"step": 5370
},
{
"epoch": 0.44855761213940304,
"grad_norm": 0.4626639187335968,
"learning_rate": 2e-05,
"loss": 0.7971,
"step": 5380
},
{
"epoch": 0.4493913623478406,
"grad_norm": 0.4505312740802765,
"learning_rate": 2e-05,
"loss": 0.7924,
"step": 5390
},
{
"epoch": 0.4502251125562781,
"grad_norm": 0.3994363844394684,
"learning_rate": 2e-05,
"loss": 0.779,
"step": 5400
},
{
"epoch": 0.4510588627647157,
"grad_norm": 0.3769174814224243,
"learning_rate": 2e-05,
"loss": 0.7853,
"step": 5410
},
{
"epoch": 0.45189261297315325,
"grad_norm": 0.4131431579589844,
"learning_rate": 2e-05,
"loss": 0.7934,
"step": 5420
},
{
"epoch": 0.4527263631815908,
"grad_norm": 0.4416811466217041,
"learning_rate": 2e-05,
"loss": 0.8067,
"step": 5430
},
{
"epoch": 0.45356011339002833,
"grad_norm": 0.40425044298171997,
"learning_rate": 2e-05,
"loss": 0.773,
"step": 5440
},
{
"epoch": 0.4543938635984659,
"grad_norm": 0.4026804566383362,
"learning_rate": 2e-05,
"loss": 0.7861,
"step": 5450
},
{
"epoch": 0.45522761380690346,
"grad_norm": 0.4136134088039398,
"learning_rate": 2e-05,
"loss": 0.7933,
"step": 5460
},
{
"epoch": 0.45606136401534103,
"grad_norm": 0.4038483798503876,
"learning_rate": 2e-05,
"loss": 0.7472,
"step": 5470
},
{
"epoch": 0.45689511422377854,
"grad_norm": 0.39567315578460693,
"learning_rate": 2e-05,
"loss": 0.7864,
"step": 5480
},
{
"epoch": 0.4577288644322161,
"grad_norm": 0.44948914647102356,
"learning_rate": 2e-05,
"loss": 0.7761,
"step": 5490
},
{
"epoch": 0.4585626146406537,
"grad_norm": 0.42369818687438965,
"learning_rate": 2e-05,
"loss": 0.7641,
"step": 5500
},
{
"epoch": 0.4593963648490912,
"grad_norm": 0.39824309945106506,
"learning_rate": 2e-05,
"loss": 0.7837,
"step": 5510
},
{
"epoch": 0.46023011505752875,
"grad_norm": 0.3905493915081024,
"learning_rate": 2e-05,
"loss": 0.8032,
"step": 5520
},
{
"epoch": 0.4610638652659663,
"grad_norm": 0.388814777135849,
"learning_rate": 2e-05,
"loss": 0.7754,
"step": 5530
},
{
"epoch": 0.4618976154744039,
"grad_norm": 0.42113202810287476,
"learning_rate": 2e-05,
"loss": 0.795,
"step": 5540
},
{
"epoch": 0.4627313656828414,
"grad_norm": 0.4102492332458496,
"learning_rate": 2e-05,
"loss": 0.7961,
"step": 5550
},
{
"epoch": 0.46356511589127897,
"grad_norm": 0.40997153520584106,
"learning_rate": 2e-05,
"loss": 0.7809,
"step": 5560
},
{
"epoch": 0.46439886609971653,
"grad_norm": 0.40787893533706665,
"learning_rate": 2e-05,
"loss": 0.771,
"step": 5570
},
{
"epoch": 0.4652326163081541,
"grad_norm": 0.4189698100090027,
"learning_rate": 2e-05,
"loss": 0.7818,
"step": 5580
},
{
"epoch": 0.4660663665165916,
"grad_norm": 0.4524160921573639,
"learning_rate": 2e-05,
"loss": 0.7759,
"step": 5590
},
{
"epoch": 0.4669001167250292,
"grad_norm": 0.4109547734260559,
"learning_rate": 2e-05,
"loss": 0.8025,
"step": 5600
},
{
"epoch": 0.46773386693346675,
"grad_norm": 0.4016934335231781,
"learning_rate": 2e-05,
"loss": 0.7813,
"step": 5610
},
{
"epoch": 0.46856761714190426,
"grad_norm": 0.4350648820400238,
"learning_rate": 2e-05,
"loss": 0.8168,
"step": 5620
},
{
"epoch": 0.4694013673503418,
"grad_norm": 0.3932511508464813,
"learning_rate": 2e-05,
"loss": 0.7952,
"step": 5630
},
{
"epoch": 0.4702351175587794,
"grad_norm": 0.38617587089538574,
"learning_rate": 2e-05,
"loss": 0.7983,
"step": 5640
},
{
"epoch": 0.47106886776721696,
"grad_norm": 0.4121549129486084,
"learning_rate": 2e-05,
"loss": 0.7672,
"step": 5650
},
{
"epoch": 0.47190261797565447,
"grad_norm": 0.4078139364719391,
"learning_rate": 2e-05,
"loss": 0.7732,
"step": 5660
},
{
"epoch": 0.47273636818409204,
"grad_norm": 0.4189227223396301,
"learning_rate": 2e-05,
"loss": 0.7747,
"step": 5670
},
{
"epoch": 0.4735701183925296,
"grad_norm": 0.39790332317352295,
"learning_rate": 2e-05,
"loss": 0.7501,
"step": 5680
},
{
"epoch": 0.47440386860096717,
"grad_norm": 0.3974267542362213,
"learning_rate": 2e-05,
"loss": 0.7785,
"step": 5690
},
{
"epoch": 0.4752376188094047,
"grad_norm": 0.3946145474910736,
"learning_rate": 2e-05,
"loss": 0.7749,
"step": 5700
},
{
"epoch": 0.47607136901784225,
"grad_norm": 0.3835632801055908,
"learning_rate": 2e-05,
"loss": 0.7647,
"step": 5710
},
{
"epoch": 0.4769051192262798,
"grad_norm": 0.4180067181587219,
"learning_rate": 2e-05,
"loss": 0.8052,
"step": 5720
},
{
"epoch": 0.4777388694347174,
"grad_norm": 0.503718376159668,
"learning_rate": 2e-05,
"loss": 0.7995,
"step": 5730
},
{
"epoch": 0.4785726196431549,
"grad_norm": 0.41256046295166016,
"learning_rate": 2e-05,
"loss": 0.7979,
"step": 5740
},
{
"epoch": 0.47940636985159246,
"grad_norm": 0.4121564030647278,
"learning_rate": 2e-05,
"loss": 0.7661,
"step": 5750
},
{
"epoch": 0.48024012006003003,
"grad_norm": 0.4072965681552887,
"learning_rate": 2e-05,
"loss": 0.8446,
"step": 5760
},
{
"epoch": 0.48107387026846754,
"grad_norm": 0.4055275022983551,
"learning_rate": 2e-05,
"loss": 0.7638,
"step": 5770
},
{
"epoch": 0.4819076204769051,
"grad_norm": 0.4475768804550171,
"learning_rate": 2e-05,
"loss": 0.7823,
"step": 5780
},
{
"epoch": 0.4827413706853427,
"grad_norm": 0.4159134328365326,
"learning_rate": 2e-05,
"loss": 0.7706,
"step": 5790
},
{
"epoch": 0.48357512089378024,
"grad_norm": 0.4165635406970978,
"learning_rate": 2e-05,
"loss": 0.7926,
"step": 5800
},
{
"epoch": 0.48440887110221775,
"grad_norm": 0.4256076514720917,
"learning_rate": 2e-05,
"loss": 0.776,
"step": 5810
},
{
"epoch": 0.4852426213106553,
"grad_norm": 0.41048702597618103,
"learning_rate": 2e-05,
"loss": 0.7775,
"step": 5820
},
{
"epoch": 0.4860763715190929,
"grad_norm": 0.46386033296585083,
"learning_rate": 2e-05,
"loss": 0.7938,
"step": 5830
},
{
"epoch": 0.48691012172753045,
"grad_norm": 0.40575647354125977,
"learning_rate": 2e-05,
"loss": 0.7745,
"step": 5840
},
{
"epoch": 0.48774387193596797,
"grad_norm": 0.39695030450820923,
"learning_rate": 2e-05,
"loss": 0.759,
"step": 5850
},
{
"epoch": 0.48857762214440553,
"grad_norm": 0.4182072579860687,
"learning_rate": 2e-05,
"loss": 0.7762,
"step": 5860
},
{
"epoch": 0.4894113723528431,
"grad_norm": 0.4042046368122101,
"learning_rate": 2e-05,
"loss": 0.8089,
"step": 5870
},
{
"epoch": 0.49024512256128067,
"grad_norm": 0.3909963369369507,
"learning_rate": 2e-05,
"loss": 0.78,
"step": 5880
},
{
"epoch": 0.4910788727697182,
"grad_norm": 0.43016335368156433,
"learning_rate": 2e-05,
"loss": 0.8178,
"step": 5890
},
{
"epoch": 0.49191262297815574,
"grad_norm": 0.4051538407802582,
"learning_rate": 2e-05,
"loss": 0.772,
"step": 5900
},
{
"epoch": 0.4927463731865933,
"grad_norm": 0.4097314774990082,
"learning_rate": 2e-05,
"loss": 0.7838,
"step": 5910
},
{
"epoch": 0.4935801233950308,
"grad_norm": 0.4231036305427551,
"learning_rate": 2e-05,
"loss": 0.7924,
"step": 5920
},
{
"epoch": 0.4944138736034684,
"grad_norm": 0.4163452684879303,
"learning_rate": 2e-05,
"loss": 0.8035,
"step": 5930
},
{
"epoch": 0.49524762381190596,
"grad_norm": 0.46998274326324463,
"learning_rate": 2e-05,
"loss": 0.7745,
"step": 5940
},
{
"epoch": 0.4960813740203435,
"grad_norm": 0.5217966437339783,
"learning_rate": 2e-05,
"loss": 0.8128,
"step": 5950
},
{
"epoch": 0.49691512422878104,
"grad_norm": 0.42332616448402405,
"learning_rate": 2e-05,
"loss": 0.8031,
"step": 5960
},
{
"epoch": 0.4977488744372186,
"grad_norm": 0.41903454065322876,
"learning_rate": 2e-05,
"loss": 0.7913,
"step": 5970
},
{
"epoch": 0.49858262464565617,
"grad_norm": 0.4150305390357971,
"learning_rate": 2e-05,
"loss": 0.7694,
"step": 5980
},
{
"epoch": 0.49941637485409374,
"grad_norm": 0.46674126386642456,
"learning_rate": 2e-05,
"loss": 0.8283,
"step": 5990
},
{
"epoch": 0.5002501250625313,
"grad_norm": 0.3992522954940796,
"learning_rate": 2e-05,
"loss": 0.7909,
"step": 6000
},
{
"epoch": 0.5010838752709689,
"grad_norm": 0.37638530135154724,
"learning_rate": 2e-05,
"loss": 0.7643,
"step": 6010
},
{
"epoch": 0.5019176254794063,
"grad_norm": 0.4354056119918823,
"learning_rate": 2e-05,
"loss": 0.7821,
"step": 6020
},
{
"epoch": 0.5027513756878439,
"grad_norm": 0.3978060185909271,
"learning_rate": 2e-05,
"loss": 0.7742,
"step": 6030
},
{
"epoch": 0.5035851258962815,
"grad_norm": 0.41143733263015747,
"learning_rate": 2e-05,
"loss": 0.795,
"step": 6040
},
{
"epoch": 0.504418876104719,
"grad_norm": 0.38169464468955994,
"learning_rate": 2e-05,
"loss": 0.7705,
"step": 6050
},
{
"epoch": 0.5052526263131566,
"grad_norm": 0.38516098260879517,
"learning_rate": 2e-05,
"loss": 0.7953,
"step": 6060
},
{
"epoch": 0.5060863765215942,
"grad_norm": 0.41435426473617554,
"learning_rate": 2e-05,
"loss": 0.7795,
"step": 6070
},
{
"epoch": 0.5069201267300317,
"grad_norm": 0.3862895965576172,
"learning_rate": 2e-05,
"loss": 0.7784,
"step": 6080
},
{
"epoch": 0.5077538769384692,
"grad_norm": 0.39563676714897156,
"learning_rate": 2e-05,
"loss": 0.7848,
"step": 6090
},
{
"epoch": 0.5085876271469068,
"grad_norm": 0.3923201858997345,
"learning_rate": 2e-05,
"loss": 0.7856,
"step": 6100
},
{
"epoch": 0.5094213773553443,
"grad_norm": 0.41635820269584656,
"learning_rate": 2e-05,
"loss": 0.8165,
"step": 6110
},
{
"epoch": 0.5102551275637819,
"grad_norm": 0.4398491382598877,
"learning_rate": 2e-05,
"loss": 0.817,
