kdcyberdude's picture
Training in progress, step 2000, checkpoint
58f4db5 verified
raw
history blame
36 kB
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 0.0520784509785541,
"eval_steps": 500,
"global_step": 2000,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0002603922548927705,
"grad_norm": 0.8521247506141663,
"learning_rate": 5.194805194805195e-06,
"loss": 0.7412,
"step": 10
},
{
"epoch": 0.000520784509785541,
"grad_norm": 0.6229312419891357,
"learning_rate": 1.038961038961039e-05,
"loss": 0.7138,
"step": 20
},
{
"epoch": 0.0007811767646783114,
"grad_norm": 0.4566498100757599,
"learning_rate": 1.5584415584415583e-05,
"loss": 0.7079,
"step": 30
},
{
"epoch": 0.001041569019571082,
"grad_norm": 0.4316692650318146,
"learning_rate": 2.077922077922078e-05,
"loss": 0.6988,
"step": 40
},
{
"epoch": 0.0013019612744638524,
"grad_norm": 0.615436315536499,
"learning_rate": 2.5974025974025972e-05,
"loss": 0.6937,
"step": 50
},
{
"epoch": 0.0015623535293566228,
"grad_norm": 0.48698583245277405,
"learning_rate": 3.1168831168831166e-05,
"loss": 0.7043,
"step": 60
},
{
"epoch": 0.0018227457842493933,
"grad_norm": 0.3984021544456482,
"learning_rate": 3.6363636363636364e-05,
"loss": 0.6563,
"step": 70
},
{
"epoch": 0.002083138039142164,
"grad_norm": 0.37576180696487427,
"learning_rate": 4.155844155844156e-05,
"loss": 0.6462,
"step": 80
},
{
"epoch": 0.0023435302940349343,
"grad_norm": 0.35269680619239807,
"learning_rate": 4.675324675324675e-05,
"loss": 0.6656,
"step": 90
},
{
"epoch": 0.0026039225489277048,
"grad_norm": 0.31541451811790466,
"learning_rate": 5.1948051948051944e-05,
"loss": 0.6547,
"step": 100
},
{
"epoch": 0.002864314803820475,
"grad_norm": 0.3462330400943756,
"learning_rate": 5.714285714285714e-05,
"loss": 0.6621,
"step": 110
},
{
"epoch": 0.0031247070587132456,
"grad_norm": 0.3465985953807831,
"learning_rate": 6.233766233766233e-05,
"loss": 0.6273,
"step": 120
},
{
"epoch": 0.003385099313606016,
"grad_norm": 0.3297797441482544,
"learning_rate": 6.753246753246754e-05,
"loss": 0.6559,
"step": 130
},
{
"epoch": 0.0036454915684987865,
"grad_norm": 0.3888818621635437,
"learning_rate": 7.272727272727273e-05,
"loss": 0.6756,
"step": 140
},
{
"epoch": 0.003905883823391557,
"grad_norm": 0.3542368710041046,
"learning_rate": 7.792207792207793e-05,
"loss": 0.6506,
"step": 150
},
{
"epoch": 0.004166276078284328,
"grad_norm": 0.37369370460510254,
"learning_rate": 8.311688311688312e-05,
"loss": 0.6645,
"step": 160
},
{
"epoch": 0.004426668333177098,
"grad_norm": 0.3700549900531769,
"learning_rate": 8.831168831168831e-05,
"loss": 0.6727,
"step": 170
},
{
"epoch": 0.004687060588069869,
"grad_norm": 0.32032889127731323,
"learning_rate": 9.35064935064935e-05,
"loss": 0.6529,
"step": 180
},
{
"epoch": 0.004947452842962639,
"grad_norm": 0.3331650495529175,
"learning_rate": 9.870129870129871e-05,
"loss": 0.6627,
"step": 190
},
{
"epoch": 0.0052078450978554095,
"grad_norm": 0.3300645351409912,
"learning_rate": 0.00010389610389610389,
"loss": 0.676,
"step": 200
},
{
"epoch": 0.0054682373527481795,
"grad_norm": 0.350356787443161,
"learning_rate": 0.00010909090909090909,
"loss": 0.6564,
"step": 210
},
{
"epoch": 0.00572862960764095,
"grad_norm": 0.382756769657135,
"learning_rate": 0.00011428571428571428,
"loss": 0.6243,
"step": 220
},
{
"epoch": 0.00598902186253372,
"grad_norm": 0.34450188279151917,
"learning_rate": 0.00011948051948051949,
"loss": 0.6611,
"step": 230
},
{
"epoch": 0.006249414117426491,
"grad_norm": 0.3705821633338928,
"learning_rate": 0.00012467532467532467,
