{
  "best_metric": 0.5701812505722046,
  "best_model_checkpoint": "miner_id_24/checkpoint-250",
  "epoch": 2.9304029304029307,
  "eval_steps": 50,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007326007326007326,
      "grad_norm": 1.0746264457702637,
      "learning_rate": 2.9999999999999997e-05,
      "loss": 0.7495,
      "step": 1
    },
    {
      "epoch": 0.007326007326007326,
      "eval_loss": 1.1676084995269775,
      "eval_runtime": 73.5757,
      "eval_samples_per_second": 7.435,
      "eval_steps_per_second": 7.435,
      "step": 1
    },
    {
      "epoch": 0.014652014652014652,
      "grad_norm": 0.2758323550224304,
      "learning_rate": 5.9999999999999995e-05,
      "loss": 0.9081,
      "step": 2
    },
    {
      "epoch": 0.02197802197802198,
      "grad_norm": 0.29802656173706055,
      "learning_rate": 8.999999999999999e-05,
      "loss": 0.8211,
      "step": 3
    },
    {
      "epoch": 0.029304029304029304,
      "grad_norm": 0.3587598502635956,
      "learning_rate": 0.00011999999999999999,
      "loss": 0.8768,
      "step": 4
    },
    {
      "epoch": 0.03663003663003663,
      "grad_norm": 0.5663146376609802,
      "learning_rate": 0.00015,
      "loss": 0.7956,
      "step": 5
    },
    {
      "epoch": 0.04395604395604396,
      "grad_norm": 0.49756062030792236,
      "learning_rate": 0.00017999999999999998,
      "loss": 0.9633,
      "step": 6
    },
    {
      "epoch": 0.05128205128205128,
      "grad_norm": 0.5426256656646729,
      "learning_rate": 0.00020999999999999998,
      "loss": 0.9303,
      "step": 7
    },
    {
      "epoch": 0.05860805860805861,
      "grad_norm": 0.44440993666648865,
      "learning_rate": 0.00023999999999999998,
      "loss": 0.8358,
      "step": 8
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.3511325418949127,
      "learning_rate": 0.00027,
      "loss": 0.8668,
      "step": 9
    },
    {
      "epoch": 0.07326007326007326,
      "grad_norm": 0.31668755412101746,
      "learning_rate": 0.0003,
      "loss": 0.7562,
      "step": 10
    },
    {
      "epoch": 0.08058608058608059,
      "grad_norm": 0.35746482014656067,
      "learning_rate": 0.0002999953270341234,
      "loss": 0.779,
      "step": 11
    },
    {
      "epoch": 0.08791208791208792,
      "grad_norm": 0.3406325876712799,
      "learning_rate": 0.00029998130842764855,
      "loss": 0.7256,
      "step": 12
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 0.37537914514541626,
      "learning_rate": 0.00029995794505402164,
      "loss": 0.7405,
      "step": 13
    },
    {
      "epoch": 0.10256410256410256,
      "grad_norm": 0.4480861723423004,
      "learning_rate": 0.00029992523836892604,
      "loss": 0.7201,
      "step": 14
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 0.5216184854507446,
      "learning_rate": 0.00029988319041019133,
      "loss": 0.7125,
      "step": 15
    },
    {
      "epoch": 0.11721611721611722,
      "grad_norm": 0.43949222564697266,
      "learning_rate": 0.00029983180379766647,
      "loss": 0.7151,
      "step": 16
    },
    {
      "epoch": 0.12454212454212454,
      "grad_norm": 0.3697758615016937,
      "learning_rate": 0.0002997710817330568,
      "loss": 0.6527,
      "step": 17
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.29461607336997986,
      "learning_rate": 0.000299701027999724,
      "loss": 0.5593,
      "step": 18
    },
    {
      "epoch": 0.1391941391941392,
      "grad_norm": 0.3185078203678131,
      "learning_rate": 0.00029962164696245076,
      "loss": 0.6053,
      "step": 19
    },
    {
      "epoch": 0.14652014652014653,
      "grad_norm": 0.4523352086544037,
      "learning_rate": 0.000299532943567169,
      "loss": 0.8082,
      "step": 20
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.3355499505996704,
      "learning_rate": 0.000299434923340651,
      "loss": 0.4784,
      "step": 21
    },
    {
      "epoch": 0.16117216117216118,
      "grad_norm": 0.38593626022338867,
      "learning_rate": 0.0002993275923901659,
      "loss": 0.7062,
      "step": 22
    },
    {
      "epoch": 0.1684981684981685,
      "grad_norm": 0.3636136054992676,
      "learning_rate": 0.00029921095740309854,
      "loss": 0.689,
      "step": 23
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 0.37379103899002075,
      "learning_rate": 0.0002990850256465331,
      "loss": 0.6864,
      "step": 24
    },
    {
      "epoch": 0.18315018315018314,
      "grad_norm": 0.44014841318130493,
      "learning_rate": 0.0002989498049668004,
      "loss": 0.5692,
      "step": 25
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 0.36174437403678894,
      "learning_rate": 0.0002988053037889886,
      "loss": 0.6588,
      "step": 26
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3935069143772125,
      "learning_rate": 0.0002986515311164188,
      "loss": 0.6105,
      "step": 27
    },
    {
      "epoch": 0.20512820512820512,
      "grad_norm": 0.4123885929584503,
      "learning_rate": 0.00029848849653008356,
      "loss": 0.5963,
      "step": 28
    },
    {
      "epoch": 0.21245421245421245,
      "grad_norm": 0.4219466745853424,
      "learning_rate": 0.00029831621018805036,
      "loss": 0.598,
      "step": 29
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 0.40744897723197937,
      "learning_rate": 0.00029813468282482856,
      "loss": 0.6318,
      "step": 30
    },
    {
      "epoch": 0.2271062271062271,
      "grad_norm": 0.41496506333351135,
      "learning_rate": 0.0002979439257507004,
      "loss": 0.5648,
      "step": 31
    },
    {
      "epoch": 0.23443223443223443,
      "grad_norm": 0.4135119318962097,
      "learning_rate": 0.0002977439508510166,
      "loss": 0.5706,
      "step": 32
    },
    {
      "epoch": 0.24175824175824176,
      "grad_norm": 0.5413480997085571,
      "learning_rate": 0.00029753477058545543,
      "loss": 0.6367,
      "step": 33
    },
    {
      "epoch": 0.2490842490842491,
      "grad_norm": 0.7710244059562683,
      "learning_rate": 0.00029731639798724705,
      "loss": 0.5927,
      "step": 34
    },
    {
      "epoch": 0.2564102564102564,
      "grad_norm": 0.29940611124038696,
      "learning_rate": 0.0002970888466623606,
      "loss": 0.6232,
      "step": 35
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.3256644606590271,
      "learning_rate": 0.00029685213078865715,
      "loss": 0.6949,
      "step": 36
    },
    {
      "epoch": 0.27106227106227104,
      "grad_norm": 0.2492157518863678,
      "learning_rate": 0.00029660626511500605,
      "loss": 0.6002,
      "step": 37
    },
    {
      "epoch": 0.2783882783882784,
      "grad_norm": 0.25613823533058167,
      "learning_rate": 0.000296351264960366,
      "loss": 0.6237,
      "step": 38
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.24584399163722992,
      "learning_rate": 0.00029608714621283063,
      "loss": 0.688,
      "step": 39
    },
    {
      "epoch": 0.29304029304029305,
      "grad_norm": 0.23079101741313934,
      "learning_rate": 0.0002958139253286385,
      "loss": 0.7131,
      "step": 40
    },
    {
      "epoch": 0.30036630036630035,
      "grad_norm": 0.28000855445861816,
      "learning_rate": 0.0002955316193311479,
      "loss": 0.6817,
      "step": 41
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.2555966377258301,
      "learning_rate": 0.000295240245809776,
      "loss": 0.6851,
      "step": 42
    },
    {
      "epoch": 0.315018315018315,
      "grad_norm": 0.24511605501174927,
      "learning_rate": 0.00029493982291890324,
      "loss": 0.6946,
      "step": 43
    },
    {
      "epoch": 0.32234432234432236,
      "grad_norm": 0.24352319538593292,
      "learning_rate": 0.00029463036937674175,
      "loss": 0.6592,
      "step": 44
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.27086544036865234,
      "learning_rate": 0.0002943119044641694,
      "loss": 0.6949,
      "step": 45
    },
    {
      "epoch": 0.336996336996337,
      "grad_norm": 0.25139376521110535,
      "learning_rate": 0.00029398444802352855,
      "loss": 0.6856,
      "step": 46
    },
    {
      "epoch": 0.3443223443223443,
      "grad_norm": 0.23585085570812225,
      "learning_rate": 0.0002936480204573894,
      "loss": 0.6426,
      "step": 47
    },
    {
      "epoch": 0.3516483516483517,
      "grad_norm": 0.24448701739311218,
      "learning_rate": 0.00029330264272727917,
      "loss": 0.5887,
      "step": 48
    },
    {
      "epoch": 0.358974358974359,
      "grad_norm": 0.2956358790397644,
      "learning_rate": 0.00029294833635237587,
      "loss": 0.6925,
      "step": 49
    },
    {
      "epoch": 0.3663003663003663,
      "grad_norm": 0.242750346660614,
      "learning_rate": 0.0002925851234081674,
      "loss": 0.5302,
      "step": 50
    },
    {
      "epoch": 0.3663003663003663,