"step": 6120
},
{
"epoch": 0.5110888777722195,
"grad_norm": 0.4159484803676605,
"learning_rate": 2e-05,
"loss": 0.7869,
"step": 6130
},
{
"epoch": 0.511922627980657,
"grad_norm": 0.4110637307167053,
"learning_rate": 2e-05,
"loss": 0.7891,
"step": 6140
},
{
"epoch": 0.5127563781890946,
"grad_norm": 0.40139102935791016,
"learning_rate": 2e-05,
"loss": 0.7938,
"step": 6150
},
{
"epoch": 0.5135901283975322,
"grad_norm": 0.42159244418144226,
"learning_rate": 2e-05,
"loss": 0.7774,
"step": 6160
},
{
"epoch": 0.5144238786059696,
"grad_norm": 0.4051986336708069,
"learning_rate": 2e-05,
"loss": 0.7952,
"step": 6170
},
{
"epoch": 0.5152576288144072,
"grad_norm": 0.44463518261909485,
"learning_rate": 2e-05,
"loss": 0.7483,
"step": 6180
},
{
"epoch": 0.5160913790228447,
"grad_norm": 0.3831866979598999,
"learning_rate": 2e-05,
"loss": 0.7623,
"step": 6190
},
{
"epoch": 0.5169251292312823,
"grad_norm": 0.4107586443424225,
"learning_rate": 2e-05,
"loss": 0.8157,
"step": 6200
},
{
"epoch": 0.5177588794397199,
"grad_norm": 0.3954658806324005,
"learning_rate": 2e-05,
"loss": 0.7678,
"step": 6210
},
{
"epoch": 0.5185926296481574,
"grad_norm": 0.3964585065841675,
"learning_rate": 2e-05,
"loss": 0.7703,
"step": 6220
},
{
"epoch": 0.519426379856595,
"grad_norm": 0.43378448486328125,
"learning_rate": 2e-05,
"loss": 0.7783,
"step": 6230
},
{
"epoch": 0.5202601300650325,
"grad_norm": 0.38542866706848145,
"learning_rate": 2e-05,
"loss": 0.7909,
"step": 6240
},
{
"epoch": 0.52109388027347,
"grad_norm": 0.40486159920692444,
"learning_rate": 2e-05,
"loss": 0.7441,
"step": 6250
},
{
"epoch": 0.5219276304819076,
"grad_norm": 0.3821077346801758,
"learning_rate": 2e-05,
"loss": 0.7627,
"step": 6260
},
{
"epoch": 0.5227613806903452,
"grad_norm": 0.4245271384716034,
"learning_rate": 2e-05,
"loss": 0.7658,
"step": 6270
},
{
"epoch": 0.5235951308987827,
"grad_norm": 0.8474158644676208,
"learning_rate": 2e-05,
"loss": 0.8393,
"step": 6280
},
{
"epoch": 0.5244288811072203,
"grad_norm": 0.406863808631897,
"learning_rate": 2e-05,
"loss": 0.7699,
"step": 6290
},
{
"epoch": 0.5252626313156579,
"grad_norm": 0.3992128074169159,
"learning_rate": 2e-05,
"loss": 0.8045,
"step": 6300
},
{
"epoch": 0.5260963815240954,
"grad_norm": 0.3938188850879669,
"learning_rate": 2e-05,
"loss": 0.7602,
"step": 6310
},
{
"epoch": 0.5269301317325329,
"grad_norm": 0.45293235778808594,
"learning_rate": 2e-05,
"loss": 0.7345,
"step": 6320
},
{
"epoch": 0.5277638819409705,
"grad_norm": 0.4538366198539734,
"learning_rate": 2e-05,
"loss": 0.7686,
"step": 6330
},
{
"epoch": 0.528597632149408,
"grad_norm": 0.4216972291469574,
"learning_rate": 2e-05,
"loss": 0.7828,
"step": 6340
},
{
"epoch": 0.5294313823578456,
"grad_norm": 0.45760735869407654,
"learning_rate": 2e-05,
"loss": 0.7924,
"step": 6350
},
{
"epoch": 0.5302651325662832,
"grad_norm": 0.4223119914531708,
"learning_rate": 2e-05,
"loss": 0.8129,
"step": 6360
},
{
"epoch": 0.5310988827747207,
"grad_norm": 0.44574737548828125,
"learning_rate": 2e-05,
"loss": 0.7704,
"step": 6370
},
{
"epoch": 0.5319326329831583,
"grad_norm": 0.397051602602005,
"learning_rate": 2e-05,
"loss": 0.7618,
"step": 6380
},
{
"epoch": 0.5327663831915957,
"grad_norm": 0.4142360985279083,
"learning_rate": 2e-05,
"loss": 0.789,
"step": 6390
},
{
"epoch": 0.5336001334000333,
"grad_norm": 0.4216917157173157,
"learning_rate": 2e-05,
"loss": 0.7801,
"step": 6400
},
{
"epoch": 0.5344338836084709,
"grad_norm": 0.39856645464897156,
"learning_rate": 2e-05,
"loss": 0.7767,
"step": 6410
},
{
"epoch": 0.5352676338169085,
"grad_norm": 0.41065314412117004,
"learning_rate": 2e-05,
"loss": 0.7863,
"step": 6420
},
{
"epoch": 0.536101384025346,
"grad_norm": 0.3866366147994995,
"learning_rate": 2e-05,
"loss": 0.7787,
"step": 6430
},
{
"epoch": 0.5369351342337836,
"grad_norm": 0.395370751619339,
"learning_rate": 2e-05,
"loss": 0.7863,
"step": 6440
},
{
"epoch": 0.5377688844422212,
"grad_norm": 0.4117308557033539,
"learning_rate": 2e-05,
"loss": 0.7969,
"step": 6450
},
{
"epoch": 0.5386026346506587,
"grad_norm": 0.41450411081314087,
"learning_rate": 2e-05,
"loss": 0.7831,
"step": 6460
},
{
"epoch": 0.5394363848590962,
"grad_norm": 0.40903282165527344,
"learning_rate": 2e-05,
"loss": 0.7909,
"step": 6470
},
{
"epoch": 0.5402701350675337,
"grad_norm": 0.40446749329566956,
"learning_rate": 2e-05,
"loss": 0.7924,
"step": 6480
},
{
"epoch": 0.5411038852759713,
"grad_norm": 0.4175577461719513,
"learning_rate": 2e-05,
"loss": 0.7587,
"step": 6490
},
{
"epoch": 0.5419376354844089,
"grad_norm": 0.43813082575798035,
"learning_rate": 2e-05,
"loss": 0.7794,
"step": 6500
},
{
"epoch": 0.5427713856928464,
"grad_norm": 0.362812876701355,
"learning_rate": 2e-05,
"loss": 0.784,
"step": 6510
},
{
"epoch": 0.543605135901284,
"grad_norm": 0.3932299017906189,
"learning_rate": 2e-05,
"loss": 0.7019,
"step": 6520
},
{
"epoch": 0.5444388861097216,
"grad_norm": 0.42082759737968445,
"learning_rate": 2e-05,
"loss": 0.7971,
"step": 6530
},
{
"epoch": 0.545272636318159,
"grad_norm": 0.4175724983215332,
"learning_rate": 2e-05,
"loss": 0.7885,
"step": 6540
},
{
"epoch": 0.5461063865265966,
"grad_norm": 0.4130610227584839,
"learning_rate": 2e-05,
"loss": 0.799,
"step": 6550
},
{
"epoch": 0.5469401367350342,
"grad_norm": 0.40662863850593567,
"learning_rate": 2e-05,
"loss": 0.7571,
"step": 6560
},
{
"epoch": 0.5477738869434717,
"grad_norm": 0.4259992837905884,
"learning_rate": 2e-05,
"loss": 0.774,
"step": 6570
},
{
"epoch": 0.5486076371519093,
"grad_norm": 0.4892905652523041,
"learning_rate": 2e-05,
"loss": 0.7714,
"step": 6580
},
{
"epoch": 0.5494413873603469,
"grad_norm": 0.42849478125572205,
"learning_rate": 2e-05,
"loss": 0.7788,
"step": 6590
},
{
"epoch": 0.5502751375687844,
"grad_norm": 0.3991333842277527,
"learning_rate": 2e-05,
"loss": 0.753,
"step": 6600
},
{
"epoch": 0.5511088877772219,
"grad_norm": 0.3950759172439575,
"learning_rate": 2e-05,
"loss": 0.7556,
"step": 6610
},
{
"epoch": 0.5519426379856595,
"grad_norm": 0.42739591002464294,
"learning_rate": 2e-05,
"loss": 0.7918,
"step": 6620
},
{
"epoch": 0.552776388194097,
"grad_norm": 0.4066850543022156,
"learning_rate": 2e-05,
"loss": 0.7678,
"step": 6630
},
{
"epoch": 0.5536101384025346,
"grad_norm": 0.40471506118774414,
"learning_rate": 2e-05,
"loss": 0.7675,
"step": 6640
},
{
"epoch": 0.5544438886109722,
"grad_norm": 0.416350781917572,
"learning_rate": 2e-05,
"loss": 0.7955,
"step": 6650
},
{
"epoch": 0.5552776388194097,
"grad_norm": 0.42777618765830994,
"learning_rate": 2e-05,
"loss": 0.8162,
"step": 6660
},
{
"epoch": 0.5561113890278473,
"grad_norm": 0.4007209241390228,
"learning_rate": 2e-05,
"loss": 0.7933,
"step": 6670
},
{
"epoch": 0.5569451392362849,
"grad_norm": 0.39440280199050903,
"learning_rate": 2e-05,
"loss": 0.7284,
"step": 6680
},
{
"epoch": 0.5577788894447223,
"grad_norm": 0.42578089237213135,
"learning_rate": 2e-05,
"loss": 0.7488,
"step": 6690
},
{
"epoch": 0.5586126396531599,
"grad_norm": 0.4375176727771759,
"learning_rate": 2e-05,
"loss": 0.7854,
"step": 6700
},
{
"epoch": 0.5594463898615974,
"grad_norm": 0.38993680477142334,
"learning_rate": 2e-05,
"loss": 0.7595,
"step": 6710
},
{
"epoch": 0.560280140070035,
"grad_norm": 0.4152563512325287,
"learning_rate": 2e-05,
"loss": 0.7766,
"step": 6720
},
{
"epoch": 0.5611138902784726,
"grad_norm": 0.4022998511791229,
"learning_rate": 2e-05,
"loss": 0.7111,
"step": 6730
},
{
"epoch": 0.5619476404869101,
"grad_norm": 0.40796366333961487,
"learning_rate": 2e-05,
"loss": 0.7973,
"step": 6740
},
{
"epoch": 0.5627813906953477,
"grad_norm": 0.4141818583011627,
"learning_rate": 2e-05,
"loss": 0.7954,
"step": 6750
},
{
"epoch": 0.5636151409037852,
"grad_norm": 0.41100749373435974,
"learning_rate": 2e-05,
"loss": 0.7688,
"step": 6760
},
{
"epoch": 0.5644488911122227,
"grad_norm": 0.4166804552078247,
"learning_rate": 2e-05,
"loss": 0.8202,
"step": 6770
},
{
"epoch": 0.5652826413206603,
"grad_norm": 0.3732641637325287,
"learning_rate": 2e-05,
"loss": 0.7498,
"step": 6780
},
{
"epoch": 0.5661163915290979,
"grad_norm": 0.40541872382164,
"learning_rate": 2e-05,
"loss": 0.7794,
"step": 6790
},
{
"epoch": 0.5669501417375354,
"grad_norm": 0.43822813034057617,
"learning_rate": 2e-05,
"loss": 0.7368,
"step": 6800
},
{
"epoch": 0.567783891945973,
"grad_norm": 0.38523465394973755,
"learning_rate": 2e-05,
"loss": 0.7932,
"step": 6810
},
{
"epoch": 0.5686176421544106,
"grad_norm": 0.40735623240470886,
"learning_rate": 2e-05,
"loss": 0.7787,
"step": 6820
},
{
"epoch": 0.5694513923628481,
"grad_norm": 0.4032224714756012,
"learning_rate": 2e-05,
"loss": 0.7517,
"step": 6830
},
{
"epoch": 0.5702851425712856,
"grad_norm": 0.4274420440196991,
"learning_rate": 2e-05,
"loss": 0.8193,
"step": 6840
},
{
"epoch": 0.5711188927797232,
"grad_norm": 0.42485517263412476,
"learning_rate": 2e-05,
"loss": 0.7757,
"step": 6850
},
{
"epoch": 0.5719526429881607,
"grad_norm": 0.40125682950019836,
"learning_rate": 2e-05,
"loss": 0.7827,
"step": 6860
},
{
"epoch": 0.5727863931965983,
"grad_norm": 0.3753862977027893,
"learning_rate": 2e-05,
"loss": 0.7599,
"step": 6870
},
{
"epoch": 0.5736201434050359,
