{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9992289899768697,
  "eval_steps": 500,
  "global_step": 648,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015420200462606013,
      "grad_norm": 0.06960189342498779,
      "learning_rate": 1e-05,
      "loss": 0.9546,
      "step": 1
    },
    {
      "epoch": 0.0030840400925212026,
      "grad_norm": 0.07705054432153702,
      "learning_rate": 2e-05,
      "loss": 1.0023,
      "step": 2
    },
    {
      "epoch": 0.004626060138781804,
      "grad_norm": 0.07115544378757477,
      "learning_rate": 3e-05,
      "loss": 0.9733,
      "step": 3
    },
    {
      "epoch": 0.006168080185042405,
      "grad_norm": 0.06770255416631699,
      "learning_rate": 4e-05,
      "loss": 0.8908,
      "step": 4
    },
    {
      "epoch": 0.007710100231303007,
      "grad_norm": 0.06454406678676605,
      "learning_rate": 5e-05,
      "loss": 0.9168,
      "step": 5
    },
    {
      "epoch": 0.009252120277563608,
      "grad_norm": 0.0818350687623024,
      "learning_rate": 6e-05,
      "loss": 0.8822,
      "step": 6
    },
    {
      "epoch": 0.01079414032382421,
      "grad_norm": 0.08504347503185272,
      "learning_rate": 7e-05,
      "loss": 0.9563,
      "step": 7
    },
    {
      "epoch": 0.01233616037008481,
      "grad_norm": 0.08642569184303284,
      "learning_rate": 8e-05,
      "loss": 0.9324,
      "step": 8
    },
    {
      "epoch": 0.013878180416345412,
      "grad_norm": 0.07200746238231659,
      "learning_rate": 9e-05,
      "loss": 0.8557,
      "step": 9
    },
    {
      "epoch": 0.015420200462606014,
      "grad_norm": 0.0539001002907753,
      "learning_rate": 0.0001,
      "loss": 0.8316,
      "step": 10
    },
    {
      "epoch": 0.016962220508866616,
      "grad_norm": 0.05532313138246536,
      "learning_rate": 0.00011000000000000002,
      "loss": 0.869,
      "step": 11
    },
    {
      "epoch": 0.018504240555127217,
      "grad_norm": 0.04828835651278496,
      "learning_rate": 0.00012,
      "loss": 0.9004,
      "step": 12
    },
    {
      "epoch": 0.020046260601387818,
      "grad_norm": 0.051899779587984085,
      "learning_rate": 0.00013000000000000002,
      "loss": 0.7818,
      "step": 13
    },
    {
      "epoch": 0.02158828064764842,
      "grad_norm": 0.07032614946365356,
      "learning_rate": 0.00014,
      "loss": 0.7946,
      "step": 14
    },
    {
      "epoch": 0.02313030069390902,
      "grad_norm": 0.08230099081993103,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.934,
      "step": 15
    },
    {
      "epoch": 0.02467232074016962,
      "grad_norm": 0.08811169862747192,
      "learning_rate": 0.00016,
      "loss": 0.8621,
      "step": 16
    },
    {
      "epoch": 0.026214340786430222,
      "grad_norm": 0.062236446887254715,
      "learning_rate": 0.00017,
      "loss": 0.8186,
      "step": 17
    },
    {
      "epoch": 0.027756360832690823,
      "grad_norm": 0.052294306457042694,
      "learning_rate": 0.00018,
      "loss": 0.8124,
      "step": 18
    },
    {
      "epoch": 0.029298380878951428,
      "grad_norm": 0.032340776175260544,
      "learning_rate": 0.00019,
      "loss": 0.8598,
      "step": 19
    },
    {
      "epoch": 0.03084040092521203,
      "grad_norm": 0.028073711320757866,
      "learning_rate": 0.0002,
      "loss": 0.9087,
      "step": 20
    },
    {
      "epoch": 0.03238242097147263,
      "grad_norm": 0.027820633724331856,
      "learning_rate": 0.00019999969691239107,
      "loss": 0.7093,
      "step": 21
    },
    {
      "epoch": 0.03392444101773323,
      "grad_norm": 0.032430652529001236,
      "learning_rate": 0.00019999878765140146,
      "loss": 0.7825,
      "step": 22
    },
    {
      "epoch": 0.03546646106399383,
      "grad_norm": 0.034685954451560974,
      "learning_rate": 0.000199997272222543,
      "loss": 0.7787,
      "step": 23
    },
    {
      "epoch": 0.03700848111025443,
      "grad_norm": 0.033446088433265686,
      "learning_rate": 0.0001999951506350017,
      "loss": 0.8636,
      "step": 24
    },
    {
      "epoch": 0.03855050115651504,
      "grad_norm": 0.026805371046066284,
      "learning_rate": 0.0001999924229016382,
      "loss": 0.904,
      "step": 25
    },
    {
      "epoch": 0.040092521202775636,
      "grad_norm": 0.024178853258490562,
      "learning_rate": 0.0001999890890389873,
      "loss": 0.7428,
      "step": 26
    },
    {
      "epoch": 0.04163454124903624,
      "grad_norm": 0.024074744433164597,
      "learning_rate": 0.00019998514906725804,
      "loss": 0.8562,
      "step": 27
    },
    {
      "epoch": 0.04317656129529684,
      "grad_norm": 0.025082379579544067,
      "learning_rate": 0.0001999806030103336,
      "loss": 0.8078,
      "step": 28
    },
    {
      "epoch": 0.04471858134155744,
      "grad_norm": 0.027726231142878532,
      "learning_rate": 0.00019997545089577102,
      "loss": 0.7133,
      "step": 29
    },
    {
      "epoch": 0.04626060138781804,
      "grad_norm": 0.02736576274037361,
      "learning_rate": 0.00019996969275480115,
      "loss": 0.7826,
      "step": 30
    },
    {
      "epoch": 0.047802621434078645,
      "grad_norm": 0.0234544537961483,
      "learning_rate": 0.0001999633286223284,
      "loss": 0.7424,
      "step": 31
    },
    {
      "epoch": 0.04934464148033924,
      "grad_norm": 0.025730784982442856,
      "learning_rate": 0.00019995635853693058,
      "loss": 0.7584,
      "step": 32
    },
    {
      "epoch": 0.05088666152659985,
      "grad_norm": 0.02729860506951809,
      "learning_rate": 0.00019994878254085861,
      "loss": 0.73,
      "step": 33
    },
    {
      "epoch": 0.052428681572860444,
      "grad_norm": 0.027428491041064262,
      "learning_rate": 0.00019994060068003627,
      "loss": 0.854,
      "step": 34
    },
    {
      "epoch": 0.05397070161912105,
      "grad_norm": 0.024362564086914062,
      "learning_rate": 0.00019993181300406005,
      "loss": 0.7441,
      "step": 35
    },
    {
      "epoch": 0.05551272166538165,
      "grad_norm": 0.024825185537338257,
      "learning_rate": 0.00019992241956619863,
      "loss": 0.7367,
      "step": 36
    },
    {
      "epoch": 0.05705474171164225,
      "grad_norm": 0.023908289149403572,
      "learning_rate": 0.00019991242042339264,
      "loss": 0.8266,
      "step": 37
    },
    {
      "epoch": 0.058596761757902856,
      "grad_norm": 0.023762725293636322,
      "learning_rate": 0.00019990181563625447,
      "loss": 0.829,
      "step": 38
    },
    {
      "epoch": 0.06013878180416345,
      "grad_norm": 0.02654297836124897,
      "learning_rate": 0.0001998906052690677,
      "loss": 0.7635,
      "step": 39
    },
    {
      "epoch": 0.06168080185042406,
      "grad_norm": 0.026318082585930824,
      "learning_rate": 0.00019987878938978684,
      "loss": 0.7623,
      "step": 40
    },
    {
      "epoch": 0.06322282189668466,
      "grad_norm": 0.024309197440743446,
      "learning_rate": 0.00019986636807003673,
      "loss": 0.7494,
      "step": 41
    },
    {
      "epoch": 0.06476484194294525,
      "grad_norm": 0.022980719804763794,
      "learning_rate": 0.00019985334138511237,
      "loss": 0.748,
      "step": 42
    },
    {
      "epoch": 0.06630686198920586,
      "grad_norm": 0.023796193301677704,
      "learning_rate": 0.00019983970941397835,
      "loss": 0.8684,
      "step": 43
    },
    {
      "epoch": 0.06784888203546646,
      "grad_norm": 0.02435590885579586,
      "learning_rate": 0.00019982547223926824,
      "loss": 0.6749,
      "step": 44
    },
    {
      "epoch": 0.06939090208172706,
      "grad_norm": 0.026482658460736275,
      "learning_rate": 0.0001998106299472843,
      "loss": 0.7684,
      "step": 45
    },
    {
      "epoch": 0.07093292212798766,
      "grad_norm": 0.025558117777109146,
      "learning_rate": 0.0001997951826279968,
      "loss": 0.7507,
      "step": 46
    },
    {
      "epoch": 0.07247494217424827,
      "grad_norm": 0.027371902018785477,
      "learning_rate": 0.00019977913037504355,
      "loss": 0.7377,
      "step": 47
    },
    {
      "epoch": 0.07401696222050887,
      "grad_norm": 0.0234097708016634,
      "learning_rate": 0.00019976247328572938,
      "loss": 0.7675,
      "step": 48
    },
    {
      "epoch": 0.07555898226676946,
      "grad_norm": 0.0241215992718935,
      "learning_rate": 0.00019974521146102537,
      "loss": 0.8079,
      "step": 49
    },
    {
      "epoch": 0.07710100231303008,
      "grad_norm": 0.025045258924365044,
      "learning_rate": 0.00019972734500556846,
      "loss": 0.8407,
      "step": 50
    },
    {
      "epoch": 0.07864302235929067,
      "grad_norm": 0.02574036829173565,
      "learning_rate": 0.0001997088740276607,
      "loss": 0.767,
      "step": 51
    },
    {
      "epoch": 0.08018504240555127,
      "grad_norm": 0.02342085726559162,
      "learning_rate": 0.00019968979863926856,
      "loss": 0.7373,
      "step": 52
    },
    {
      "epoch": 0.08172706245181187,
      "grad_norm": 0.023467406630516052,
      "learning_rate": 0.0001996701189560223,
      "loss": 0.6529,
      "step": 53
    },
    {
      "epoch": 0.08326908249807248,
      "grad_norm": 0.02330499142408371,
      "learning_rate": 0.00019964983509721527,
      "loss": 0.7347,
      "step": 54
    },
    {
      "epoch": 0.08481110254433308,
      "grad_norm": 0.027940964326262474,
      "learning_rate": 0.00019962894718580324,
      "loss": 0.9313,
      "step": 55
    },
    {
      "epoch": 0.08635312259059368,
      "grad_norm": 0.024525761604309082,
      "learning_rate": 0.00019960745534840354,
      "loss": 0.767,
      "step": 56
    },
    {
      "epoch": 0.08789514263685427,
      "grad_norm": 0.024538526311516762,
      "learning_rate": 0.00019958535971529434,
      "loss": 0.7659,
      "step": 57
    },
    {
      "epoch": 0.08943716268311488,
      "grad_norm": 0.02253701537847519,
      "learning_rate": 0.00019956266042041394,
      "loss": 0.7805,
      "step": 58
    },
    {
      "epoch": 0.09097918272937548,
      "grad_norm": 0.023676637560129166,
      "learning_rate": 0.0001995393576013598,
      "loss": 0.7894,
      "step": 59
    },
    {
      "epoch": 0.09252120277563608,
      "grad_norm": 0.022134529426693916,
      "learning_rate": 0.0001995154513993878,
      "loss": 0.7492,
      "step": 60
    },
    {
      "epoch": 0.09406322282189669,
      "grad_norm": 0.02350509911775589,
      "learning_rate": 0.00019949094195941152,
      "loss": 0.6902,
      "step": 61
    },
    {
      "epoch": 0.09560524286815729,
      "grad_norm": 0.02464171312749386,
      "learning_rate": 0.00019946582943000102,
      "loss": 0.7836,
      "step": 62
    },
    {
      "epoch": 0.09714726291441789,
      "grad_norm": 0.023095758631825447,
      "learning_rate": 0.00019944011396338222,
      "loss": 0.8321,
      "step": 63
    },
    {
      "epoch": 0.09868928296067848,
      "grad_norm": 0.026240425184369087,
      "learning_rate": 0.00019941379571543596,
      "loss": 0.8461,
      "step": 64
    },
    {
      "epoch": 0.1002313030069391,
      "grad_norm": 0.02174345962703228,
      "learning_rate": 0.00019938687484569693,
      "loss": 0.6388,
      "step": 65
    },
    {
      "epoch": 0.1017733230531997,
      "grad_norm": 0.02867325395345688,
      "learning_rate": 0.00019935935151735277,
      "loss": 0.826,
      "step": 66
    },
    {
      "epoch": 0.10331534309946029,
      "grad_norm": 0.02631618268787861,
      "learning_rate": 0.00019933122589724302,
      "loss": 0.9407,
      "step": 67
    },
    {
      "epoch": 0.10485736314572089,
      "grad_norm": 0.022020747885107994,
      "learning_rate": 0.0001993024981558583,
      "loss": 0.7004,
      "step": 68
    },
    {
      "epoch": 0.1063993831919815,
      "grad_norm": 0.02743780054152012,
      "learning_rate": 0.000199273168467339,
      "loss": 0.7607,
      "step": 69
    },
    {
      "epoch": 0.1079414032382421,
      "grad_norm": 0.028378015384078026,
      "learning_rate": 0.00019924323700947448,
      "loss": 0.8604,
      "step": 70
    },
    {
      "epoch": 0.1094834232845027,
      "grad_norm": 0.0275627039372921,
      "learning_rate": 0.00019921270396370172,
      "loss": 0.835,
      "step": 71
    },
    {
      "epoch": 0.1110254433307633,
      "grad_norm": 0.023099975660443306,
      "learning_rate": 0.0001991815695151046,
      "loss": 0.7028,
      "step": 72
    },
    {
      "epoch": 0.1125674633770239,
      "grad_norm": 0.028545403853058815,
      "learning_rate": 0.00019914983385241236,
      "loss": 0.8248,
      "step": 73
    },
    {
      "epoch": 0.1141094834232845,
      "grad_norm": 0.02746577188372612,
      "learning_rate": 0.00019911749716799873,
      "loss": 0.7309,
      "step": 74
    },
    {
      "epoch": 0.1156515034695451,
      "grad_norm": 0.024899670854210854,
      "learning_rate": 0.00019908455965788067,
      "loss": 0.7473,
      "step": 75
    },
    {
      "epoch": 0.11719352351580571,
      "grad_norm": 0.024973087012767792,
      "learning_rate": 0.00019905102152171727,
      "loss": 0.8362,
      "step": 76
    },
    {
      "epoch": 0.11873554356206631,
      "grad_norm": 0.023668723180890083,
      "learning_rate": 0.0001990168829628083,
      "loss": 0.7677,
      "step": 77
    },
    {
      "epoch": 0.1202775636083269,
      "grad_norm": 0.02495860867202282,
      "learning_rate": 0.0001989821441880933,
      "loss": 0.7341,
      "step": 78
    },
    {
      "epoch": 0.1218195836545875,
      "grad_norm": 0.02537156455218792,
      "learning_rate": 0.00019894680540815006,
      "loss": 0.6767,
      "step": 79
    },
    {
      "epoch": 0.12336160370084812,
      "grad_norm": 0.0246786717325449,
      "learning_rate": 0.0001989108668371936,
      "loss": 0.7959,
      "step": 80
    },
    {
      "epoch": 0.12490362374710871,
      "grad_norm": 0.02471376582980156,
      "learning_rate": 0.00019887432869307458,
      "loss": 0.6787,
      "step": 81
    },
    {
      "epoch": 0.1264456437933693,
      "grad_norm": 0.025275586172938347,
      "learning_rate": 0.00019883719119727816,
      "loss": 0.7753,
      "step": 82