      "eval_loss": 0.6130701303482056,
      "eval_runtime": 73.3992,
      "eval_samples_per_second": 7.452,
      "eval_steps_per_second": 7.452,
      "step": 50
    },
    {
      "epoch": 0.37362637362637363,
      "grad_norm": 0.2964664399623871,
      "learning_rate": 0.0002922130265250764,
      "loss": 0.6552,
      "step": 51
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 0.3150418996810913,
      "learning_rate": 0.00029183206888705004,
      "loss": 0.6041,
      "step": 52
    },
    {
      "epoch": 0.3882783882783883,
      "grad_norm": 0.2626626491546631,
      "learning_rate": 0.00029144227423011555,
      "loss": 0.6236,
      "step": 53
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.31966981291770935,
      "learning_rate": 0.0002910436668409013,
      "loss": 0.6936,
      "step": 54
    },
    {
      "epoch": 0.40293040293040294,
      "grad_norm": 0.3115909695625305,
      "learning_rate": 0.00029063627155512375,
      "loss": 0.5992,
      "step": 55
    },
    {
      "epoch": 0.41025641025641024,
      "grad_norm": 0.29618480801582336,
      "learning_rate": 0.0002902201137560397,
      "loss": 0.5781,
      "step": 56
    },
    {
      "epoch": 0.4175824175824176,
      "grad_norm": 0.2827432453632355,
      "learning_rate": 0.0002897952193728652,
      "loss": 0.5961,
      "step": 57
    },
    {
      "epoch": 0.4249084249084249,
      "grad_norm": 0.30941715836524963,
      "learning_rate": 0.00028936161487915955,
      "loss": 0.6069,
      "step": 58
    },
    {
      "epoch": 0.43223443223443225,
      "grad_norm": 0.34647953510284424,
      "learning_rate": 0.00028891932729117615,
      "loss": 0.6544,
      "step": 59
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 0.34131157398223877,
      "learning_rate": 0.0002884683841661791,
      "loss": 0.5973,
      "step": 60
    },
    {
      "epoch": 0.4468864468864469,
      "grad_norm": 0.3378750681877136,
      "learning_rate": 0.00028800881360072615,
      "loss": 0.5805,
      "step": 61
    },
    {
      "epoch": 0.4542124542124542,
      "grad_norm": 0.3864741027355194,
      "learning_rate": 0.0002875406442289183,
      "loss": 0.5829,
      "step": 62
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.31040650606155396,
      "learning_rate": 0.0002870639052206155,
      "loss": 0.5408,
      "step": 63
    },
    {
      "epoch": 0.46886446886446886,
      "grad_norm": 0.3510590195655823,
      "learning_rate": 0.0002865786262796193,
      "loss": 0.5623,
      "step": 64
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 0.34330350160598755,
      "learning_rate": 0.00028608483764182215,
      "loss": 0.5304,
      "step": 65
    },
    {
      "epoch": 0.4835164835164835,
      "grad_norm": 0.3788071274757385,
      "learning_rate": 0.0002855825700733235,
      "loss": 0.4966,
      "step": 66
    },
    {
      "epoch": 0.4908424908424908,
      "grad_norm": 0.38324546813964844,
      "learning_rate": 0.00028507185486851275,
      "loss": 0.44,
      "step": 67
    },
    {
      "epoch": 0.4981684981684982,
      "grad_norm": 0.4564480185508728,
      "learning_rate": 0.0002845527238481195,
      "loss": 0.4097,
      "step": 68
    },
    {
      "epoch": 0.5054945054945055,
      "grad_norm": 0.238909512758255,
      "learning_rate": 0.0002840252093572311,
      "loss": 0.6646,
      "step": 69
    },
    {
      "epoch": 0.5128205128205128,
      "grad_norm": 0.2642434239387512,
      "learning_rate": 0.000283489344263277,
      "loss": 0.6419,
      "step": 70
    },
    {
      "epoch": 0.5201465201465202,
      "grad_norm": 0.2626118063926697,
      "learning_rate": 0.00028294516195398125,
      "loss": 0.6318,
      "step": 71
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.23919053375720978,
      "learning_rate": 0.00028239269633528204,
      "loss": 0.6266,
      "step": 72
    },
    {
      "epoch": 0.5347985347985348,
      "grad_norm": 0.25669869780540466,
      "learning_rate": 0.000281831981829219,
      "loss": 0.6594,
      "step": 73
    },
    {
      "epoch": 0.5421245421245421,
      "grad_norm": 0.21138758957386017,
      "learning_rate": 0.00028126305337178905,
      "loss": 0.5986,
      "step": 74
    },
    {
      "epoch": 0.5494505494505495,
      "grad_norm": 0.24748112261295319,
      "learning_rate": 0.0002806859464107689,
      "loss": 0.6108,
      "step": 75
    },
    {
      "epoch": 0.5567765567765568,
      "grad_norm": 0.23385199904441833,
      "learning_rate": 0.00028010069690350716,
      "loss": 0.6049,
      "step": 76
    },
    {
      "epoch": 0.5641025641025641,
      "grad_norm": 0.2671392560005188,
      "learning_rate": 0.00027950734131468346,
      "loss": 0.6324,
      "step": 77
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.20720772445201874,
      "learning_rate": 0.00027890591661403676,
      "loss": 0.538,
      "step": 78
    },
    {
      "epoch": 0.5787545787545788,
      "grad_norm": 0.26165518164634705,
      "learning_rate": 0.00027829646027406174,
      "loss": 0.6713,
      "step": 79
    },
    {
      "epoch": 0.5860805860805861,
      "grad_norm": 0.285157173871994,
      "learning_rate": 0.00027767901026767416,
      "loss": 0.7407,
      "step": 80
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.24118804931640625,
      "learning_rate": 0.00027705360506584484,
      "loss": 0.6414,
      "step": 81
    },
    {
      "epoch": 0.6007326007326007,
      "grad_norm": 0.2540411651134491,
      "learning_rate": 0.00027642028363520255,
      "loss": 0.6584,
      "step": 82
    },
    {
      "epoch": 0.608058608058608,
      "grad_norm": 0.2713707685470581,
      "learning_rate": 0.0002757790854356066,
      "loss": 0.6356,
      "step": 83
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.25061967968940735,
      "learning_rate": 0.0002751300504176876,
      "loss": 0.5919,
      "step": 84
    },
    {
      "epoch": 0.6227106227106227,
      "grad_norm": 0.2813633382320404,
      "learning_rate": 0.0002744732190203589,
      "loss": 0.6507,
      "step": 85
    },
    {
      "epoch": 0.63003663003663,
      "grad_norm": 0.36446070671081543,
      "learning_rate": 0.00027380863216829645,
      "loss": 0.6146,
      "step": 86
    },
    {
      "epoch": 0.6373626373626373,
      "grad_norm": 0.2936757802963257,
      "learning_rate": 0.00027313633126938936,
      "loss": 0.5807,
      "step": 87
    },
    {
      "epoch": 0.6446886446886447,
      "grad_norm": 0.32543811202049255,
      "learning_rate": 0.0002724563582121598,
      "loss": 0.633,
      "step": 88
    },
    {
      "epoch": 0.652014652014652,
      "grad_norm": 0.26980024576187134,
      "learning_rate": 0.0002717687553631531,
      "loss": 0.5771,
      "step": 89
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.3081660568714142,
      "learning_rate": 0.0002710735655642978,
      "loss": 0.5795,
      "step": 90
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.30959567427635193,
      "learning_rate": 0.0002703708321302367,
      "loss": 0.5278,
      "step": 91
    },
    {
      "epoch": 0.673992673992674,
      "grad_norm": 0.30625343322753906,
      "learning_rate": 0.0002696605988456279,
      "loss": 0.5816,
      "step": 92
    },
    {
      "epoch": 0.6813186813186813,
      "grad_norm": 0.31666725873947144,
      "learning_rate": 0.00026894290996241677,
      "loss": 0.5393,
      "step": 93
    },
    {
      "epoch": 0.6886446886446886,
      "grad_norm": 0.31827884912490845,
      "learning_rate": 0.0002682178101970788,
      "loss": 0.5869,
      "step": 94
    },
    {
      "epoch": 0.6959706959706959,
      "grad_norm": 0.3418588936328888,
      "learning_rate": 0.00026748534472783355,
      "loss": 0.5939,
      "step": 95
    },
    {
      "epoch": 0.7032967032967034,
      "grad_norm": 0.35669511556625366,
      "learning_rate": 0.00026674555919182943,
      "loss": 0.6145,
      "step": 96
    },
    {
      "epoch": 0.7106227106227107,
      "grad_norm": 0.3676556348800659,
      "learning_rate": 0.00026599849968230084,
      "loss": 0.5306,
      "step": 97
    },
    {
      "epoch": 0.717948717948718,
      "grad_norm": 0.3910490870475769,
      "learning_rate": 0.00026524421274569556,
      "loss": 0.6035,
      "step": 98
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.3907155394554138,
      "learning_rate": 0.00026448274537877527,
      "loss": 0.5149,
      "step": 99
    },
    {
      "epoch": 0.7326007326007326,
      "grad_norm": 0.3669157326221466,
      "learning_rate": 0.0002637141450256868,
      "loss": 0.4153,
      "step": 100
    },
    {
      "epoch": 0.7326007326007326,
      "eval_loss": 0.5930299162864685,
      "eval_runtime": 73.3788,
      "eval_samples_per_second": 7.454,
      "eval_steps_per_second": 7.454,
      "step": 100