"grad_norm": 0.4047851860523224,
"learning_rate": 2e-05,
"loss": 0.769,
"step": 6880
},
{
"epoch": 0.5744538936134734,
"grad_norm": 0.4743858575820923,
"learning_rate": 2e-05,
"loss": 0.7983,
"step": 6890
},
{
"epoch": 0.575287643821911,
"grad_norm": 0.41161036491394043,
"learning_rate": 2e-05,
"loss": 0.7541,
"step": 6900
},
{
"epoch": 0.5761213940303485,
"grad_norm": 0.38420966267585754,
"learning_rate": 2e-05,
"loss": 0.778,
"step": 6910
},
{
"epoch": 0.576955144238786,
"grad_norm": 0.38210660219192505,
"learning_rate": 2e-05,
"loss": 0.7651,
"step": 6920
},
{
"epoch": 0.5777888944472236,
"grad_norm": 0.43036583065986633,
"learning_rate": 2e-05,
"loss": 0.7863,
"step": 6930
},
{
"epoch": 0.5786226446556612,
"grad_norm": 0.39827024936676025,
"learning_rate": 2e-05,
"loss": 0.8041,
"step": 6940
},
{
"epoch": 0.5794563948640987,
"grad_norm": 0.41293787956237793,
"learning_rate": 2e-05,
"loss": 0.7765,
"step": 6950
},
{
"epoch": 0.5802901450725363,
"grad_norm": 0.4139253497123718,
"learning_rate": 2e-05,
"loss": 0.7566,
"step": 6960
},
{
"epoch": 0.5811238952809739,
"grad_norm": 0.4031422436237335,
"learning_rate": 2e-05,
"loss": 0.7632,
"step": 6970
},
{
"epoch": 0.5819576454894114,
"grad_norm": 0.39518383145332336,
"learning_rate": 2e-05,
"loss": 0.759,
"step": 6980
},
{
"epoch": 0.5827913956978489,
"grad_norm": 0.3950090706348419,
"learning_rate": 2e-05,
"loss": 0.7439,
"step": 6990
},
{
"epoch": 0.5836251459062864,
"grad_norm": 0.531944215297699,
"learning_rate": 2e-05,
"loss": 0.7591,
"step": 7000
},
{
"epoch": 0.584458896114724,
"grad_norm": 0.423953115940094,
"learning_rate": 2e-05,
"loss": 0.7967,
"step": 7010
},
{
"epoch": 0.5852926463231616,
"grad_norm": 0.41707277297973633,
"learning_rate": 2e-05,
"loss": 0.785,
"step": 7020
},
{
"epoch": 0.5861263965315991,
"grad_norm": 0.41199740767478943,
"learning_rate": 2e-05,
"loss": 0.7757,
"step": 7030
},
{
"epoch": 0.5869601467400367,
"grad_norm": 0.39054033160209656,
"learning_rate": 2e-05,
"loss": 0.7537,
"step": 7040
},
{
"epoch": 0.5877938969484743,
"grad_norm": 0.3923576772212982,
"learning_rate": 2e-05,
"loss": 0.7949,
"step": 7050
},
{
"epoch": 0.5886276471569117,
"grad_norm": 0.3921205997467041,
"learning_rate": 2e-05,
"loss": 0.7634,
"step": 7060
},
{
"epoch": 0.5894613973653493,
"grad_norm": 0.3942367732524872,
"learning_rate": 2e-05,
"loss": 0.7804,
"step": 7070
},
{
"epoch": 0.5902951475737869,
"grad_norm": 0.589249849319458,
"learning_rate": 2e-05,
"loss": 0.7318,
"step": 7080
},
{
"epoch": 0.5911288977822244,
"grad_norm": 0.4015662670135498,
"learning_rate": 2e-05,
"loss": 0.7369,
"step": 7090
},
{
"epoch": 0.591962647990662,
"grad_norm": 0.37851282954216003,
"learning_rate": 2e-05,
"loss": 0.7616,
"step": 7100
},
{
"epoch": 0.5927963981990996,
"grad_norm": 0.40204712748527527,
"learning_rate": 2e-05,
"loss": 0.771,
"step": 7110
},
{
"epoch": 0.5936301484075371,
"grad_norm": 0.3840367794036865,
"learning_rate": 2e-05,
"loss": 0.7851,
"step": 7120
},
{
"epoch": 0.5944638986159747,
"grad_norm": 0.5389959216117859,
"learning_rate": 2e-05,
"loss": 0.7549,
"step": 7130
},
{
"epoch": 0.5952976488244122,
"grad_norm": 0.42619073390960693,
"learning_rate": 2e-05,
"loss": 0.7724,
"step": 7140
},
{
"epoch": 0.5961313990328497,
"grad_norm": 0.4142972230911255,
"learning_rate": 2e-05,
"loss": 0.8149,
"step": 7150
},
{
"epoch": 0.5969651492412873,
"grad_norm": 0.39575308561325073,
"learning_rate": 2e-05,
"loss": 0.7971,
"step": 7160
},
{
"epoch": 0.5977988994497249,
"grad_norm": 0.38236916065216064,
"learning_rate": 2e-05,
"loss": 0.8188,
"step": 7170
},
{
"epoch": 0.5986326496581624,
"grad_norm": 0.4183010756969452,
"learning_rate": 2e-05,
"loss": 0.7706,
"step": 7180
},
{
"epoch": 0.5994663998666,
"grad_norm": 0.3784348666667938,
"learning_rate": 2e-05,
"loss": 0.7854,
"step": 7190
},
{
"epoch": 0.6003001500750376,
"grad_norm": 0.40792569518089294,
"learning_rate": 2e-05,
"loss": 0.7506,
"step": 7200
},
{
"epoch": 0.601133900283475,
"grad_norm": 0.40807461738586426,
"learning_rate": 2e-05,
"loss": 0.7502,
"step": 7210
},
{
"epoch": 0.6019676504919126,
"grad_norm": 0.4042102098464966,
"learning_rate": 2e-05,
"loss": 0.7527,
"step": 7220
},
{
"epoch": 0.6028014007003502,
"grad_norm": 0.4178937077522278,
"learning_rate": 2e-05,
"loss": 0.7597,
"step": 7230
},
{
"epoch": 0.6036351509087877,
"grad_norm": 0.3911868929862976,
"learning_rate": 2e-05,
"loss": 0.767,
"step": 7240
},
{
"epoch": 0.6044689011172253,
"grad_norm": 0.40752682089805603,
"learning_rate": 2e-05,
"loss": 0.7828,
"step": 7250
},
{
"epoch": 0.6053026513256629,
"grad_norm": 0.40975794196128845,
"learning_rate": 2e-05,
"loss": 0.7792,
"step": 7260
},
{
"epoch": 0.6061364015341004,
"grad_norm": 0.4044291079044342,
"learning_rate": 2e-05,
"loss": 0.721,
"step": 7270
},
{
"epoch": 0.606970151742538,
"grad_norm": 0.3805142641067505,
"learning_rate": 2e-05,
"loss": 0.7537,
"step": 7280
},
{
"epoch": 0.6078039019509754,
"grad_norm": 0.4105410873889923,
"learning_rate": 2e-05,
"loss": 0.7942,
"step": 7290
},
{
"epoch": 0.608637652159413,
"grad_norm": 0.3947274088859558,
"learning_rate": 2e-05,
"loss": 0.753,
"step": 7300
},
{
"epoch": 0.6094714023678506,
"grad_norm": 0.394817978143692,
"learning_rate": 2e-05,
"loss": 0.7493,
"step": 7310
},
{
"epoch": 0.6103051525762881,
"grad_norm": 0.3988485634326935,
"learning_rate": 2e-05,
"loss": 0.7736,
"step": 7320
},
{
"epoch": 0.6111389027847257,
"grad_norm": 0.3918416202068329,
"learning_rate": 2e-05,
"loss": 0.7584,
"step": 7330
},
{
"epoch": 0.6119726529931633,
"grad_norm": 0.4257700443267822,
"learning_rate": 2e-05,
"loss": 0.7721,
"step": 7340
},
{
"epoch": 0.6128064032016008,
"grad_norm": 0.4015794098377228,
"learning_rate": 2e-05,
"loss": 0.7607,
"step": 7350
},
{
"epoch": 0.6136401534100383,
"grad_norm": 0.424656480550766,
"learning_rate": 2e-05,
"loss": 0.7875,
"step": 7360
},
{
"epoch": 0.6144739036184759,
"grad_norm": 0.4136902689933777,
"learning_rate": 2e-05,
"loss": 0.7583,
"step": 7370
},
{
"epoch": 0.6153076538269134,
"grad_norm": 0.40394720435142517,
"learning_rate": 2e-05,
"loss": 0.7477,
"step": 7380
},
{
"epoch": 0.616141404035351,
"grad_norm": 0.3668685853481293,
"learning_rate": 2e-05,
"loss": 0.7762,
"step": 7390
},
{
"epoch": 0.6169751542437886,
"grad_norm": 0.38078662753105164,
"learning_rate": 2e-05,
"loss": 0.7708,
"step": 7400
},
{
"epoch": 0.6178089044522261,
"grad_norm": 0.40312954783439636,
"learning_rate": 2e-05,
"loss": 0.7792,
"step": 7410
},
{
"epoch": 0.6186426546606637,
"grad_norm": 0.40910857915878296,
"learning_rate": 2e-05,
"loss": 0.7564,
"step": 7420
},
{
"epoch": 0.6194764048691013,
"grad_norm": 0.41707944869995117,
"learning_rate": 2e-05,
"loss": 0.7271,
"step": 7430
},
{
"epoch": 0.6203101550775387,
"grad_norm": 0.3910035490989685,
"learning_rate": 2e-05,
"loss": 0.7469,
"step": 7440
},
{
"epoch": 0.6211439052859763,
"grad_norm": 0.4092378616333008,
"learning_rate": 2e-05,
"loss": 0.7675,
"step": 7450
},
{
"epoch": 0.6219776554944139,
"grad_norm": 0.4258081912994385,
"learning_rate": 2e-05,
"loss": 0.7446,
"step": 7460
},
{
"epoch": 0.6228114057028514,
"grad_norm": 0.4197872579097748,
"learning_rate": 2e-05,
"loss": 0.7514,
"step": 7470
},
{
"epoch": 0.623645155911289,
"grad_norm": 0.39821550250053406,
"learning_rate": 2e-05,
"loss": 0.7542,
"step": 7480
},
{
"epoch": 0.6244789061197266,
"grad_norm": 0.40905749797821045,
"learning_rate": 2e-05,
"loss": 0.7883,
"step": 7490
},
{
"epoch": 0.6253126563281641,
"grad_norm": 0.39396387338638306,
"learning_rate": 2e-05,
"loss": 0.7712,
"step": 7500
},
{
"epoch": 0.6261464065366016,
"grad_norm": 0.43739452958106995,
"learning_rate": 2e-05,
"loss": 0.7678,
"step": 7510
},
{
"epoch": 0.6269801567450392,
"grad_norm": 0.40112653374671936,
"learning_rate": 2e-05,
"loss": 0.7558,
"step": 7520
},
{
"epoch": 0.6278139069534767,
"grad_norm": 0.4849221408367157,
"learning_rate": 2e-05,
"loss": 0.7693,
"step": 7530
},
{
"epoch": 0.6286476571619143,
"grad_norm": 0.4131027162075043,
"learning_rate": 2e-05,
"loss": 0.77,
"step": 7540
},
{
"epoch": 0.6294814073703519,
"grad_norm": 0.39116302132606506,
"learning_rate": 2e-05,
"loss": 0.7857,
"step": 7550
},
{
"epoch": 0.6303151575787894,
"grad_norm": 0.42183244228363037,
"learning_rate": 2e-05,
"loss": 0.7852,
"step": 7560
},
{
"epoch": 0.631148907787227,
"grad_norm": 0.40927785634994507,
"learning_rate": 2e-05,
"loss": 0.7774,
"step": 7570
},
{
"epoch": 0.6319826579956646,
"grad_norm": 0.41807958483695984,
"learning_rate": 2e-05,
"loss": 0.7687,
"step": 7580
},
{
"epoch": 0.632816408204102,
"grad_norm": 0.3869718611240387,
"learning_rate": 2e-05,
"loss": 0.7873,
"step": 7590
},
{
"epoch": 0.6336501584125396,
"grad_norm": 0.4295596778392792,
"learning_rate": 2e-05,
"loss": 0.7874,
"step": 7600
},
{
"epoch": 0.6344839086209771,
"grad_norm": 0.4131230413913727,
"learning_rate": 2e-05,
"loss": 0.7802,
"step": 7610
},
{
"epoch": 0.6353176588294147,
"grad_norm": 0.4279577434062958,
"learning_rate": 2e-05,
"loss": 0.7707,
"step": 7620
},
{
"epoch": 0.6361514090378523,
"grad_norm": 0.38862118124961853,
