{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.9820359281437125,
  "eval_steps": 500,
  "global_step": 166,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.011976047904191617,
      "grad_norm": 2.5615657136716083,
      "learning_rate": 1e-06,
      "loss": 2.3086,
      "step": 1
    },
    {
      "epoch": 0.023952095808383235,
      "grad_norm": 2.5773761069534853,
      "learning_rate": 1e-06,
      "loss": 2.3322,
      "step": 2
    },
    {
      "epoch": 0.03592814371257485,
      "grad_norm": 2.5489911065299875,
      "learning_rate": 1e-06,
      "loss": 2.3189,
      "step": 3
    },
    {
      "epoch": 0.04790419161676647,
      "grad_norm": 2.5641980239668305,
      "learning_rate": 1e-06,
      "loss": 2.3221,
      "step": 4
    },
    {
      "epoch": 0.059880239520958084,
      "grad_norm": 2.495418092335473,
      "learning_rate": 1e-06,
      "loss": 2.3203,
      "step": 5
    },
    {
      "epoch": 0.0718562874251497,
      "grad_norm": 2.5165101811100494,
      "learning_rate": 1e-06,
      "loss": 2.3189,
      "step": 6
    },
    {
      "epoch": 0.08383233532934131,
      "grad_norm": 2.504162196802967,
      "learning_rate": 1e-06,
      "loss": 2.314,
      "step": 7
    },
    {
      "epoch": 0.09580838323353294,
      "grad_norm": 2.4814364171413796,
      "learning_rate": 1e-06,
      "loss": 2.3104,
      "step": 8
    },
    {
      "epoch": 0.10778443113772455,
      "grad_norm": 2.3774878160101096,
      "learning_rate": 1e-06,
      "loss": 2.3067,
      "step": 9
    },
    {
      "epoch": 0.11976047904191617,
      "grad_norm": 2.3475602586392705,
      "learning_rate": 1e-06,
      "loss": 2.3168,
      "step": 10
    },
    {
      "epoch": 0.1317365269461078,
      "grad_norm": 2.333993760427704,
      "learning_rate": 1e-06,
      "loss": 2.322,
      "step": 11
    },
    {
      "epoch": 0.1437125748502994,
      "grad_norm": 2.316543273634108,
      "learning_rate": 1e-06,
      "loss": 2.321,
      "step": 12
    },
    {
      "epoch": 0.15568862275449102,
      "grad_norm": 2.302388927121058,
      "learning_rate": 1e-06,
      "loss": 2.312,
      "step": 13
    },
    {
      "epoch": 0.16766467065868262,
      "grad_norm": 2.2987978050220024,
      "learning_rate": 1e-06,
      "loss": 2.303,
      "step": 14
    },
    {
      "epoch": 0.17964071856287425,
      "grad_norm": 2.2639488675683603,
      "learning_rate": 1e-06,
      "loss": 2.3105,
      "step": 15
    },
    {
      "epoch": 0.19161676646706588,
      "grad_norm": 2.261718181341385,
      "learning_rate": 1e-06,
      "loss": 2.2994,
      "step": 16
    },
    {
      "epoch": 0.20359281437125748,
      "grad_norm": 1.8660446500221628,
      "learning_rate": 1e-06,
      "loss": 2.3085,
      "step": 17
    },
    {
      "epoch": 0.2155688622754491,
      "grad_norm": 1.8596074219892773,
      "learning_rate": 1e-06,
      "loss": 2.3006,
      "step": 18
    },
    {
      "epoch": 0.2275449101796407,
      "grad_norm": 1.8643371283543244,
      "learning_rate": 1e-06,
      "loss": 2.2872,
      "step": 19
    },
    {
      "epoch": 0.23952095808383234,
      "grad_norm": 1.8534509057908637,
      "learning_rate": 1e-06,
      "loss": 2.3008,
      "step": 20
    },
    {
      "epoch": 0.25149700598802394,
      "grad_norm": 1.8138301856421146,
      "learning_rate": 1e-06,
      "loss": 2.2948,
      "step": 21
    },
    {
      "epoch": 0.2634730538922156,
      "grad_norm": 1.81412136269699,
      "learning_rate": 1e-06,
      "loss": 2.2899,
      "step": 22
    },
    {
      "epoch": 0.2754491017964072,
      "grad_norm": 1.821596307651106,
      "learning_rate": 1e-06,
      "loss": 2.2967,
      "step": 23
    },
    {
      "epoch": 0.2874251497005988,
      "grad_norm": 1.8118117090950443,
      "learning_rate": 1e-06,
      "loss": 2.2969,