    },
    {
      "epoch": 0.73992673992674,
      "grad_norm": 0.5483953952789307,
      "learning_rate": 0.0002629384595750065,
      "loss": 0.4924,
      "step": 101
    },
    {
      "epoch": 0.7472527472527473,
      "grad_norm": 0.44320136308670044,
      "learning_rate": 0.00026215573735675635,
      "loss": 0.4333,
      "step": 102
    },
    {
      "epoch": 0.7545787545787546,
      "grad_norm": 0.2921634316444397,
      "learning_rate": 0.0002613660271393924,
      "loss": 0.5333,
      "step": 103
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.3033207654953003,
      "learning_rate": 0.0002605693781267668,
      "loss": 0.6723,
      "step": 104
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.21631714701652527,
      "learning_rate": 0.00025976583995506147,
      "loss": 0.7413,
      "step": 105
    },
    {
      "epoch": 0.7765567765567766,
      "grad_norm": 0.2756958305835724,
      "learning_rate": 0.0002589554626896959,
      "loss": 0.6334,
      "step": 106
    },
    {
      "epoch": 0.7838827838827839,
      "grad_norm": 0.23255576193332672,
      "learning_rate": 0.0002581382968222075,
      "loss": 0.6241,
      "step": 107
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.2933904230594635,
      "learning_rate": 0.00025731439326710564,
      "loss": 0.6238,
      "step": 108
    },
    {
      "epoch": 0.7985347985347986,
      "grad_norm": 0.24506813287734985,
      "learning_rate": 0.0002564838033586999,
      "loss": 0.7049,
      "step": 109
    },
    {
      "epoch": 0.8058608058608059,
      "grad_norm": 0.21781164407730103,
      "learning_rate": 0.0002556465788479008,
      "loss": 0.5831,
      "step": 110
    },
    {
      "epoch": 0.8131868131868132,
      "grad_norm": 0.23479105532169342,
      "learning_rate": 0.00025480277189899594,
      "loss": 0.6347,
      "step": 111
    },
    {
      "epoch": 0.8205128205128205,
      "grad_norm": 0.22827807068824768,
      "learning_rate": 0.00025395243508639974,
      "loss": 0.5881,
      "step": 112
    },
    {
      "epoch": 0.8278388278388278,
      "grad_norm": 0.24758267402648926,
      "learning_rate": 0.00025309562139137765,
      "loss": 0.6288,
      "step": 113
    },
    {
      "epoch": 0.8351648351648352,
      "grad_norm": 0.23672336339950562,
      "learning_rate": 0.00025223238419874505,
      "loss": 0.623,
      "step": 114
    },
    {
      "epoch": 0.8424908424908425,
      "grad_norm": 0.25866055488586426,
      "learning_rate": 0.0002513627772935413,
      "loss": 0.6076,
      "step": 115
    },
    {
      "epoch": 0.8498168498168498,
      "grad_norm": 0.23350456357002258,
      "learning_rate": 0.00025048685485767826,
      "loss": 0.6124,
      "step": 116
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.26988059282302856,
      "learning_rate": 0.00024960467146656465,
      "loss": 0.667,
      "step": 117
    },
    {
      "epoch": 0.8644688644688645,
      "grad_norm": 0.2606026530265808,
      "learning_rate": 0.0002487162820857056,
      "loss": 0.514,
      "step": 118
    },
    {
      "epoch": 0.8717948717948718,
      "grad_norm": 0.26499950885772705,
      "learning_rate": 0.00024782174206727797,
      "loss": 0.5818,
      "step": 119
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 0.2778685390949249,
      "learning_rate": 0.00024692110714668144,
      "loss": 0.6545,
      "step": 120
    },
    {
      "epoch": 0.8864468864468864,
      "grad_norm": 0.2645077705383301,
      "learning_rate": 0.00024601443343906607,
      "loss": 0.5948,
      "step": 121
    },
    {
      "epoch": 0.8937728937728938,
      "grad_norm": 0.2799476385116577,
      "learning_rate": 0.00024510177743583577,
      "loss": 0.6282,
      "step": 122
    },
    {
      "epoch": 0.9010989010989011,
      "grad_norm": 0.3192484676837921,
      "learning_rate": 0.00024418319600112877,
      "loss": 0.6482,
      "step": 123
    },
    {
      "epoch": 0.9084249084249084,
      "grad_norm": 0.28705793619155884,
      "learning_rate": 0.00024325874636827428,
      "loss": 0.6307,
      "step": 124
    },
    {
      "epoch": 0.9157509157509157,
      "grad_norm": 0.30531764030456543,
      "learning_rate": 0.00024232848613622686,
      "loss": 0.5717,
      "step": 125
    },
    {
      "epoch": 0.9230769230769231,
      "grad_norm": 0.31991544365882874,
      "learning_rate": 0.00024139247326597748,
      "loss": 0.5068,
      "step": 126
    },
    {
      "epoch": 0.9304029304029304,
      "grad_norm": 0.40226104855537415,
      "learning_rate": 0.00024045076607694216,
      "loss": 0.7029,
      "step": 127
    },
    {
      "epoch": 0.9377289377289377,
      "grad_norm": 0.38639435172080994,
      "learning_rate": 0.0002395034232433284,
      "loss": 0.5574,
      "step": 128
    },
    {
      "epoch": 0.945054945054945,
      "grad_norm": 0.35603398084640503,
      "learning_rate": 0.00023855050379047922,
      "loss": 0.568,
      "step": 129
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.3355114459991455,
      "learning_rate": 0.00023759206709119595,
      "loss": 0.4997,
      "step": 130
    },
    {
      "epoch": 0.9597069597069597,
      "grad_norm": 0.39614033699035645,
      "learning_rate": 0.0002366281728620383,
      "loss": 0.5225,
      "step": 131
    },
    {
      "epoch": 0.967032967032967,
      "grad_norm": 0.33072763681411743,
      "learning_rate": 0.0002356588811596042,
      "loss": 0.427,
      "step": 132
    },
    {
      "epoch": 0.9743589743589743,
      "grad_norm": 0.5783118605613708,
      "learning_rate": 0.00023468425237678769,
      "loss": 0.5669,
      "step": 133
    },
    {
      "epoch": 0.9816849816849816,
      "grad_norm": 0.44978731870651245,
      "learning_rate": 0.000233704347239016,
      "loss": 0.5213,
      "step": 134
    },
    {
      "epoch": 0.989010989010989,
      "grad_norm": 0.4447237551212311,
      "learning_rate": 0.0002327192268004661,
      "loss": 0.4526,
      "step": 135
    },
    {
      "epoch": 0.9963369963369964,
      "grad_norm": 0.5178239941596985,
      "learning_rate": 0.00023172895244026056,
      "loss": 0.419,
      "step": 136
    },
    {
      "epoch": 1.0036630036630036,
      "grad_norm": 0.5518823266029358,
      "learning_rate": 0.0002307335858586433,
      "loss": 0.9609,
      "step": 137
    },
    {
      "epoch": 1.010989010989011,
      "grad_norm": 0.19367220997810364,
      "learning_rate": 0.0002297331890731352,
      "loss": 0.6718,
      "step": 138
    },
    {
      "epoch": 1.0183150183150182,
      "grad_norm": 0.2209685742855072,
      "learning_rate": 0.0002287278244146702,
      "loss": 0.6591,
      "step": 139
    },
    {
      "epoch": 1.0256410256410255,
      "grad_norm": 0.2094419300556183,
      "learning_rate": 0.00022771755452371162,
      "loss": 0.5926,
      "step": 140
    },
    {
      "epoch": 1.032967032967033,
      "grad_norm": 0.22118069231510162,
      "learning_rate": 0.00022670244234634902,
      "loss": 0.6281,
      "step": 141
    },
    {
      "epoch": 1.0402930402930404,
      "grad_norm": 0.23426313698291779,
      "learning_rate": 0.00022568255113037658,
      "loss": 0.5911,
      "step": 142
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.22640864551067352,
      "learning_rate": 0.00022465794442135244,
      "loss": 0.6435,
      "step": 143
    },
    {
      "epoch": 1.054945054945055,
      "grad_norm": 0.2409924864768982,
      "learning_rate": 0.000223628686058639,
      "loss": 0.594,
      "step": 144
    },
    {
      "epoch": 1.0622710622710623,
      "grad_norm": 0.2898027002811432,
      "learning_rate": 0.00022259484017142582,
      "loss": 0.578,
      "step": 145
    },
    {
      "epoch": 1.0695970695970696,
      "grad_norm": 0.2668663561344147,
      "learning_rate": 0.00022155647117473343,
      "loss": 0.6175,
      "step": 146
    },
    {
      "epoch": 1.0769230769230769,
      "grad_norm": 0.25386887788772583,
      "learning_rate": 0.00022051364376540045,
      "loss": 0.5452,
      "step": 147
    },
    {
      "epoch": 1.0842490842490842,
      "grad_norm": 0.2420186847448349,
      "learning_rate": 0.00021946642291805214,
      "loss": 0.5267,
      "step": 148
    },
    {
      "epoch": 1.0915750915750915,
      "grad_norm": 0.26154059171676636,
      "learning_rate": 0.00021841487388105235,
      "loss": 0.5904,
      "step": 149
    },
    {
      "epoch": 1.098901098901099,
      "grad_norm": 0.25012269616127014,
      "learning_rate": 0.00021735906217243802,
      "loss": 0.6004,
      "step": 150
    },
    {
      "epoch": 1.098901098901099,
      "eval_loss": 0.5869444012641907,
      "eval_runtime": 73.5969,
      "eval_samples_per_second": 7.432,
      "eval_steps_per_second": 7.432,
      "step": 150
    },
    {
      "epoch": 1.1062271062271063,