"learning_rate": 2e-05,
"loss": 0.7664,
"step": 7630
},
{
"epoch": 0.6369851592462898,
"grad_norm": 0.3931245803833008,
"learning_rate": 2e-05,
"loss": 0.7454,
"step": 7640
},
{
"epoch": 0.6378189094547274,
"grad_norm": 0.42397618293762207,
"learning_rate": 2e-05,
"loss": 0.7763,
"step": 7650
},
{
"epoch": 0.6386526596631649,
"grad_norm": 0.39719584584236145,
"learning_rate": 2e-05,
"loss": 0.7657,
"step": 7660
},
{
"epoch": 0.6394864098716024,
"grad_norm": 0.39000746607780457,
"learning_rate": 2e-05,
"loss": 0.7693,
"step": 7670
},
{
"epoch": 0.64032016008004,
"grad_norm": 0.39978599548339844,
"learning_rate": 2e-05,
"loss": 0.7646,
"step": 7680
},
{
"epoch": 0.6411539102884776,
"grad_norm": 0.39447516202926636,
"learning_rate": 2e-05,
"loss": 0.7743,
"step": 7690
},
{
"epoch": 0.6419876604969151,
"grad_norm": 0.42921537160873413,
"learning_rate": 2e-05,
"loss": 0.7505,
"step": 7700
},
{
"epoch": 0.6428214107053527,
"grad_norm": 0.39384615421295166,
"learning_rate": 2e-05,
"loss": 0.7709,
"step": 7710
},
{
"epoch": 0.6436551609137903,
"grad_norm": 0.39075666666030884,
"learning_rate": 2e-05,
"loss": 0.7522,
"step": 7720
},
{
"epoch": 0.6444889111222277,
"grad_norm": 0.4037090539932251,
"learning_rate": 2e-05,
"loss": 0.7802,
"step": 7730
},
{
"epoch": 0.6453226613306653,
"grad_norm": 0.40936294198036194,
"learning_rate": 2e-05,
"loss": 0.7989,
"step": 7740
},
{
"epoch": 0.6461564115391029,
"grad_norm": 0.39490777254104614,
"learning_rate": 2e-05,
"loss": 0.7475,
"step": 7750
},
{
"epoch": 0.6469901617475404,
"grad_norm": 0.40207839012145996,
"learning_rate": 2e-05,
"loss": 0.7833,
"step": 7760
},
{
"epoch": 0.647823911955978,
"grad_norm": 0.4039244055747986,
"learning_rate": 2e-05,
"loss": 0.7668,
"step": 7770
},
{
"epoch": 0.6486576621644156,
"grad_norm": 0.442971795797348,
"learning_rate": 2e-05,
"loss": 0.7415,
"step": 7780
},
{
"epoch": 0.6494914123728531,
"grad_norm": 0.4225422739982605,
"learning_rate": 2e-05,
"loss": 0.7397,
"step": 7790
},
{
"epoch": 0.6503251625812907,
"grad_norm": 0.43148040771484375,
"learning_rate": 2e-05,
"loss": 0.774,
"step": 7800
},
{
"epoch": 0.6511589127897282,
"grad_norm": 0.4100188910961151,
"learning_rate": 2e-05,
"loss": 0.7746,
"step": 7810
},
{
"epoch": 0.6519926629981657,
"grad_norm": 0.4085281789302826,
"learning_rate": 2e-05,
"loss": 0.7925,
"step": 7820
},
{
"epoch": 0.6528264132066033,
"grad_norm": 0.3926294445991516,
"learning_rate": 2e-05,
"loss": 0.7491,
"step": 7830
},
{
"epoch": 0.6536601634150409,
"grad_norm": 0.39077022671699524,
"learning_rate": 2e-05,
"loss": 0.7572,
"step": 7840
},
{
"epoch": 0.6544939136234784,
"grad_norm": 0.38497063517570496,
"learning_rate": 2e-05,
"loss": 0.7644,
"step": 7850
},
{
"epoch": 0.655327663831916,
"grad_norm": 0.3917582035064697,
"learning_rate": 2e-05,
"loss": 0.7524,
"step": 7860
},
{
"epoch": 0.6561614140403536,
"grad_norm": 0.38123998045921326,
"learning_rate": 2e-05,
"loss": 0.7722,
"step": 7870
},
{
"epoch": 0.656995164248791,
"grad_norm": 0.4405210018157959,
"learning_rate": 2e-05,
"loss": 0.7624,
"step": 7880
},
{
"epoch": 0.6578289144572286,
"grad_norm": 0.4257303774356842,
"learning_rate": 2e-05,
"loss": 0.7871,
"step": 7890
},
{
"epoch": 0.6586626646656661,
"grad_norm": 0.401308536529541,
"learning_rate": 2e-05,
"loss": 0.7743,
"step": 7900
},
{
"epoch": 0.6594964148741037,
"grad_norm": 0.39987578988075256,
"learning_rate": 2e-05,
"loss": 0.7721,
"step": 7910
},
{
"epoch": 0.6603301650825413,
"grad_norm": 0.3687119781970978,
"learning_rate": 2e-05,
"loss": 0.7552,
"step": 7920
},
{
"epoch": 0.6611639152909788,
"grad_norm": 0.39139750599861145,
"learning_rate": 2e-05,
"loss": 0.8012,
"step": 7930
},
{
"epoch": 0.6619976654994164,
"grad_norm": 0.3856688439846039,
"learning_rate": 2e-05,
"loss": 0.7722,
"step": 7940
},
{
"epoch": 0.662831415707854,
"grad_norm": 0.3945103883743286,
"learning_rate": 2e-05,
"loss": 0.7874,
"step": 7950
},
{
"epoch": 0.6636651659162914,
"grad_norm": 0.4290179908275604,
"learning_rate": 2e-05,
"loss": 0.7884,
"step": 7960
},
{
"epoch": 0.664498916124729,
"grad_norm": 0.41466137766838074,
"learning_rate": 2e-05,
"loss": 0.7893,
"step": 7970
},
{
"epoch": 0.6653326663331666,
"grad_norm": 0.39913076162338257,
"learning_rate": 2e-05,
"loss": 0.747,
"step": 7980
},
{
"epoch": 0.6661664165416041,
"grad_norm": 0.39209118485450745,
"learning_rate": 2e-05,
"loss": 0.7632,
"step": 7990
},
{
"epoch": 0.6670001667500417,
"grad_norm": 0.3955627679824829,
"learning_rate": 2e-05,
"loss": 0.7754,
"step": 8000
},
{
"epoch": 0.6678339169584793,
"grad_norm": 0.391986221075058,
"learning_rate": 2e-05,
"loss": 0.7714,
"step": 8010
},
{
"epoch": 0.6686676671669168,
"grad_norm": 0.3995739817619324,
"learning_rate": 2e-05,
"loss": 0.7758,
"step": 8020
},
{
"epoch": 0.6695014173753543,
"grad_norm": 0.3804994821548462,
"learning_rate": 2e-05,
"loss": 0.7801,
"step": 8030
},
{
"epoch": 0.6703351675837919,
"grad_norm": 0.42434659600257874,
"learning_rate": 2e-05,
"loss": 0.7643,
"step": 8040
},
{
"epoch": 0.6711689177922294,
"grad_norm": 0.41371819376945496,
"learning_rate": 2e-05,
"loss": 0.7858,
"step": 8050
},
{
"epoch": 0.672002668000667,
"grad_norm": 0.4279904067516327,
"learning_rate": 2e-05,
"loss": 0.7607,
"step": 8060
},
{
"epoch": 0.6728364182091046,
"grad_norm": 0.40448811650276184,
"learning_rate": 2e-05,
"loss": 0.7765,
"step": 8070
},
{
"epoch": 0.6736701684175421,
"grad_norm": 0.41851434111595154,
"learning_rate": 2e-05,
"loss": 0.788,
"step": 8080
},
{
"epoch": 0.6745039186259797,
"grad_norm": 0.40321028232574463,
"learning_rate": 2e-05,
"loss": 0.7884,
"step": 8090
},
{
"epoch": 0.6753376688344173,
"grad_norm": 0.4149765074253082,
"learning_rate": 2e-05,
"loss": 0.752,
"step": 8100
},
{
"epoch": 0.6761714190428547,
"grad_norm": 0.41213586926460266,
"learning_rate": 2e-05,
"loss": 0.7911,
"step": 8110
},
{
"epoch": 0.6770051692512923,
"grad_norm": 0.4024345576763153,
"learning_rate": 2e-05,
"loss": 0.7813,
"step": 8120
},
{
"epoch": 0.6778389194597298,
"grad_norm": 0.40908560156822205,
"learning_rate": 2e-05,
"loss": 0.7555,
"step": 8130
},
{
"epoch": 0.6786726696681674,
"grad_norm": 0.42870476841926575,
"learning_rate": 2e-05,
"loss": 0.768,
"step": 8140
},
{
"epoch": 0.679506419876605,
"grad_norm": 0.3825284242630005,
"learning_rate": 2e-05,
"loss": 0.7735,
"step": 8150
},
{
"epoch": 0.6803401700850426,
"grad_norm": 0.40324142575263977,
"learning_rate": 2e-05,
"loss": 0.7761,
"step": 8160
},
{
"epoch": 0.6811739202934801,
"grad_norm": 0.3652316927909851,
"learning_rate": 2e-05,
"loss": 0.7423,
"step": 8170
},
{
"epoch": 0.6820076705019176,
"grad_norm": 0.4055224359035492,
"learning_rate": 2e-05,
"loss": 0.7678,
"step": 8180
},
{
"epoch": 0.6828414207103551,
"grad_norm": 0.3948476016521454,
"learning_rate": 2e-05,
"loss": 0.7873,
"step": 8190
},
{
"epoch": 0.6836751709187927,
"grad_norm": 0.3991617262363434,
"learning_rate": 2e-05,
"loss": 0.7583,
"step": 8200
},
{
"epoch": 0.6845089211272303,
"grad_norm": 0.4038161635398865,
"learning_rate": 2e-05,
"loss": 0.7813,
"step": 8210
},
{
"epoch": 0.6853426713356678,
"grad_norm": 0.39887186884880066,
"learning_rate": 2e-05,
"loss": 0.7821,
"step": 8220
},
{
"epoch": 0.6861764215441054,
"grad_norm": 0.41044560074806213,
"learning_rate": 2e-05,
"loss": 0.7874,
"step": 8230
},
{
"epoch": 0.687010171752543,
"grad_norm": 0.396358847618103,
"learning_rate": 2e-05,
"loss": 0.7416,
"step": 8240
},
{
"epoch": 0.6878439219609805,
"grad_norm": 0.3983939588069916,
"learning_rate": 2e-05,
"loss": 0.7589,
"step": 8250
},
{
"epoch": 0.688677672169418,
"grad_norm": 0.4087740480899811,
"learning_rate": 2e-05,
"loss": 0.7582,
"step": 8260
},
{
"epoch": 0.6895114223778556,
"grad_norm": 0.6407231092453003,
"learning_rate": 2e-05,
"loss": 0.7525,
"step": 8270
},
{
"epoch": 0.6903451725862931,
"grad_norm": 0.42374947667121887,
"learning_rate": 2e-05,
"loss": 0.772,
"step": 8280
},
{
"epoch": 0.6911789227947307,
"grad_norm": 0.4298012852668762,
"learning_rate": 2e-05,
"loss": 0.7643,
"step": 8290
},
{
"epoch": 0.6920126730031683,
"grad_norm": 0.385529488325119,
"learning_rate": 2e-05,
"loss": 0.758,
"step": 8300
},
{
"epoch": 0.6928464232116058,
"grad_norm": 0.4181244671344757,
"learning_rate": 2e-05,
"loss": 0.7483,
"step": 8310
},
{
"epoch": 0.6936801734200434,
"grad_norm": 0.38629084825515747,
"learning_rate": 2e-05,
"loss": 0.7608,
"step": 8320
},
{
"epoch": 0.6945139236284809,
"grad_norm": 0.41015684604644775,
"learning_rate": 2e-05,
"loss": 0.7645,
"step": 8330
},
{
"epoch": 0.6953476738369184,
"grad_norm": 0.41802528500556946,
"learning_rate": 2e-05,
"loss": 0.7741,
"step": 8340
},
{
"epoch": 0.696181424045356,
"grad_norm": 0.3878299593925476,
"learning_rate": 2e-05,
"loss": 0.7615,
"step": 8350
},
{
"epoch": 0.6970151742537936,
"grad_norm": 0.39036163687705994,
"learning_rate": 2e-05,
"loss": 0.7428,
"step": 8360
},
{
"epoch": 0.6978489244622311,
"grad_norm": 0.40534332394599915,
"learning_rate": 2e-05,
"loss": 0.7592,
"step": 8370
},
{
"epoch": 0.6986826746706687,
"grad_norm": 0.404338002204895,
"learning_rate": 2e-05,
"loss": 0.7739,