      "step": 24
    },
    {
      "epoch": 0.2994011976047904,
      "grad_norm": 1.780362304046831,
      "learning_rate": 1e-06,
      "loss": 2.3023,
      "step": 25
    },
    {
      "epoch": 0.31137724550898205,
      "grad_norm": 1.747692085337293,
      "learning_rate": 1e-06,
      "loss": 2.2952,
      "step": 26
    },
    {
      "epoch": 0.32335329341317365,
      "grad_norm": 1.7383178165500712,
      "learning_rate": 1e-06,
      "loss": 2.286,
      "step": 27
    },
    {
      "epoch": 0.33532934131736525,
      "grad_norm": 1.7694584322479294,
      "learning_rate": 1e-06,
      "loss": 2.2964,
      "step": 28
    },
    {
      "epoch": 0.3473053892215569,
      "grad_norm": 1.7307827415862227,
      "learning_rate": 1e-06,
      "loss": 2.2871,
      "step": 29
    },
    {
      "epoch": 0.3592814371257485,
      "grad_norm": 1.7756077058372248,
      "learning_rate": 1e-06,
      "loss": 2.3018,
      "step": 30
    },
    {
      "epoch": 0.3712574850299401,
      "grad_norm": 1.6569877610122026,
      "learning_rate": 1e-06,
      "loss": 2.2784,
      "step": 31
    },
    {
      "epoch": 0.38323353293413176,
      "grad_norm": 1.4051537618421257,
      "learning_rate": 1e-06,
      "loss": 2.2764,
      "step": 32
    },
    {
      "epoch": 0.39520958083832336,
      "grad_norm": 1.2745401979535236,
      "learning_rate": 1e-06,
      "loss": 2.2706,
      "step": 33
    },
    {
      "epoch": 0.40718562874251496,
      "grad_norm": 1.2299996626422867,
      "learning_rate": 1e-06,
      "loss": 2.2593,
      "step": 34
    },
    {
      "epoch": 0.41916167664670656,
      "grad_norm": 1.2580507659520745,
      "learning_rate": 1e-06,
      "loss": 2.2705,
      "step": 35
    },
    {
      "epoch": 0.4311377245508982,
      "grad_norm": 1.2481843435811928,
      "learning_rate": 1e-06,
      "loss": 2.2708,
      "step": 36
    },
    {
      "epoch": 0.4431137724550898,
      "grad_norm": 1.2626123054128822,
      "learning_rate": 1e-06,
      "loss": 2.2636,
      "step": 37
    },
    {
      "epoch": 0.4550898203592814,
      "grad_norm": 1.2419949588465158,
      "learning_rate": 1e-06,
      "loss": 2.2593,
      "step": 38
    },
    {
      "epoch": 0.46706586826347307,
      "grad_norm": 1.244572241926842,
      "learning_rate": 1e-06,
      "loss": 2.2531,
      "step": 39
    },
    {
      "epoch": 0.47904191616766467,
      "grad_norm": 1.2345334641611154,
      "learning_rate": 1e-06,
      "loss": 2.2651,
      "step": 40
    },
    {
      "epoch": 0.49101796407185627,
      "grad_norm": 1.2179094002836452,
      "learning_rate": 1e-06,
      "loss": 2.2721,
      "step": 41
    },
    {
      "epoch": 0.5029940119760479,
      "grad_norm": 1.2027541000732906,
      "learning_rate": 1e-06,
      "loss": 2.2568,
      "step": 42
    },
    {
      "epoch": 0.5149700598802395,
      "grad_norm": 1.209440540437922,
      "learning_rate": 1e-06,
      "loss": 2.2504,
      "step": 43
    },
    {
      "epoch": 0.5269461077844312,
      "grad_norm": 1.2156193632106038,
      "learning_rate": 1e-06,
      "loss": 2.2611,
      "step": 44
    },
    {
      "epoch": 0.5389221556886228,
      "grad_norm": 1.1809317447027605,
      "learning_rate": 1e-06,
      "loss": 2.2637,
      "step": 45
    },
    {
      "epoch": 0.5508982035928144,
      "grad_norm": 1.1826529774139363,
      "learning_rate": 1e-06,
      "loss": 2.2536,
      "step": 46
    },
    {
      "epoch": 0.562874251497006,
      "grad_norm": 1.173882364883566,
      "learning_rate": 1e-06,
      "loss": 2.2543,
      "step": 47
    },
    {
      "epoch": 0.5748502994011976,
      "grad_norm": 1.1473458364746005,
      "learning_rate": 1e-06,
      "loss": 2.252,
      "step": 48
    },
    {
      "epoch": 0.5868263473053892,
      "grad_norm": 1.1551199243421189,