      "grad_norm": 0.2936391234397888,
      "learning_rate": 0.00021629905357583687,
      "loss": 0.6069,
      "step": 151
    },
    {
      "epoch": 1.1135531135531136,
      "grad_norm": 0.3034394383430481,
      "learning_rate": 0.00021523491413636894,
      "loss": 0.4688,
      "step": 152
    },
    {
      "epoch": 1.120879120879121,
      "grad_norm": 0.2803559899330139,
      "learning_rate": 0.00021416671015653144,
      "loss": 0.5647,
      "step": 153
    },
    {
      "epoch": 1.1282051282051282,
      "grad_norm": 0.3114618957042694,
      "learning_rate": 0.00021309450819206763,
      "loss": 0.4767,
      "step": 154
    },
    {
      "epoch": 1.1355311355311355,
      "grad_norm": 0.3169534206390381,
      "learning_rate": 0.0002120183750478201,
      "loss": 0.5048,
      "step": 155
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.3803180754184723,
      "learning_rate": 0.00021093837777356835,
      "loss": 0.5439,
      "step": 156
    },
    {
      "epoch": 1.15018315018315,
      "grad_norm": 0.3590928614139557,
      "learning_rate": 0.00020985458365985112,
      "loss": 0.6012,
      "step": 157
    },
    {
      "epoch": 1.1575091575091574,
      "grad_norm": 0.3438403606414795,
      "learning_rate": 0.00020876706023377394,
      "loss": 0.4902,
      "step": 158
    },
    {
      "epoch": 1.164835164835165,
      "grad_norm": 0.35391849279403687,
      "learning_rate": 0.0002076758752548016,
      "loss": 0.4655,
      "step": 159
    },
    {
      "epoch": 1.1721611721611722,
      "grad_norm": 0.3842090666294098,
      "learning_rate": 0.0002065810967105364,
      "loss": 0.4753,
      "step": 160
    },
    {
      "epoch": 1.1794871794871795,
      "grad_norm": 0.35003578662872314,
      "learning_rate": 0.000205482792812482,
      "loss": 0.4344,
      "step": 161
    },
    {
      "epoch": 1.1868131868131868,
      "grad_norm": 0.3732411563396454,
      "learning_rate": 0.0002043810319917937,
      "loss": 0.4107,
      "step": 162
    },
    {
      "epoch": 1.1941391941391941,
      "grad_norm": 0.4202706515789032,
      "learning_rate": 0.00020327588289501425,
      "loss": 0.5001,
      "step": 163
    },
    {
      "epoch": 1.2014652014652014,
      "grad_norm": 0.41824397444725037,
      "learning_rate": 0.00020216741437979735,
      "loss": 0.4344,
      "step": 164
    },
    {
      "epoch": 1.2087912087912087,
      "grad_norm": 0.5380794405937195,
      "learning_rate": 0.00020105569551061693,
      "loss": 0.4992,
      "step": 165
    },
    {
      "epoch": 1.2161172161172162,
      "grad_norm": 0.557085394859314,
      "learning_rate": 0.00019994079555446417,
      "loss": 0.4411,
      "step": 166
    },
    {
      "epoch": 1.2234432234432235,
      "grad_norm": 0.485733300447464,
      "learning_rate": 0.00019882278397653175,
      "loss": 0.4401,
      "step": 167
    },
    {
      "epoch": 1.2307692307692308,
      "grad_norm": 1.3742977380752563,
      "learning_rate": 0.0001977017304358857,
      "loss": 0.3275,
      "step": 168
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.5038601756095886,
      "learning_rate": 0.00019657770478112533,
      "loss": 0.3036,
      "step": 169
    },
    {
      "epoch": 1.2454212454212454,
      "grad_norm": 0.615625262260437,
      "learning_rate": 0.00019545077704603088,
      "loss": 0.3079,
      "step": 170
    },
    {
      "epoch": 1.2527472527472527,
      "grad_norm": 0.4520106315612793,
      "learning_rate": 0.00019432101744520052,
      "loss": 0.4792,
      "step": 171
    },
    {
      "epoch": 1.26007326007326,
      "grad_norm": 0.4422815442085266,
      "learning_rate": 0.00019318849636967497,
      "loss": 0.5819,
      "step": 172
    },
    {
      "epoch": 1.2673992673992673,
      "grad_norm": 0.39762523770332336,
      "learning_rate": 0.00019205328438255215,
      "loss": 0.6133,
      "step": 173
    },
    {
      "epoch": 1.2747252747252746,
      "grad_norm": 0.308088481426239,
      "learning_rate": 0.00019091545221459048,
      "loss": 0.5021,
      "step": 174
    },
    {
      "epoch": 1.282051282051282,
      "grad_norm": 0.3217431902885437,
      "learning_rate": 0.0001897750707598018,
      "loss": 0.5656,
      "step": 175
    },
    {
      "epoch": 1.2893772893772895,
      "grad_norm": 0.34072449803352356,
      "learning_rate": 0.00018863221107103453,
      "loss": 0.6147,
      "step": 176
    },
    {
      "epoch": 1.2967032967032968,
      "grad_norm": 0.3127173185348511,
      "learning_rate": 0.00018748694435554626,
      "loss": 0.5093,
      "step": 177
    },
    {
      "epoch": 1.304029304029304,
      "grad_norm": 0.28147441148757935,
      "learning_rate": 0.00018633934197056747,
      "loss": 0.5148,
      "step": 178
    },
    {
      "epoch": 1.3113553113553114,
      "grad_norm": 0.32677727937698364,
      "learning_rate": 0.00018518947541885532,
      "loss": 0.5213,
      "step": 179
    },
    {
      "epoch": 1.3186813186813187,
      "grad_norm": 0.3397771120071411,
      "learning_rate": 0.0001840374163442385,
      "loss": 0.5752,
      "step": 180
    },
    {
      "epoch": 1.326007326007326,
      "grad_norm": 0.32977497577667236,
      "learning_rate": 0.00018288323652715372,
      "loss": 0.6049,
      "step": 181
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.3196227550506592,
      "learning_rate": 0.00018172700788017285,
      "loss": 0.6103,
      "step": 182
    },
    {
      "epoch": 1.3406593406593408,
      "grad_norm": 0.3648357689380646,
      "learning_rate": 0.0001805688024435228,
      "loss": 0.6024,
      "step": 183
    },
    {
      "epoch": 1.347985347985348,
      "grad_norm": 0.3467482924461365,
      "learning_rate": 0.00017940869238059672,
      "loss": 0.6184,
      "step": 184
    },
    {
      "epoch": 1.3553113553113554,
      "grad_norm": 0.34417080879211426,
      "learning_rate": 0.00017824674997345765,
      "loss": 0.5201,
      "step": 185
    },
    {
      "epoch": 1.3626373626373627,
      "grad_norm": 0.32738953828811646,
      "learning_rate": 0.0001770830476183353,
      "loss": 0.4373,
      "step": 186
    },
    {
      "epoch": 1.36996336996337,
      "grad_norm": 0.3495752513408661,
      "learning_rate": 0.00017591765782111493,
      "loss": 0.5156,
      "step": 187
    },
    {
      "epoch": 1.3772893772893773,
      "grad_norm": 0.38357013463974,
      "learning_rate": 0.0001747506531928199,
      "loss": 0.5689,
      "step": 188
    },
    {
      "epoch": 1.3846153846153846,
      "grad_norm": 0.3947698473930359,
      "learning_rate": 0.00017358210644508761,
      "loss": 0.5288,
      "step": 189
    },
    {
      "epoch": 1.3919413919413919,
      "grad_norm": 0.39951273798942566,
      "learning_rate": 0.00017241209038563915,
      "loss": 0.4936,
      "step": 190
    },
    {
      "epoch": 1.3992673992673992,
      "grad_norm": 0.46843069791793823,
      "learning_rate": 0.0001712406779137427,
      "loss": 0.5193,
      "step": 191
    },
    {
      "epoch": 1.4065934065934065,
      "grad_norm": 0.4092109799385071,
      "learning_rate": 0.00017006794201567186,
      "loss": 0.4587,
      "step": 192
    },
    {
      "epoch": 1.4139194139194138,
      "grad_norm": 0.5061143636703491,
      "learning_rate": 0.00016889395576015763,
      "loss": 0.4816,
      "step": 193
    },
    {
      "epoch": 1.4212454212454213,
      "grad_norm": 0.4533427655696869,
      "learning_rate": 0.0001677187922938362,
      "loss": 0.5173,
      "step": 194
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.4554060399532318,
      "learning_rate": 0.00016654252483669124,
      "loss": 0.4767,
      "step": 195
    },
    {
      "epoch": 1.435897435897436,
      "grad_norm": 0.4680671691894531,
      "learning_rate": 0.00016536522667749196,
      "loss": 0.4486,
      "step": 196
    },
    {
      "epoch": 1.4432234432234432,
      "grad_norm": 0.5479559898376465,
      "learning_rate": 0.00016418697116922672,
      "loss": 0.4627,
      "step": 197
    },
    {
      "epoch": 1.4505494505494505,
      "grad_norm": 0.5161874890327454,
      "learning_rate": 0.00016300783172453265,
      "loss": 0.4527,
      "step": 198
    },
    {
      "epoch": 1.4578754578754578,
      "grad_norm": 0.4987958073616028,
      "learning_rate": 0.00016182788181112146,
      "loss": 0.43,
      "step": 199
    },
    {
      "epoch": 1.4652014652014653,
      "grad_norm": 0.5920132994651794,
      "learning_rate": 0.00016064719494720238,
      "loss": 0.4271,
      "step": 200
    },
    {
      "epoch": 1.4652014652014653,
      "eval_loss": 0.5827460885047913,
      "eval_runtime": 73.578,
      "eval_samples_per_second": 7.434,
      "eval_steps_per_second": 7.434,
      "step": 200
    },
    {
      "epoch": 1.4725274725274726,
      "grad_norm": 0.5107991695404053,