"step": 8380
},
{
"epoch": 0.6995164248791063,
"grad_norm": 0.44270095229148865,
"learning_rate": 2e-05,
"loss": 0.8095,
"step": 8390
},
{
"epoch": 0.7003501750875438,
"grad_norm": 0.38693076372146606,
"learning_rate": 2e-05,
"loss": 0.7866,
"step": 8400
},
{
"epoch": 0.7011839252959813,
"grad_norm": 0.49266791343688965,
"learning_rate": 2e-05,
"loss": 0.764,
"step": 8410
},
{
"epoch": 0.7020176755044188,
"grad_norm": 0.3934873938560486,
"learning_rate": 2e-05,
"loss": 0.767,
"step": 8420
},
{
"epoch": 0.7028514257128564,
"grad_norm": 0.41682329773902893,
"learning_rate": 2e-05,
"loss": 0.7758,
"step": 8430
},
{
"epoch": 0.703685175921294,
"grad_norm": 0.38372254371643066,
"learning_rate": 2e-05,
"loss": 0.7439,
"step": 8440
},
{
"epoch": 0.7045189261297315,
"grad_norm": 0.37386441230773926,
"learning_rate": 2e-05,
"loss": 0.7853,
"step": 8450
},
{
"epoch": 0.7053526763381691,
"grad_norm": 0.4697357714176178,
"learning_rate": 2e-05,
"loss": 0.8111,
"step": 8460
},
{
"epoch": 0.7061864265466067,
"grad_norm": 0.40680500864982605,
"learning_rate": 2e-05,
"loss": 0.7764,
"step": 8470
},
{
"epoch": 0.7070201767550441,
"grad_norm": 0.4105947017669678,
"learning_rate": 2e-05,
"loss": 0.7591,
"step": 8480
},
{
"epoch": 0.7078539269634817,
"grad_norm": 0.3956372141838074,
"learning_rate": 2e-05,
"loss": 0.7743,
"step": 8490
},
{
"epoch": 0.7086876771719193,
"grad_norm": 0.402149498462677,
"learning_rate": 2e-05,
"loss": 0.7854,
"step": 8500
},
{
"epoch": 0.7095214273803568,
"grad_norm": 0.38664889335632324,
"learning_rate": 2e-05,
"loss": 0.7852,
"step": 8510
},
{
"epoch": 0.7103551775887944,
"grad_norm": 0.39993536472320557,
"learning_rate": 2e-05,
"loss": 0.7565,
"step": 8520
},
{
"epoch": 0.711188927797232,
"grad_norm": 0.4271695017814636,
"learning_rate": 2e-05,
"loss": 0.7492,
"step": 8530
},
{
"epoch": 0.7120226780056695,
"grad_norm": 0.3880975544452667,
"learning_rate": 2e-05,
"loss": 0.754,
"step": 8540
},
{
"epoch": 0.7128564282141071,
"grad_norm": 0.3925435245037079,
"learning_rate": 2e-05,
"loss": 0.7436,
"step": 8550
},
{
"epoch": 0.7136901784225446,
"grad_norm": 0.4248669445514679,
"learning_rate": 2e-05,
"loss": 0.7572,
"step": 8560
},
{
"epoch": 0.7145239286309821,
"grad_norm": 0.39947909116744995,
"learning_rate": 2e-05,
"loss": 0.786,
"step": 8570
},
{
"epoch": 0.7153576788394197,
"grad_norm": 0.3807201385498047,
"learning_rate": 2e-05,
"loss": 0.7406,
"step": 8580
},
{
"epoch": 0.7161914290478573,
"grad_norm": 0.4620365500450134,
"learning_rate": 2e-05,
"loss": 0.751,
"step": 8590
},
{
"epoch": 0.7170251792562948,
"grad_norm": 0.39219191670417786,
"learning_rate": 2e-05,
"loss": 0.7565,
"step": 8600
},
{
"epoch": 0.7178589294647324,
"grad_norm": 0.40298888087272644,
"learning_rate": 2e-05,
"loss": 0.7443,
"step": 8610
},
{
"epoch": 0.71869267967317,
"grad_norm": 0.36500459909439087,
"learning_rate": 2e-05,
"loss": 0.7684,
"step": 8620
},
{
"epoch": 0.7195264298816074,
"grad_norm": 0.3964237570762634,
"learning_rate": 2e-05,
"loss": 0.7782,
"step": 8630
},
{
"epoch": 0.720360180090045,
"grad_norm": 0.38322901725769043,
"learning_rate": 2e-05,
"loss": 0.7518,
"step": 8640
},
{
"epoch": 0.7211939302984826,
"grad_norm": 0.42500829696655273,
"learning_rate": 2e-05,
"loss": 0.7552,
"step": 8650
},
{
"epoch": 0.7220276805069201,
"grad_norm": 0.3893665373325348,
"learning_rate": 2e-05,
"loss": 0.7432,
"step": 8660
},
{
"epoch": 0.7228614307153577,
"grad_norm": 0.4375983476638794,
"learning_rate": 2e-05,
"loss": 0.7578,
"step": 8670
},
{
"epoch": 0.7236951809237953,
"grad_norm": 0.37185636162757874,
"learning_rate": 2e-05,
"loss": 0.7642,
"step": 8680
},
{
"epoch": 0.7245289311322328,
"grad_norm": 0.40260371565818787,
"learning_rate": 2e-05,
"loss": 0.7828,
"step": 8690
},
{
"epoch": 0.7253626813406704,
"grad_norm": 0.38819533586502075,
"learning_rate": 2e-05,
"loss": 0.7846,
"step": 8700
},
{
"epoch": 0.7261964315491078,
"grad_norm": 0.42326703667640686,
"learning_rate": 2e-05,
"loss": 0.7633,
"step": 8710
},
{
"epoch": 0.7270301817575454,
"grad_norm": 0.39317795634269714,
"learning_rate": 2e-05,
"loss": 0.7747,
"step": 8720
},
{
"epoch": 0.727863931965983,
"grad_norm": 0.3761366009712219,
"learning_rate": 2e-05,
"loss": 0.7647,
"step": 8730
},
{
"epoch": 0.7286976821744205,
"grad_norm": 0.3893985450267792,
"learning_rate": 2e-05,
"loss": 0.7568,
"step": 8740
},
{
"epoch": 0.7295314323828581,
"grad_norm": 0.3928586542606354,
"learning_rate": 2e-05,
"loss": 0.782,
"step": 8750
},
{
"epoch": 0.7303651825912957,
"grad_norm": 0.404919296503067,
"learning_rate": 2e-05,
"loss": 0.7598,
"step": 8760
},
{
"epoch": 0.7311989327997332,
"grad_norm": 0.4029577672481537,
"learning_rate": 2e-05,
"loss": 0.7921,
"step": 8770
},
{
"epoch": 0.7320326830081707,
"grad_norm": 0.40573135018348694,
"learning_rate": 2e-05,
"loss": 0.7609,
"step": 8780
},
{
"epoch": 0.7328664332166083,
"grad_norm": 0.4164227545261383,
"learning_rate": 2e-05,
"loss": 0.7507,
"step": 8790
},
{
"epoch": 0.7337001834250458,
"grad_norm": 0.38627713918685913,
"learning_rate": 2e-05,
"loss": 0.7608,
"step": 8800
},
{
"epoch": 0.7345339336334834,
"grad_norm": 0.39315980672836304,
"learning_rate": 2e-05,
"loss": 0.7682,
"step": 8810
},
{
"epoch": 0.735367683841921,
"grad_norm": 0.39643529057502747,
"learning_rate": 2e-05,
"loss": 0.7394,
"step": 8820
},
{
"epoch": 0.7362014340503585,
"grad_norm": 0.4358176290988922,
"learning_rate": 2e-05,
"loss": 0.7609,
"step": 8830
},
{
"epoch": 0.7370351842587961,
"grad_norm": 0.3987131714820862,
"learning_rate": 2e-05,
"loss": 0.7573,
"step": 8840
},
{
"epoch": 0.7378689344672336,
"grad_norm": 0.40374505519866943,
"learning_rate": 2e-05,
"loss": 0.7871,
"step": 8850
},
{
"epoch": 0.7387026846756711,
"grad_norm": 0.39530327916145325,
"learning_rate": 2e-05,
"loss": 0.7353,
"step": 8860
},
{
"epoch": 0.7395364348841087,
"grad_norm": 0.3905327022075653,
"learning_rate": 2e-05,
"loss": 0.7307,
"step": 8870
},
{
"epoch": 0.7403701850925463,
"grad_norm": 0.3636264204978943,
"learning_rate": 2e-05,
"loss": 0.7457,
"step": 8880
},
{
"epoch": 0.7412039353009838,
"grad_norm": 0.43109795451164246,
"learning_rate": 2e-05,
"loss": 0.7737,
"step": 8890
},
{
"epoch": 0.7420376855094214,
"grad_norm": 0.39507147669792175,
"learning_rate": 2e-05,
"loss": 0.7314,
"step": 8900
},
{
"epoch": 0.742871435717859,
"grad_norm": 0.4606911540031433,
"learning_rate": 2e-05,
"loss": 0.7563,
"step": 8910
},
{
"epoch": 0.7437051859262965,
"grad_norm": 0.38444623351097107,
"learning_rate": 2e-05,
"loss": 0.7628,
"step": 8920
},
{
"epoch": 0.744538936134734,
"grad_norm": 0.41106024384498596,
"learning_rate": 2e-05,
"loss": 0.7519,
"step": 8930
},
{
"epoch": 0.7453726863431716,
"grad_norm": 0.4173847436904907,
"learning_rate": 2e-05,
"loss": 0.7655,
"step": 8940
},
{
"epoch": 0.7462064365516091,
"grad_norm": 0.37928488850593567,
"learning_rate": 2e-05,
"loss": 0.745,
"step": 8950
},
{
"epoch": 0.7470401867600467,
"grad_norm": 0.3811960220336914,
"learning_rate": 2e-05,
"loss": 0.7682,
"step": 8960
},
{
"epoch": 0.7478739369684843,
"grad_norm": 0.4046102464199066,
"learning_rate": 2e-05,
"loss": 0.7492,
"step": 8970
},
{
"epoch": 0.7487076871769218,
"grad_norm": 0.3864096701145172,
"learning_rate": 2e-05,
"loss": 0.7864,
"step": 8980
},
{
"epoch": 0.7495414373853594,
"grad_norm": 0.40592026710510254,
"learning_rate": 2e-05,
"loss": 0.7556,
"step": 8990
},
{
"epoch": 0.7503751875937968,
"grad_norm": 0.41038432717323303,
"learning_rate": 2e-05,
"loss": 0.7712,
"step": 9000
},
{
"epoch": 0.7512089378022344,
"grad_norm": 0.41375765204429626,
"learning_rate": 2e-05,
"loss": 0.7521,
"step": 9010
},
{
"epoch": 0.752042688010672,
"grad_norm": 0.4071480929851532,
"learning_rate": 2e-05,
"loss": 0.7411,
"step": 9020
},
{
"epoch": 0.7528764382191095,
"grad_norm": 0.4072341322898865,
"learning_rate": 2e-05,
"loss": 0.7426,
"step": 9030
},
{
"epoch": 0.7537101884275471,
"grad_norm": 0.40955018997192383,
"learning_rate": 2e-05,
"loss": 0.7802,
"step": 9040
},
{
"epoch": 0.7545439386359847,
"grad_norm": 0.42766857147216797,
"learning_rate": 2e-05,
"loss": 0.7476,
"step": 9050
},
{
"epoch": 0.7553776888444222,
"grad_norm": 0.39602699875831604,
"learning_rate": 2e-05,
"loss": 0.7755,
"step": 9060
},
{
"epoch": 0.7562114390528598,
"grad_norm": 0.41948801279067993,
"learning_rate": 2e-05,
"loss": 0.7446,
"step": 9070
},
{
"epoch": 0.7570451892612973,
"grad_norm": 0.4056944251060486,
"learning_rate": 2e-05,
"loss": 0.7327,
"step": 9080
},
{
"epoch": 0.7578789394697348,
"grad_norm": 0.6610334515571594,
"learning_rate": 2e-05,
"loss": 0.7396,
"step": 9090
},
{
"epoch": 0.7587126896781724,
"grad_norm": 0.4127954840660095,
"learning_rate": 2e-05,
"loss": 0.7387,
"step": 9100
},
{
"epoch": 0.75954643988661,
"grad_norm": 0.37848764657974243,
"learning_rate": 2e-05,
"loss": 0.767,
"step": 9110
},
{
"epoch": 0.7603801900950475,
"grad_norm": 0.4141720235347748,
"learning_rate": 2e-05,
"loss": 0.7707,
"step": 9120
},
{
"epoch": 0.7612139403034851,
"grad_norm": 0.40630799531936646,
"learning_rate": 2e-05,
"loss": 0.7529,
"step": 9130
},
{
"epoch": 0.7620476905119227,
