{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.49961449498843485,
  "eval_steps": 500,
  "global_step": 324,
  "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
    }
  ],
  "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": 4.348585504514507e+18,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}