      "learning_rate": 0.000159465844696901,
      "loss": 0.3252,
      "step": 201
    },
    {
      "epoch": 1.47985347985348,
      "grad_norm": 0.5588508248329163,
      "learning_rate": 0.0001582839046656762,
      "loss": 0.3086,
      "step": 202
    },
    {
      "epoch": 1.4871794871794872,
      "grad_norm": 0.5706549882888794,
      "learning_rate": 0.0001571014484957337,
      "loss": 0.2613,
      "step": 203
    },
    {
      "epoch": 1.4945054945054945,
      "grad_norm": 0.8393925428390503,
      "learning_rate": 0.0001559185498614379,
      "loss": 0.3406,
      "step": 204
    },
    {
      "epoch": 1.5018315018315018,
      "grad_norm": 0.6459693312644958,
      "learning_rate": 0.0001547352824647216,
      "loss": 0.3553,
      "step": 205
    },
    {
      "epoch": 1.5091575091575091,
      "grad_norm": 0.313265323638916,
      "learning_rate": 0.00015355172003049357,
      "loss": 0.4846,
      "step": 206
    },
    {
      "epoch": 1.5164835164835164,
      "grad_norm": 0.3253680169582367,
      "learning_rate": 0.00015236793630204554,
      "loss": 0.5412,
      "step": 207
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.35269081592559814,
      "learning_rate": 0.000151184005036457,
      "loss": 0.6062,
      "step": 208
    },
    {
      "epoch": 1.531135531135531,
      "grad_norm": 0.3606890141963959,
      "learning_rate": 0.00015,
      "loss": 0.5544,
      "step": 209
    },
    {
      "epoch": 1.5384615384615383,
      "grad_norm": 0.36298248171806335,
      "learning_rate": 0.000148815994963543,
      "loss": 0.542,
      "step": 210
    },
    {
      "epoch": 1.5457875457875456,
      "grad_norm": 0.36222681403160095,
      "learning_rate": 0.00014763206369795446,
      "loss": 0.6695,
      "step": 211
    },
    {
      "epoch": 1.5531135531135531,
      "grad_norm": 0.4112010598182678,
      "learning_rate": 0.00014644827996950643,
      "loss": 0.6308,
      "step": 212
    },
    {
      "epoch": 1.5604395604395604,
      "grad_norm": 0.33088386058807373,
      "learning_rate": 0.00014526471753527838,
      "loss": 0.5061,
      "step": 213
    },
    {
      "epoch": 1.5677655677655677,
      "grad_norm": 0.3446553349494934,
      "learning_rate": 0.0001440814501385621,
      "loss": 0.5424,
      "step": 214
    },
    {
      "epoch": 1.575091575091575,
      "grad_norm": 0.3574959933757782,
      "learning_rate": 0.0001428985515042663,
      "loss": 0.448,
      "step": 215
    },
    {
      "epoch": 1.5824175824175826,
      "grad_norm": 0.35467544198036194,
      "learning_rate": 0.00014171609533432378,
      "loss": 0.5307,
      "step": 216
    },
    {
      "epoch": 1.5897435897435899,
      "grad_norm": 0.34874802827835083,
      "learning_rate": 0.00014053415530309896,
      "loss": 0.5321,
      "step": 217
    },
    {
      "epoch": 1.5970695970695972,
      "grad_norm": 0.37879034876823425,
      "learning_rate": 0.0001393528050527976,
      "loss": 0.4935,
      "step": 218
    },
    {
      "epoch": 1.6043956043956045,
      "grad_norm": 0.3754430115222931,
      "learning_rate": 0.00013817211818887852,
      "loss": 0.5807,
      "step": 219
    },
    {
      "epoch": 1.6117216117216118,
      "grad_norm": 0.40496763586997986,
      "learning_rate": 0.0001369921682754674,
      "loss": 0.6015,
      "step": 220
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.38105273246765137,
      "learning_rate": 0.00013581302883077325,
      "loss": 0.512,
      "step": 221
    },
    {
      "epoch": 1.6263736263736264,
      "grad_norm": 0.45323583483695984,
      "learning_rate": 0.000134634773322508,
      "loss": 0.5284,
      "step": 222
    },
    {
      "epoch": 1.6336996336996337,
      "grad_norm": 0.4019657075405121,
      "learning_rate": 0.00013345747516330873,
      "loss": 0.5855,
      "step": 223
    },
    {
      "epoch": 1.641025641025641,
      "grad_norm": 0.40215152502059937,
      "learning_rate": 0.0001322812077061638,
      "loss": 0.472,
      "step": 224
    },
    {
      "epoch": 1.6483516483516483,
      "grad_norm": 0.4318372309207916,
      "learning_rate": 0.0001311060442398424,
      "loss": 0.4597,
      "step": 225
    },
    {
      "epoch": 1.6556776556776556,
      "grad_norm": 0.39995384216308594,
      "learning_rate": 0.00012993205798432814,
      "loss": 0.4269,
      "step": 226
    },
    {
      "epoch": 1.6630036630036629,
      "grad_norm": 0.44160038232803345,
      "learning_rate": 0.0001287593220862573,
      "loss": 0.495,
      "step": 227
    },
    {
      "epoch": 1.6703296703296702,
      "grad_norm": 0.4725303649902344,
      "learning_rate": 0.00012758790961436083,
      "loss": 0.4705,
      "step": 228
    },
    {
      "epoch": 1.6776556776556777,
      "grad_norm": 0.7378038763999939,
      "learning_rate": 0.0001264178935549124,
      "loss": 0.4881,
      "step": 229
    },
    {
      "epoch": 1.684981684981685,
      "grad_norm": 0.5113095045089722,
      "learning_rate": 0.0001252493468071801,
      "loss": 0.4921,
      "step": 230
    },
    {
      "epoch": 1.6923076923076923,
      "grad_norm": 0.5403740406036377,
      "learning_rate": 0.00012408234217888508,
      "loss": 0.4288,
      "step": 231
    },
    {
      "epoch": 1.6996336996336996,
      "grad_norm": 0.5715883374214172,
      "learning_rate": 0.0001229169523816647,
      "loss": 0.3966,
      "step": 232
    },
    {
      "epoch": 1.7069597069597071,
      "grad_norm": 0.6109308004379272,
      "learning_rate": 0.00012175325002654229,
      "loss": 0.4353,
      "step": 233
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.5063544511795044,
      "learning_rate": 0.00012059130761940328,
      "loss": 0.3582,
      "step": 234
    },
    {
      "epoch": 1.7216117216117217,
      "grad_norm": 0.5469954609870911,
      "learning_rate": 0.00011943119755647719,
      "loss": 0.3257,
      "step": 235
    },
    {
      "epoch": 1.728937728937729,
      "grad_norm": 0.6388989686965942,
      "learning_rate": 0.00011827299211982714,
      "loss": 0.3494,
      "step": 236
    },
    {
      "epoch": 1.7362637362637363,
      "grad_norm": 0.6123701333999634,
      "learning_rate": 0.00011711676347284631,
      "loss": 0.2883,
      "step": 237
    },
    {
      "epoch": 1.7435897435897436,
      "grad_norm": 0.8964057564735413,
      "learning_rate": 0.00011596258365576144,
      "loss": 0.3418,
      "step": 238
    },
    {
      "epoch": 1.750915750915751,
      "grad_norm": 0.5625249147415161,
      "learning_rate": 0.0001148105245811447,
      "loss": 0.3956,
      "step": 239
    },
    {
      "epoch": 1.7582417582417582,
      "grad_norm": 0.3839769661426544,
      "learning_rate": 0.00011366065802943254,
      "loss": 0.5822,
      "step": 240
    },
    {
      "epoch": 1.7655677655677655,
      "grad_norm": 0.38849931955337524,
      "learning_rate": 0.00011251305564445375,
      "loss": 0.7068,
      "step": 241
    },
    {
      "epoch": 1.7728937728937728,
      "grad_norm": 0.3844453990459442,
      "learning_rate": 0.00011136778892896552,
      "loss": 0.5259,
      "step": 242
    },
    {
      "epoch": 1.7802197802197801,
      "grad_norm": 0.39755213260650635,
      "learning_rate": 0.00011022492924019817,
      "loss": 0.5587,
      "step": 243
    },
    {
      "epoch": 1.7875457875457874,
      "grad_norm": 0.4066022038459778,
      "learning_rate": 0.00010908454778540952,
      "loss": 0.5985,
      "step": 244
    },
    {
      "epoch": 1.7948717948717947,
      "grad_norm": 0.453279048204422,
      "learning_rate": 0.00010794671561744785,
      "loss": 0.6355,
      "step": 245
    },
    {
      "epoch": 1.8021978021978022,
      "grad_norm": 0.44758322834968567,
      "learning_rate": 0.00010681150363032503,
      "loss": 0.5131,
      "step": 246
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.39223358035087585,
      "learning_rate": 0.00010567898255479951,
      "loss": 0.5434,
      "step": 247
    },
    {
      "epoch": 1.8168498168498168,
      "grad_norm": 0.38072723150253296,
      "learning_rate": 0.00010454922295396907,
      "loss": 0.5052,
      "step": 248
    },
    {
      "epoch": 1.8241758241758241,
      "grad_norm": 0.3893994092941284,
      "learning_rate": 0.00010342229521887467,
      "loss": 0.5188,
      "step": 249
    },
    {
      "epoch": 1.8315018315018317,
      "grad_norm": 0.3957141041755676,
      "learning_rate": 0.00010229826956411426,
      "loss": 0.4949,
      "step": 250
    },
    {
      "epoch": 1.8315018315018317,
      "eval_loss": 0.5701812505722046,
      "eval_runtime": 73.3521,
      "eval_samples_per_second": 7.457,
      "eval_steps_per_second": 7.457,
      "step": 250
    },
    {
      "epoch": 1.838827838827839,
      "grad_norm": 0.3748125433921814,