"grad_norm": 0.43661007285118103,
"learning_rate": 2e-05,
"loss": 0.7207,
"step": 9140
},
{
"epoch": 0.7628814407203601,
"grad_norm": 0.4310365617275238,
"learning_rate": 2e-05,
"loss": 0.7945,
"step": 9150
},
{
"epoch": 0.7637151909287977,
"grad_norm": 0.4166373610496521,
"learning_rate": 2e-05,
"loss": 0.7209,
"step": 9160
},
{
"epoch": 0.7645489411372353,
"grad_norm": 0.3919469714164734,
"learning_rate": 2e-05,
"loss": 0.7273,
"step": 9170
},
{
"epoch": 0.7653826913456728,
"grad_norm": 0.4063626229763031,
"learning_rate": 2e-05,
"loss": 0.7664,
"step": 9180
},
{
"epoch": 0.7662164415541104,
"grad_norm": 0.42380741238594055,
"learning_rate": 2e-05,
"loss": 0.7479,
"step": 9190
},
{
"epoch": 0.767050191762548,
"grad_norm": 0.3696325421333313,
"learning_rate": 2e-05,
"loss": 0.7525,
"step": 9200
},
{
"epoch": 0.7678839419709855,
"grad_norm": 0.38599899411201477,
"learning_rate": 2e-05,
"loss": 0.7329,
"step": 9210
},
{
"epoch": 0.7687176921794231,
"grad_norm": 0.3852783739566803,
"learning_rate": 2e-05,
"loss": 0.7222,
"step": 9220
},
{
"epoch": 0.7695514423878606,
"grad_norm": 0.3935507833957672,
"learning_rate": 2e-05,
"loss": 0.76,
"step": 9230
},
{
"epoch": 0.7703851925962981,
"grad_norm": 0.3797072470188141,
"learning_rate": 2e-05,
"loss": 0.7576,
"step": 9240
},
{
"epoch": 0.7712189428047357,
"grad_norm": 0.4081142544746399,
"learning_rate": 2e-05,
"loss": 0.7689,
"step": 9250
},
{
"epoch": 0.7720526930131733,
"grad_norm": 0.39046430587768555,
"learning_rate": 2e-05,
"loss": 0.7279,
"step": 9260
},
{
"epoch": 0.7728864432216108,
"grad_norm": 0.38060101866722107,
"learning_rate": 2e-05,
"loss": 0.7437,
"step": 9270
},
{
"epoch": 0.7737201934300484,
"grad_norm": 0.4081495404243469,
"learning_rate": 2e-05,
"loss": 0.7376,
"step": 9280
},
{
"epoch": 0.774553943638486,
"grad_norm": 0.4310022294521332,
"learning_rate": 2e-05,
"loss": 0.7803,
"step": 9290
},
{
"epoch": 0.7753876938469234,
"grad_norm": 0.42943447828292847,
"learning_rate": 2e-05,
"loss": 0.7706,
"step": 9300
},
{
"epoch": 0.776221444055361,
"grad_norm": 0.3787987232208252,
"learning_rate": 2e-05,
"loss": 0.7347,
"step": 9310
},
{
"epoch": 0.7770551942637985,
"grad_norm": 0.3832138776779175,
"learning_rate": 2e-05,
"loss": 0.7433,
"step": 9320
},
{
"epoch": 0.7778889444722361,
"grad_norm": 0.3959273099899292,
"learning_rate": 2e-05,
"loss": 0.7562,
"step": 9330
},
{
"epoch": 0.7787226946806737,
"grad_norm": 0.3838410973548889,
"learning_rate": 2e-05,
"loss": 0.7455,
"step": 9340
},
{
"epoch": 0.7795564448891112,
"grad_norm": 0.4161594808101654,
"learning_rate": 2e-05,
"loss": 0.7792,
"step": 9350
},
{
"epoch": 0.7803901950975488,
"grad_norm": 0.37788036465644836,
"learning_rate": 2e-05,
"loss": 0.7546,
"step": 9360
},
{
"epoch": 0.7812239453059864,
"grad_norm": 0.405375599861145,
"learning_rate": 2e-05,
"loss": 0.7643,
"step": 9370
},
{
"epoch": 0.7820576955144238,
"grad_norm": 0.4067181944847107,
"learning_rate": 2e-05,
"loss": 0.7488,
"step": 9380
},
{
"epoch": 0.7828914457228614,
"grad_norm": 0.3847503364086151,
"learning_rate": 2e-05,
"loss": 0.7365,
"step": 9390
},
{
"epoch": 0.783725195931299,
"grad_norm": 0.41827332973480225,
"learning_rate": 2e-05,
"loss": 0.7538,
"step": 9400
},
{
"epoch": 0.7845589461397365,
"grad_norm": 0.39410826563835144,
"learning_rate": 2e-05,
"loss": 0.7693,
"step": 9410
},
{
"epoch": 0.7853926963481741,
"grad_norm": 0.39415037631988525,
"learning_rate": 2e-05,
"loss": 0.751,
"step": 9420
},
{
"epoch": 0.7862264465566117,
"grad_norm": 0.3858663737773895,
"learning_rate": 2e-05,
"loss": 0.7511,
"step": 9430
},
{
"epoch": 0.7870601967650492,
"grad_norm": 0.40644869208335876,
"learning_rate": 2e-05,
"loss": 0.7467,
"step": 9440
},
{
"epoch": 0.7878939469734867,
"grad_norm": 0.3866288661956787,
"learning_rate": 2e-05,
"loss": 0.7463,
"step": 9450
},
{
"epoch": 0.7887276971819243,
"grad_norm": 0.3962755501270294,
"learning_rate": 2e-05,
"loss": 0.7365,
"step": 9460
},
{
"epoch": 0.7895614473903618,
"grad_norm": 0.413374125957489,
"learning_rate": 2e-05,
"loss": 0.7465,
"step": 9470
},
{
"epoch": 0.7903951975987994,
"grad_norm": 0.394319623708725,
"learning_rate": 2e-05,
"loss": 0.7641,
"step": 9480
},
{
"epoch": 0.791228947807237,
"grad_norm": 0.38536977767944336,
"learning_rate": 2e-05,
"loss": 0.7429,
"step": 9490
},
{
"epoch": 0.7920626980156745,
"grad_norm": 0.39534062147140503,
"learning_rate": 2e-05,
"loss": 0.7422,
"step": 9500
},
{
"epoch": 0.7928964482241121,
"grad_norm": 0.3917052149772644,
"learning_rate": 2e-05,
"loss": 0.7704,
"step": 9510
},
{
"epoch": 0.7937301984325497,
"grad_norm": 0.38315916061401367,
"learning_rate": 2e-05,
"loss": 0.7667,
"step": 9520
},
{
"epoch": 0.7945639486409871,
"grad_norm": 0.3985026180744171,
"learning_rate": 2e-05,
"loss": 0.7579,
"step": 9530
},
{
"epoch": 0.7953976988494247,
"grad_norm": 0.4088324010372162,
"learning_rate": 2e-05,
"loss": 0.7372,
"step": 9540
},
{
"epoch": 0.7962314490578623,
"grad_norm": 0.40837791562080383,
"learning_rate": 2e-05,
"loss": 0.7785,
"step": 9550
},
{
"epoch": 0.7970651992662998,
"grad_norm": 0.39128032326698303,
"learning_rate": 2e-05,
"loss": 0.7514,
"step": 9560
},
{
"epoch": 0.7978989494747374,
"grad_norm": 0.3946499526500702,
"learning_rate": 2e-05,
"loss": 0.7683,
"step": 9570
},
{
"epoch": 0.798732699683175,
"grad_norm": 0.3937230408191681,
"learning_rate": 2e-05,
"loss": 0.7455,
"step": 9580
},
{
"epoch": 0.7995664498916125,
"grad_norm": 0.40006640553474426,
"learning_rate": 2e-05,
"loss": 0.7623,
"step": 9590
},
{
"epoch": 0.80040020010005,
"grad_norm": 0.3917764723300934,
"learning_rate": 2e-05,
"loss": 0.7403,
"step": 9600
},
{
"epoch": 0.8012339503084875,
"grad_norm": 0.4152166545391083,
"learning_rate": 2e-05,
"loss": 0.7664,
"step": 9610
},
{
"epoch": 0.8020677005169251,
"grad_norm": 0.3971850275993347,
"learning_rate": 2e-05,
"loss": 0.7767,
"step": 9620
},
{
"epoch": 0.8029014507253627,
"grad_norm": 0.40349045395851135,
"learning_rate": 2e-05,
"loss": 0.7318,
"step": 9630
},
{
"epoch": 0.8037352009338002,
"grad_norm": 0.42315709590911865,
"learning_rate": 2e-05,
"loss": 0.7461,
"step": 9640
},
{
"epoch": 0.8045689511422378,
"grad_norm": 0.3877435624599457,
"learning_rate": 2e-05,
"loss": 0.7451,
"step": 9650
},
{
"epoch": 0.8054027013506754,
"grad_norm": 0.43053361773490906,
"learning_rate": 2e-05,
"loss": 0.7756,
"step": 9660
},
{
"epoch": 0.8062364515591129,
"grad_norm": 0.39297330379486084,
"learning_rate": 2e-05,
"loss": 0.7527,
"step": 9670
},
{
"epoch": 0.8070702017675504,
"grad_norm": 0.3919180929660797,
"learning_rate": 2e-05,
"loss": 0.7369,
"step": 9680
},
{
"epoch": 0.807903951975988,
"grad_norm": 0.39803096652030945,
"learning_rate": 2e-05,
"loss": 0.7529,
"step": 9690
},
{
"epoch": 0.8087377021844255,
"grad_norm": 0.397615909576416,
"learning_rate": 2e-05,
"loss": 0.7894,
"step": 9700
},
{
"epoch": 0.8095714523928631,
"grad_norm": 0.44117361307144165,
"learning_rate": 2e-05,
"loss": 0.7688,
"step": 9710
},
{
"epoch": 0.8104052026013007,
"grad_norm": 0.4047308564186096,
"learning_rate": 2e-05,
"loss": 0.768,
"step": 9720
},
{
"epoch": 0.8112389528097382,
"grad_norm": 0.39468100666999817,
"learning_rate": 2e-05,
"loss": 0.7748,
"step": 9730
},
{
"epoch": 0.8120727030181758,
"grad_norm": 0.4222877025604248,
"learning_rate": 2e-05,
"loss": 0.8085,
"step": 9740
},
{
"epoch": 0.8129064532266133,
"grad_norm": 0.40079978108406067,
"learning_rate": 2e-05,
"loss": 0.7668,
"step": 9750
},
{
"epoch": 0.8137402034350508,
"grad_norm": 0.4399901330471039,
"learning_rate": 2e-05,
"loss": 0.7555,
"step": 9760
},
{
"epoch": 0.8145739536434884,
"grad_norm": 0.43609243631362915,
"learning_rate": 2e-05,
"loss": 0.7556,
"step": 9770
},
{
"epoch": 0.815407703851926,
"grad_norm": 0.40186384320259094,
"learning_rate": 2e-05,
"loss": 0.7552,
"step": 9780
},
{
"epoch": 0.8162414540603635,
"grad_norm": 0.40199702978134155,
"learning_rate": 2e-05,
"loss": 0.7879,
"step": 9790
},
{
"epoch": 0.8170752042688011,
"grad_norm": 0.3956231474876404,
"learning_rate": 2e-05,
"loss": 0.7447,
"step": 9800
},
{
"epoch": 0.8179089544772387,
"grad_norm": 0.393880695104599,
"learning_rate": 2e-05,
"loss": 0.7166,
"step": 9810
},
{
"epoch": 0.8187427046856762,
"grad_norm": 0.39305606484413147,
"learning_rate": 2e-05,
"loss": 0.769,
"step": 9820
},
{
"epoch": 0.8195764548941137,
"grad_norm": 0.41382071375846863,
"learning_rate": 2e-05,
"loss": 0.7551,
"step": 9830
},
{
"epoch": 0.8204102051025512,
"grad_norm": 0.424653559923172,
"learning_rate": 2e-05,
"loss": 0.7821,
"step": 9840
},
{
"epoch": 0.8212439553109888,
"grad_norm": 0.4138897657394409,
"learning_rate": 2e-05,
"loss": 0.7605,
"step": 9850
},
{
"epoch": 0.8220777055194264,
"grad_norm": 0.4150356650352478,
"learning_rate": 2e-05,
"loss": 0.7444,
"step": 9860
},
{
"epoch": 0.822911455727864,
"grad_norm": 0.3832564055919647,
"learning_rate": 2e-05,
"loss": 0.7718,
"step": 9870
},
{
"epoch": 0.8237452059363015,
"grad_norm": 0.37413719296455383,
"learning_rate": 2e-05,
"loss": 0.7337,
"step": 9880
},
{
"epoch": 0.8245789561447391,
"grad_norm": 0.5606051087379456,