    },
    {
      "epoch": 0.12798766383962992,
      "grad_norm": 0.021094506606459618,
      "learning_rate": 0.00019879945457492267,
      "loss": 0.758,
      "step": 83
    },
    {
      "epoch": 0.1295296838858905,
      "grad_norm": 0.02534683421254158,
      "learning_rate": 0.00019876111905475815,
      "loss": 0.818,
      "step": 84
    },
    {
      "epoch": 0.13107170393215112,
      "grad_norm": 0.024033140391111374,
      "learning_rate": 0.00019872218486916498,
      "loss": 0.775,
      "step": 85
    },
    {
      "epoch": 0.13261372397841173,
      "grad_norm": 0.023884933441877365,
      "learning_rate": 0.00019868265225415265,
      "loss": 0.7918,
      "step": 86
    },
    {
      "epoch": 0.1341557440246723,
      "grad_norm": 0.026067111641168594,
      "learning_rate": 0.00019864252144935794,
      "loss": 0.8368,
      "step": 87
    },
    {
      "epoch": 0.13569776407093292,
      "grad_norm": 0.02631264552474022,
      "learning_rate": 0.00019860179269804394,
      "loss": 0.7138,
      "step": 88
    },
    {
      "epoch": 0.13723978411719354,
      "grad_norm": 0.022870918735861778,
      "learning_rate": 0.00019856046624709822,
      "loss": 0.7423,
      "step": 89
    },
    {
      "epoch": 0.13878180416345412,
      "grad_norm": 0.02922765538096428,
      "learning_rate": 0.00019851854234703145,
      "loss": 0.7498,
      "step": 90
    },
    {
      "epoch": 0.14032382420971473,
      "grad_norm": 0.02589617855846882,
      "learning_rate": 0.00019847602125197598,
      "loss": 0.7438,
      "step": 91
    },
    {
      "epoch": 0.14186584425597532,
      "grad_norm": 0.02394738420844078,
      "learning_rate": 0.00019843290321968412,
      "loss": 0.7094,
      "step": 92
    },
    {
      "epoch": 0.14340786430223593,
      "grad_norm": 0.02237016148865223,
      "learning_rate": 0.0001983891885115267,
      "loss": 0.7868,
      "step": 93
    },
    {
      "epoch": 0.14494988434849654,
      "grad_norm": 0.028733767569065094,
      "learning_rate": 0.00019834487739249146,
      "loss": 0.8178,
      "step": 94
    },
    {
      "epoch": 0.14649190439475712,
      "grad_norm": 0.023086342960596085,
      "learning_rate": 0.0001982999701311814,
      "loss": 0.8368,
      "step": 95
    },
    {
      "epoch": 0.14803392444101773,
      "grad_norm": 0.025624489411711693,
      "learning_rate": 0.0001982544669998132,
      "loss": 0.7731,
      "step": 96
    },
    {
      "epoch": 0.14957594448727835,
      "grad_norm": 0.028302457183599472,
      "learning_rate": 0.0001982083682742156,
      "loss": 0.7942,
      "step": 97
    },
    {
      "epoch": 0.15111796453353893,
      "grad_norm": 0.025008324533700943,
      "learning_rate": 0.00019816167423382765,
      "loss": 0.7393,
      "step": 98
    },
    {
      "epoch": 0.15265998457979954,
      "grad_norm": 0.026291735470294952,
      "learning_rate": 0.00019811438516169702,
      "loss": 0.8016,
      "step": 99
    },
    {
      "epoch": 0.15420200462606015,
      "grad_norm": 0.031547173857688904,
      "learning_rate": 0.00019806650134447838,
      "loss": 0.8597,
      "step": 100
    },
    {
      "epoch": 0.15574402467232074,
      "grad_norm": 0.024978285655379295,
      "learning_rate": 0.00019801802307243153,
      "loss": 0.8182,
      "step": 101
    },
    {
      "epoch": 0.15728604471858135,
      "grad_norm": 0.023977672681212425,
      "learning_rate": 0.00019796895063941978,
      "loss": 0.8374,
      "step": 102
    },
    {
      "epoch": 0.15882806476484193,
      "grad_norm": 0.025743963196873665,
      "learning_rate": 0.000197919284342908,
      "loss": 0.7326,
      "step": 103
    },
    {
      "epoch": 0.16037008481110254,
      "grad_norm": 0.02554011158645153,
      "learning_rate": 0.00019786902448396104,
      "loss": 0.7703,
      "step": 104
    },
    {
      "epoch": 0.16191210485736315,
      "grad_norm": 0.027971483767032623,
      "learning_rate": 0.00019781817136724165,
      "loss": 0.6845,
      "step": 105
    },
    {
      "epoch": 0.16345412490362374,
      "grad_norm": 0.02789183147251606,
      "learning_rate": 0.00019776672530100886,
      "loss": 0.838,
      "step": 106
    },
    {
      "epoch": 0.16499614494988435,
      "grad_norm": 0.029534442350268364,
      "learning_rate": 0.00019771468659711595,
      "loss": 0.7428,
      "step": 107
    },
    {
      "epoch": 0.16653816499614496,
      "grad_norm": 0.02910265140235424,
      "learning_rate": 0.00019766205557100868,
      "loss": 0.8891,
      "step": 108
    },
    {
      "epoch": 0.16808018504240554,
      "grad_norm": 0.02285209856927395,
      "learning_rate": 0.00019760883254172327,
      "loss": 0.7425,
      "step": 109
    },
    {
      "epoch": 0.16962220508866616,
      "grad_norm": 0.025452135130763054,
      "learning_rate": 0.0001975550178318845,
      "loss": 0.7617,
      "step": 110
    },
    {
      "epoch": 0.17116422513492677,
      "grad_norm": 0.02843882516026497,
      "learning_rate": 0.00019750061176770385,
      "loss": 0.9045,
      "step": 111
    },
    {
      "epoch": 0.17270624518118735,
      "grad_norm": 0.026800749823451042,
      "learning_rate": 0.00019744561467897735,
      "loss": 0.72,
      "step": 112
    },
    {
      "epoch": 0.17424826522744796,
      "grad_norm": 0.021131988614797592,
      "learning_rate": 0.00019739002689908377,
      "loss": 0.6511,
      "step": 113
    },
    {
      "epoch": 0.17579028527370855,
      "grad_norm": 0.02588481456041336,
      "learning_rate": 0.00019733384876498245,
      "loss": 0.7168,
      "step": 114
    },
    {
      "epoch": 0.17733230531996916,
      "grad_norm": 0.031303439289331436,
      "learning_rate": 0.00019727708061721133,
      "loss": 0.8685,
      "step": 115
    },
    {
      "epoch": 0.17887432536622977,
      "grad_norm": 0.02867058850824833,
      "learning_rate": 0.00019721972279988477,
      "loss": 0.655,
      "step": 116
    },
    {
      "epoch": 0.18041634541249035,
      "grad_norm": 0.03866586834192276,
      "learning_rate": 0.00019716177566069174,
      "loss": 0.7957,
      "step": 117
    },
    {
      "epoch": 0.18195836545875096,
      "grad_norm": 0.029205329716205597,
      "learning_rate": 0.00019710323955089343,
      "loss": 0.7617,
      "step": 118
    },
    {
      "epoch": 0.18350038550501158,
      "grad_norm": 0.024928180500864983,
      "learning_rate": 0.00019704411482532116,
      "loss": 0.6982,
      "step": 119
    },
    {
      "epoch": 0.18504240555127216,
      "grad_norm": 0.02545573003590107,
      "learning_rate": 0.0001969844018423744,
      "loss": 0.6067,
      "step": 120
    },
    {
      "epoch": 0.18658442559753277,
      "grad_norm": 0.02810928039252758,
      "learning_rate": 0.0001969241009640185,
      "loss": 0.7112,
      "step": 121
    },
    {
      "epoch": 0.18812644564379338,
      "grad_norm": 0.022296108305454254,
      "learning_rate": 0.00019686321255578238,
      "loss": 0.6598,
      "step": 122
    },
    {
      "epoch": 0.18966846569005397,
      "grad_norm": 0.02429027482867241,
      "learning_rate": 0.00019680173698675648,
      "loss": 0.6381,
      "step": 123
    },
    {
      "epoch": 0.19121048573631458,
      "grad_norm": 0.027076730504631996,
      "learning_rate": 0.0001967396746295905,
      "loss": 0.717,
      "step": 124
    },
    {
      "epoch": 0.19275250578257516,
      "grad_norm": 0.02401566132903099,
      "learning_rate": 0.00019667702586049108,
      "loss": 0.8002,
      "step": 125
    },
    {
      "epoch": 0.19429452582883577,
      "grad_norm": 0.024678878486156464,
      "learning_rate": 0.00019661379105921948,
      "loss": 0.7834,
      "step": 126
    },
    {
      "epoch": 0.19583654587509639,
      "grad_norm": 0.029240388423204422,
      "learning_rate": 0.00019654997060908946,
      "loss": 0.8793,
      "step": 127
    },
    {
      "epoch": 0.19737856592135697,
      "grad_norm": 0.02550147846341133,
      "learning_rate": 0.0001964855648969647,
      "loss": 0.6742,
      "step": 128
    },
    {
      "epoch": 0.19892058596761758,
      "grad_norm": 0.02416900172829628,
      "learning_rate": 0.00019642057431325672,
      "loss": 0.7728,
      "step": 129
    },
    {
      "epoch": 0.2004626060138782,
      "grad_norm": 0.024728331714868546,
      "learning_rate": 0.0001963549992519223,
      "loss": 0.7237,
      "step": 130
    },
    {
      "epoch": 0.20200462606013878,
      "grad_norm": 0.025203561410307884,
      "learning_rate": 0.00019628884011046123,
      "loss": 0.7491,
      "step": 131
    },
    {
      "epoch": 0.2035466461063994,
      "grad_norm": 0.02104656957089901,
      "learning_rate": 0.00019622209728991383,
      "loss": 0.7324,
      "step": 132
    },
    {
      "epoch": 0.20508866615265997,
      "grad_norm": 0.03518475592136383,
      "learning_rate": 0.00019615477119485855,
      "loss": 0.8982,
      "step": 133
    },
    {
      "epoch": 0.20663068619892058,
      "grad_norm": 0.026010941714048386,
      "learning_rate": 0.00019608686223340945,
      "loss": 0.7451,
      "step": 134
    },
    {
      "epoch": 0.2081727062451812,
      "grad_norm": 0.025345437228679657,
      "learning_rate": 0.00019601837081721386,
      "loss": 0.705,
      "step": 135
    },
    {
      "epoch": 0.20971472629144178,
      "grad_norm": 0.02374056540429592,
      "learning_rate": 0.00019594929736144976,
      "loss": 0.7307,
      "step": 136
    },
    {
      "epoch": 0.2112567463377024,
      "grad_norm": 0.026990080252289772,
      "learning_rate": 0.00019587964228482332,
      "loss": 0.8173,
      "step": 137
    },
    {
      "epoch": 0.212798766383963,
      "grad_norm": 0.026662928983569145,
      "learning_rate": 0.00019580940600956638,
      "loss": 0.818,
      "step": 138
    },
    {
      "epoch": 0.21434078643022358,
      "grad_norm": 0.026762284338474274,
      "learning_rate": 0.00019573858896143376,
      "loss": 0.6674,
      "step": 139
    },
    {
      "epoch": 0.2158828064764842,
      "grad_norm": 0.02683679386973381,
      "learning_rate": 0.00019566719156970095,
      "loss": 0.7569,
      "step": 140
    },
    {
      "epoch": 0.2174248265227448,
      "grad_norm": 0.022990800440311432,
      "learning_rate": 0.00019559521426716118,
      "loss": 0.7051,
      "step": 141
    },
    {
      "epoch": 0.2189668465690054,
      "grad_norm": 0.022913858294487,
      "learning_rate": 0.00019552265749012303,
      "loss": 0.7483,
      "step": 142
    },
    {
      "epoch": 0.220508866615266,
      "grad_norm": 0.025732524693012238,
      "learning_rate": 0.00019544952167840777,
      "loss": 0.8484,
      "step": 143
    },
    {
      "epoch": 0.2220508866615266,
      "grad_norm": 0.024254556745290756,
      "learning_rate": 0.00019537580727534644,
      "loss": 0.747,
      "step": 144
    },
    {
      "epoch": 0.2235929067077872,
      "grad_norm": 0.02940620854496956,
      "learning_rate": 0.0001953015147277776,
      "loss": 0.8204,
      "step": 145
    },
    {
      "epoch": 0.2251349267540478,
      "grad_norm": 0.02590208128094673,
      "learning_rate": 0.00019522664448604418,
      "loss": 0.7778,
      "step": 146
    },
    {
      "epoch": 0.2266769468003084,
      "grad_norm": 0.02748725563287735,
      "learning_rate": 0.00019515119700399107,
      "loss": 0.7782,
      "step": 147
    },
    {
      "epoch": 0.228218966846569,
      "grad_norm": 0.024179786443710327,
      "learning_rate": 0.00019507517273896222,
      "loss": 0.7651,
      "step": 148
    },
    {
      "epoch": 0.22976098689282962,
      "grad_norm": 0.02463974617421627,
      "learning_rate": 0.00019499857215179786,
      "loss": 0.8215,
      "step": 149
    },
    {
      "epoch": 0.2313030069390902,
      "grad_norm": 0.024559814482927322,
      "learning_rate": 0.00019492139570683178,
      "loss": 0.7539,
      "step": 150
    },
    {
      "epoch": 0.2328450269853508,
      "grad_norm": 0.023420870304107666,
      "learning_rate": 0.00019484364387188847,
      "loss": 0.7035,
      "step": 151
    },
    {
      "epoch": 0.23438704703161142,
      "grad_norm": 0.026096729561686516,
      "learning_rate": 0.00019476531711828027,
      "loss": 0.8033,
      "step": 152
    },
    {
      "epoch": 0.235929067077872,
      "grad_norm": 0.02388446033000946,
      "learning_rate": 0.0001946864159208045,
      "loss": 0.6746,
      "step": 153
    },
    {
      "epoch": 0.23747108712413262,
      "grad_norm": 0.02306438237428665,
      "learning_rate": 0.0001946069407577408,
      "loss": 0.7062,
      "step": 154
    },
    {
      "epoch": 0.2390131071703932,
      "grad_norm": 0.024697955697774887,
      "learning_rate": 0.00019452689211084775,
      "loss": 0.7691,
      "step": 155
    },
    {
      "epoch": 0.2405551272166538,
      "grad_norm": 0.026947690173983574,
      "learning_rate": 0.00019444627046536056,
      "loss": 0.7347,
      "step": 156
    },
    {
      "epoch": 0.24209714726291442,
      "grad_norm": 0.02345297671854496,
      "learning_rate": 0.00019436507630998757,
      "loss": 0.745,
      "step": 157
    },
    {
      "epoch": 0.243639167309175,
      "grad_norm": 0.029198188334703445,
      "learning_rate": 0.00019428331013690765,
      "loss": 0.7862,
      "step": 158
    },
    {
      "epoch": 0.24518118735543562,
      "grad_norm": 0.025465266779065132,
      "learning_rate": 0.00019420097244176706,
      "loss": 0.6685,
      "step": 159
    },
    {
      "epoch": 0.24672320740169623,
      "grad_norm": 0.02786502055823803,
      "learning_rate": 0.00019411806372367655,
      "loss": 0.725,
      "step": 160
    },
    {
      "epoch": 0.24826522744795682,
      "grad_norm": 0.02317357063293457,
      "learning_rate": 0.0001940345844852082,
      "loss": 0.7075,
      "step": 161
    },
    {
      "epoch": 0.24980724749421743,
      "grad_norm": 0.02511444129049778,
      "learning_rate": 0.00019395053523239245,
      "loss": 0.7102,
      "step": 162
    },
    {
      "epoch": 0.25134926754047804,
      "grad_norm": 0.02567203901708126,
      "learning_rate": 0.00019386591647471506,
      "loss": 0.8113,