"loss": 0.6384,
"step": 240
},
{
"epoch": 0.006509806372319262,
"grad_norm": 0.36822304129600525,
"learning_rate": 0.00012987012987012987,
"loss": 0.6415,
"step": 250
},
{
"epoch": 0.006770198627212032,
"grad_norm": 0.32358303666114807,
"learning_rate": 0.00013506493506493507,
"loss": 0.6584,
"step": 260
},
{
"epoch": 0.007030590882104803,
"grad_norm": 0.33386844396591187,
"learning_rate": 0.00014025974025974028,
"loss": 0.6702,
"step": 270
},
{
"epoch": 0.007290983136997573,
"grad_norm": 0.32447949051856995,
"learning_rate": 0.00014545454545454546,
"loss": 0.6519,
"step": 280
},
{
"epoch": 0.007551375391890344,
"grad_norm": 0.3388073146343231,
"learning_rate": 0.00015064935064935066,
"loss": 0.6735,
"step": 290
},
{
"epoch": 0.007811767646783114,
"grad_norm": 0.39655518531799316,
"learning_rate": 0.00015584415584415587,
"loss": 0.672,
"step": 300
},
{
"epoch": 0.008072159901675884,
"grad_norm": 0.41258928179740906,
"learning_rate": 0.00016103896103896104,
"loss": 0.6626,
"step": 310
},
{
"epoch": 0.008332552156568656,
"grad_norm": 0.3963010311126709,
"learning_rate": 0.00016623376623376625,
"loss": 0.6653,
"step": 320
},
{
"epoch": 0.008592944411461426,
"grad_norm": 0.3641106188297272,
"learning_rate": 0.00017142857142857143,
"loss": 0.6389,
"step": 330
},
{
"epoch": 0.008853336666354196,
"grad_norm": 0.38745763897895813,
"learning_rate": 0.00017662337662337663,
"loss": 0.6928,
"step": 340
},
{
"epoch": 0.009113728921246966,
"grad_norm": 0.4573372006416321,
"learning_rate": 0.00018181818181818183,
"loss": 0.6679,
"step": 350
},
{
"epoch": 0.009374121176139737,
"grad_norm": 0.45714282989501953,
"learning_rate": 0.000187012987012987,
"loss": 0.6453,
"step": 360
},
{
"epoch": 0.009634513431032507,
"grad_norm": 0.37631818652153015,
"learning_rate": 0.00019220779220779222,
"loss": 0.6467,
"step": 370
},
{
"epoch": 0.009894905685925277,
"grad_norm": 0.3658345639705658,
"learning_rate": 0.00019740259740259742,
"loss": 0.6631,
"step": 380
},
{
"epoch": 0.010155297940818049,
"grad_norm": 0.3953540623188019,
"learning_rate": 0.00019999996515752773,
"loss": 0.6573,
"step": 390
},
{
"epoch": 0.010415690195710819,
"grad_norm": 0.377763569355011,
"learning_rate": 0.00019999968641789507,
"loss": 0.6664,
"step": 400
},
{
"epoch": 0.010676082450603589,
"grad_norm": 0.37128835916519165,
"learning_rate": 0.0001999991289394067,
"loss": 0.6342,
"step": 410
},
{
"epoch": 0.010936474705496359,
"grad_norm": 0.33881694078445435,
"learning_rate": 0.00019999829272361654,
"loss": 0.6476,
"step": 420
},
{
"epoch": 0.01119686696038913,
"grad_norm": 0.39774075150489807,
"learning_rate": 0.00019999717777285545,
"loss": 0.633,
"step": 430
},
{
"epoch": 0.0114572592152819,
"grad_norm": 0.41350051760673523,
"learning_rate": 0.00019999578409023126,
"loss": 0.6541,
"step": 440
},
{
"epoch": 0.01171765147017467,
"grad_norm": 0.47954171895980835,
"learning_rate": 0.00019999411167962868,
"loss": 0.6545,
"step": 450
},
{
"epoch": 0.01197804372506744,
"grad_norm": 0.46860000491142273,
"learning_rate": 0.00019999216054570942,
"loss": 0.6512,
"step": 460
},
{
"epoch": 0.012238435979960213,
"grad_norm": 0.4395809471607208,
"learning_rate": 0.00019998993069391205,
"loss": 0.6587,
"step": 470
},
{
"epoch": 0.012498828234852983,
"grad_norm": 0.43222516775131226,
"learning_rate": 0.00019998742213045206,
"loss": 0.6292,
"step": 480
},
{
"epoch": 0.012759220489745753,
"grad_norm": 0.39363613724708557,
"learning_rate": 0.00019998463486232179,
"loss": 0.6319,
"step": 490
},
{
"epoch": 0.013019612744638524,