"learning_rate": 2e-05,
"loss": 0.7721,
"step": 9890
},
{
"epoch": 0.8254127063531765,
"grad_norm": 0.36941978335380554,
"learning_rate": 2e-05,
"loss": 0.7293,
"step": 9900
},
{
"epoch": 0.8262464565616141,
"grad_norm": 0.39024338126182556,
"learning_rate": 2e-05,
"loss": 0.7822,
"step": 9910
},
{
"epoch": 0.8270802067700517,
"grad_norm": 0.422211617231369,
"learning_rate": 2e-05,
"loss": 0.7662,
"step": 9920
},
{
"epoch": 0.8279139569784892,
"grad_norm": 0.3873042166233063,
"learning_rate": 2e-05,
"loss": 0.7439,
"step": 9930
},
{
"epoch": 0.8287477071869268,
"grad_norm": 0.4306544065475464,
"learning_rate": 2e-05,
"loss": 0.7728,
"step": 9940
},
{
"epoch": 0.8295814573953644,
"grad_norm": 0.4090830981731415,
"learning_rate": 2e-05,
"loss": 0.7746,
"step": 9950
},
{
"epoch": 0.8304152076038019,
"grad_norm": 0.42116236686706543,
"learning_rate": 2e-05,
"loss": 0.7776,
"step": 9960
},
{
"epoch": 0.8312489578122395,
"grad_norm": 0.3845221698284149,
"learning_rate": 2e-05,
"loss": 0.7448,
"step": 9970
},
{
"epoch": 0.832082708020677,
"grad_norm": 0.4948175549507141,
"learning_rate": 2e-05,
"loss": 0.7399,
"step": 9980
},
{
"epoch": 0.8329164582291145,
"grad_norm": 0.3986336886882782,
"learning_rate": 2e-05,
"loss": 0.7627,
"step": 9990
},
{
"epoch": 0.8337502084375521,
"grad_norm": 0.4078438878059387,
"learning_rate": 2e-05,
"loss": 0.7415,
"step": 10000
},
{
"epoch": 0.8345839586459897,
"grad_norm": 0.40257495641708374,
"learning_rate": 2e-05,
"loss": 0.7377,
"step": 10010
},
{
"epoch": 0.8354177088544272,
"grad_norm": 0.43063539266586304,
"learning_rate": 2e-05,
"loss": 0.7944,
"step": 10020
},
{
"epoch": 0.8362514590628648,
"grad_norm": 0.41410669684410095,
"learning_rate": 2e-05,
"loss": 0.7587,
"step": 10030
},
{
"epoch": 0.8370852092713024,
"grad_norm": 0.40166938304901123,
"learning_rate": 2e-05,
"loss": 0.7499,
"step": 10040
},
{
"epoch": 0.8379189594797398,
"grad_norm": 0.3863232135772705,
"learning_rate": 2e-05,
"loss": 0.7644,
"step": 10050
},
{
"epoch": 0.8387527096881774,
"grad_norm": 0.4473024010658264,
"learning_rate": 2e-05,
"loss": 0.7915,
"step": 10060
},
{
"epoch": 0.839586459896615,
"grad_norm": 0.38932719826698303,
"learning_rate": 2e-05,
"loss": 0.7439,
"step": 10070
},
{
"epoch": 0.8404202101050525,
"grad_norm": 0.38489505648612976,
"learning_rate": 2e-05,
"loss": 0.7502,
"step": 10080
},
{
"epoch": 0.8412539603134901,
"grad_norm": 0.39946386218070984,
"learning_rate": 2e-05,
"loss": 0.7196,
"step": 10090
},
{
"epoch": 0.8420877105219277,
"grad_norm": 0.4102977216243744,
"learning_rate": 2e-05,
"loss": 0.7545,
"step": 10100
},
{
"epoch": 0.8429214607303652,
"grad_norm": 0.4001510739326477,
"learning_rate": 2e-05,
"loss": 0.7555,
"step": 10110
},
{
"epoch": 0.8437552109388027,
"grad_norm": 0.3942747116088867,
"learning_rate": 2e-05,
"loss": 0.759,
"step": 10120
},
{
"epoch": 0.8445889611472402,
"grad_norm": 0.45337966084480286,
"learning_rate": 2e-05,
"loss": 0.7367,
"step": 10130
},
{
"epoch": 0.8454227113556778,
"grad_norm": 0.38540589809417725,
"learning_rate": 2e-05,
"loss": 0.7392,
"step": 10140
},
{
"epoch": 0.8462564615641154,
"grad_norm": 0.40045589208602905,
"learning_rate": 2e-05,
"loss": 0.7648,
"step": 10150
},
{
"epoch": 0.847090211772553,
"grad_norm": 0.409315824508667,
"learning_rate": 2e-05,
"loss": 0.7384,
"step": 10160
},
{
"epoch": 0.8479239619809905,
"grad_norm": 0.39985573291778564,
"learning_rate": 2e-05,
"loss": 0.7729,
"step": 10170
},
{
"epoch": 0.8487577121894281,
"grad_norm": 0.4048546850681305,
"learning_rate": 1.999957358086795e-05,
"loss": 0.752,
"step": 10180
},
{
"epoch": 0.8495914623978656,
"grad_norm": 0.40265771746635437,
"learning_rate": 1.9991993813020483e-05,
"loss": 0.75,
"step": 10190
},
{
"epoch": 0.8504252126063031,
"grad_norm": 0.424346923828125,
"learning_rate": 1.9974946373028628e-05,
"loss": 0.7646,
"step": 10200
},
{
"epoch": 0.8512589628147407,
"grad_norm": 0.40627628564834595,
"learning_rate": 1.994844749501764e-05,
"loss": 0.7454,
"step": 10210
},
{
"epoch": 0.8520927130231782,
"grad_norm": 0.4106254279613495,
"learning_rate": 1.9912522413632988e-05,
"loss": 0.7475,
"step": 10220
},
{
"epoch": 0.8529264632316158,
"grad_norm": 0.4623664617538452,
"learning_rate": 1.9867205340009656e-05,
"loss": 0.7472,
"step": 10230
},
{
"epoch": 0.8537602134400534,
"grad_norm": 0.3809194564819336,
"learning_rate": 1.9812539429193164e-05,
"loss": 0.7508,
"step": 10240
},
{
"epoch": 0.8545939636484909,
"grad_norm": 0.38315585255622864,
"learning_rate": 1.9748576739043423e-05,
"loss": 0.7611,
"step": 10250
},
{
"epoch": 0.8554277138569285,
"grad_norm": 0.41685402393341064,
"learning_rate": 1.967537818066047e-05,
"loss": 0.7243,
"step": 10260
},
{
"epoch": 0.856261464065366,
"grad_norm": 0.4031088650226593,
"learning_rate": 1.959301346037941e-05,
"loss": 0.7532,
"step": 10270
},
{
"epoch": 0.8570952142738035,
"grad_norm": 0.38420358300209045,
"learning_rate": 1.9501561013389646e-05,
"loss": 0.7586,
"step": 10280
},
{
"epoch": 0.8579289644822411,
"grad_norm": 0.38613128662109375,
"learning_rate": 1.9401107929041795e-05,
"loss": 0.7634,
"step": 10290
},
{
"epoch": 0.8587627146906787,
"grad_norm": 0.4051407277584076,
"learning_rate": 1.9291749867913225e-05,
"loss": 0.7641,
"step": 10300
},
{
"epoch": 0.8595964648991162,
"grad_norm": 0.38893383741378784,
"learning_rate": 1.91735909707114e-05,
"loss": 0.7556,
"step": 10310
},
{
"epoch": 0.8604302151075538,
"grad_norm": 0.37228941917419434,
"learning_rate": 1.9046743759101545e-05,
"loss": 0.7489,
"step": 10320
},
{
"epoch": 0.8612639653159914,
"grad_norm": 0.3989238440990448,
"learning_rate": 1.8911329028553324e-05,
"loss": 0.7363,
"step": 10330
},
{
"epoch": 0.8620977155244289,
"grad_norm": 0.4020388722419739,
"learning_rate": 1.876747573330835e-05,
"loss": 0.7327,
"step": 10340
},
{
"epoch": 0.8629314657328664,
"grad_norm": 0.397251695394516,
"learning_rate": 1.8615320863578244e-05,
"loss": 0.7571,
"step": 10350
},
{
"epoch": 0.863765215941304,
"grad_norm": 0.40196287631988525,
"learning_rate": 1.8455009315090036e-05,
"loss": 0.7175,
"step": 10360
},
{
"epoch": 0.8645989661497415,
"grad_norm": 0.3879379630088806,
"learning_rate": 1.8286693751103294e-05,
"loss": 0.7612,
"step": 10370
},
{
"epoch": 0.8654327163581791,
"grad_norm": 0.4093306362628937,
"learning_rate": 1.811053445703024e-05,
"loss": 0.7641,
"step": 10380
},
{
"epoch": 0.8662664665666167,
"grad_norm": 0.3943707048892975,
"learning_rate": 1.7926699187797375e-05,
"loss": 0.7613,
"step": 10390
},
{
"epoch": 0.8671002167750542,
"grad_norm": 0.37616631388664246,
"learning_rate": 1.7735363008093995e-05,
"loss": 0.7668,
"step": 10400
},
{
"epoch": 0.8679339669834918,
"grad_norm": 0.36308473348617554,
"learning_rate": 1.7536708125659577e-05,
"loss": 0.7857,
"step": 10410
},
{
"epoch": 0.8687677171919292,
"grad_norm": 0.3812304437160492,
"learning_rate": 1.733092371776905e-05,
"loss": 0.7371,
"step": 10420
},
{
"epoch": 0.8696014674003668,
"grad_norm": 0.4048880636692047,
"learning_rate": 1.7118205751080915e-05,
"loss": 0.7728,
"step": 10430
},
{
"epoch": 0.8704352176088044,
"grad_norm": 0.409601628780365,
"learning_rate": 1.6898756795019935e-05,
"loss": 0.7586,
"step": 10440
},
{
"epoch": 0.871268967817242,
"grad_norm": 0.39381006360054016,
"learning_rate": 1.667278582887211e-05,
"loss": 0.7047,
"step": 10450
},
{
"epoch": 0.8721027180256795,
"grad_norm": 0.37099140882492065,
"learning_rate": 1.6440508042775545e-05,
"loss": 0.7512,
"step": 10460
},
{
"epoch": 0.8729364682341171,
"grad_norm": 0.37427759170532227,
"learning_rate": 1.6202144632796796e-05,
"loss": 0.7565,
"step": 10470
},
{
"epoch": 0.8737702184425546,
"grad_norm": 0.4058534502983093,
"learning_rate": 1.595792259028783e-05,
"loss": 0.7442,
"step": 10480
},
{
"epoch": 0.8746039686509922,
"grad_norm": 0.4051295518875122,
"learning_rate": 1.570807448572419e-05,
"loss": 0.7453,
"step": 10490
},
{
"epoch": 0.8754377188594297,
"grad_norm": 0.39752498269081116,
"learning_rate": 1.5452838247230197e-05,
"loss": 0.7447,
"step": 10500
},
{
"epoch": 0.8762714690678672,
"grad_norm": 0.4177260398864746,
"learning_rate": 1.5192456934002106e-05,
"loss": 0.7531,
"step": 10510
},
{
"epoch": 0.8771052192763048,
"grad_norm": 0.4967744052410126,
"learning_rate": 1.492717850484502e-05,
"loss": 0.7428,
"step": 10520
},
{
"epoch": 0.8779389694847424,
"grad_norm": 0.407562255859375,
"learning_rate": 1.4657255582043904e-05,
"loss": 0.7667,
"step": 10530
},
{
"epoch": 0.8787727196931799,
"grad_norm": 0.40194448828697205,
"learning_rate": 1.4382945210793663e-05,
"loss": 0.7367,
"step": 10540
},
{
"epoch": 0.8796064699016175,
"grad_norm": 0.3896706700325012,
"learning_rate": 1.4104508614417267e-05,
"loss": 0.7193,
"step": 10550
},
{
"epoch": 0.8804402201100551,
"grad_norm": 0.3807949423789978,
"learning_rate": 1.382221094560512e-05,
"loss": 0.7362,
"step": 10560
},
{
"epoch": 0.8812739703184925,
"grad_norm": 0.3761776089668274,
"learning_rate": 1.3536321033912506e-05,
"loss": 0.7717,
"step": 10570
},
{
"epoch": 0.8821077205269301,
"grad_norm": 0.40223434567451477,
"learning_rate": 1.3247111129755609e-05,