      "learning_rate": 0.00010117721602346823,
      "loss": 0.482,
      "step": 251
    },
    {
      "epoch": 1.8461538461538463,
      "grad_norm": 0.35637104511260986,
      "learning_rate": 0.00010005920444553586,
      "loss": 0.4196,
      "step": 252
    },
    {
      "epoch": 1.8534798534798536,
      "grad_norm": 0.45035073161125183,
      "learning_rate": 9.894430448938305e-05,
      "loss": 0.5593,
      "step": 253
    },
    {
      "epoch": 1.8608058608058609,
      "grad_norm": 0.42238089442253113,
      "learning_rate": 9.783258562020263e-05,
      "loss": 0.4647,
      "step": 254
    },
    {
      "epoch": 1.8681318681318682,
      "grad_norm": 0.3975355625152588,
      "learning_rate": 9.672411710498575e-05,
      "loss": 0.5369,
      "step": 255
    },
    {
      "epoch": 1.8754578754578755,
      "grad_norm": 0.4017747640609741,
      "learning_rate": 9.561896800820633e-05,
      "loss": 0.4813,
      "step": 256
    },
    {
      "epoch": 1.8827838827838828,
      "grad_norm": 0.3966550827026367,
      "learning_rate": 9.4517207187518e-05,
      "loss": 0.425,
      "step": 257
    },
    {
      "epoch": 1.89010989010989,
      "grad_norm": 0.4850409924983978,
      "learning_rate": 9.341890328946358e-05,
      "loss": 0.6023,
      "step": 258
    },
    {
      "epoch": 1.8974358974358974,
      "grad_norm": 0.4538116753101349,
      "learning_rate": 9.23241247451984e-05,
      "loss": 0.4504,
      "step": 259
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.42693740129470825,
      "learning_rate": 9.123293976622602e-05,
      "loss": 0.4383,
      "step": 260
    },
    {
      "epoch": 1.912087912087912,
      "grad_norm": 0.529269814491272,
      "learning_rate": 9.014541634014885e-05,
      "loss": 0.5292,
      "step": 261
    },
    {
      "epoch": 1.9194139194139193,
      "grad_norm": 0.520923912525177,
      "learning_rate": 8.906162222643167e-05,
      "loss": 0.5155,
      "step": 262
    },
    {
      "epoch": 1.9267399267399268,
      "grad_norm": 0.47154876589775085,
      "learning_rate": 8.798162495217989e-05,
      "loss": 0.3989,
      "step": 263
    },
    {
      "epoch": 1.934065934065934,
      "grad_norm": 0.5603944659233093,
      "learning_rate": 8.690549180793239e-05,
      "loss": 0.4806,
      "step": 264
    },
    {
      "epoch": 1.9413919413919414,
      "grad_norm": 0.5125073194503784,
      "learning_rate": 8.583328984346854e-05,
      "loss": 0.4296,
      "step": 265
    },
    {
      "epoch": 1.9487179487179487,
      "grad_norm": 0.519232988357544,
      "learning_rate": 8.476508586363106e-05,
      "loss": 0.4025,
      "step": 266
    },
    {
      "epoch": 1.9560439560439562,
      "grad_norm": 0.5697182416915894,
      "learning_rate": 8.370094642416314e-05,
      "loss": 0.3478,
      "step": 267
    },
    {
      "epoch": 1.9633699633699635,
      "grad_norm": 0.516194760799408,
      "learning_rate": 8.264093782756195e-05,
      "loss": 0.3657,
      "step": 268
    },
    {
      "epoch": 1.9706959706959708,
      "grad_norm": 0.6397049427032471,
      "learning_rate": 8.158512611894759e-05,
      "loss": 0.4872,
      "step": 269
    },
    {
      "epoch": 1.978021978021978,
      "grad_norm": 0.6545494794845581,
      "learning_rate": 8.053357708194783e-05,
      "loss": 0.3736,
      "step": 270
    },
    {
      "epoch": 1.9853479853479854,
      "grad_norm": 0.6731343269348145,
      "learning_rate": 7.948635623459958e-05,
      "loss": 0.3911,
      "step": 271
    },
    {
      "epoch": 1.9926739926739927,
      "grad_norm": 0.8151178359985352,
      "learning_rate": 7.844352882526661e-05,
      "loss": 0.2981,
      "step": 272
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.9851661920547485,
      "learning_rate": 7.740515982857419e-05,
      "loss": 0.5828,
      "step": 273
    },
    {
      "epoch": 2.0073260073260073,
      "grad_norm": 0.26004815101623535,
      "learning_rate": 7.637131394136096e-05,
      "loss": 0.45,
      "step": 274
    },
    {
      "epoch": 2.0146520146520146,
      "grad_norm": 0.27779507637023926,
      "learning_rate": 7.534205557864752e-05,
      "loss": 0.5448,
      "step": 275
    },
    {
      "epoch": 2.021978021978022,
      "grad_norm": 0.31077465415000916,
      "learning_rate": 7.431744886962338e-05,
      "loss": 0.5772,
      "step": 276
    },
    {
      "epoch": 2.029304029304029,
      "grad_norm": 0.3218604326248169,
      "learning_rate": 7.329755765365101e-05,
      "loss": 0.4763,
      "step": 277
    },
    {
      "epoch": 2.0366300366300365,
      "grad_norm": 0.35660311579704285,
      "learning_rate": 7.228244547628837e-05,
      "loss": 0.5446,
      "step": 278
    },
    {
      "epoch": 2.043956043956044,
      "grad_norm": 0.369620680809021,
      "learning_rate": 7.127217558532974e-05,
      "loss": 0.5142,
      "step": 279
    },
    {
      "epoch": 2.051282051282051,
      "grad_norm": 0.374860942363739,
      "learning_rate": 7.02668109268648e-05,
      "loss": 0.4916,
      "step": 280
    },
    {
      "epoch": 2.0586080586080584,
      "grad_norm": 0.38749629259109497,
      "learning_rate": 6.926641414135674e-05,
      "loss": 0.4357,
      "step": 281
    },
    {
      "epoch": 2.065934065934066,
      "grad_norm": 0.405636191368103,
      "learning_rate": 6.827104755973947e-05,
      "loss": 0.4206,
      "step": 282
    },
    {
      "epoch": 2.0732600732600734,
      "grad_norm": 0.40589308738708496,
      "learning_rate": 6.728077319953388e-05,
      "loss": 0.4861,
      "step": 283
    },
    {
      "epoch": 2.0805860805860807,
      "grad_norm": 0.4325176775455475,
      "learning_rate": 6.629565276098398e-05,
      "loss": 0.4732,
      "step": 284
    },
    {
      "epoch": 2.087912087912088,
      "grad_norm": 0.4640852212905884,
      "learning_rate": 6.531574762321226e-05,
      "loss": 0.4558,
      "step": 285
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.43299245834350586,
      "learning_rate": 6.434111884039579e-05,
      "loss": 0.4278,
      "step": 286
    },
    {
      "epoch": 2.1025641025641026,
      "grad_norm": 0.4622572660446167,
      "learning_rate": 6.337182713796172e-05,
      "loss": 0.4749,
      "step": 287
    },
    {
      "epoch": 2.10989010989011,
      "grad_norm": 0.47975558042526245,
      "learning_rate": 6.240793290880404e-05,
      "loss": 0.3462,
      "step": 288
    },
    {
      "epoch": 2.1172161172161172,
      "grad_norm": 0.48463815450668335,
      "learning_rate": 6.144949620952074e-05,
      "loss": 0.4606,
      "step": 289
    },
    {
      "epoch": 2.1245421245421245,
      "grad_norm": 0.5988311767578125,
      "learning_rate": 6.049657675667161e-05,
      "loss": 0.3281,
      "step": 290
    },
    {
      "epoch": 2.131868131868132,
      "grad_norm": 0.43833500146865845,
      "learning_rate": 5.954923392305783e-05,
      "loss": 0.3536,
      "step": 291
    },
    {
      "epoch": 2.139194139194139,
      "grad_norm": 0.5085727572441101,
      "learning_rate": 5.860752673402253e-05,
      "loss": 0.3745,
      "step": 292
    },
    {
      "epoch": 2.1465201465201464,
      "grad_norm": 0.5323147177696228,
      "learning_rate": 5.767151386377313e-05,
      "loss": 0.4184,
      "step": 293
    },
    {
      "epoch": 2.1538461538461537,
      "grad_norm": 0.5333714485168457,
      "learning_rate": 5.6741253631725734e-05,
      "loss": 0.2953,
      "step": 294
    },
    {
      "epoch": 2.161172161172161,
      "grad_norm": 0.5652948021888733,
      "learning_rate": 5.581680399887123e-05,
      "loss": 0.3118,
      "step": 295
    },
    {
      "epoch": 2.1684981684981683,
      "grad_norm": 0.6583665609359741,
      "learning_rate": 5.4898222564164196e-05,
      "loss": 0.2828,
      "step": 296
    },
    {
      "epoch": 2.1758241758241756,
      "grad_norm": 0.603283703327179,
      "learning_rate": 5.398556656093393e-05,
      "loss": 0.31,
      "step": 297
    },
    {
      "epoch": 2.183150183150183,
      "grad_norm": 0.770128607749939,
      "learning_rate": 5.307889285331851e-05,
      "loss": 0.3279,
      "step": 298
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.6317210793495178,
      "learning_rate": 5.2178257932721996e-05,
      "loss": 0.3703,
      "step": 299
    },
    {
      "epoch": 2.197802197802198,
      "grad_norm": 0.6448614597320557,
      "learning_rate": 5.128371791429436e-05,
      "loss": 0.3123,
      "step": 300
    },
    {
      "epoch": 2.197802197802198,
      "eval_loss": 0.6170002222061157,
      "eval_runtime": 73.4287,
      "eval_samples_per_second": 7.449,
      "eval_steps_per_second": 7.449,
      "step": 300
    },
    {
      "epoch": 2.2051282051282053,
      "grad_norm": 0.599308431148529,
      "learning_rate": 5.039532853343533e-05,
      "loss": 0.249,
      "step": 301
    },