      "step": 163
    },
    {
      "epoch": 0.2528912875867386,
      "grad_norm": 0.02611825056374073,
      "learning_rate": 0.00019378072872511398,
      "loss": 0.786,
      "step": 164
    },
    {
      "epoch": 0.2544333076329992,
      "grad_norm": 0.02788010984659195,
      "learning_rate": 0.0001936949724999762,
      "loss": 0.684,
      "step": 165
    },
    {
      "epoch": 0.25597532767925985,
      "grad_norm": 0.026200013235211372,
      "learning_rate": 0.0001936086483191347,
      "loss": 0.7563,
      "step": 166
    },
    {
      "epoch": 0.25751734772552043,
      "grad_norm": 0.024887658655643463,
      "learning_rate": 0.00019352175670586533,
      "loss": 0.6896,
      "step": 167
    },
    {
      "epoch": 0.259059367771781,
      "grad_norm": 0.027471961453557014,
      "learning_rate": 0.00019343429818688347,
      "loss": 0.8109,
      "step": 168
    },
    {
      "epoch": 0.26060138781804165,
      "grad_norm": 0.024350160732865334,
      "learning_rate": 0.00019334627329234102,
      "loss": 0.7178,
      "step": 169
    },
    {
      "epoch": 0.26214340786430224,
      "grad_norm": 0.02346990443766117,
      "learning_rate": 0.00019325768255582302,
      "loss": 0.6508,
      "step": 170
    },
    {
      "epoch": 0.2636854279105628,
      "grad_norm": 0.028655072674155235,
      "learning_rate": 0.00019316852651434462,
      "loss": 0.7036,
      "step": 171
    },
    {
      "epoch": 0.26522744795682346,
      "grad_norm": 0.024629781022667885,
      "learning_rate": 0.0001930788057083476,
      "loss": 0.774,
      "step": 172
    },
    {
      "epoch": 0.26676946800308404,
      "grad_norm": 0.023107299581170082,
      "learning_rate": 0.0001929885206816973,
      "loss": 0.7021,
      "step": 173
    },
    {
      "epoch": 0.2683114880493446,
      "grad_norm": 0.022794177755713463,
      "learning_rate": 0.00019289767198167916,
      "loss": 0.7469,
      "step": 174
    },
    {
      "epoch": 0.26985350809560527,
      "grad_norm": 0.026097161695361137,
      "learning_rate": 0.00019280626015899546,
      "loss": 0.7325,
      "step": 175
    },
    {
      "epoch": 0.27139552814186585,
      "grad_norm": 0.029879910871386528,
      "learning_rate": 0.00019271428576776205,
      "loss": 0.7614,
      "step": 176
    },
    {
      "epoch": 0.27293754818812643,
      "grad_norm": 0.026986606419086456,
      "learning_rate": 0.00019262174936550487,
      "loss": 0.7718,
      "step": 177
    },
    {
      "epoch": 0.2744795682343871,
      "grad_norm": 0.025835467502474785,
      "learning_rate": 0.00019252865151315665,
      "loss": 0.7511,
      "step": 178
    },
    {
      "epoch": 0.27602158828064766,
      "grad_norm": 0.028101902455091476,
      "learning_rate": 0.00019243499277505355,
      "loss": 0.8136,
      "step": 179
    },
    {
      "epoch": 0.27756360832690824,
      "grad_norm": 0.028153471648693085,
      "learning_rate": 0.00019234077371893155,
      "loss": 0.8798,
      "step": 180
    },
    {
      "epoch": 0.2791056283731688,
      "grad_norm": 0.024540267884731293,
      "learning_rate": 0.0001922459949159233,
      "loss": 0.7854,
      "step": 181
    },
    {
      "epoch": 0.28064764841942946,
      "grad_norm": 0.023485183715820312,
      "learning_rate": 0.00019215065694055437,
      "loss": 0.6655,
      "step": 182
    },
    {
      "epoch": 0.28218966846569005,
      "grad_norm": 0.023394625633955002,
      "learning_rate": 0.00019205476037073997,
      "loss": 0.759,
      "step": 183
    },
    {
      "epoch": 0.28373168851195063,
      "grad_norm": 0.025181008502840996,
      "learning_rate": 0.00019195830578778132,
      "loss": 0.7649,
      "step": 184
    },
    {
      "epoch": 0.28527370855821127,
      "grad_norm": 0.023696815595030785,
      "learning_rate": 0.0001918612937763622,
      "loss": 0.7469,
      "step": 185
    },
    {
      "epoch": 0.28681572860447185,
      "grad_norm": 0.025794658809900284,
      "learning_rate": 0.00019176372492454537,
      "loss": 0.7623,
      "step": 186
    },
    {
      "epoch": 0.28835774865073244,
      "grad_norm": 0.02523699589073658,
      "learning_rate": 0.00019166559982376904,
      "loss": 0.6621,
      "step": 187
    },
    {
      "epoch": 0.2898997686969931,
      "grad_norm": 0.02426300384104252,
      "learning_rate": 0.00019156691906884325,
      "loss": 0.748,
      "step": 188
    },
    {
      "epoch": 0.29144178874325366,
      "grad_norm": 0.024227775633335114,
      "learning_rate": 0.0001914676832579463,
      "loss": 0.724,
      "step": 189
    },
    {
      "epoch": 0.29298380878951424,
      "grad_norm": 0.031684551388025284,
      "learning_rate": 0.00019136789299262108,
      "loss": 0.8939,
      "step": 190
    },
    {
      "epoch": 0.2945258288357749,
      "grad_norm": 0.023766616359353065,
      "learning_rate": 0.0001912675488777714,
      "loss": 0.7179,
      "step": 191
    },
    {
      "epoch": 0.29606784888203547,
      "grad_norm": 0.02463400922715664,
      "learning_rate": 0.0001911666515216585,
      "loss": 0.8202,
      "step": 192
    },
    {
      "epoch": 0.29760986892829605,
      "grad_norm": 0.0225905179977417,
      "learning_rate": 0.00019106520153589708,
      "loss": 0.6357,
      "step": 193
    },
    {
      "epoch": 0.2991518889745567,
      "grad_norm": 0.022882292047142982,
      "learning_rate": 0.00019096319953545185,
      "loss": 0.7506,
      "step": 194
    },
    {
      "epoch": 0.3006939090208173,
      "grad_norm": 0.027596216648817062,
      "learning_rate": 0.00019086064613863364,
      "loss": 0.7669,
      "step": 195
    },
    {
      "epoch": 0.30223592906707786,
      "grad_norm": 0.030367175117135048,
      "learning_rate": 0.00019075754196709572,
      "loss": 0.7792,
      "step": 196
    },
    {
      "epoch": 0.3037779491133385,
      "grad_norm": 0.025017013773322105,
      "learning_rate": 0.00019065388764583004,
      "loss": 0.6977,
      "step": 197
    },
    {
      "epoch": 0.3053199691595991,
      "grad_norm": 0.02788584679365158,
      "learning_rate": 0.0001905496838031634,
      "loss": 0.6871,
      "step": 198
    },
    {
      "epoch": 0.30686198920585966,
      "grad_norm": 0.032745130360126495,
      "learning_rate": 0.00019044493107075368,
      "loss": 0.8934,
      "step": 199
    },
    {
      "epoch": 0.3084040092521203,
      "grad_norm": 0.027039945125579834,
      "learning_rate": 0.00019033963008358598,
      "loss": 0.6522,
      "step": 200
    },
    {
      "epoch": 0.3099460292983809,
      "grad_norm": 0.03149978816509247,
      "learning_rate": 0.0001902337814799688,
      "loss": 0.844,
      "step": 201
    },
    {
      "epoch": 0.31148804934464147,
      "grad_norm": 0.024369308724999428,
      "learning_rate": 0.0001901273859015301,
      "loss": 0.7202,
      "step": 202
    },
    {
      "epoch": 0.31303006939090205,
      "grad_norm": 0.05448361113667488,
      "learning_rate": 0.00019002044399321356,
      "loss": 0.8301,
      "step": 203
    },
    {
      "epoch": 0.3145720894371627,
      "grad_norm": 0.02388385497033596,
      "learning_rate": 0.0001899129564032745,
      "loss": 0.7105,
      "step": 204
    },
    {
      "epoch": 0.3161141094834233,
      "grad_norm": 0.02488291636109352,
      "learning_rate": 0.00018980492378327607,
      "loss": 0.7393,
      "step": 205
    },
    {
      "epoch": 0.31765612952968386,
      "grad_norm": 0.023874662816524506,
      "learning_rate": 0.00018969634678808522,
      "loss": 0.6791,
      "step": 206
    },
    {
      "epoch": 0.3191981495759445,
      "grad_norm": 0.030418075621128082,
      "learning_rate": 0.0001895872260758688,
      "loss": 0.75,
      "step": 207
    },
    {
      "epoch": 0.3207401696222051,
      "grad_norm": 0.02990088053047657,
      "learning_rate": 0.00018947756230808954,
      "loss": 0.7986,
      "step": 208
    },
    {
      "epoch": 0.32228218966846567,
      "grad_norm": 0.027980022132396698,
      "learning_rate": 0.00018936735614950197,
      "loss": 0.7054,
      "step": 209
    },
    {
      "epoch": 0.3238242097147263,
      "grad_norm": 0.026269223541021347,
      "learning_rate": 0.00018925660826814856,
      "loss": 0.8195,
      "step": 210
    },
    {
      "epoch": 0.3253662297609869,
      "grad_norm": 0.025045178830623627,
      "learning_rate": 0.0001891453193353555,
      "loss": 0.7221,
      "step": 211
    },
    {
      "epoch": 0.3269082498072475,
      "grad_norm": 0.021175356581807137,
      "learning_rate": 0.00018903349002572873,
      "loss": 0.6513,
      "step": 212
    },
    {
      "epoch": 0.3284502698535081,
      "grad_norm": 0.023593388497829437,
      "learning_rate": 0.0001889211210171498,
      "loss": 0.7405,
      "step": 213
    },
    {
      "epoch": 0.3299922898997687,
      "grad_norm": 0.027270464226603508,
      "learning_rate": 0.00018880821299077183,
      "loss": 0.7184,
      "step": 214
    },
    {
      "epoch": 0.3315343099460293,
      "grad_norm": 0.025203121826052666,
      "learning_rate": 0.00018869476663101523,
      "loss": 0.6659,
      "step": 215
    },
    {
      "epoch": 0.3330763299922899,
      "grad_norm": 0.024924185127019882,
      "learning_rate": 0.0001885807826255638,
      "loss": 0.7412,
      "step": 216
    },
    {
      "epoch": 0.3346183500385505,
      "grad_norm": 0.022862501442432404,
      "learning_rate": 0.00018846626166536026,
      "loss": 0.6984,
      "step": 217
    },
    {
      "epoch": 0.3361603700848111,
      "grad_norm": 0.022781461477279663,
      "learning_rate": 0.0001883512044446023,
      "loss": 0.6374,
      "step": 218
    },
    {
      "epoch": 0.33770239013107173,
      "grad_norm": 0.023618346080183983,
      "learning_rate": 0.0001882356116607383,
      "loss": 0.6948,
      "step": 219
    },
    {
      "epoch": 0.3392444101773323,
      "grad_norm": 0.02586747333407402,
      "learning_rate": 0.0001881194840144631,
      "loss": 0.7682,
      "step": 220
    },
    {
      "epoch": 0.3407864302235929,
      "grad_norm": 0.026834698393940926,
      "learning_rate": 0.00018800282220971366,
      "loss": 0.7546,
      "step": 221
    },
    {
      "epoch": 0.34232845026985353,
      "grad_norm": 0.028564658015966415,
      "learning_rate": 0.00018788562695366495,
      "loss": 0.8267,
      "step": 222
    },
    {
      "epoch": 0.3438704703161141,
      "grad_norm": 0.02490355260670185,
      "learning_rate": 0.00018776789895672558,
      "loss": 0.6937,
      "step": 223
    },
    {
      "epoch": 0.3454124903623747,
      "grad_norm": 0.03545152395963669,
      "learning_rate": 0.00018764963893253347,
      "loss": 0.7001,
      "step": 224
    },
    {
      "epoch": 0.3469545104086353,
      "grad_norm": 0.02449451945722103,
      "learning_rate": 0.00018753084759795158,
      "loss": 0.8165,
      "step": 225
    },
    {
      "epoch": 0.3484965304548959,
      "grad_norm": 0.027851196005940437,
      "learning_rate": 0.00018741152567306355,
      "loss": 0.7196,
      "step": 226
    },
    {
      "epoch": 0.3500385505011565,
      "grad_norm": 0.02707446552813053,
      "learning_rate": 0.00018729167388116934,
      "loss": 0.8375,
      "step": 227
    },
    {
      "epoch": 0.3515805705474171,
      "grad_norm": 0.02902469038963318,
      "learning_rate": 0.00018717129294878074,
      "loss": 0.6744,
      "step": 228
    },
    {
      "epoch": 0.35312259059367773,
      "grad_norm": 0.031537748873233795,
      "learning_rate": 0.0001870503836056172,
      "loss": 0.7552,
      "step": 229
    },
    {
      "epoch": 0.3546646106399383,
      "grad_norm": 0.026265786960721016,
      "learning_rate": 0.00018692894658460117,
      "loss": 0.7551,
      "step": 230
    },
    {
      "epoch": 0.3562066306861989,
      "grad_norm": 0.02483406662940979,
      "learning_rate": 0.0001868069826218538,
      "loss": 0.7233,
      "step": 231
    },
    {
      "epoch": 0.35774865073245954,
      "grad_norm": 0.024800019338726997,
      "learning_rate": 0.0001866844924566904,
      "loss": 0.7371,
      "step": 232
    },
    {
      "epoch": 0.3592906707787201,
      "grad_norm": 0.02515244670212269,
      "learning_rate": 0.00018656147683161593,
      "loss": 0.7621,
      "step": 233
    },
    {
      "epoch": 0.3608326908249807,
      "grad_norm": 0.02592633105814457,
      "learning_rate": 0.00018643793649232072,
      "loss": 0.7539,
      "step": 234
    },
    {
      "epoch": 0.36237471087124135,
      "grad_norm": 0.0275077186524868,
      "learning_rate": 0.00018631387218767561,
      "loss": 0.6925,
      "step": 235
    },
    {
      "epoch": 0.36391673091750193,
      "grad_norm": 0.027163324877619743,
      "learning_rate": 0.00018618928466972775,
      "loss": 0.7867,
      "step": 236
    },
    {
      "epoch": 0.3654587509637625,
      "grad_norm": 0.026956308633089066,
      "learning_rate": 0.0001860641746936957,
      "loss": 0.7813,
      "step": 237
    },
    {
      "epoch": 0.36700077101002315,
      "grad_norm": 0.02884814888238907,
      "learning_rate": 0.0001859385430179652,
      "loss": 0.7366,
      "step": 238
    },
    {
      "epoch": 0.36854279105628374,
      "grad_norm": 0.025071945041418076,
      "learning_rate": 0.00018581239040408432,
      "loss": 0.708,
      "step": 239
    },
    {
      "epoch": 0.3700848111025443,
      "grad_norm": 0.032973822206258774,
      "learning_rate": 0.00018568571761675893,
      "loss": 0.6544,
      "step": 240
    },
    {
      "epoch": 0.37162683114880496,
      "grad_norm": 0.02571587637066841,
      "learning_rate": 0.0001855585254238481,
      "loss": 0.7633,
      "step": 241
    },
    {
      "epoch": 0.37316885119506554,
      "grad_norm": 0.027229083701968193,
      "learning_rate": 0.00018543081459635935,
      "loss": 0.7752,
      "step": 242
    },
    {
      "epoch": 0.3747108712413261,
      "grad_norm": 0.022508805617690086,
      "learning_rate": 0.00018530258590844409,
      "loss": 0.6437,
      "step": 243
    },
    {
      "epoch": 0.37625289128758677,
      "grad_norm": 0.026772433891892433,
      "learning_rate": 0.00018517384013739285,