"loss": 0.7447,
"step": 10580
},
{
"epoch": 0.8829414707353677,
"grad_norm": 0.44566163420677185,
"learning_rate": 1.2954856645149868e-05,
"loss": 0.7618,
"step": 10590
},
{
"epoch": 0.8837752209438052,
"grad_norm": 0.3852149546146393,
"learning_rate": 1.2659835891437553e-05,
"loss": 0.7168,
"step": 10600
},
{
"epoch": 0.8846089711522428,
"grad_norm": 0.43151143193244934,
"learning_rate": 1.236232981425436e-05,
"loss": 0.737,
"step": 10610
},
{
"epoch": 0.8854427213606804,
"grad_norm": 0.41107502579689026,
"learning_rate": 1.2062621725987402e-05,
"loss": 0.7667,
"step": 10620
},
{
"epoch": 0.8862764715691179,
"grad_norm": 0.39373138546943665,
"learning_rate": 1.1760997035979318e-05,
"loss": 0.7389,
"step": 10630
},
{
"epoch": 0.8871102217775555,
"grad_norm": 0.4359895586967468,
"learning_rate": 1.1457742978735514e-05,
"loss": 0.7393,
"step": 10640
},
{
"epoch": 0.887943971985993,
"grad_norm": 0.3692585527896881,
"learning_rate": 1.1153148340393298e-05,
"loss": 0.7469,
"step": 10650
},
{
"epoch": 0.8887777221944305,
"grad_norm": 0.3929360806941986,
"learning_rate": 1.0847503183713424e-05,
"loss": 0.7384,
"step": 10660
},
{
"epoch": 0.8896114724028681,
"grad_norm": 0.3801104426383972,
"learning_rate": 1.0541098571855896e-05,
"loss": 0.7394,
"step": 10670
},
{
"epoch": 0.8904452226113057,
"grad_norm": 0.37870684266090393,
"learning_rate": 1.0234226291203123e-05,
"loss": 0.7686,
"step": 10680
},
{
"epoch": 0.8912789728197432,
"grad_norm": 0.3559103012084961,
"learning_rate": 9.927178573494333e-06,
"loss": 0.7376,
"step": 10690
},
{
"epoch": 0.8921127230281808,
"grad_norm": 0.373339980840683,
"learning_rate": 9.620247817535902e-06,
"loss": 0.746,
"step": 10700
},
{
"epoch": 0.8929464732366184,
"grad_norm": 0.37791451811790466,
"learning_rate": 9.313726310752581e-06,
"loss": 0.749,
"step": 10710
},
{
"epoch": 0.8937802234450558,
"grad_norm": 0.3804498016834259,
"learning_rate": 9.00790595084477e-06,
"loss": 0.7297,
"step": 10720
},
{
"epoch": 0.8946139736534934,
"grad_norm": 0.4025641679763794,
"learning_rate": 8.703077967816944e-06,
"loss": 0.7546,
"step": 10730
},
{
"epoch": 0.8954477238619309,
"grad_norm": 0.3704034388065338,
"learning_rate": 8.39953264664192e-06,
"loss": 0.7439,
"step": 10740
},
{
"epoch": 0.8962814740703685,
"grad_norm": 0.37772586941719055,
"learning_rate": 8.097559050825058e-06,
"loss": 0.7601,
"step": 10750
},
{
"epoch": 0.8971152242788061,
"grad_norm": 0.3745128810405731,
"learning_rate": 7.79744474713166e-06,
"loss": 0.7225,
"step": 10760
},
{
"epoch": 0.8979489744872436,
"grad_norm": 0.3776002526283264,
"learning_rate": 7.499475531739696e-06,
"loss": 0.7088,
"step": 10770
},
{
"epoch": 0.8987827246956812,
"grad_norm": 0.37730729579925537,
"learning_rate": 7.203935158078662e-06,
"loss": 0.7264,
"step": 10780
},
{
"epoch": 0.8996164749041188,
"grad_norm": 0.39154091477394104,
"learning_rate": 6.911105066613709e-06,
"loss": 0.7319,
"step": 10790
},
{
"epoch": 0.9004502251125562,
"grad_norm": 0.43097835779190063,
"learning_rate": 6.621264116832394e-06,
"loss": 0.759,
"step": 10800
},
{
"epoch": 0.9012839753209938,
"grad_norm": 0.42627617716789246,
"learning_rate": 6.334688321689274e-06,
"loss": 0.7502,
"step": 10810
},
{
"epoch": 0.9021177255294314,
"grad_norm": 0.39662250876426697,
"learning_rate": 6.051650584761237e-06,
"loss": 0.6932,
"step": 10820
},
{
"epoch": 0.9029514757378689,
"grad_norm": 0.4144646227359772,
"learning_rate": 5.772420440363841e-06,
"loss": 0.7655,
"step": 10830
},
{
"epoch": 0.9037852259463065,
"grad_norm": 0.3992006778717041,
"learning_rate": 5.497263796876207e-06,
"loss": 0.7318,
"step": 10840
},
{
"epoch": 0.9046189761547441,
"grad_norm": 0.379840612411499,
"learning_rate": 5.226442683518813e-06,
"loss": 0.7544,
"step": 10850
},
{
"epoch": 0.9054527263631816,
"grad_norm": 0.3885243833065033,
"learning_rate": 4.960215000825432e-06,
"loss": 0.7219,
"step": 10860
},
{
"epoch": 0.9062864765716191,
"grad_norm": 0.386182576417923,
"learning_rate": 4.698834275046711e-06,
"loss": 0.755,
"step": 10870
},
{
"epoch": 0.9071202267800567,
"grad_norm": 0.38182371854782104,
"learning_rate": 4.442549416719423e-06,
"loss": 0.7578,
"step": 10880
},
{
"epoch": 0.9079539769884942,
"grad_norm": 0.38716039061546326,
"learning_rate": 4.1916044836311565e-06,
"loss": 0.7277,
"step": 10890
},
{
"epoch": 0.9087877271969318,
"grad_norm": 0.3713051974773407,
"learning_rate": 3.94623844840626e-06,
"loss": 0.7271,
"step": 10900
},
{
"epoch": 0.9096214774053694,
"grad_norm": 0.40132370591163635,
"learning_rate": 3.7066849709343467e-06,
"loss": 0.7317,
"step": 10910
},
{
"epoch": 0.9104552276138069,
"grad_norm": 0.4100184142589569,
"learning_rate": 3.473172175858059e-06,
"loss": 0.7361,
"step": 10920
},
{
"epoch": 0.9112889778222445,
"grad_norm": 0.4052720069885254,
"learning_rate": 3.2459224353320046e-06,
"loss": 0.7578,
"step": 10930
},
{
"epoch": 0.9121227280306821,
"grad_norm": 0.3823261559009552,
"learning_rate": 3.025152157259735e-06,
"loss": 0.7464,
"step": 10940
},
{
"epoch": 0.9129564782391195,
"grad_norm": 0.37718498706817627,
"learning_rate": 2.811071579210425e-06,
"loss": 0.7335,
"step": 10950
},
{
"epoch": 0.9137902284475571,
"grad_norm": 0.41351038217544556,
"learning_rate": 2.603884568211513e-06,
"loss": 0.7417,
"step": 10960
},
{
"epoch": 0.9146239786559947,
"grad_norm": 0.388394832611084,
"learning_rate": 2.4037884266079434e-06,
"loss": 0.7619,
"step": 10970
},
{
"epoch": 0.9154577288644322,
"grad_norm": 0.3748188316822052,
"learning_rate": 2.2109737041728955e-06,
"loss": 0.7369,
"step": 10980
},
{
"epoch": 0.9162914790728698,
"grad_norm": 0.37020859122276306,
"learning_rate": 2.0256240166489454e-06,
"loss": 0.7255,
"step": 10990
},
{
"epoch": 0.9171252292813074,
"grad_norm": 0.3901329040527344,
"learning_rate": 1.847915870892413e-06,
"loss": 0.7473,
"step": 11000
},
{
"epoch": 0.9179589794897449,
"grad_norm": 0.40195220708847046,
"learning_rate": 1.6780184967874715e-06,
"loss": 0.7163,
"step": 11010
},
{
"epoch": 0.9187927296981824,
"grad_norm": 0.36612290143966675,
"learning_rate": 1.5160936860900294e-06,
"loss": 0.7423,
"step": 11020
},
{
"epoch": 0.9196264799066199,
"grad_norm": 0.41208454966545105,
"learning_rate": 1.3622956383548762e-06,
"loss": 0.7384,
"step": 11030
},
{
"epoch": 0.9204602301150575,
"grad_norm": 0.3827102780342102,
"learning_rate": 1.216770814092834e-06,
"loss": 0.6978,
"step": 11040
},
{
"epoch": 0.9212939803234951,
"grad_norm": 0.38724175095558167,
"learning_rate": 1.0796577952977013e-06,
"loss": 0.7109,
"step": 11050
},
{
"epoch": 0.9221277305319326,
"grad_norm": 0.37209346890449524,
"learning_rate": 9.510871534758705e-07,
"loss": 0.7254,
"step": 11060
},
{
"epoch": 0.9229614807403702,
"grad_norm": 0.4128079414367676,
"learning_rate": 8.311813253042334e-07,
"loss": 0.7358,
"step": 11070
},
{
"epoch": 0.9237952309488078,
"grad_norm": 0.38232487440109253,
"learning_rate": 7.200544960348308e-07,
"loss": 0.7124,
"step": 11080
},
{
"epoch": 0.9246289811572453,
"grad_norm": 0.41867467761039734,
"learning_rate": 6.178124907572545e-07,
"loss": 0.7245,
"step": 11090
},
{
"epoch": 0.9254627313656828,
"grad_norm": 0.43368789553642273,
"learning_rate": 5.245526736223528e-07,
"loss": 0.6945,
"step": 11100
},
{
"epoch": 0.9262964815741204,
"grad_norm": 0.3890843689441681,
"learning_rate": 4.403638551232205e-07,
"loss": 0.7199,
"step": 11110
},
{
"epoch": 0.9271302317825579,
"grad_norm": 0.3757689595222473,
"learning_rate": 3.6532620752175616e-07,
"loss": 0.7294,
"step": 11120
},
{
"epoch": 0.9279639819909955,
"grad_norm": 0.3891938030719757,
"learning_rate": 2.9951118850133247e-07,
"loss": 0.7298,
"step": 11130
},
{
"epoch": 0.9287977321994331,
"grad_norm": 0.38250407576560974,
"learning_rate": 2.429814731182774e-07,
"loss": 0.7349,
"step": 11140
},
{
"epoch": 0.9296314824078706,
"grad_norm": 0.3869253396987915,
"learning_rate": 1.957908941169813e-07,
"loss": 0.7275,
"step": 11150
},
{
"epoch": 0.9304652326163082,
"grad_norm": 0.3851337432861328,
"learning_rate": 1.5798439066545254e-07,
"loss": 0.7147,
"step": 11160
},
{
"epoch": 0.9312989828247457,
"grad_norm": 0.39653924107551575,
"learning_rate": 1.2959796556014471e-07,
"loss": 0.7545,
"step": 11170
},
{
"epoch": 0.9321327330331832,
"grad_norm": 0.385099858045578,
"learning_rate": 1.1065865094081884e-07,
"loss": 0.732,
"step": 11180
},
{
"epoch": 0.9329664832416208,
"grad_norm": 0.4001409411430359,
"learning_rate": 1.011844825480734e-07,
"loss": 0.7176,
"step": 11190
},
{
"epoch": 0.9332999833249959,
"step": 11194,
"total_flos": 4.547514943786923e+19,
"train_loss": 0.004173955939509133,
"train_runtime": 613.8635,
"train_samples_per_second": 218.824,
"train_steps_per_second": 18.235
}
],
"logging_steps": 10,
"max_steps": 11194,
"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": 4.547514943786923e+19,
"train_batch_size": 1,
"trial_name": null,
"trial_params": null
}
{
"best_global_step": null,
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.9332999833249959,
"eval_steps": 500,
"global_step": 11194,
"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,