"grad_norm": 0.4984697699546814,
"learning_rate": 0.0001999815688972905,
"loss": 0.6488,
"step": 500
},
{
"epoch": 0.013280004999531294,
"grad_norm": 0.4710462689399719,
"learning_rate": 0.00019997822424390422,
"loss": 0.6633,
"step": 510
},
{
"epoch": 0.013540397254424064,
"grad_norm": 0.4141169786453247,
"learning_rate": 0.00019997460091148586,
"loss": 0.6471,
"step": 520
},
{
"epoch": 0.013800789509316834,
"grad_norm": 0.39957430958747864,
"learning_rate": 0.00019997069891013503,
"loss": 0.6226,
"step": 530
},
{
"epoch": 0.014061181764209606,
"grad_norm": 0.4508794844150543,
"learning_rate": 0.00019996651825072826,
"loss": 0.6559,
"step": 540
},
{
"epoch": 0.014321574019102376,
"grad_norm": 0.4256739020347595,
"learning_rate": 0.00019996205894491856,
"loss": 0.6551,
"step": 550
},
{
"epoch": 0.014581966273995146,
"grad_norm": 0.43204987049102783,
"learning_rate": 0.00019995732100513592,
"loss": 0.6254,
"step": 560
},
{
"epoch": 0.014842358528887916,
"grad_norm": 0.37589946389198303,
"learning_rate": 0.00019995230444458682,
"loss": 0.6543,
"step": 570
},
{
"epoch": 0.015102750783780688,
"grad_norm": 0.40850168466567993,
"learning_rate": 0.0001999470092772544,
"loss": 0.6474,
"step": 580
},
{
"epoch": 0.015363143038673458,
"grad_norm": 0.3754895031452179,
"learning_rate": 0.00019994143551789839,
"loss": 0.6502,
"step": 590
},
{
"epoch": 0.015623535293566228,
"grad_norm": 0.3857438266277313,
"learning_rate": 0.00019993558318205507,
"loss": 0.6544,
"step": 600
},
{
"epoch": 0.015883927548459,
"grad_norm": 0.4063841998577118,
"learning_rate": 0.00019992945228603724,
"loss": 0.639,
"step": 610
},
{
"epoch": 0.016144319803351768,
"grad_norm": 0.35183581709861755,
"learning_rate": 0.0001999230428469341,
"loss": 0.6442,
"step": 620
},
{
"epoch": 0.01640471205824454,
"grad_norm": 0.4158167243003845,
"learning_rate": 0.00019991635488261138,
"loss": 0.6586,
"step": 630
},
{
"epoch": 0.01666510431313731,
"grad_norm": 0.45118188858032227,
"learning_rate": 0.00019990938841171104,
"loss": 0.6581,
"step": 640
},
{
"epoch": 0.01692549656803008,
"grad_norm": 0.39950400590896606,
"learning_rate": 0.0001999021434536514,
"loss": 0.6712,
"step": 650
},
{
"epoch": 0.01718588882292285,
"grad_norm": 0.35208678245544434,
"learning_rate": 0.00019989462002862704,
"loss": 0.6398,
"step": 660
},
{
"epoch": 0.017446281077815623,
"grad_norm": 0.38008975982666016,
"learning_rate": 0.0001998868181576088,
"loss": 0.6479,
"step": 670
},
{
"epoch": 0.01770667333270839,
"grad_norm": 0.4314909875392914,
"learning_rate": 0.00019987873786234348,
"loss": 0.6358,
"step": 680
},
{
"epoch": 0.017967065587601163,
"grad_norm": 0.3982577323913574,
"learning_rate": 0.00019987037916535417,
"loss": 0.6361,
"step": 690
},
{
"epoch": 0.01822745784249393,
"grad_norm": 0.3529202342033386,
"learning_rate": 0.0001998617420899398,
"loss": 0.64,
"step": 700
},
{
"epoch": 0.018487850097386703,
"grad_norm": 0.41149991750717163,
"learning_rate": 0.0001998528266601754,
"loss": 0.6684,
"step": 710
},
{
"epoch": 0.018748242352279475,
"grad_norm": 0.42630311846733093,
"learning_rate": 0.0001998436329009118,
"loss": 0.6429,
"step": 720
},
{
"epoch": 0.019008634607172243,
"grad_norm": 0.4028918147087097,
"learning_rate": 0.00019983416083777563,
"loss": 0.6573,
"step": 730
},
{
"epoch": 0.019269026862065015,
"grad_norm": 0.3785901963710785,
"learning_rate": 0.0001998244104971693,
"loss": 0.6132,
"step": 740
},
{
"epoch": 0.019529419116957786,
"grad_norm": 0.39018985629081726,
"learning_rate": 0.0001998143819062709,