      "loss": 0.805,
      "step": 244
    },
    {
      "epoch": 0.37779491133384735,
      "grad_norm": 0.023964572697877884,
      "learning_rate": 0.00018504457806363056,
      "loss": 0.7378,
      "step": 245
    },
    {
      "epoch": 0.37933693138010793,
      "grad_norm": 0.02789299376308918,
      "learning_rate": 0.0001849148004707119,
      "loss": 0.772,
      "step": 246
    },
    {
      "epoch": 0.3808789514263685,
      "grad_norm": 0.031168216839432716,
      "learning_rate": 0.00018478450814531647,
      "loss": 0.8299,
      "step": 247
    },
    {
      "epoch": 0.38242097147262916,
      "grad_norm": 0.03058604896068573,
      "learning_rate": 0.00018465370187724408,
      "loss": 0.694,
      "step": 248
    },
    {
      "epoch": 0.38396299151888974,
      "grad_norm": 0.028347650542855263,
      "learning_rate": 0.0001845223824594099,
      "loss": 0.7373,
      "step": 249
    },
    {
      "epoch": 0.3855050115651503,
      "grad_norm": 0.025979626923799515,
      "learning_rate": 0.00018439055068783966,
      "loss": 0.8036,
      "step": 250
    },
    {
      "epoch": 0.38704703161141096,
      "grad_norm": 0.029867777600884438,
      "learning_rate": 0.0001842582073616649,
      "loss": 0.7655,
      "step": 251
    },
    {
      "epoch": 0.38858905165767155,
      "grad_norm": 0.025117915123701096,
      "learning_rate": 0.00018412535328311814,
      "loss": 0.7532,
      "step": 252
    },
    {
      "epoch": 0.39013107170393213,
      "grad_norm": 0.023947982117533684,
      "learning_rate": 0.00018399198925752778,
      "loss": 0.6967,
      "step": 253
    },
    {
      "epoch": 0.39167309175019277,
      "grad_norm": 0.025846531614661217,
      "learning_rate": 0.00018385811609331352,
      "loss": 0.7382,
      "step": 254
    },
    {
      "epoch": 0.39321511179645335,
      "grad_norm": 0.025034697726368904,
      "learning_rate": 0.00018372373460198138,
      "loss": 0.7282,
      "step": 255
    },
    {
      "epoch": 0.39475713184271394,
      "grad_norm": 0.02547437883913517,
      "learning_rate": 0.00018358884559811856,
      "loss": 0.7447,
      "step": 256
    },
    {
      "epoch": 0.3962991518889746,
      "grad_norm": 0.027032596990466118,
      "learning_rate": 0.0001834534498993888,
      "loss": 0.7395,
      "step": 257
    },
    {
      "epoch": 0.39784117193523516,
      "grad_norm": 0.027110572904348373,
      "learning_rate": 0.0001833175483265273,
      "loss": 0.7963,
      "step": 258
    },
    {
      "epoch": 0.39938319198149574,
      "grad_norm": 0.027663685381412506,
      "learning_rate": 0.00018318114170333568,
      "loss": 0.7893,
      "step": 259
    },
    {
      "epoch": 0.4009252120277564,
      "grad_norm": 0.027797933667898178,
      "learning_rate": 0.00018304423085667714,
      "loss": 0.7228,
      "step": 260
    },
    {
      "epoch": 0.40246723207401697,
      "grad_norm": 0.026281701400876045,
      "learning_rate": 0.0001829068166164712,
      "loss": 0.749,
      "step": 261
    },
    {
      "epoch": 0.40400925212027755,
      "grad_norm": 0.024708108976483345,
      "learning_rate": 0.00018276889981568906,
      "loss": 0.6307,
      "step": 262
    },
    {
      "epoch": 0.4055512721665382,
      "grad_norm": 0.028213316574692726,
      "learning_rate": 0.0001826304812903481,
      "loss": 0.8186,
      "step": 263
    },
    {
      "epoch": 0.4070932922127988,
      "grad_norm": 0.024718405678868294,
      "learning_rate": 0.00018249156187950715,
      "loss": 0.7077,
      "step": 264
    },
    {
      "epoch": 0.40863531225905936,
      "grad_norm": 0.02398741990327835,
      "learning_rate": 0.00018235214242526125,
      "loss": 0.7041,
      "step": 265
    },
    {
      "epoch": 0.41017733230531994,
      "grad_norm": 0.03176787495613098,
      "learning_rate": 0.00018221222377273657,
      "loss": 0.7036,
      "step": 266
    },
    {
      "epoch": 0.4117193523515806,
      "grad_norm": 0.028862686827778816,
      "learning_rate": 0.0001820718067700853,
      "loss": 0.7947,
      "step": 267
    },
    {
      "epoch": 0.41326137239784116,
      "grad_norm": 0.026759544387459755,
      "learning_rate": 0.0001819308922684805,
      "loss": 0.7737,
      "step": 268
    },
    {
      "epoch": 0.41480339244410175,
      "grad_norm": 0.02719755284488201,
      "learning_rate": 0.00018178948112211103,
      "loss": 0.7403,
      "step": 269
    },
    {
      "epoch": 0.4163454124903624,
      "grad_norm": 0.024756524711847305,
      "learning_rate": 0.0001816475741881761,
      "loss": 0.6994,
      "step": 270
    },
    {
      "epoch": 0.41788743253662297,
      "grad_norm": 0.03232420235872269,
      "learning_rate": 0.00018150517232688049,
      "loss": 0.7866,
      "step": 271
    },
    {
      "epoch": 0.41942945258288356,
      "grad_norm": 0.027607185766100883,
      "learning_rate": 0.00018136227640142894,
      "loss": 0.7905,
      "step": 272
    },
    {
      "epoch": 0.4209714726291442,
      "grad_norm": 0.024344706907868385,
      "learning_rate": 0.00018121888727802113,
      "loss": 0.7408,
      "step": 273
    },
    {
      "epoch": 0.4225134926754048,
      "grad_norm": 0.025088010355830193,
      "learning_rate": 0.0001810750058258464,
      "loss": 0.737,
      "step": 274
    },
    {
      "epoch": 0.42405551272166536,
      "grad_norm": 0.023952683433890343,
      "learning_rate": 0.00018093063291707847,
      "loss": 0.7764,
      "step": 275
    },
    {
      "epoch": 0.425597532767926,
      "grad_norm": 0.0288414116948843,
      "learning_rate": 0.00018078576942687008,
      "loss": 0.7035,
      "step": 276
    },
    {
      "epoch": 0.4271395528141866,
      "grad_norm": 0.02681080810725689,
      "learning_rate": 0.0001806404162333479,
      "loss": 0.739,
      "step": 277
    },
    {
      "epoch": 0.42868157286044717,
      "grad_norm": 0.0266602523624897,
      "learning_rate": 0.0001804945742176069,
      "loss": 0.7213,
      "step": 278
    },
    {
      "epoch": 0.4302235929067078,
      "grad_norm": 0.025282425805926323,
      "learning_rate": 0.00018034824426370523,
      "loss": 0.6807,
      "step": 279
    },
    {
      "epoch": 0.4317656129529684,
      "grad_norm": 0.025683747604489326,
      "learning_rate": 0.00018020142725865888,
      "loss": 0.7283,
      "step": 280
    },
    {
      "epoch": 0.433307632999229,
      "grad_norm": 0.024966144934296608,
      "learning_rate": 0.00018005412409243606,
      "loss": 0.7096,
      "step": 281
    },
    {
      "epoch": 0.4348496530454896,
      "grad_norm": 0.027953188866376877,
      "learning_rate": 0.00017990633565795208,
      "loss": 0.8148,
      "step": 282
    },
    {
      "epoch": 0.4363916730917502,
      "grad_norm": 0.02772989496588707,
      "learning_rate": 0.00017975806285106387,
      "loss": 0.8568,
      "step": 283
    },
    {
      "epoch": 0.4379336931380108,
      "grad_norm": 0.028020409867167473,
      "learning_rate": 0.00017960930657056438,
      "loss": 0.6732,
      "step": 284
    },
    {
      "epoch": 0.4394757131842714,
      "grad_norm": 0.025754399597644806,
      "learning_rate": 0.00017946006771817733,
      "loss": 0.7238,
      "step": 285
    },
    {
      "epoch": 0.441017733230532,
      "grad_norm": 0.030171813443303108,
      "learning_rate": 0.00017931034719855166,
      "loss": 0.7493,
      "step": 286
    },
    {
      "epoch": 0.4425597532767926,
      "grad_norm": 0.026995845139026642,
      "learning_rate": 0.00017916014591925605,
      "loss": 0.6118,
      "step": 287
    },
    {
      "epoch": 0.4441017733230532,
      "grad_norm": 0.03541433438658714,
      "learning_rate": 0.00017900946479077346,
      "loss": 0.7243,
      "step": 288
    },
    {
      "epoch": 0.4456437933693138,
      "grad_norm": 0.029751230031251907,
      "learning_rate": 0.00017885830472649553,
      "loss": 0.7081,
      "step": 289
    },
    {
      "epoch": 0.4471858134155744,
      "grad_norm": 0.022569075226783752,
      "learning_rate": 0.00017870666664271707,
      "loss": 0.6488,
      "step": 290
    },
    {
      "epoch": 0.448727833461835,
      "grad_norm": 0.03262341767549515,
      "learning_rate": 0.00017855455145863062,
      "loss": 0.7626,
      "step": 291
    },
    {
      "epoch": 0.4502698535080956,
      "grad_norm": 0.02811555750668049,
      "learning_rate": 0.0001784019600963207,
      "loss": 0.7485,
      "step": 292
    },
    {
      "epoch": 0.4518118735543562,
      "grad_norm": 0.02504836954176426,
      "learning_rate": 0.00017824889348075837,
      "loss": 0.7636,
      "step": 293
    },
    {
      "epoch": 0.4533538936006168,
      "grad_norm": 0.02362634427845478,
      "learning_rate": 0.00017809535253979547,
      "loss": 0.6915,
      "step": 294
    },
    {
      "epoch": 0.4548959136468774,
      "grad_norm": 0.029891418293118477,
      "learning_rate": 0.00017794133820415916,
      "loss": 0.7686,
      "step": 295
    },
    {
      "epoch": 0.456437933693138,
      "grad_norm": 0.02471439354121685,
      "learning_rate": 0.0001777868514074462,
      "loss": 0.6693,
      "step": 296
    },
    {
      "epoch": 0.4579799537393986,
      "grad_norm": 0.025612330064177513,
      "learning_rate": 0.00017763189308611722,
      "loss": 0.7364,
      "step": 297
    },
    {
      "epoch": 0.45952197378565923,
      "grad_norm": 0.026865236461162567,
      "learning_rate": 0.00017747646417949113,
      "loss": 0.7445,
      "step": 298
    },
    {
      "epoch": 0.4610639938319198,
      "grad_norm": 0.024343574419617653,
      "learning_rate": 0.00017732056562973954,
      "loss": 0.6271,
      "step": 299
    },
    {
      "epoch": 0.4626060138781804,
      "grad_norm": 0.02818606235086918,
      "learning_rate": 0.00017716419838188077,
      "loss": 0.7753,
      "step": 300
    },
    {
      "epoch": 0.46414803392444104,
      "grad_norm": 0.026821713894605637,
      "learning_rate": 0.00017700736338377435,
      "loss": 0.6976,
      "step": 301
    },
    {
      "epoch": 0.4656900539707016,
      "grad_norm": 0.025784511119127274,
      "learning_rate": 0.00017685006158611516,
      "loss": 0.7062,
      "step": 302
    },
    {
      "epoch": 0.4672320740169622,
      "grad_norm": 0.028515879064798355,
      "learning_rate": 0.00017669229394242766,
      "loss": 0.7909,
      "step": 303
    },
    {
      "epoch": 0.46877409406322285,
      "grad_norm": 0.024095451459288597,
      "learning_rate": 0.0001765340614090603,
      "loss": 0.7535,
      "step": 304
    },
    {
      "epoch": 0.47031611410948343,
      "grad_norm": 0.025953758507966995,
      "learning_rate": 0.0001763753649451794,
      "loss": 0.7623,
      "step": 305
    },
    {
      "epoch": 0.471858134155744,
      "grad_norm": 0.03294069692492485,
      "learning_rate": 0.00017621620551276366,
      "loss": 0.8946,
      "step": 306
    },
    {
      "epoch": 0.47340015420200465,
      "grad_norm": 0.028394997119903564,
      "learning_rate": 0.00017605658407659808,
      "loss": 0.7251,
      "step": 307
    },
    {
      "epoch": 0.47494217424826524,
      "grad_norm": 0.025346368551254272,
      "learning_rate": 0.00017589650160426828,
      "loss": 0.7074,
      "step": 308
    },
    {
      "epoch": 0.4764841942945258,
      "grad_norm": 0.025906400755047798,
      "learning_rate": 0.0001757359590661545,
      "loss": 0.6472,
      "step": 309
    },
    {
      "epoch": 0.4780262143407864,
      "grad_norm": 0.02889554388821125,
      "learning_rate": 0.00017557495743542585,
      "loss": 0.715,
      "step": 310
    },
    {
      "epoch": 0.47956823438704704,
      "grad_norm": 0.029205597937107086,
      "learning_rate": 0.00017541349768803428,
      "loss": 0.698,
      "step": 311
    },
    {
      "epoch": 0.4811102544333076,
      "grad_norm": 0.02610400691628456,
      "learning_rate": 0.0001752515808027088,
      "loss": 0.7073,
      "step": 312
    },
    {
      "epoch": 0.4826522744795682,
      "grad_norm": 0.023945793509483337,
      "learning_rate": 0.00017508920776094944,
      "loss": 0.6865,
      "step": 313
    },
    {
      "epoch": 0.48419429452582885,
      "grad_norm": 0.028426503762602806,
      "learning_rate": 0.0001749263795470213,
      "loss": 0.7264,
      "step": 314
    },
    {
      "epoch": 0.48573631457208943,
      "grad_norm": 0.02865850180387497,
      "learning_rate": 0.0001747630971479487,
      "loss": 0.7204,
      "step": 315
    },
    {
      "epoch": 0.48727833461835,
      "grad_norm": 0.027321334928274155,
      "learning_rate": 0.00017459936155350908,
      "loss": 0.7491,
      "step": 316
    },
    {
      "epoch": 0.48882035466461066,
      "grad_norm": 0.02754514105618,
      "learning_rate": 0.00017443517375622704,
      "loss": 0.7567,
      "step": 317
    },
    {
      "epoch": 0.49036237471087124,
      "grad_norm": 0.028822382912039757,
      "learning_rate": 0.00017427053475136826,
      "loss": 0.7559,
      "step": 318
    },
    {
      "epoch": 0.4919043947571318,
      "grad_norm": 0.03181014209985733,
      "learning_rate": 0.00017410544553693365,
      "loss": 0.7704,
      "step": 319
    },
    {
      "epoch": 0.49344641480339246,
      "grad_norm": 0.023862695321440697,
      "learning_rate": 0.00017393990711365312,
      "loss": 0.6085,
      "step": 320
    },
    {
      "epoch": 0.49498843484965305,
      "grad_norm": 0.02703220769762993,
      "learning_rate": 0.00017377392048497953,
      "loss": 0.6979,
      "step": 321
    },
    {
      "epoch": 0.49653045489591363,
      "grad_norm": 0.025343257933855057,
      "learning_rate": 0.00017360748665708268,
      "loss": 0.7287,
      "step": 322
    },
    {
      "epoch": 0.49807247494217427,
      "grad_norm": 0.02830134704709053,
      "learning_rate": 0.00017344060663884324,
      "loss": 0.8054,
      "step": 323
    },
    {
      "epoch": 0.49961449498843485,
      "grad_norm": 0.025809939950704575,
      "learning_rate": 0.00017327328144184646,
      "loss": 0.704,
      "step": 324
    },
    {
      "epoch": 0.5011565150346955,
      "grad_norm": 0.027546260505914688,
      "learning_rate": 0.00017310551208037626,