    {
      "epoch": 2.2124542124542126,
      "grad_norm": 0.7922989130020142,
      "learning_rate": 4.951314514232175e-05,
      "loss": 0.2308,
      "step": 302
    },
    {
      "epoch": 2.21978021978022,
      "grad_norm": 0.8403403162956238,
      "learning_rate": 4.863722270645869e-05,
      "loss": 0.2293,
      "step": 303
    },
    {
      "epoch": 2.227106227106227,
      "grad_norm": 0.8893972039222717,
      "learning_rate": 4.776761580125495e-05,
      "loss": 0.2041,
      "step": 304
    },
    {
      "epoch": 2.2344322344322345,
      "grad_norm": 0.6155855059623718,
      "learning_rate": 4.690437860862234e-05,
      "loss": 0.1374,
      "step": 305
    },
    {
      "epoch": 2.241758241758242,
      "grad_norm": 0.7354236245155334,
      "learning_rate": 4.6047564913600234e-05,
      "loss": 0.1482,
      "step": 306
    },
    {
      "epoch": 2.249084249084249,
      "grad_norm": 2.1080105304718018,
      "learning_rate": 4.519722810100403e-05,
      "loss": 0.1127,
      "step": 307
    },
    {
      "epoch": 2.2564102564102564,
      "grad_norm": 0.4302568733692169,
      "learning_rate": 4.435342115209916e-05,
      "loss": 0.5135,
      "step": 308
    },
    {
      "epoch": 2.2637362637362637,
      "grad_norm": 0.8538389205932617,
      "learning_rate": 4.35161966413001e-05,
      "loss": 0.6252,
      "step": 309
    },
    {
      "epoch": 2.271062271062271,
      "grad_norm": 0.7556006908416748,
      "learning_rate": 4.2685606732894316e-05,
      "loss": 0.4975,
      "step": 310
    },
    {
      "epoch": 2.2783882783882783,
      "grad_norm": 0.58868408203125,
      "learning_rate": 4.186170317779257e-05,
      "loss": 0.4612,
      "step": 311
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.7426422238349915,
      "learning_rate": 4.1044537310304135e-05,
      "loss": 0.458,
      "step": 312
    },
    {
      "epoch": 2.293040293040293,
      "grad_norm": 0.6092411279678345,
      "learning_rate": 4.023416004493849e-05,
      "loss": 0.5098,
      "step": 313
    },
    {
      "epoch": 2.3003663003663,
      "grad_norm": 0.6772862076759338,
      "learning_rate": 3.943062187323317e-05,
      "loss": 0.5537,
      "step": 314
    },
    {
      "epoch": 2.3076923076923075,
      "grad_norm": 0.5766953229904175,
      "learning_rate": 3.863397286060752e-05,
      "loss": 0.4449,
      "step": 315
    },
    {
      "epoch": 2.315018315018315,
      "grad_norm": 0.5632515549659729,
      "learning_rate": 3.784426264324364e-05,
      "loss": 0.4455,
      "step": 316
    },
    {
      "epoch": 2.3223443223443225,
      "grad_norm": 0.4638958275318146,
      "learning_rate": 3.7061540424993455e-05,
      "loss": 0.3575,
      "step": 317
    },
    {
      "epoch": 2.32967032967033,
      "grad_norm": 0.5185256004333496,
      "learning_rate": 3.628585497431319e-05,
      "loss": 0.4092,
      "step": 318
    },
    {
      "epoch": 2.336996336996337,
      "grad_norm": 0.4830188751220703,
      "learning_rate": 3.551725462122475e-05,
      "loss": 0.4283,
      "step": 319
    },
    {
      "epoch": 2.3443223443223444,
      "grad_norm": 0.5283904075622559,
      "learning_rate": 3.47557872543044e-05,
      "loss": 0.4279,
      "step": 320
    },
    {
      "epoch": 2.3516483516483517,
      "grad_norm": 0.48210349678993225,
      "learning_rate": 3.400150031769916e-05,
      "loss": 0.3868,
      "step": 321
    },
    {
      "epoch": 2.358974358974359,
      "grad_norm": 0.49750009179115295,
      "learning_rate": 3.325444080817054e-05,
      "loss": 0.4265,
      "step": 322
    },
    {
      "epoch": 2.3663003663003663,
      "grad_norm": 0.5228102803230286,
      "learning_rate": 3.251465527216644e-05,
      "loss": 0.3988,
      "step": 323
    },
    {
      "epoch": 2.3736263736263736,
      "grad_norm": 0.4787524938583374,
      "learning_rate": 3.178218980292116e-05,
      "loss": 0.4338,
      "step": 324
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.5247374773025513,
      "learning_rate": 3.1057090037583195e-05,
      "loss": 0.457,
      "step": 325
    },
    {
      "epoch": 2.3882783882783882,
      "grad_norm": 0.49824175238609314,
      "learning_rate": 3.03394011543721e-05,
      "loss": 0.3382,
      "step": 326
    },
    {
      "epoch": 2.3956043956043955,
      "grad_norm": 0.5834226012229919,
      "learning_rate": 2.9629167869763314e-05,
      "loss": 0.4105,
      "step": 327
    },
    {
      "epoch": 2.402930402930403,
      "grad_norm": 0.5177899599075317,
      "learning_rate": 2.8926434435702213e-05,
      "loss": 0.3676,
      "step": 328
    },
    {
      "epoch": 2.41025641025641,
      "grad_norm": 0.5421662926673889,
      "learning_rate": 2.823124463684692e-05,
      "loss": 0.3891,
      "step": 329
    },
    {
      "epoch": 2.4175824175824174,
      "grad_norm": 0.6656437516212463,
      "learning_rate": 2.7543641787840137e-05,
      "loss": 0.4003,
      "step": 330
    },
    {
      "epoch": 2.4249084249084247,
      "grad_norm": 0.5354308485984802,
      "learning_rate": 2.6863668730610628e-05,
      "loss": 0.334,
      "step": 331
    },
    {
      "epoch": 2.4322344322344325,
      "grad_norm": 0.5242961049079895,
      "learning_rate": 2.6191367831703597e-05,
      "loss": 0.3575,
      "step": 332
    },
    {
      "epoch": 2.4395604395604398,
      "grad_norm": 0.5668814182281494,
      "learning_rate": 2.5526780979641132e-05,
      "loss": 0.251,
      "step": 333
    },
    {
      "epoch": 2.446886446886447,
      "grad_norm": 0.6647098064422607,
      "learning_rate": 2.486994958231238e-05,
      "loss": 0.3012,
      "step": 334
    },
    {
      "epoch": 2.4542124542124544,
      "grad_norm": 0.590238630771637,
      "learning_rate": 2.422091456439338e-05,
      "loss": 0.2125,
      "step": 335
    },
    {
      "epoch": 2.4615384615384617,
      "grad_norm": 0.6544525027275085,
      "learning_rate": 2.3579716364797406e-05,
      "loss": 0.2345,
      "step": 336
    },
    {
      "epoch": 2.468864468864469,
      "grad_norm": 0.6543833017349243,
      "learning_rate": 2.294639493415517e-05,
      "loss": 0.2455,
      "step": 337
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.8714612126350403,
      "learning_rate": 2.2320989732325816e-05,
      "loss": 0.2462,
      "step": 338
    },
    {
      "epoch": 2.4835164835164836,
      "grad_norm": 0.8587841391563416,
      "learning_rate": 2.170353972593825e-05,
      "loss": 0.1519,
      "step": 339
    },
    {
      "epoch": 2.490842490842491,
      "grad_norm": 0.6549997329711914,
      "learning_rate": 2.1094083385963202e-05,
      "loss": 0.1206,
      "step": 340
    },
    {
      "epoch": 2.498168498168498,
      "grad_norm": 0.5828280448913574,
      "learning_rate": 2.049265868531651e-05,
      "loss": 0.0964,
      "step": 341
    },
    {
      "epoch": 2.5054945054945055,
      "grad_norm": 0.29954391717910767,
      "learning_rate": 1.989930309649282e-05,
      "loss": 0.4719,
      "step": 342
    },
    {
      "epoch": 2.5128205128205128,
      "grad_norm": 0.41014474630355835,
      "learning_rate": 1.9314053589231067e-05,
      "loss": 0.5926,
      "step": 343
    },
    {
      "epoch": 2.52014652014652,
      "grad_norm": 0.42200765013694763,
      "learning_rate": 1.873694662821096e-05,
      "loss": 0.5305,
      "step": 344
    },
    {
      "epoch": 2.5274725274725274,
      "grad_norm": 0.4672837257385254,
      "learning_rate": 1.816801817078093e-05,
      "loss": 0.5177,
      "step": 345
    },
    {
      "epoch": 2.5347985347985347,
      "grad_norm": 0.45549672842025757,
      "learning_rate": 1.760730366471796e-05,
      "loss": 0.4906,
      "step": 346
    },
    {
      "epoch": 2.542124542124542,
      "grad_norm": 0.42634275555610657,
      "learning_rate": 1.705483804601871e-05,
      "loss": 0.4466,
      "step": 347
    },
    {
      "epoch": 2.5494505494505493,
      "grad_norm": 0.5157731175422668,
      "learning_rate": 1.6510655736722967e-05,
      "loss": 0.5153,
      "step": 348
    },
    {
      "epoch": 2.5567765567765566,
      "grad_norm": 0.6015162467956543,
      "learning_rate": 1.5974790642768903e-05,
      "loss": 0.4401,
      "step": 349
    },
    {
      "epoch": 2.564102564102564,
      "grad_norm": 0.5981739163398743,
      "learning_rate": 1.5447276151880473e-05,
      "loss": 0.5157,
      "step": 350
    },
    {
      "epoch": 2.564102564102564,
      "eval_loss": 0.6206538081169128,
      "eval_runtime": 73.5137,
      "eval_samples_per_second": 7.441,
      "eval_steps_per_second": 7.441,
      "step": 350
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.5820057988166809,
      "learning_rate": 1.4928145131487267e-05,
      "loss": 0.4702,
      "step": 351
    },
    {
      "epoch": 2.578754578754579,