"loss": 0.6287,
"step": 750
},
{
"epoch": 0.019789811371850555,
"grad_norm": 0.4268128573894501,
"learning_rate": 0.00019980407509303413,
"loss": 0.6585,
"step": 760
},
{
"epoch": 0.020050203626743326,
"grad_norm": 0.4293033480644226,
"learning_rate": 0.00019979349008618808,
"loss": 0.6843,
"step": 770
},
{
"epoch": 0.020310595881636098,
"grad_norm": 0.38943207263946533,
"learning_rate": 0.00019978262691523743,
"loss": 0.6265,
"step": 780
},
{
"epoch": 0.020570988136528866,
"grad_norm": 0.40528395771980286,
"learning_rate": 0.00019977148561046217,
"loss": 0.6392,
"step": 790
},
{
"epoch": 0.020831380391421638,
"grad_norm": 0.4273380935192108,
"learning_rate": 0.0001997600662029175,
"loss": 0.6615,
"step": 800
},
{
"epoch": 0.021091772646314406,
"grad_norm": 0.4269028306007385,
"learning_rate": 0.00019974836872443388,
"loss": 0.6412,
"step": 810
},
{
"epoch": 0.021352164901207178,
"grad_norm": 0.3542031943798065,
"learning_rate": 0.0001997363932076168,
"loss": 0.6606,
"step": 820
},
{
"epoch": 0.02161255715609995,
"grad_norm": 0.36826202273368835,
"learning_rate": 0.00019972413968584682,
"loss": 0.6387,
"step": 830
},
{
"epoch": 0.021872949410992718,
"grad_norm": 0.4278506338596344,
"learning_rate": 0.0001997116081932793,
"loss": 0.6544,
"step": 840
},
{
"epoch": 0.02213334166588549,
"grad_norm": 0.467886358499527,
"learning_rate": 0.0001996987987648446,
"loss": 0.6524,
"step": 850
},
{
"epoch": 0.02239373392077826,
"grad_norm": 0.36823606491088867,
"learning_rate": 0.0001996857114362476,
"loss": 0.6553,
"step": 860
},
{
"epoch": 0.02265412617567103,
"grad_norm": 0.42569059133529663,
"learning_rate": 0.00019967234624396793,
"loss": 0.6484,
"step": 870
},
{
"epoch": 0.0229145184305638,
"grad_norm": 0.36995476484298706,
"learning_rate": 0.00019965870322525965,
"loss": 0.6626,
"step": 880
},
{
"epoch": 0.023174910685456573,
"grad_norm": 0.4284444749355316,
"learning_rate": 0.0001996447824181513,
"loss": 0.6579,
"step": 890
},
{
"epoch": 0.02343530294034934,
"grad_norm": 0.36263275146484375,
"learning_rate": 0.0001996305838614457,
"loss": 0.6466,
"step": 900
},
{
"epoch": 0.023695695195242113,
"grad_norm": 0.43936702609062195,
"learning_rate": 0.00019961610759471984,
"loss": 0.6534,
"step": 910
},
{
"epoch": 0.02395608745013488,
"grad_norm": 0.37757524847984314,
"learning_rate": 0.00019960135365832486,
"loss": 0.6344,
"step": 920
},
{
"epoch": 0.024216479705027653,
"grad_norm": 0.40086570382118225,
"learning_rate": 0.00019958632209338587,
"loss": 0.6265,
"step": 930
},
{
"epoch": 0.024476871959920425,
"grad_norm": 0.3435315489768982,
"learning_rate": 0.00019957101294180174,
"loss": 0.6479,
"step": 940
},
{
"epoch": 0.024737264214813193,
"grad_norm": 0.34466204047203064,
"learning_rate": 0.00019955542624624522,
"loss": 0.641,
"step": 950
},
{
"epoch": 0.024997656469705965,
"grad_norm": 0.46282994747161865,
"learning_rate": 0.00019953956205016256,
"loss": 0.6389,
"step": 960
},
{
"epoch": 0.025258048724598737,
"grad_norm": 0.3815780580043793,
"learning_rate": 0.00019952342039777362,
"loss": 0.6472,
"step": 970
},
{
"epoch": 0.025518440979491505,
"grad_norm": 0.43121904134750366,
"learning_rate": 0.00019950700133407163,
"loss": 0.6314,
"step": 980
},
{
"epoch": 0.025778833234384277,
"grad_norm": 0.41635170578956604,
"learning_rate": 0.00019949030490482296,
"loss": 0.6483,
"step": 990
},
{
"epoch": 0.02603922548927705,
"grad_norm": 0.3946804106235504,
"learning_rate": 0.0001994733311565673,
"loss": 0.6383,
"step": 1000
},
{
"epoch": 0.026299617744169817,