      "loss": 0.7099,
      "step": 325
    },
    {
      "epoch": 0.5026985350809561,
      "grad_norm": 0.027951935306191444,
      "learning_rate": 0.00017293729957140893,
      "loss": 0.878,
      "step": 326
    },
    {
      "epoch": 0.5042405551272167,
      "grad_norm": 0.026868853718042374,
      "learning_rate": 0.000172768644934607,
      "loss": 0.7714,
      "step": 327
    },
    {
      "epoch": 0.5057825751734772,
      "grad_norm": 0.026975559070706367,
      "learning_rate": 0.0001725995491923131,
      "loss": 0.7526,
      "step": 328
    },
    {
      "epoch": 0.5073245952197378,
      "grad_norm": 0.027235837653279305,
      "learning_rate": 0.0001724300133695437,
      "loss": 0.6515,
      "step": 329
    },
    {
      "epoch": 0.5088666152659984,
      "grad_norm": 0.032752856612205505,
      "learning_rate": 0.00017226003849398294,
      "loss": 0.8019,
      "step": 330
    },
    {
      "epoch": 0.5104086353122591,
      "grad_norm": 0.029344195500016212,
      "learning_rate": 0.0001720896255959764,
      "loss": 0.9296,
      "step": 331
    },
    {
      "epoch": 0.5119506553585197,
      "grad_norm": 0.025766605511307716,
      "learning_rate": 0.00017191877570852483,
      "loss": 0.7944,
      "step": 332
    },
    {
      "epoch": 0.5134926754047803,
      "grad_norm": 0.023067327216267586,
      "learning_rate": 0.0001717474898672779,
      "loss": 0.6528,
      "step": 333
    },
    {
      "epoch": 0.5150346954510409,
      "grad_norm": 0.026817042380571365,
      "learning_rate": 0.00017157576911052796,
      "loss": 0.763,
      "step": 334
    },
    {
      "epoch": 0.5165767154973014,
      "grad_norm": 0.02811489813029766,
      "learning_rate": 0.00017140361447920364,
      "loss": 0.7936,
      "step": 335
    },
    {
      "epoch": 0.518118735543562,
      "grad_norm": 0.02597888559103012,
      "learning_rate": 0.00017123102701686372,
      "loss": 0.7217,
      "step": 336
    },
    {
      "epoch": 0.5196607555898227,
      "grad_norm": 0.030244017019867897,
      "learning_rate": 0.00017105800776969055,
      "loss": 0.756,
      "step": 337
    },
    {
      "epoch": 0.5212027756360833,
      "grad_norm": 0.028289398178458214,
      "learning_rate": 0.00017088455778648397,
      "loss": 0.7972,
      "step": 338
    },
    {
      "epoch": 0.5227447956823439,
      "grad_norm": 0.02397543005645275,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.6358,
      "step": 339
    },
    {
      "epoch": 0.5242868157286045,
      "grad_norm": 0.02565479464828968,
      "learning_rate": 0.00017053636982021844,
      "loss": 0.6912,
      "step": 340
    },
    {
      "epoch": 0.525828835774865,
      "grad_norm": 0.027768775820732117,
      "learning_rate": 0.00017036163394778864,
      "loss": 0.7997,
      "step": 341
    },
    {
      "epoch": 0.5273708558211256,
      "grad_norm": 0.033537182956933975,
      "learning_rate": 0.00017018647156057096,
      "loss": 0.7363,
      "step": 342
    },
    {
      "epoch": 0.5289128758673862,
      "grad_norm": 0.030843475833535194,
      "learning_rate": 0.00017001088372035637,
      "loss": 0.6977,
      "step": 343
    },
    {
      "epoch": 0.5304548959136469,
      "grad_norm": 0.026586662977933884,
      "learning_rate": 0.00016983487149151486,
      "loss": 0.7874,
      "step": 344
    },
    {
      "epoch": 0.5319969159599075,
      "grad_norm": 0.027003532275557518,
      "learning_rate": 0.00016965843594098892,
      "loss": 0.7895,
      "step": 345
    },
    {
      "epoch": 0.5335389360061681,
      "grad_norm": 0.02772395871579647,
      "learning_rate": 0.00016948157813828716,
      "loss": 0.7799,
      "step": 346
    },
    {
      "epoch": 0.5350809560524287,
      "grad_norm": 0.025633979588747025,
      "learning_rate": 0.0001693042991554777,
      "loss": 0.744,
      "step": 347
    },
    {
      "epoch": 0.5366229760986893,
      "grad_norm": 0.033604227006435394,
      "learning_rate": 0.00016912660006718186,
      "loss": 0.6707,
      "step": 348
    },
    {
      "epoch": 0.5381649961449498,
      "grad_norm": 0.03711126372218132,
      "learning_rate": 0.00016894848195056746,
      "loss": 0.8468,
      "step": 349
    },
    {
      "epoch": 0.5397070161912105,
      "grad_norm": 0.02382393553853035,
      "learning_rate": 0.00016876994588534234,
      "loss": 0.6884,
      "step": 350
    },
    {
      "epoch": 0.5412490362374711,
      "grad_norm": 0.02597069926559925,
      "learning_rate": 0.0001685909929537479,
      "loss": 0.7789,
      "step": 351
    },
    {
      "epoch": 0.5427910562837317,
      "grad_norm": 0.027003685012459755,
      "learning_rate": 0.0001684116242405525,
      "loss": 0.7364,
      "step": 352
    },
    {
      "epoch": 0.5443330763299923,
      "grad_norm": 0.028209254145622253,
      "learning_rate": 0.00016823184083304482,
      "loss": 0.8014,
      "step": 353
    },
    {
      "epoch": 0.5458750963762529,
      "grad_norm": 0.025543801486492157,
      "learning_rate": 0.0001680516438210273,
      "loss": 0.7241,
      "step": 354
    },
    {
      "epoch": 0.5474171164225135,
      "grad_norm": 0.024730654433369637,
      "learning_rate": 0.00016787103429680955,
      "loss": 0.6425,
      "step": 355
    },
    {
      "epoch": 0.5489591364687741,
      "grad_norm": 0.02615622617304325,
      "learning_rate": 0.0001676900133552018,
      "loss": 0.7091,
      "step": 356
    },
    {
      "epoch": 0.5505011565150347,
      "grad_norm": 0.025628188624978065,
      "learning_rate": 0.00016750858209350808,
      "loss": 0.848,
      "step": 357
    },
    {
      "epoch": 0.5520431765612953,
      "grad_norm": 0.02642144076526165,
      "learning_rate": 0.0001673267416115198,
      "loss": 0.7026,
      "step": 358
    },
    {
      "epoch": 0.5535851966075559,
      "grad_norm": 0.02542021870613098,
      "learning_rate": 0.00016714449301150883,
      "loss": 0.6338,
      "step": 359
    },
    {
      "epoch": 0.5551272166538165,
      "grad_norm": 0.028573600575327873,
      "learning_rate": 0.00016696183739822108,
      "loss": 0.7553,
      "step": 360
    },
    {
      "epoch": 0.5566692367000771,
      "grad_norm": 0.024142924696207047,
      "learning_rate": 0.00016677877587886956,
      "loss": 0.7327,
      "step": 361
    },
    {
      "epoch": 0.5582112567463376,
      "grad_norm": 0.029369287192821503,
      "learning_rate": 0.00016659530956312788,
      "loss": 0.7728,
      "step": 362
    },
    {
      "epoch": 0.5597532767925983,
      "grad_norm": 0.02711080014705658,
      "learning_rate": 0.00016641143956312336,
      "loss": 0.6843,
      "step": 363
    },
    {
      "epoch": 0.5612952968388589,
      "grad_norm": 0.027241146191954613,
      "learning_rate": 0.00016622716699343033,
      "loss": 0.8534,
      "step": 364
    },
    {
      "epoch": 0.5628373168851195,
      "grad_norm": 0.030265534296631813,
      "learning_rate": 0.0001660424929710635,
      "loss": 0.8579,
      "step": 365
    },
    {
      "epoch": 0.5643793369313801,
      "grad_norm": 0.029054157435894012,
      "learning_rate": 0.000165857418615471,
      "loss": 0.75,
      "step": 366
    },
    {
      "epoch": 0.5659213569776407,
      "grad_norm": 0.029963452368974686,
      "learning_rate": 0.0001656719450485278,
      "loss": 0.7464,
      "step": 367
    },
    {
      "epoch": 0.5674633770239013,
      "grad_norm": 0.025763841345906258,
      "learning_rate": 0.00016548607339452853,
      "loss": 0.6632,
      "step": 368
    },
    {
      "epoch": 0.569005397070162,
      "grad_norm": 0.02374422177672386,
      "learning_rate": 0.00016529980478018115,
      "loss": 0.6546,
      "step": 369
    },
    {
      "epoch": 0.5705474171164225,
      "grad_norm": 0.02538699097931385,
      "learning_rate": 0.00016511314033459994,
      "loss": 0.6603,
      "step": 370
    },
    {
      "epoch": 0.5720894371626831,
      "grad_norm": 0.028310047462582588,
      "learning_rate": 0.0001649260811892984,
      "loss": 0.6088,
      "step": 371
    },
    {
      "epoch": 0.5736314572089437,
      "grad_norm": 0.02981553040444851,
      "learning_rate": 0.00016473862847818277,
      "loss": 0.8053,
      "step": 372
    },
    {
      "epoch": 0.5751734772552043,
      "grad_norm": 0.025665050372481346,
      "learning_rate": 0.0001645507833375449,
      "loss": 0.6779,
      "step": 373
    },
    {
      "epoch": 0.5767154973014649,
      "grad_norm": 0.030752114951610565,
      "learning_rate": 0.0001643625469060555,
      "loss": 0.6893,
      "step": 374
    },
    {
      "epoch": 0.5782575173477256,
      "grad_norm": 0.02725459821522236,
      "learning_rate": 0.00016417392032475715,
      "loss": 0.7879,
      "step": 375
    },
    {
      "epoch": 0.5797995373939862,
      "grad_norm": 0.02713746391236782,
      "learning_rate": 0.00016398490473705743,
      "loss": 0.7578,
      "step": 376
    },
    {
      "epoch": 0.5813415574402467,
      "grad_norm": 0.02641828916966915,
      "learning_rate": 0.000163795501288722,
      "loss": 0.7335,
      "step": 377
    },
    {
      "epoch": 0.5828835774865073,
      "grad_norm": 0.027243638411164284,
      "learning_rate": 0.00016360571112786765,
      "loss": 0.6873,
      "step": 378
    },
    {
      "epoch": 0.5844255975327679,
      "grad_norm": 0.028045805171132088,
      "learning_rate": 0.00016341553540495532,
      "loss": 0.7141,
      "step": 379
    },
    {
      "epoch": 0.5859676175790285,
      "grad_norm": 0.029962563887238503,
      "learning_rate": 0.00016322497527278306,
      "loss": 0.882,
      "step": 380
    },
    {
      "epoch": 0.5875096376252892,
      "grad_norm": 0.027544857934117317,
      "learning_rate": 0.00016303403188647913,
      "loss": 0.6695,
      "step": 381
    },
    {
      "epoch": 0.5890516576715498,
      "grad_norm": 0.02867518924176693,
      "learning_rate": 0.00016284270640349514,
      "loss": 0.8052,
      "step": 382
    },
    {
      "epoch": 0.5905936777178104,
      "grad_norm": 0.02330535091459751,
      "learning_rate": 0.00016265099998359866,
      "loss": 0.6825,
      "step": 383
    },
    {
      "epoch": 0.5921356977640709,
      "grad_norm": 0.030629336833953857,
      "learning_rate": 0.00016245891378886655,
      "loss": 0.8545,
      "step": 384
    },
    {
      "epoch": 0.5936777178103315,
      "grad_norm": 0.030393701046705246,
      "learning_rate": 0.00016226644898367768,
      "loss": 0.7342,
      "step": 385
    },
    {
      "epoch": 0.5952197378565921,
      "grad_norm": 0.02500557340681553,
      "learning_rate": 0.000162073606734706,
      "loss": 0.6975,
      "step": 386
    },
    {
      "epoch": 0.5967617579028527,
      "grad_norm": 0.031064705923199654,
      "learning_rate": 0.00016188038821091344,
      "loss": 0.7903,
      "step": 387
    },
    {
      "epoch": 0.5983037779491134,
      "grad_norm": 0.02647087723016739,
      "learning_rate": 0.00016168679458354284,
      "loss": 0.745,
      "step": 388
    },
    {
      "epoch": 0.599845797995374,
      "grad_norm": 0.02917948178946972,
      "learning_rate": 0.00016149282702611077,
      "loss": 0.7819,
      "step": 389
    },
    {
      "epoch": 0.6013878180416345,
      "grad_norm": 0.02458810992538929,
      "learning_rate": 0.00016129848671440046,
      "loss": 0.6466,
      "step": 390
    },
    {
      "epoch": 0.6029298380878951,
      "grad_norm": 0.023677226155996323,
      "learning_rate": 0.00016110377482645477,
      "loss": 0.7161,
      "step": 391
    },
    {
      "epoch": 0.6044718581341557,
      "grad_norm": 0.02807523123919964,
      "learning_rate": 0.00016090869254256892,
      "loss": 0.7164,
      "step": 392
    },
    {
      "epoch": 0.6060138781804163,
      "grad_norm": 0.031006982550024986,
      "learning_rate": 0.0001607132410452833,
      "loss": 0.7781,
      "step": 393
    },
    {
      "epoch": 0.607555898226677,
      "grad_norm": 0.029372677206993103,
      "learning_rate": 0.00016051742151937655,
      "loss": 0.7034,
      "step": 394
    },
    {
      "epoch": 0.6090979182729376,
      "grad_norm": 0.025212230160832405,
      "learning_rate": 0.00016032123515185797,
      "loss": 0.6567,
      "step": 395
    },
    {
      "epoch": 0.6106399383191982,
      "grad_norm": 0.024775920435786247,
      "learning_rate": 0.00016012468313196084,
      "loss": 0.6319,
      "step": 396
    },
    {
      "epoch": 0.6121819583654587,
      "grad_norm": 0.02687055990099907,
      "learning_rate": 0.0001599277666511347,
      "loss": 0.7214,
      "step": 397
    },
    {
      "epoch": 0.6137239784117193,
      "grad_norm": 0.028431419283151627,
      "learning_rate": 0.0001597304869030385,
      "loss": 0.7815,
      "step": 398
    },
    {
      "epoch": 0.6152659984579799,
      "grad_norm": 0.027922354638576508,
      "learning_rate": 0.00015953284508353317,
      "loss": 0.7016,
      "step": 399
    },
    {
      "epoch": 0.6168080185042406,
      "grad_norm": 0.02737678587436676,
      "learning_rate": 0.00015933484239067446,
      "loss": 0.7507,
      "step": 400
    },
    {
      "epoch": 0.6183500385505012,
      "grad_norm": 0.02791019156575203,
      "learning_rate": 0.00015913648002470563,
      "loss": 0.705,
      "step": 401
    },
    {
      "epoch": 0.6198920585967618,
      "grad_norm": 0.027861539274454117,
      "learning_rate": 0.0001589377591880501,
      "loss": 0.7208,
      "step": 402
    },
    {
      "epoch": 0.6214340786430224,
      "grad_norm": 0.02952715940773487,
      "learning_rate": 0.00015873868108530443,
      "loss": 0.7114,
      "step": 403
    },
    {
      "epoch": 0.6229760986892829,
      "grad_norm": 0.02896735444664955,
      "learning_rate": 0.0001585392469232307,
      "loss": 0.7797,
      "step": 404
    },
    {
      "epoch": 0.6245181187355435,
      "grad_norm": 0.02640017308294773,
      "learning_rate": 0.00015833945791074943,
      "loss": 0.7186,
      "step": 405
    },
    {
      "epoch": 0.6260601387818041,
      "grad_norm": 0.025937926024198532,
      "learning_rate": 0.000158139315258932,
      "loss": 0.781,