      "grad_norm": 0.5424510836601257,
      "learning_rate": 1.4417429926676482e-05,
      "loss": 0.4174,
      "step": 352
    },
    {
      "epoch": 2.586080586080586,
      "grad_norm": 0.6577489376068115,
      "learning_rate": 1.39151623581778e-05,
      "loss": 0.4169,
      "step": 353
    },
    {
      "epoch": 2.5934065934065935,
      "grad_norm": 0.5944687128067017,
      "learning_rate": 1.3421373720380669e-05,
      "loss": 0.4272,
      "step": 354
    },
    {
      "epoch": 2.600732600732601,
      "grad_norm": 0.7125936150550842,
      "learning_rate": 1.2936094779384486e-05,
      "loss": 0.4438,
      "step": 355
    },
    {
      "epoch": 2.608058608058608,
      "grad_norm": 0.679352879524231,
      "learning_rate": 1.245935577108168e-05,
      "loss": 0.4949,
      "step": 356
    },
    {
      "epoch": 2.6153846153846154,
      "grad_norm": 1.0750776529312134,
      "learning_rate": 1.199118639927385e-05,
      "loss": 0.3986,
      "step": 357
    },
    {
      "epoch": 2.6227106227106227,
      "grad_norm": 0.8349664211273193,
      "learning_rate": 1.1531615833820906e-05,
      "loss": 0.4152,
      "step": 358
    },
    {
      "epoch": 2.63003663003663,
      "grad_norm": 0.770355761051178,
      "learning_rate": 1.108067270882384e-05,
      "loss": 0.4878,
      "step": 359
    },
    {
      "epoch": 2.6373626373626373,
      "grad_norm": 0.7165803909301758,
      "learning_rate": 1.0638385120840414e-05,
      "loss": 0.3852,
      "step": 360
    },
    {
      "epoch": 2.6446886446886446,
      "grad_norm": 0.7379334568977356,
      "learning_rate": 1.0204780627134784e-05,
      "loss": 0.4758,
      "step": 361
    },
    {
      "epoch": 2.652014652014652,
      "grad_norm": 0.6477860808372498,
      "learning_rate": 9.77988624396025e-06,
      "loss": 0.3718,
      "step": 362
    },
    {
      "epoch": 2.659340659340659,
      "grad_norm": 0.6215366721153259,
      "learning_rate": 9.363728444876239e-06,
      "loss": 0.3146,
      "step": 363
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.7191038727760315,
      "learning_rate": 8.956333159098677e-06,
      "loss": 0.2567,
      "step": 364
    },
    {
      "epoch": 2.6739926739926743,
      "grad_norm": 0.6438663005828857,
      "learning_rate": 8.557725769884444e-06,
      "loss": 0.3366,
      "step": 365
    },
    {
      "epoch": 2.6813186813186816,
      "grad_norm": 0.7834159135818481,
      "learning_rate": 8.167931112949955e-06,
      "loss": 0.2802,
      "step": 366
    },
    {
      "epoch": 2.688644688644689,
      "grad_norm": 0.687300443649292,
      "learning_rate": 7.786973474923569e-06,
      "loss": 0.3275,
      "step": 367
    },
    {
      "epoch": 2.695970695970696,
      "grad_norm": 0.633350133895874,
      "learning_rate": 7.41487659183258e-06,
      "loss": 0.2462,
      "step": 368
    },
    {
      "epoch": 2.7032967032967035,
      "grad_norm": 0.8299592137336731,
      "learning_rate": 7.051663647624117e-06,
      "loss": 0.2847,
      "step": 369
    },
    {
      "epoch": 2.7106227106227108,
      "grad_norm": 0.6400296688079834,
      "learning_rate": 6.697357272720782e-06,
      "loss": 0.239,
      "step": 370
    },
    {
      "epoch": 2.717948717948718,
      "grad_norm": 0.620663583278656,
      "learning_rate": 6.35197954261058e-06,
      "loss": 0.183,
      "step": 371
    },
    {
      "epoch": 2.7252747252747254,
      "grad_norm": 0.7446674108505249,
      "learning_rate": 6.015551976471433e-06,
      "loss": 0.2334,
      "step": 372
    },
    {
      "epoch": 2.7326007326007327,
      "grad_norm": 0.8476528525352478,
      "learning_rate": 5.688095535830573e-06,
      "loss": 0.1747,
      "step": 373
    },
    {
      "epoch": 2.73992673992674,
      "grad_norm": 0.8313474655151367,
      "learning_rate": 5.369630623258248e-06,
      "loss": 0.189,
      "step": 374
    },
    {
      "epoch": 2.7472527472527473,
      "grad_norm": 0.9323949217796326,
      "learning_rate": 5.060177081096728e-06,
      "loss": 0.0911,
      "step": 375
    },
    {
      "epoch": 2.7545787545787546,
      "grad_norm": 0.33731380105018616,
      "learning_rate": 4.759754190223925e-06,
      "loss": 0.4471,
      "step": 376
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.37849536538124084,
      "learning_rate": 4.468380668852068e-06,
      "loss": 0.6115,
      "step": 377
    },
    {
      "epoch": 2.769230769230769,
      "grad_norm": 0.4009314775466919,
      "learning_rate": 4.186074671361456e-06,
      "loss": 0.575,
      "step": 378
    },
    {
      "epoch": 2.7765567765567765,
      "grad_norm": 0.3839149475097656,
      "learning_rate": 3.912853787169345e-06,
      "loss": 0.5056,
      "step": 379
    },
    {
      "epoch": 2.7838827838827838,
      "grad_norm": 0.40725114941596985,
      "learning_rate": 3.6487350396339597e-06,
      "loss": 0.4408,
      "step": 380
    },
    {
      "epoch": 2.791208791208791,
      "grad_norm": 0.4696556329727173,
      "learning_rate": 3.3937348849939204e-06,
      "loss": 0.5321,
      "step": 381
    },
    {
      "epoch": 2.7985347985347984,
      "grad_norm": 0.43771475553512573,
      "learning_rate": 3.147869211342818e-06,
      "loss": 0.4356,
      "step": 382
    },
    {
      "epoch": 2.8058608058608057,
      "grad_norm": 0.5101984739303589,
      "learning_rate": 2.911153337639388e-06,
      "loss": 0.4499,
      "step": 383
    },
    {
      "epoch": 2.813186813186813,
      "grad_norm": 0.5081220865249634,
      "learning_rate": 2.683602012752939e-06,
      "loss": 0.4756,
      "step": 384
    },
    {
      "epoch": 2.8205128205128203,
      "grad_norm": 0.5413169264793396,
      "learning_rate": 2.4652294145445226e-06,
      "loss": 0.4866,
      "step": 385
    },
    {
      "epoch": 2.8278388278388276,
      "grad_norm": 0.5008475184440613,
      "learning_rate": 2.256049148983441e-06,
      "loss": 0.4641,
      "step": 386
    },
    {
      "epoch": 2.8351648351648353,
      "grad_norm": 0.5848665833473206,
      "learning_rate": 2.0560742492995885e-06,
      "loss": 0.4572,
      "step": 387
    },
    {
      "epoch": 2.8424908424908426,
      "grad_norm": 0.6183776259422302,
      "learning_rate": 1.8653171751714379e-06,
      "loss": 0.5198,
      "step": 388
    },
    {
      "epoch": 2.84981684981685,
      "grad_norm": 0.5888795852661133,
      "learning_rate": 1.6837898119496263e-06,
      "loss": 0.451,
      "step": 389
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.5763834118843079,
      "learning_rate": 1.5115034699164308e-06,
      "loss": 0.4926,
      "step": 390
    },
    {
      "epoch": 2.8644688644688645,
      "grad_norm": 0.6053770184516907,
      "learning_rate": 1.348468883581183e-06,
      "loss": 0.443,
      "step": 391
    },
    {
      "epoch": 2.871794871794872,
      "grad_norm": 0.5707501769065857,
      "learning_rate": 1.19469621101132e-06,
      "loss": 0.4184,
      "step": 392
    },
    {
      "epoch": 2.879120879120879,
      "grad_norm": 0.5886608958244324,
      "learning_rate": 1.0501950331995578e-06,
      "loss": 0.4002,
      "step": 393
    },
    {
      "epoch": 2.8864468864468864,
      "grad_norm": 0.5797408223152161,
      "learning_rate": 9.149743534668353e-07,
      "loss": 0.4117,
      "step": 394
    },
    {
      "epoch": 2.8937728937728937,
      "grad_norm": 0.7185364961624146,
      "learning_rate": 7.890425969014625e-07,
      "loss": 0.4059,
      "step": 395
    },
    {
      "epoch": 2.901098901098901,
      "grad_norm": 0.7297194004058838,
      "learning_rate": 6.724076098341247e-07,
      "loss": 0.3407,
      "step": 396
    },
    {
      "epoch": 2.9084249084249083,
      "grad_norm": 0.6948420405387878,
      "learning_rate": 5.650766593489897e-07,
      "loss": 0.3564,
      "step": 397
    },
    {
      "epoch": 2.9157509157509156,
      "grad_norm": 0.6854040026664734,
      "learning_rate": 4.6705643283102003e-07,
      "loss": 0.4018,
      "step": 398
    },
    {
      "epoch": 2.9230769230769234,
      "grad_norm": 0.7185117602348328,
      "learning_rate": 3.7835303754918943e-07,
      "loss": 0.3607,
      "step": 399
    },
    {
      "epoch": 2.9304029304029307,
      "grad_norm": 0.6749255061149597,
      "learning_rate": 2.9897200027598767e-07,
      "loss": 0.276,
      "step": 400
    },
    {
      "epoch": 2.9304029304029307,
      "eval_loss": 0.60358726978302,
      "eval_runtime": 73.527,
      "eval_samples_per_second": 7.439,
      "eval_steps_per_second": 7.439,
      "step": 400
    }
  ],
  "logging_steps": 1,
  "max_steps": 408,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 50,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 3
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5.659682780951347e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}