"grad_norm": 0.48494285345077515,
"learning_rate": 0.0001994560801366171,
"loss": 0.6617,
"step": 1010
},
{
"epoch": 0.02656000999906259,
"grad_norm": 0.4007907807826996,
"learning_rate": 0.00019943855189305792,
"loss": 0.6187,
"step": 1020
},
{
"epoch": 0.026820402253955357,
"grad_norm": 0.4674074649810791,
"learning_rate": 0.00019942074647474786,
"loss": 0.6629,
"step": 1030
},
{
"epoch": 0.02708079450884813,
"grad_norm": 0.3703964650630951,
"learning_rate": 0.00019940266393131775,
"loss": 0.6606,
"step": 1040
},
{
"epoch": 0.0273411867637409,
"grad_norm": 0.4177350401878357,
"learning_rate": 0.00019938430431317081,
"loss": 0.6285,
"step": 1050
},
{
"epoch": 0.02760157901863367,
"grad_norm": 0.391641765832901,
"learning_rate": 0.00019936566767148257,
"loss": 0.6448,
"step": 1060
},
{
"epoch": 0.02786197127352644,
"grad_norm": 0.38827773928642273,
"learning_rate": 0.00019934675405820077,
"loss": 0.6272,
"step": 1070
},
{
"epoch": 0.028122363528419212,
"grad_norm": 0.41332709789276123,
"learning_rate": 0.00019932756352604515,
"loss": 0.6316,
"step": 1080
},
{
"epoch": 0.02838275578331198,
"grad_norm": 0.38579726219177246,
"learning_rate": 0.00019930809612850735,
"loss": 0.6357,
"step": 1090
},
{
"epoch": 0.028643148038204752,
"grad_norm": 0.4541114568710327,
"learning_rate": 0.00019928835191985076,
"loss": 0.6546,
"step": 1100
},
{
"epoch": 0.028903540293097524,
"grad_norm": 0.37385833263397217,
"learning_rate": 0.0001992683309551103,
"loss": 0.6378,
"step": 1110
},
{
"epoch": 0.029163932547990292,
"grad_norm": 0.39442044496536255,
"learning_rate": 0.00019924803329009243,
"loss": 0.6549,
"step": 1120
},
{
"epoch": 0.029424324802883064,
"grad_norm": 0.3960839509963989,
"learning_rate": 0.00019922745898137473,
"loss": 0.6304,
"step": 1130
},
{
"epoch": 0.029684717057775832,
"grad_norm": 0.4159034192562103,
"learning_rate": 0.00019920660808630598,
"loss": 0.6503,
"step": 1140
},
{
"epoch": 0.029945109312668604,
"grad_norm": 0.4242476522922516,
"learning_rate": 0.00019918548066300592,
"loss": 0.6305,
"step": 1150
},
{
"epoch": 0.030205501567561376,
"grad_norm": 0.4142429530620575,
"learning_rate": 0.0001991640767703651,
"loss": 0.6246,
"step": 1160
},
{
"epoch": 0.030465893822454144,
"grad_norm": 0.4049033522605896,
"learning_rate": 0.00019914239646804462,
"loss": 0.6315,
"step": 1170
},
{
"epoch": 0.030726286077346916,
"grad_norm": 0.4325621426105499,
"learning_rate": 0.00019912043981647616,
"loss": 0.6467,
"step": 1180
},
{
"epoch": 0.030986678332239687,
"grad_norm": 0.35380443930625916,
"learning_rate": 0.00019909820687686157,
"loss": 0.6416,
"step": 1190
},
{
"epoch": 0.031247070587132456,
"grad_norm": 0.3798046410083771,
"learning_rate": 0.0001990756977111729,
"loss": 0.6367,
"step": 1200
},
{
"epoch": 0.03150746284202523,
"grad_norm": 0.4257236123085022,
"learning_rate": 0.0001990529123821522,
"loss": 0.6414,
"step": 1210
},
{
"epoch": 0.031767855096918,
"grad_norm": 0.4575822055339813,
"learning_rate": 0.00019902985095331113,
"loss": 0.6647,
"step": 1220
},
{
"epoch": 0.03202824735181077,
"grad_norm": 0.34732112288475037,
"learning_rate": 0.00019900651348893114,
"loss": 0.6446,
"step": 1230
},
{
"epoch": 0.032288639606703536,
"grad_norm": 0.4493260979652405,
"learning_rate": 0.00019898290005406296,
"loss": 0.6672,
"step": 1240
},
{
"epoch": 0.03254903186159631,
"grad_norm": 0.39185160398483276,
"learning_rate": 0.00019895901071452667,
"loss": 0.6581,
"step": 1250
},
{
"epoch": 0.03280942411648908,
"grad_norm": 0.37691834568977356,
"learning_rate": 0.0001989348455369113,