      "step": 406
    },
    {
      "epoch": 0.6276021588280648,
      "grad_norm": 0.02851933054625988,
      "learning_rate": 0.00015793882018099364,
      "loss": 0.7522,
      "step": 407
    },
    {
      "epoch": 0.6291441788743254,
      "grad_norm": 0.02368611842393875,
      "learning_rate": 0.00015773797389228582,
      "loss": 0.719,
      "step": 408
    },
    {
      "epoch": 0.630686198920586,
      "grad_norm": 0.026969095692038536,
      "learning_rate": 0.00015753677761028896,
      "loss": 0.7554,
      "step": 409
    },
    {
      "epoch": 0.6322282189668466,
      "grad_norm": 0.02418413758277893,
      "learning_rate": 0.00015733523255460506,
      "loss": 0.6919,
      "step": 410
    },
    {
      "epoch": 0.6337702390131071,
      "grad_norm": 0.026073114946484566,
      "learning_rate": 0.0001571333399469503,
      "loss": 0.7059,
      "step": 411
    },
    {
      "epoch": 0.6353122590593677,
      "grad_norm": 0.027075573801994324,
      "learning_rate": 0.0001569311010111476,
      "loss": 0.7239,
      "step": 412
    },
    {
      "epoch": 0.6368542791056284,
      "grad_norm": 0.02724389173090458,
      "learning_rate": 0.00015672851697311934,
      "loss": 0.7615,
      "step": 413
    },
    {
      "epoch": 0.638396299151889,
      "grad_norm": 0.026826992630958557,
      "learning_rate": 0.00015652558906087971,
      "loss": 0.8138,
      "step": 414
    },
    {
      "epoch": 0.6399383191981496,
      "grad_norm": 0.02641242742538452,
      "learning_rate": 0.00015632231850452747,
      "loss": 0.6956,
      "step": 415
    },
    {
      "epoch": 0.6414803392444102,
      "grad_norm": 0.02495909109711647,
      "learning_rate": 0.00015611870653623825,
      "loss": 0.7546,
      "step": 416
    },
    {
      "epoch": 0.6430223592906708,
      "grad_norm": 0.035753343254327774,
      "learning_rate": 0.00015591475439025745,
      "loss": 0.7257,
      "step": 417
    },
    {
      "epoch": 0.6445643793369313,
      "grad_norm": 0.03195042535662651,
      "learning_rate": 0.00015571046330289237,
      "loss": 0.693,
      "step": 418
    },
    {
      "epoch": 0.646106399383192,
      "grad_norm": 0.027049189433455467,
      "learning_rate": 0.00015550583451250503,
      "loss": 0.7602,
      "step": 419
    },
    {
      "epoch": 0.6476484194294526,
      "grad_norm": 0.027553152292966843,
      "learning_rate": 0.00015530086925950434,
      "loss": 0.7723,
      "step": 420
    },
    {
      "epoch": 0.6491904394757132,
      "grad_norm": 0.025219090282917023,
      "learning_rate": 0.00015509556878633894,
      "loss": 0.7011,
      "step": 421
    },
    {
      "epoch": 0.6507324595219738,
      "grad_norm": 0.029802288860082626,
      "learning_rate": 0.00015488993433748944,
      "loss": 0.6898,
      "step": 422
    },
    {
      "epoch": 0.6522744795682344,
      "grad_norm": 0.02772880345582962,
      "learning_rate": 0.00015468396715946083,
      "loss": 0.7399,
      "step": 423
    },
    {
      "epoch": 0.653816499614495,
      "grad_norm": 0.025485830381512642,
      "learning_rate": 0.00015447766850077517,
      "loss": 0.6622,
      "step": 424
    },
    {
      "epoch": 0.6553585196607556,
      "grad_norm": 0.027489742264151573,
      "learning_rate": 0.00015427103961196376,
      "loss": 0.8027,
      "step": 425
    },
    {
      "epoch": 0.6569005397070162,
      "grad_norm": 0.026778720319271088,
      "learning_rate": 0.00015406408174555976,
      "loss": 0.7804,
      "step": 426
    },
    {
      "epoch": 0.6584425597532768,
      "grad_norm": 0.027850337326526642,
      "learning_rate": 0.00015385679615609042,
      "loss": 0.7645,
      "step": 427
    },
    {
      "epoch": 0.6599845797995374,
      "grad_norm": 0.02659332938492298,
      "learning_rate": 0.00015364918410006967,
      "loss": 0.7609,
      "step": 428
    },
    {
      "epoch": 0.661526599845798,
      "grad_norm": 0.0292272437363863,
      "learning_rate": 0.0001534412468359903,
      "loss": 0.7788,
      "step": 429
    },
    {
      "epoch": 0.6630686198920586,
      "grad_norm": 0.02392621338367462,
      "learning_rate": 0.00015323298562431648,
      "loss": 0.675,
      "step": 430
    },
    {
      "epoch": 0.6646106399383191,
      "grad_norm": 0.030261410400271416,
      "learning_rate": 0.00015302440172747605,
      "loss": 0.6585,
      "step": 431
    },
    {
      "epoch": 0.6661526599845798,
      "grad_norm": 0.031531739979982376,
      "learning_rate": 0.00015281549640985294,
      "loss": 0.8002,
      "step": 432
    },
    {
      "epoch": 0.6676946800308404,
      "grad_norm": 0.025663699954748154,
      "learning_rate": 0.00015260627093777936,
      "loss": 0.7068,
      "step": 433
    },
    {
      "epoch": 0.669236700077101,
      "grad_norm": 0.02657734416425228,
      "learning_rate": 0.00015239672657952832,
      "loss": 0.7369,
      "step": 434
    },
    {
      "epoch": 0.6707787201233616,
      "grad_norm": 0.027592379599809647,
      "learning_rate": 0.0001521868646053058,
      "loss": 0.7245,
      "step": 435
    },
    {
      "epoch": 0.6723207401696222,
      "grad_norm": 0.02645149454474449,
      "learning_rate": 0.00015197668628724303,
      "loss": 0.718,
      "step": 436
    },
    {
      "epoch": 0.6738627602158828,
      "grad_norm": 0.02535802498459816,
      "learning_rate": 0.00015176619289938888,
      "loss": 0.6926,
      "step": 437
    },
    {
      "epoch": 0.6754047802621435,
      "grad_norm": 0.02912677638232708,
      "learning_rate": 0.00015155538571770218,
      "loss": 0.8564,
      "step": 438
    },
    {
      "epoch": 0.676946800308404,
      "grad_norm": 0.023175543174147606,
      "learning_rate": 0.00015134426602004375,
      "loss": 0.6568,
      "step": 439
    },
    {
      "epoch": 0.6784888203546646,
      "grad_norm": 0.02832154743373394,
      "learning_rate": 0.00015113283508616895,
      "loss": 0.6571,
      "step": 440
    },
    {
      "epoch": 0.6800308404009252,
      "grad_norm": 0.029950594529509544,
      "learning_rate": 0.0001509210941977196,
      "loss": 0.8564,
      "step": 441
    },
    {
      "epoch": 0.6815728604471858,
      "grad_norm": 0.02448093518614769,
      "learning_rate": 0.00015070904463821658,
      "loss": 0.6936,
      "step": 442
    },
    {
      "epoch": 0.6831148804934464,
      "grad_norm": 0.027585268020629883,
      "learning_rate": 0.00015049668769305172,
      "loss": 0.7991,
      "step": 443
    },
    {
      "epoch": 0.6846569005397071,
      "grad_norm": 0.025705596432089806,
      "learning_rate": 0.00015028402464948022,
      "loss": 0.7187,
      "step": 444
    },
    {
      "epoch": 0.6861989205859677,
      "grad_norm": 0.02810623310506344,
      "learning_rate": 0.00015007105679661276,
      "loss": 0.7315,
      "step": 445
    },
    {
      "epoch": 0.6877409406322282,
      "grad_norm": 0.02478802390396595,
      "learning_rate": 0.0001498577854254076,
      "loss": 0.7201,
      "step": 446
    },
    {
      "epoch": 0.6892829606784888,
      "grad_norm": 0.03222353756427765,
      "learning_rate": 0.0001496442118286631,
      "loss": 0.796,
      "step": 447
    },
    {
      "epoch": 0.6908249807247494,
      "grad_norm": 0.025557026267051697,
      "learning_rate": 0.00014943033730100935,
      "loss": 0.6066,
      "step": 448
    },
    {
      "epoch": 0.69236700077101,
      "grad_norm": 0.02581370249390602,
      "learning_rate": 0.00014921616313890072,
      "loss": 0.7186,
      "step": 449
    },
    {
      "epoch": 0.6939090208172706,
      "grad_norm": 0.025746649131178856,
      "learning_rate": 0.00014900169064060802,
      "loss": 0.703,
      "step": 450
    },
    {
      "epoch": 0.6954510408635313,
      "grad_norm": 0.03065100871026516,
      "learning_rate": 0.00014878692110621028,
      "loss": 0.7724,
      "step": 451
    },
    {
      "epoch": 0.6969930609097919,
      "grad_norm": 0.03629877045750618,
      "learning_rate": 0.00014857185583758723,
      "loss": 0.7703,
      "step": 452
    },
    {
      "epoch": 0.6985350809560524,
      "grad_norm": 0.025341391563415527,
      "learning_rate": 0.0001483564961384112,
      "loss": 0.6492,
      "step": 453
    },
    {
      "epoch": 0.700077101002313,
      "grad_norm": 0.03427153080701828,
      "learning_rate": 0.0001481408433141394,
      "loss": 0.7148,
      "step": 454
    },
    {
      "epoch": 0.7016191210485736,
      "grad_norm": 0.023825203999876976,
      "learning_rate": 0.0001479248986720057,
      "loss": 0.6197,
      "step": 455
    },
    {
      "epoch": 0.7031611410948342,
      "grad_norm": 0.026944074779748917,
      "learning_rate": 0.00014770866352101307,
      "loss": 0.7273,
      "step": 456
    },
    {
      "epoch": 0.7047031611410949,
      "grad_norm": 0.028203219175338745,
      "learning_rate": 0.00014749213917192538,
      "loss": 0.7741,
      "step": 457
    },
    {
      "epoch": 0.7062451811873555,
      "grad_norm": 0.024622568860650063,
      "learning_rate": 0.00014727532693725962,
      "loss": 0.6212,
      "step": 458
    },
    {
      "epoch": 0.707787201233616,
      "grad_norm": 0.023979736492037773,
      "learning_rate": 0.00014705822813127777,
      "loss": 0.6863,
      "step": 459
    },
    {
      "epoch": 0.7093292212798766,
      "grad_norm": 0.027042685076594353,
      "learning_rate": 0.00014684084406997903,
      "loss": 0.7746,
      "step": 460
    },
    {
      "epoch": 0.7108712413261372,
      "grad_norm": 0.026160864159464836,
      "learning_rate": 0.00014662317607109168,
      "loss": 0.727,
      "step": 461
    },
    {
      "epoch": 0.7124132613723978,
      "grad_norm": 0.035195063799619675,
      "learning_rate": 0.0001464052254540652,
      "loss": 0.9004,
      "step": 462
    },
    {
      "epoch": 0.7139552814186585,
      "grad_norm": 0.02714708261191845,
      "learning_rate": 0.00014618699354006223,
      "loss": 0.6853,
      "step": 463
    },
    {
      "epoch": 0.7154973014649191,
      "grad_norm": 0.027736373245716095,
      "learning_rate": 0.0001459684816519505,
      "loss": 0.7095,
      "step": 464
    },
    {
      "epoch": 0.7170393215111797,
      "grad_norm": 0.032326798886060715,
      "learning_rate": 0.000145749691114295,
      "loss": 0.7256,
      "step": 465
    },
    {
      "epoch": 0.7185813415574402,
      "grad_norm": 0.028024908155202866,
      "learning_rate": 0.00014553062325334967,
      "loss": 0.7213,
      "step": 466
    },
    {
      "epoch": 0.7201233616037008,
      "grad_norm": 0.026767205446958542,
      "learning_rate": 0.00014531127939704965,
      "loss": 0.6619,
      "step": 467
    },
    {
      "epoch": 0.7216653816499614,
      "grad_norm": 0.025469880551099777,
      "learning_rate": 0.00014509166087500302,
      "loss": 0.6174,
      "step": 468
    },
    {
      "epoch": 0.723207401696222,
      "grad_norm": 0.03378410264849663,
      "learning_rate": 0.00014487176901848285,
      "loss": 0.6447,
      "step": 469
    },
    {
      "epoch": 0.7247494217424827,
      "grad_norm": 0.026924695819616318,
      "learning_rate": 0.00014465160516041904,
      "loss": 0.7116,
      "step": 470
    },
    {
      "epoch": 0.7262914417887433,
      "grad_norm": 0.029700160026550293,
      "learning_rate": 0.00014443117063539038,
      "loss": 0.811,
      "step": 471
    },
    {
      "epoch": 0.7278334618350039,
      "grad_norm": 0.030913611873984337,
      "learning_rate": 0.00014421046677961626,
      "loss": 0.77,
      "step": 472
    },
    {
      "epoch": 0.7293754818812644,
      "grad_norm": 0.029507668688893318,
      "learning_rate": 0.0001439894949309489,
      "loss": 0.7813,
      "step": 473
    },
    {
      "epoch": 0.730917501927525,
      "grad_norm": 0.028620922937989235,
      "learning_rate": 0.00014376825642886472,
      "loss": 0.7401,
      "step": 474
    },
    {
      "epoch": 0.7324595219737856,
      "grad_norm": 0.025677144527435303,
      "learning_rate": 0.0001435467526144568,
      "loss": 0.7408,
      "step": 475
    },
    {
      "epoch": 0.7340015420200463,
      "grad_norm": 0.025129586458206177,
      "learning_rate": 0.00014332498483042637,
      "loss": 0.6585,
      "step": 476
    },
    {
      "epoch": 0.7355435620663069,
      "grad_norm": 0.026812126860022545,
      "learning_rate": 0.0001431029544210747,
      "loss": 0.8063,
      "step": 477
    },
    {
      "epoch": 0.7370855821125675,
      "grad_norm": 0.02705306001007557,
      "learning_rate": 0.0001428806627322952,
      "loss": 0.7655,
      "step": 478
    },
    {
      "epoch": 0.7386276021588281,
      "grad_norm": 0.026533039286732674,
      "learning_rate": 0.0001426581111115649,
      "loss": 0.6685,
      "step": 479
    },
    {
      "epoch": 0.7401696222050886,
      "grad_norm": 0.030538393184542656,
      "learning_rate": 0.00014243530090793667,
      "loss": 0.7389,
      "step": 480
    },
    {
      "epoch": 0.7417116422513492,
      "grad_norm": 0.027102958410978317,
      "learning_rate": 0.00014221223347203068,
      "loss": 0.726,
      "step": 481
    },
    {
      "epoch": 0.7432536622976099,
      "grad_norm": 0.024465948343276978,
      "learning_rate": 0.00014198891015602646,
      "loss": 0.6379,
      "step": 482
    },
    {
      "epoch": 0.7447956823438705,
      "grad_norm": 0.027429422363638878,
      "learning_rate": 0.00014176533231365464,
      "loss": 0.726,
      "step": 483
    },
    {
      "epoch": 0.7463377023901311,
      "grad_norm": 0.02289111353456974,
      "learning_rate": 0.00014154150130018866,
      "loss": 0.6354,
      "step": 484
    },
    {
      "epoch": 0.7478797224363917,
      "grad_norm": 0.027374420315027237,
      "learning_rate": 0.00014131741847243665,
      "loss": 0.8206,
      "step": 485
    },
    {
      "epoch": 0.7494217424826523,
      "grad_norm": 0.029361480847001076,
      "learning_rate": 0.0001410930851887332,
      "loss": 0.6994,
      "step": 486
    },
    {
      "epoch": 0.7509637625289128,
      "grad_norm": 0.027077002450823784,
      "learning_rate": 0.00014086850280893107,
      "loss": 0.7133,
      "step": 487
    },