"loss": 0.644,
"step": 1260
},
{
"epoch": 0.03306981637138185,
"grad_norm": 0.378093421459198,
"learning_rate": 0.0001989104045885748,
"loss": 0.6515,
"step": 1270
},
{
"epoch": 0.03333020862627462,
"grad_norm": 0.37683796882629395,
"learning_rate": 0.00019888568793764385,
"loss": 0.6281,
"step": 1280
},
{
"epoch": 0.03359060088116739,
"grad_norm": 0.37529483437538147,
"learning_rate": 0.00019886069565301355,
"loss": 0.6606,
"step": 1290
},
{
"epoch": 0.03385099313606016,
"grad_norm": 0.3849285840988159,
"learning_rate": 0.00019883542780434733,
"loss": 0.6388,
"step": 1300
},
{
"epoch": 0.03411138539095293,
"grad_norm": 0.3860384523868561,
"learning_rate": 0.0001988098844620767,
"loss": 0.6612,
"step": 1310
},
{
"epoch": 0.0343717776458457,
"grad_norm": 0.4840448200702667,
"learning_rate": 0.0001987840656974011,
"loss": 0.6432,
"step": 1320
},
{
"epoch": 0.034632169900738474,
"grad_norm": 0.3508262038230896,
"learning_rate": 0.00019875797158228775,
"loss": 0.6549,
"step": 1330
},
{
"epoch": 0.034892562155631246,
"grad_norm": 0.4253254234790802,
"learning_rate": 0.00019873160218947125,
"loss": 0.6303,
"step": 1340
},
{
"epoch": 0.03515295441052401,
"grad_norm": 0.37659895420074463,
"learning_rate": 0.00019870495759245362,
"loss": 0.6278,
"step": 1350
},
{
"epoch": 0.03541334666541678,
"grad_norm": 0.36914440989494324,
"learning_rate": 0.0001986780378655039,
"loss": 0.6614,
"step": 1360
},
{
"epoch": 0.035673738920309554,
"grad_norm": 0.40397894382476807,
"learning_rate": 0.0001986508430836581,
"loss": 0.6295,
"step": 1370
},
{
"epoch": 0.035934131175202326,
"grad_norm": 0.3998821973800659,
"learning_rate": 0.0001986233733227188,
"loss": 0.6705,
"step": 1380
},
{
"epoch": 0.0361945234300951,
"grad_norm": 0.37330886721611023,
"learning_rate": 0.00019859562865925525,
"loss": 0.6537,
"step": 1390
},
{
"epoch": 0.03645491568498786,
"grad_norm": 0.3862515091896057,
"learning_rate": 0.00019856760917060277,
"loss": 0.6576,
"step": 1400
},
{
"epoch": 0.036715307939880634,
"grad_norm": 0.39040204882621765,
"learning_rate": 0.00019853931493486287,
"loss": 0.6697,
"step": 1410
},
{
"epoch": 0.036975700194773406,
"grad_norm": 0.3295992910861969,
"learning_rate": 0.00019851074603090277,
"loss": 0.6175,
"step": 1420
},
{
"epoch": 0.03723609244966618,
"grad_norm": 0.33969369530677795,
"learning_rate": 0.00019848190253835536,
"loss": 0.6453,
"step": 1430
},
{
"epoch": 0.03749648470455895,
"grad_norm": 0.456320196390152,
"learning_rate": 0.00019845278453761896,
"loss": 0.6392,
"step": 1440
},
{
"epoch": 0.03775687695945172,
"grad_norm": 0.3699491024017334,
"learning_rate": 0.00019842339210985696,
"loss": 0.636,
"step": 1450
},
{
"epoch": 0.038017269214344486,
"grad_norm": 0.41601112484931946,
"learning_rate": 0.00019839372533699774,
"loss": 0.6566,
"step": 1460
},
{
"epoch": 0.03827766146923726,
"grad_norm": 0.39745938777923584,
"learning_rate": 0.00019836378430173438,
"loss": 0.6421,
"step": 1470
},
{
"epoch": 0.03853805372413003,
"grad_norm": 0.38357457518577576,
"learning_rate": 0.0001983335690875245,
"loss": 0.6355,
"step": 1480
},
{
"epoch": 0.0387984459790228,
"grad_norm": 0.3879673182964325,
"learning_rate": 0.00019830307977858984,
"loss": 0.6295,
"step": 1490
},
{
"epoch": 0.03905883823391557,
"grad_norm": 0.42652568221092224,
"learning_rate": 0.00019827231645991623,
"loss": 0.6374,
"step": 1500
},
{
"epoch": 0.03931923048880834,
"grad_norm": 0.3830074369907379,
"learning_rate": 0.00019824127921725326,
"loss": 0.6292,
"step": 1510
},
{
"epoch": 0.03957962274370111,