    {
      "epoch": 0.7525057825751735,
      "grad_norm": 0.028823737055063248,
      "learning_rate": 0.000140643672694393,
      "loss": 0.7975,
      "step": 488
    },
    {
      "epoch": 0.7540478026214341,
      "grad_norm": 0.02851509116590023,
      "learning_rate": 0.0001404185962079834,
      "loss": 0.7497,
      "step": 489
    },
    {
      "epoch": 0.7555898226676947,
      "grad_norm": 0.025098523125052452,
      "learning_rate": 0.00014019327471406022,
      "loss": 0.6978,
      "step": 490
    },
    {
      "epoch": 0.7571318427139553,
      "grad_norm": 0.03084149770438671,
      "learning_rate": 0.00013996770957846644,
      "loss": 0.7607,
      "step": 491
    },
    {
      "epoch": 0.7586738627602159,
      "grad_norm": 0.02702442556619644,
      "learning_rate": 0.00013974190216852202,
      "loss": 0.7639,
      "step": 492
    },
    {
      "epoch": 0.7602158828064765,
      "grad_norm": 0.033685747534036636,
      "learning_rate": 0.00013951585385301555,
      "loss": 0.7793,
      "step": 493
    },
    {
      "epoch": 0.761757902852737,
      "grad_norm": 0.028003569692373276,
      "learning_rate": 0.00013928956600219592,
      "loss": 0.755,
      "step": 494
    },
    {
      "epoch": 0.7632999228989977,
      "grad_norm": 0.026269137859344482,
      "learning_rate": 0.00013906303998776392,
      "loss": 0.7896,
      "step": 495
    },
    {
      "epoch": 0.7648419429452583,
      "grad_norm": 0.027992503717541695,
      "learning_rate": 0.0001388362771828642,
      "loss": 0.6472,
      "step": 496
    },
    {
      "epoch": 0.7663839629915189,
      "grad_norm": 0.028174640610814095,
      "learning_rate": 0.00013860927896207665,
      "loss": 0.765,
      "step": 497
    },
    {
      "epoch": 0.7679259830377795,
      "grad_norm": 0.04180079326033592,
      "learning_rate": 0.0001383820467014082,
      "loss": 0.7479,
      "step": 498
    },
    {
      "epoch": 0.7694680030840401,
      "grad_norm": 0.028985602781176567,
      "learning_rate": 0.00013815458177828454,
      "loss": 0.7121,
      "step": 499
    },
    {
      "epoch": 0.7710100231303006,
      "grad_norm": 0.026408828794956207,
      "learning_rate": 0.00013792688557154166,
      "loss": 0.7411,
      "step": 500
    },
    {
      "epoch": 0.7725520431765613,
      "grad_norm": 0.027537405490875244,
      "learning_rate": 0.00013769895946141752,
      "loss": 0.7628,
      "step": 501
    },
    {
      "epoch": 0.7740940632228219,
      "grad_norm": 0.028669610619544983,
      "learning_rate": 0.00013747080482954377,
      "loss": 0.7698,
      "step": 502
    },
    {
      "epoch": 0.7756360832690825,
      "grad_norm": 0.027917267754673958,
      "learning_rate": 0.00013724242305893715,
      "loss": 0.8452,
      "step": 503
    },
    {
      "epoch": 0.7771781033153431,
      "grad_norm": 0.031637243926525116,
      "learning_rate": 0.00013701381553399145,
      "loss": 0.7457,
      "step": 504
    },
    {
      "epoch": 0.7787201233616037,
      "grad_norm": 0.027903905138373375,
      "learning_rate": 0.00013678498364046876,
      "loss": 0.7475,
      "step": 505
    },
    {
      "epoch": 0.7802621434078643,
      "grad_norm": 0.03381239250302315,
      "learning_rate": 0.00013655592876549134,
      "loss": 0.836,
      "step": 506
    },
    {
      "epoch": 0.781804163454125,
      "grad_norm": 0.0790882334113121,
      "learning_rate": 0.0001363266522975331,
      "loss": 0.5842,
      "step": 507
    },
    {
      "epoch": 0.7833461835003855,
      "grad_norm": 0.03034863993525505,
      "learning_rate": 0.00013609715562641115,
      "loss": 0.8256,
      "step": 508
    },
    {
      "epoch": 0.7848882035466461,
      "grad_norm": 0.029499804601073265,
      "learning_rate": 0.0001358674401432774,
      "loss": 0.7145,
      "step": 509
    },
    {
      "epoch": 0.7864302235929067,
      "grad_norm": 0.0285016018897295,
      "learning_rate": 0.00013563750724061025,
      "loss": 0.6712,
      "step": 510
    },
    {
      "epoch": 0.7879722436391673,
      "grad_norm": 0.02717653289437294,
      "learning_rate": 0.0001354073583122059,
      "loss": 0.6807,
      "step": 511
    },
    {
      "epoch": 0.7895142636854279,
      "grad_norm": 0.023634063079953194,
      "learning_rate": 0.00013517699475317017,
      "loss": 0.6677,
      "step": 512
    },
    {
      "epoch": 0.7910562837316885,
      "grad_norm": 0.02920868992805481,
      "learning_rate": 0.00013494641795990986,
      "loss": 0.7865,
      "step": 513
    },
    {
      "epoch": 0.7925983037779492,
      "grad_norm": 0.040133338421583176,
      "learning_rate": 0.00013471562933012432,
      "loss": 0.7786,
      "step": 514
    },
    {
      "epoch": 0.7941403238242097,
      "grad_norm": 0.028838159516453743,
      "learning_rate": 0.00013448463026279704,
      "loss": 0.7689,
      "step": 515
    },
    {
      "epoch": 0.7956823438704703,
      "grad_norm": 0.02688550017774105,
      "learning_rate": 0.00013425342215818718,
      "loss": 0.7659,
      "step": 516
    },
    {
      "epoch": 0.7972243639167309,
      "grad_norm": 0.027155300602316856,
      "learning_rate": 0.0001340220064178209,
      "loss": 0.7353,
      "step": 517
    },
    {
      "epoch": 0.7987663839629915,
      "grad_norm": 0.03566644340753555,
      "learning_rate": 0.00013379038444448306,
      "loss": 0.827,
      "step": 518
    },
    {
      "epoch": 0.8003084040092521,
      "grad_norm": 0.0266974326223135,
      "learning_rate": 0.00013355855764220868,
      "loss": 0.7693,
      "step": 519
    },
    {
      "epoch": 0.8018504240555128,
      "grad_norm": 0.026248447597026825,
      "learning_rate": 0.00013332652741627446,
      "loss": 0.7659,
      "step": 520
    },
    {
      "epoch": 0.8033924441017734,
      "grad_norm": 0.030487187206745148,
      "learning_rate": 0.00013309429517318998,
      "loss": 0.7244,
      "step": 521
    },
    {
      "epoch": 0.8049344641480339,
      "grad_norm": 0.031918346881866455,
      "learning_rate": 0.00013286186232068972,
      "loss": 0.6111,
      "step": 522
    },
    {
      "epoch": 0.8064764841942945,
      "grad_norm": 0.03194589167833328,
      "learning_rate": 0.00013262923026772388,
      "loss": 0.7521,
      "step": 523
    },
    {
      "epoch": 0.8080185042405551,
      "grad_norm": 0.029390091076493263,
      "learning_rate": 0.00013239640042445036,
      "loss": 0.7689,
      "step": 524
    },
    {
      "epoch": 0.8095605242868157,
      "grad_norm": 0.025920424610376358,
      "learning_rate": 0.000132163374202226,
      "loss": 0.7102,
      "step": 525
    },
    {
      "epoch": 0.8111025443330764,
      "grad_norm": 0.02453307807445526,
      "learning_rate": 0.000131930153013598,
      "loss": 0.712,
      "step": 526
    },
    {
      "epoch": 0.812644564379337,
      "grad_norm": 0.035026635974645615,
      "learning_rate": 0.0001316967382722954,
      "loss": 0.789,
      "step": 527
    },
    {
      "epoch": 0.8141865844255975,
      "grad_norm": 0.02895597368478775,
      "learning_rate": 0.0001314631313932205,
      "loss": 0.8087,
      "step": 528
    },
    {
      "epoch": 0.8157286044718581,
      "grad_norm": 0.02956031821668148,
      "learning_rate": 0.00013122933379244034,
      "loss": 0.7514,
      "step": 529
    },
    {
      "epoch": 0.8172706245181187,
      "grad_norm": 0.027792761102318764,
      "learning_rate": 0.00013099534688717804,
      "loss": 0.7843,
      "step": 530
    },
    {
      "epoch": 0.8188126445643793,
      "grad_norm": 0.023245403543114662,
      "learning_rate": 0.00013076117209580418,
      "loss": 0.6878,
      "step": 531
    },
    {
      "epoch": 0.8203546646106399,
      "grad_norm": 0.030602406710386276,
      "learning_rate": 0.00013052681083782836,
      "loss": 0.6504,
      "step": 532
    },
    {
      "epoch": 0.8218966846569006,
      "grad_norm": 0.0250953808426857,
      "learning_rate": 0.00013029226453389043,
      "loss": 0.6255,
      "step": 533
    },
    {
      "epoch": 0.8234387047031612,
      "grad_norm": 0.02791382372379303,
      "learning_rate": 0.00013005753460575194,
      "loss": 0.7252,
      "step": 534
    },
    {
      "epoch": 0.8249807247494217,
      "grad_norm": 0.025774458423256874,
      "learning_rate": 0.0001298226224762876,
      "loss": 0.7252,
      "step": 535
    },
    {
      "epoch": 0.8265227447956823,
      "grad_norm": 0.026806412264704704,
      "learning_rate": 0.00012958752956947645,
      "loss": 0.7702,
      "step": 536
    },
    {
      "epoch": 0.8280647648419429,
      "grad_norm": 0.02904200740158558,
      "learning_rate": 0.00012935225731039348,
      "loss": 0.7573,
      "step": 537
    },
    {
      "epoch": 0.8296067848882035,
      "grad_norm": 0.03018496371805668,
      "learning_rate": 0.00012911680712520082,
      "loss": 0.6854,
      "step": 538
    },
    {
      "epoch": 0.8311488049344642,
      "grad_norm": 0.028921302407979965,
      "learning_rate": 0.00012888118044113912,
      "loss": 0.7372,
      "step": 539
    },
    {
      "epoch": 0.8326908249807248,
      "grad_norm": 0.02912386879324913,
      "learning_rate": 0.00012864537868651892,
      "loss": 0.864,
      "step": 540
    },
    {
      "epoch": 0.8342328450269854,
      "grad_norm": 0.03150784596800804,
      "learning_rate": 0.00012840940329071211,
      "loss": 0.6846,
      "step": 541
    },
    {
      "epoch": 0.8357748650732459,
      "grad_norm": 0.026627201586961746,
      "learning_rate": 0.00012817325568414297,
      "loss": 0.6596,
      "step": 542
    },
    {
      "epoch": 0.8373168851195065,
      "grad_norm": 0.026762191206216812,
      "learning_rate": 0.00012793693729827983,
      "loss": 0.7859,
      "step": 543
    },
    {
      "epoch": 0.8388589051657671,
      "grad_norm": 0.0270906463265419,
      "learning_rate": 0.00012770044956562611,
      "loss": 0.76,
      "step": 544
    },
    {
      "epoch": 0.8404009252120278,
      "grad_norm": 0.029391184449195862,
      "learning_rate": 0.0001274637939197119,
      "loss": 0.7153,
      "step": 545
    },
    {
      "epoch": 0.8419429452582884,
      "grad_norm": 0.028473293408751488,
      "learning_rate": 0.00012722697179508508,
      "loss": 0.7083,
      "step": 546
    },
    {
      "epoch": 0.843484965304549,
      "grad_norm": 0.028644869104027748,
      "learning_rate": 0.00012698998462730264,
      "loss": 0.7531,
      "step": 547
    },
    {
      "epoch": 0.8450269853508096,
      "grad_norm": 0.0290384441614151,
      "learning_rate": 0.00012675283385292212,
      "loss": 0.8323,
      "step": 548
    },
    {
      "epoch": 0.8465690053970701,
      "grad_norm": 0.027428725734353065,
      "learning_rate": 0.00012651552090949263,
      "loss": 0.783,
      "step": 549
    },
    {
      "epoch": 0.8481110254433307,
      "grad_norm": 0.0316435806453228,
      "learning_rate": 0.00012627804723554651,
      "loss": 0.7303,
      "step": 550
    },
    {
      "epoch": 0.8496530454895914,
      "grad_norm": 0.031257808208465576,
      "learning_rate": 0.00012604041427059036,
      "loss": 0.6641,
      "step": 551
    },
    {
      "epoch": 0.851195065535852,
      "grad_norm": 0.031232839450240135,
      "learning_rate": 0.00012580262345509622,
      "loss": 0.8266,
      "step": 552
    },
    {
      "epoch": 0.8527370855821126,
      "grad_norm": 0.028075871989130974,
      "learning_rate": 0.00012556467623049312,
      "loss": 0.6852,
      "step": 553
    },
    {
      "epoch": 0.8542791056283732,
      "grad_norm": 0.0269178319722414,
      "learning_rate": 0.0001253265740391582,
      "loss": 0.6774,
      "step": 554
    },
    {
      "epoch": 0.8558211256746338,
      "grad_norm": 0.033746860921382904,
      "learning_rate": 0.00012508831832440794,
      "loss": 0.6704,
      "step": 555
    },
    {
      "epoch": 0.8573631457208943,
      "grad_norm": 0.02507774904370308,
      "learning_rate": 0.0001248499105304894,
      "loss": 0.6364,
      "step": 556
    },
    {
      "epoch": 0.8589051657671549,
      "grad_norm": 0.027239350602030754,
      "learning_rate": 0.00012461135210257155,
      "loss": 0.7503,
      "step": 557
    },
    {
      "epoch": 0.8604471858134156,
      "grad_norm": 0.031841401010751724,
      "learning_rate": 0.00012437264448673647,
      "loss": 0.7201,
      "step": 558
    },
    {
      "epoch": 0.8619892058596762,
      "grad_norm": 0.025972798466682434,
      "learning_rate": 0.00012413378912997058,
      "loss": 0.7265,
      "step": 559
    },
    {
      "epoch": 0.8635312259059368,
      "grad_norm": 0.02815602719783783,
      "learning_rate": 0.00012389478748015583,
      "loss": 0.6922,
      "step": 560
    },
    {
      "epoch": 0.8650732459521974,
      "grad_norm": 0.03288137540221214,
      "learning_rate": 0.00012365564098606102,
      "loss": 0.6516,
      "step": 561
    },
    {
      "epoch": 0.866615265998458,
      "grad_norm": 0.02655138447880745,
      "learning_rate": 0.00012341635109733293,
      "loss": 0.6192,
      "step": 562
    },
    {
      "epoch": 0.8681572860447185,
      "grad_norm": 0.029187412932515144,
      "learning_rate": 0.00012317691926448754,
      "loss": 0.8307,
      "step": 563
    },
    {
      "epoch": 0.8696993060909792,
      "grad_norm": 0.029966147616505623,
      "learning_rate": 0.00012293734693890132,
      "loss": 0.7285,
      "step": 564
    },
    {
      "epoch": 0.8712413261372398,
      "grad_norm": 0.02818044275045395,
      "learning_rate": 0.0001226976355728023,
      "loss": 0.7171,
      "step": 565
    },
    {
      "epoch": 0.8727833461835004,
      "grad_norm": 0.02721909061074257,
      "learning_rate": 0.00012245778661926137,
      "loss": 0.6913,
      "step": 566
    },
    {
      "epoch": 0.874325366229761,
      "grad_norm": 0.030929675325751305,
      "learning_rate": 0.0001222178015321835,
      "loss": 0.8006,
      "step": 567
    },
    {
      "epoch": 0.8758673862760216,
      "grad_norm": 0.026720581576228142,
      "learning_rate": 0.00012197768176629876,
      "loss": 0.7348,
      "step": 568
    },
    {
      "epoch": 0.8774094063222821,
      "grad_norm": 0.02792746014893055,
      "learning_rate": 0.00012173742877715373,
      "loss": 0.786,
      "step": 569
    },
    {
      "epoch": 0.8789514263685428,
      "grad_norm": 0.025372346863150597,
      "learning_rate": 0.00012149704402110243,
      "loss": 0.6832,
      "step": 570
    },
    {
      "epoch": 0.8804934464148034,
      "grad_norm": 0.025779495015740395,
      "learning_rate": 0.00012125652895529766,
      "loss": 0.7465,
      "step": 571
    },
    {
      "epoch": 0.882035466461064,
      "grad_norm": 0.028759067878127098,
      "learning_rate": 0.00012101588503768224,
      "loss": 0.7755,
      "step": 572
    },
    {
      "epoch": 0.8835774865073246,
      "grad_norm": 0.0319170206785202,
      "learning_rate": 0.00012077511372697985,
      "loss": 0.7758,
      "step": 573
    },
    {
      "epoch": 0.8851195065535852,
      "grad_norm": 0.0287742018699646,
      "learning_rate": 0.00012053421648268662,
      "loss": 0.7556,
      "step": 574
    },
    {
      "epoch": 0.8866615265998458,
      "grad_norm": 0.027272436767816544,
      "learning_rate": 0.00012029319476506182,
      "loss": 0.6341,
      "step": 575
    },
    {
      "epoch": 0.8882035466461063,
      "grad_norm": 0.02786344476044178,
      "learning_rate": 0.00012005205003511948,
      "loss": 0.7248,
      "step": 576
    },
    {
      "epoch": 0.889745566692367,
      "grad_norm": 0.023950345814228058,
      "learning_rate": 0.00011981078375461915,
      "loss": 0.6907,
      "step": 577
    },
    {
      "epoch": 0.8912875867386276,
      "grad_norm": 0.0248698852956295,
      "learning_rate": 0.00011956939738605721,
      "loss": 0.6612,
      "step": 578
    },
    {
      "epoch": 0.8928296067848882,
      "grad_norm": 0.02722037211060524,
      "learning_rate": 0.00011932789239265802,
      "loss": 0.6179,
      "step": 579
    },
    {
      "epoch": 0.8943716268311488,
      "grad_norm": 0.02561650238931179,
      "learning_rate": 0.00011908627023836503,
      "loss": 0.7478,
      "step": 580
    },
    {
      "epoch": 0.8959136468774094,
      "grad_norm": 0.027791699394583702,
      "learning_rate": 0.00011884453238783185,
      "loss": 0.7803,
      "step": 581
    },
    {
      "epoch": 0.89745566692367,
      "grad_norm": 0.033503565937280655,
      "learning_rate": 0.00011860268030641338,
      "loss": 0.7978,
      "step": 582
    },
    {
      "epoch": 0.8989976869699307,
      "grad_norm": 0.0275451447814703,
      "learning_rate": 0.00011836071546015703,
      "loss": 0.7458,
      "step": 583
    },
    {
      "epoch": 0.9005397070161912,
      "grad_norm": 0.02638075314462185,
      "learning_rate": 0.00011811863931579377,
      "loss": 0.5823,
      "step": 584
    },
    {
      "epoch": 0.9020817270624518,
      "grad_norm": 0.029536547139286995,
      "learning_rate": 0.00011787645334072913,
      "loss": 0.829,
      "step": 585
    },
    {
      "epoch": 0.9036237471087124,
      "grad_norm": 0.029731806367635727,
      "learning_rate": 0.0001176341590030345,
      "loss": 0.7553,
      "step": 586
    },
    {
      "epoch": 0.905165767154973,
      "grad_norm": 0.02816937118768692,
      "learning_rate": 0.00011739175777143812,
      "loss": 0.7094,
      "step": 587
    },
    {
      "epoch": 0.9067077872012336,
      "grad_norm": 0.026959970593452454,
      "learning_rate": 0.00011714925111531619,
      "loss": 0.7368,
      "step": 588
    },
    {
      "epoch": 0.9082498072474943,
      "grad_norm": 0.027997490018606186,
      "learning_rate": 0.0001169066405046839,
      "loss": 0.7864,
      "step": 589
    },
    {
      "epoch": 0.9097918272937549,
      "grad_norm": 0.025101030245423317,
      "learning_rate": 0.00011666392741018675,
      "loss": 0.6445,
      "step": 590
    },
    {
      "epoch": 0.9113338473400154,
      "grad_norm": 0.038789402693510056,
      "learning_rate": 0.00011642111330309129,
      "loss": 0.7104,
      "step": 591
    },
    {
      "epoch": 0.912875867386276,
      "grad_norm": 0.0264846533536911,
      "learning_rate": 0.0001161781996552765,
      "loss": 0.7034,
      "step": 592
    },
    {
      "epoch": 0.9144178874325366,
      "grad_norm": 0.03629022464156151,
      "learning_rate": 0.00011593518793922468,
      "loss": 0.8121,
      "step": 593
    },
    {
      "epoch": 0.9159599074787972,
      "grad_norm": 0.025432435795664787,
      "learning_rate": 0.00011569207962801263,
      "loss": 0.6726,
      "step": 594
    },
    {
      "epoch": 0.9175019275250579,
      "grad_norm": 0.02553374320268631,
      "learning_rate": 0.00011544887619530275,
      "loss": 0.659,
      "step": 595
    },
    {
      "epoch": 0.9190439475713185,
      "grad_norm": 0.02498779632151127,
      "learning_rate": 0.0001152055791153339,
      "loss": 0.5868,
      "step": 596
    },
    {
      "epoch": 0.920585967617579,
      "grad_norm": 0.029489582404494286,
      "learning_rate": 0.00011496218986291273,
      "loss": 0.673,
      "step": 597
    },
    {
      "epoch": 0.9221279876638396,
      "grad_norm": 0.029334766790270805,
      "learning_rate": 0.00011471870991340459,
      "loss": 0.8011,
      "step": 598
    },
    {
      "epoch": 0.9236700077101002,
      "grad_norm": 0.0274631530046463,
      "learning_rate": 0.00011447514074272451,
      "loss": 0.721,
      "step": 599
    },
    {
      "epoch": 0.9252120277563608,
      "grad_norm": 0.028073586523532867,
      "learning_rate": 0.00011423148382732853,
      "loss": 0.839,
      "step": 600
    },
    {
      "epoch": 0.9267540478026214,
      "grad_norm": 0.028757184743881226,
      "learning_rate": 0.00011398774064420443,
      "loss": 0.7409,
      "step": 601
    },
    {
      "epoch": 0.9282960678488821,
      "grad_norm": 0.026308685541152954,
      "learning_rate": 0.00011374391267086302,
      "loss": 0.7517,
      "step": 602
    },
    {
      "epoch": 0.9298380878951427,
      "grad_norm": 0.027558207511901855,
      "learning_rate": 0.00011350000138532902,
      "loss": 0.7041,
      "step": 603
    },
    {
      "epoch": 0.9313801079414032,
      "grad_norm": 0.02995571680366993,
      "learning_rate": 0.0001132560082661322,
      "loss": 0.842,
      "step": 604
    },
    {
      "epoch": 0.9329221279876638,
      "grad_norm": 0.028026850894093513,
      "learning_rate": 0.00011301193479229841,
      "loss": 0.7639,
      "step": 605
    },
    {
      "epoch": 0.9344641480339244,
      "grad_norm": 0.026926511898636818,
      "learning_rate": 0.00011276778244334055,
      "loss": 0.6315,
      "step": 606
    },
    {
      "epoch": 0.936006168080185,
      "grad_norm": 0.031490955501794815,
      "learning_rate": 0.00011252355269924963,
      "loss": 0.5844,
      "step": 607
    },
    {
      "epoch": 0.9375481881264457,
      "grad_norm": 0.028631744906306267,
      "learning_rate": 0.00011227924704048585,
      "loss": 0.6431,
      "step": 608
    },
    {
      "epoch": 0.9390902081727063,
      "grad_norm": 0.029599271714687347,
      "learning_rate": 0.00011203486694796957,
      "loss": 0.7085,
      "step": 609
    },
    {
      "epoch": 0.9406322282189669,
      "grad_norm": 0.027870824560523033,
      "learning_rate": 0.00011179041390307235,
      "loss": 0.7381,
      "step": 610
    },
    {
      "epoch": 0.9421742482652274,
      "grad_norm": 0.030139662325382233,
      "learning_rate": 0.00011154588938760794,
      "loss": 0.7299,
      "step": 611
    },
    {
      "epoch": 0.943716268311488,
      "grad_norm": 0.031028704717755318,
      "learning_rate": 0.00011130129488382341,
      "loss": 0.747,
      "step": 612
    },
    {
      "epoch": 0.9452582883577486,
      "grad_norm": 0.02865663915872574,
      "learning_rate": 0.00011105663187438997,
      "loss": 0.7025,
      "step": 613
    },
    {
      "epoch": 0.9468003084040093,
      "grad_norm": 0.029388774186372757,
      "learning_rate": 0.00011081190184239419,
      "loss": 0.6645,
      "step": 614
    },
    {
      "epoch": 0.9483423284502699,
      "grad_norm": 0.023502621799707413,
      "learning_rate": 0.00011056710627132884,
      "loss": 0.6455,
      "step": 615
    },
    {
      "epoch": 0.9498843484965305,
      "grad_norm": 0.02663263864815235,
      "learning_rate": 0.00011032224664508405,
      "loss": 0.7677,
      "step": 616
    },
    {
      "epoch": 0.9514263685427911,
      "grad_norm": 0.02990710362792015,
      "learning_rate": 0.00011007732444793814,
      "loss": 0.7017,
      "step": 617
    },
    {
      "epoch": 0.9529683885890516,
      "grad_norm": 0.029992980882525444,
      "learning_rate": 0.00010983234116454886,
      "loss": 0.7969,
      "step": 618
    },
    {
      "epoch": 0.9545104086353122,
      "grad_norm": 0.03714431822299957,
      "learning_rate": 0.00010958729827994404,
      "loss": 0.7646,
      "step": 619
    },
    {
      "epoch": 0.9560524286815728,
      "grad_norm": 0.030639756470918655,
      "learning_rate": 0.00010934219727951301,
      "loss": 0.8926,
      "step": 620
    },
    {
      "epoch": 0.9575944487278335,
      "grad_norm": 0.030243555083870888,
      "learning_rate": 0.00010909703964899729,
      "loss": 0.6676,
      "step": 621
    },
    {
      "epoch": 0.9591364687740941,
      "grad_norm": 0.029893988743424416,
      "learning_rate": 0.00010885182687448161,
      "loss": 0.7238,
      "step": 622
    },
    {
      "epoch": 0.9606784888203547,
      "grad_norm": 0.02677508443593979,
      "learning_rate": 0.00010860656044238511,
      "loss": 0.7378,
      "step": 623
    },
    {
      "epoch": 0.9622205088666153,
      "grad_norm": 0.02502857707440853,
      "learning_rate": 0.00010836124183945208,
      "loss": 0.7129,
      "step": 624
    },
    {
      "epoch": 0.9637625289128758,
      "grad_norm": 0.02673465758562088,
      "learning_rate": 0.00010811587255274313,
      "loss": 0.7046,
      "step": 625
    },
    {
      "epoch": 0.9653045489591364,
      "grad_norm": 0.030728284269571304,
      "learning_rate": 0.00010787045406962607,
      "loss": 0.752,
      "step": 626
    },
    {
      "epoch": 0.9668465690053971,
      "grad_norm": 0.02698132023215294,
      "learning_rate": 0.00010762498787776687,
      "loss": 0.6365,
      "step": 627
    },
    {
      "epoch": 0.9683885890516577,
      "grad_norm": 0.03070535510778427,
      "learning_rate": 0.0001073794754651208,
      "loss": 0.7465,
      "step": 628
    },
    {
      "epoch": 0.9699306090979183,
      "grad_norm": 0.026031676679849625,
      "learning_rate": 0.00010713391831992323,
      "loss": 0.6991,
      "step": 629
    },
    {
      "epoch": 0.9714726291441789,
      "grad_norm": 0.02689627930521965,
      "learning_rate": 0.00010688831793068078,
      "loss": 0.6468,
      "step": 630
    },
    {
      "epoch": 0.9730146491904395,
      "grad_norm": 0.028856465592980385,
      "learning_rate": 0.00010664267578616207,
      "loss": 0.7051,
      "step": 631
    },
    {
      "epoch": 0.9745566692367,
      "grad_norm": 0.027791066095232964,
      "learning_rate": 0.00010639699337538898,
      "loss": 0.7247,
      "step": 632
    },
    {
      "epoch": 0.9760986892829607,
      "grad_norm": 0.02929227240383625,
      "learning_rate": 0.00010615127218762733,
      "loss": 0.6994,
      "step": 633
    },
    {
      "epoch": 0.9776407093292213,
      "grad_norm": 0.0322168804705143,
      "learning_rate": 0.0001059055137123781,
      "loss": 0.753,
      "step": 634
    },
    {
      "epoch": 0.9791827293754819,
      "grad_norm": 0.02872268296778202,
      "learning_rate": 0.00010565971943936825,
      "loss": 0.7451,
      "step": 635
    },
    {
      "epoch": 0.9807247494217425,
      "grad_norm": 0.03104063868522644,
      "learning_rate": 0.00010541389085854176,
      "loss": 0.7482,
      "step": 636
    },
    {
      "epoch": 0.9822667694680031,
      "grad_norm": 0.026641814038157463,
      "learning_rate": 0.00010516802946005058,
      "loss": 0.7034,
      "step": 637
    },
    {
      "epoch": 0.9838087895142636,
      "grad_norm": 0.027356311678886414,
      "learning_rate": 0.00010492213673424553,
      "loss": 0.6459,
      "step": 638
    },
    {
      "epoch": 0.9853508095605242,
      "grad_norm": 0.031015669927001,
      "learning_rate": 0.00010467621417166745,
      "loss": 0.8185,
      "step": 639
    },
    {
      "epoch": 0.9868928296067849,
      "grad_norm": 0.024331575259566307,
      "learning_rate": 0.00010443026326303789,
      "loss": 0.64,
      "step": 640
    },
    {
      "epoch": 0.9884348496530455,
      "grad_norm": 0.026257265359163284,
      "learning_rate": 0.00010418428549925032,
      "loss": 0.6634,
      "step": 641
    },
    {
      "epoch": 0.9899768696993061,
      "grad_norm": 0.026038171723484993,
      "learning_rate": 0.00010393828237136107,
      "loss": 0.728,
      "step": 642
    },
    {
      "epoch": 0.9915188897455667,
      "grad_norm": 0.028959324583411217,
      "learning_rate": 0.00010369225537058002,
      "loss": 0.7315,
      "step": 643
    },
    {
      "epoch": 0.9930609097918273,
      "grad_norm": 0.026242226362228394,
      "learning_rate": 0.00010344620598826198,
      "loss": 0.7096,
      "step": 644
    },
    {
      "epoch": 0.9946029298380878,
      "grad_norm": 0.029856307432055473,
      "learning_rate": 0.00010320013571589726,
      "loss": 0.7052,
      "step": 645
    },
    {
      "epoch": 0.9961449498843485,
      "grad_norm": 0.03145446628332138,
      "learning_rate": 0.00010295404604510286,
      "loss": 0.8392,
      "step": 646
    },
    {
      "epoch": 0.9976869699306091,
      "grad_norm": 0.032184895128011703,
      "learning_rate": 0.00010270793846761347,
      "loss": 0.7936,
      "step": 647
    },
    {
      "epoch": 0.9992289899768697,
      "grad_norm": 0.027684815227985382,
      "learning_rate": 0.00010246181447527212,
      "loss": 0.6861,
      "step": 648
    }
  ],
  "logging_steps": 1,
  "max_steps": 1296,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 324,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.697171009029014e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}