"grad_norm": 0.39314061403274536,
"learning_rate": 0.00019820996813711407,
"loss": 0.6416,
"step": 1520
},
{
"epoch": 0.03984001499859388,
"grad_norm": 0.3321419060230255,
"learning_rate": 0.0001981783833067751,
"loss": 0.6206,
"step": 1530
},
{
"epoch": 0.04010040725348665,
"grad_norm": 0.41209813952445984,
"learning_rate": 0.0001981465248142758,
"loss": 0.6576,
"step": 1540
},
{
"epoch": 0.040360799508379425,
"grad_norm": 0.4043482542037964,
"learning_rate": 0.00019811439274841842,
"loss": 0.6588,
"step": 1550
},
{
"epoch": 0.040621191763272196,
"grad_norm": 0.4470541179180145,
"learning_rate": 0.00019808198719876782,
"loss": 0.6595,
"step": 1560
},
{
"epoch": 0.04088158401816496,
"grad_norm": 0.3442763090133667,
"learning_rate": 0.00019804930825565112,
"loss": 0.6584,
"step": 1570
},
{
"epoch": 0.04114197627305773,
"grad_norm": 0.4013935923576355,
"learning_rate": 0.00019801635601015752,
"loss": 0.6315,
"step": 1580
},
{
"epoch": 0.041402368527950505,
"grad_norm": 0.36532357335090637,
"learning_rate": 0.00019798313055413808,
"loss": 0.6453,
"step": 1590
},
{
"epoch": 0.041662760782843276,
"grad_norm": 0.4390687644481659,
"learning_rate": 0.00019794963198020525,
"loss": 0.6375,
"step": 1600
},
{
"epoch": 0.04192315303773605,
"grad_norm": 0.3687056601047516,
"learning_rate": 0.00019791586038173296,
"loss": 0.637,
"step": 1610
},
{
"epoch": 0.04218354529262881,
"grad_norm": 0.372841477394104,
"learning_rate": 0.00019788181585285602,
"loss": 0.6322,
"step": 1620
},
{
"epoch": 0.042443937547521585,
"grad_norm": 0.3459762632846832,
"learning_rate": 0.00019784749848847003,
"loss": 0.62,
"step": 1630
},
{
"epoch": 0.042704329802414356,
"grad_norm": 0.4031515121459961,
"learning_rate": 0.0001978129083842312,
"loss": 0.6438,
"step": 1640
},
{
"epoch": 0.04296472205730713,
"grad_norm": 0.39984458684921265,
"learning_rate": 0.00019777804563655583,
"loss": 0.6224,
"step": 1650
},
{
"epoch": 0.0432251143121999,
"grad_norm": 0.37194013595581055,
"learning_rate": 0.00019774291034262026,
"loss": 0.6258,
"step": 1660
},
{
"epoch": 0.04348550656709267,
"grad_norm": 0.3989511728286743,
"learning_rate": 0.00019770750260036054,
"loss": 0.6385,
"step": 1670
},
{
"epoch": 0.043745898821985436,
"grad_norm": 0.3801423907279968,
"learning_rate": 0.00019767182250847207,
"loss": 0.6234,
"step": 1680
},
{
"epoch": 0.04400629107687821,
"grad_norm": 0.3838658034801483,
"learning_rate": 0.00019763587016640948,
"loss": 0.656,
"step": 1690
},
{
"epoch": 0.04426668333177098,
"grad_norm": 0.5071051716804504,
"learning_rate": 0.00019759964567438623,
"loss": 0.6385,
"step": 1700
},
{
"epoch": 0.04452707558666375,
"grad_norm": 0.3741011321544647,
"learning_rate": 0.00019756314913337432,
"loss": 0.6452,
"step": 1710
},
{
"epoch": 0.04478746784155652,
"grad_norm": 0.41739609837532043,
"learning_rate": 0.00019752638064510415,
"loss": 0.627,
"step": 1720
},
{
"epoch": 0.04504786009644929,
"grad_norm": 0.38942453265190125,
"learning_rate": 0.00019748934031206414,
"loss": 0.6486,
"step": 1730
},
{
"epoch": 0.04530825235134206,
"grad_norm": 0.40764692425727844,
"learning_rate": 0.00019745202823750034,
"loss": 0.6311,
"step": 1740
},
{
"epoch": 0.04556864460623483,
"grad_norm": 0.4089398682117462,
"learning_rate": 0.0001974144445254164,
"loss": 0.6262,
"step": 1750
},
{
"epoch": 0.0458290368611276,
"grad_norm": 0.4223162531852722,
"learning_rate": 0.00019737658928057302,
"loss": 0.6633,
"step": 1760
},
{
"epoch": 0.046089429116020375,
"grad_norm": 0.4696766436100006,
"learning_rate": 0.00019733846260848776,
"loss": 0.6448,
"step": 1770
},
{
"epoch": 0.04634982137091315,
"grad_norm": 0.34561800956726074,
"learning_rate": 0.0001973000646154349,
"loss": 0.6629,
"step": 1780
},
{
"epoch": 0.04661021362580591,
"grad_norm": 0.3809750974178314,
"learning_rate": 0.00019726139540844484,
"loss": 0.6261,
"step": 1790
},
{
"epoch": 0.04687060588069868,
"grad_norm": 0.37188807129859924,
"learning_rate": 0.00019722245509530401,
"loss": 0.6392,
"step": 1800
},
{
"epoch": 0.047130998135591455,
"grad_norm": 0.36847737431526184,
"learning_rate": 0.00019718324378455458,
"loss": 0.6238,
"step": 1810
},
{
"epoch": 0.04739139039048423,
"grad_norm": 0.34314194321632385,
"learning_rate": 0.00019714376158549404,
"loss": 0.6512,
"step": 1820
},
{
"epoch": 0.047651782645377,
"grad_norm": 0.3639289140701294,
"learning_rate": 0.00019710400860817494,
"loss": 0.6481,
"step": 1830
},
{
"epoch": 0.04791217490026976,
"grad_norm": 0.34774431586265564,
"learning_rate": 0.00019706398496340463,
"loss": 0.6583,
"step": 1840
},
{
"epoch": 0.048172567155162535,
"grad_norm": 0.37768319249153137,
"learning_rate": 0.00019702369076274494,
"loss": 0.6241,
"step": 1850
},
{
"epoch": 0.04843295941005531,
"grad_norm": 0.3546730875968933,
"learning_rate": 0.0001969831261185118,
"loss": 0.6222,
"step": 1860
},
{
"epoch": 0.04869335166494808,
"grad_norm": 0.3773512840270996,
"learning_rate": 0.00019694229114377494,
"loss": 0.6201,
"step": 1870
},
{
"epoch": 0.04895374391984085,
"grad_norm": 0.3787965774536133,
"learning_rate": 0.00019690118595235774,
"loss": 0.6339,
"step": 1880
},
{
"epoch": 0.04921413617473362,
"grad_norm": 0.3667986989021301,
"learning_rate": 0.00019685981065883663,
"loss": 0.6253,
"step": 1890
},
{
"epoch": 0.04947452842962639,
"grad_norm": 0.39258262515068054,
"learning_rate": 0.00019681816537854102,
"loss": 0.6417,
"step": 1900
},
{
"epoch": 0.04973492068451916,
"grad_norm": 0.3514678478240967,
"learning_rate": 0.00019677625022755289,
"loss": 0.6473,
"step": 1910
},
{
"epoch": 0.04999531293941193,
"grad_norm": 0.38365432620048523,
"learning_rate": 0.00019673406532270634,
"loss": 0.6363,
"step": 1920
},
{
"epoch": 0.0502557051943047,
"grad_norm": 0.34043630957603455,
"learning_rate": 0.00019669161078158753,
"loss": 0.6249,
"step": 1930
},
{
"epoch": 0.050516097449197474,
"grad_norm": 0.41065657138824463,
"learning_rate": 0.0001966488867225341,
"loss": 0.6479,
"step": 1940
},
{
"epoch": 0.05077648970409024,
"grad_norm": 0.3435451090335846,
"learning_rate": 0.00019660589326463498,
"loss": 0.6498,
"step": 1950
},
{
"epoch": 0.05103688195898301,
"grad_norm": 0.3457126021385193,
"learning_rate": 0.00019656263052773002,
"loss": 0.6188,
"step": 1960
},
{
"epoch": 0.05129727421387578,
"grad_norm": 0.34488430619239807,
"learning_rate": 0.00019651909863240965,
"loss": 0.6352,
"step": 1970
},
{
"epoch": 0.051557666468768554,
"grad_norm": 0.34936293959617615,
"learning_rate": 0.00019647529770001456,
"loss": 0.6331,
"step": 1980
},
{
"epoch": 0.051818058723661325,
"grad_norm": 0.34119752049446106,
"learning_rate": 0.00019643122785263536,
"loss": 0.6188,
"step": 1990
},
{
"epoch": 0.0520784509785541,
"grad_norm": 0.35101839900016785,
"learning_rate": 0.00019638688921311224,
"loss": 0.6339,
"step": 2000
}
],
"logging_steps": 10,
"max_steps": 19202,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 500,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": false
},
"attributes": {}
}
},
"total_flos": 1.13160820359168e+18,
"train_batch_size": 3,
"trial_name": null,
"trial_params": null
}