      "learning_rate": 1e-06,
      "loss": 2.2604,
      "step": 49
    },
    {
      "epoch": 0.5988023952095808,
      "grad_norm": 1.1520053185511139,
      "learning_rate": 1e-06,
      "loss": 2.2571,
      "step": 50
    },
    {
      "epoch": 0.6107784431137725,
      "grad_norm": 1.1237813312947265,
      "learning_rate": 1e-06,
      "loss": 2.247,
      "step": 51
    },
    {
      "epoch": 0.6227544910179641,
      "grad_norm": 1.1322867564382475,
      "learning_rate": 1e-06,
      "loss": 2.2607,
      "step": 52
    },
    {
      "epoch": 0.6347305389221557,
      "grad_norm": 1.1241702784408114,
      "learning_rate": 1e-06,
      "loss": 2.2461,
      "step": 53
    },
    {
      "epoch": 0.6467065868263473,
      "grad_norm": 1.1030714149741052,
      "learning_rate": 1e-06,
      "loss": 2.2569,
      "step": 54
    },
    {
      "epoch": 0.6586826347305389,
      "grad_norm": 1.1147423461510102,
      "learning_rate": 1e-06,
      "loss": 2.2419,
      "step": 55
    },
    {
      "epoch": 0.6706586826347305,
      "grad_norm": 1.0729801001524597,
      "learning_rate": 1e-06,
      "loss": 2.2511,
      "step": 56
    },
    {
      "epoch": 0.6826347305389222,
      "grad_norm": 1.0438039117359488,
      "learning_rate": 1e-06,
      "loss": 2.2388,
      "step": 57
    },
    {
      "epoch": 0.6946107784431138,
      "grad_norm": 0.9763927603089774,
      "learning_rate": 1e-06,
      "loss": 2.2307,
      "step": 58
    },
    {
      "epoch": 0.7065868263473054,
      "grad_norm": 0.9164962634656145,
      "learning_rate": 1e-06,
      "loss": 2.227,
      "step": 59
    },
    {
      "epoch": 0.718562874251497,
      "grad_norm": 0.848311700014838,
      "learning_rate": 1e-06,
      "loss": 2.2153,
      "step": 60
    },
    {
      "epoch": 0.7305389221556886,
      "grad_norm": 0.7776204108137212,
      "learning_rate": 1e-06,
      "loss": 2.2227,
      "step": 61
    },
    {
      "epoch": 0.7425149700598802,
      "grad_norm": 0.7319953234131772,
      "learning_rate": 1e-06,
      "loss": 2.2182,
      "step": 62
    },
    {
      "epoch": 0.7544910179640718,
      "grad_norm": 0.6909482211546656,
      "learning_rate": 1e-06,
      "loss": 2.2145,
      "step": 63
    },
    {
      "epoch": 0.7664670658682635,
      "grad_norm": 0.6738176870137997,
      "learning_rate": 1e-06,
      "loss": 2.2083,
      "step": 64
    },
    {
      "epoch": 0.7784431137724551,
      "grad_norm": 0.6464473261385877,
      "learning_rate": 1e-06,
      "loss": 2.2032,
      "step": 65
    },
    {
      "epoch": 0.7904191616766467,
      "grad_norm": 0.626337164367754,
      "learning_rate": 1e-06,
      "loss": 2.2189,
      "step": 66
    },
    {
      "epoch": 0.8023952095808383,
      "grad_norm": 0.6207173763836306,
      "learning_rate": 1e-06,
      "loss": 2.2093,
      "step": 67
    },
    {
      "epoch": 0.8143712574850299,
      "grad_norm": 0.6168240564884324,
      "learning_rate": 1e-06,
      "loss": 2.2067,
      "step": 68
    },
    {
      "epoch": 0.8263473053892215,
      "grad_norm": 0.6148534111975588,
      "learning_rate": 1e-06,
      "loss": 2.2146,
      "step": 69
    },
    {
      "epoch": 0.8383233532934131,
      "grad_norm": 0.611544755836136,
      "learning_rate": 1e-06,
      "loss": 2.2055,
      "step": 70
    },
    {
      "epoch": 0.8502994011976048,
      "grad_norm": 0.611863129737121,
      "learning_rate": 1e-06,
      "loss": 2.2144,
      "step": 71
    },
    {
      "epoch": 0.8622754491017964,
      "grad_norm": 0.6028090268614178,
      "learning_rate": 1e-06,
      "loss": 2.209,
      "step": 72
    },
    {
      "epoch": 0.874251497005988,
      "grad_norm": 0.6091038720653699,
      "learning_rate": 1e-06,
      "loss": 2.2048,
      "step": 73
    },
    {
      "epoch": 0.8862275449101796,
      "grad_norm": 0.5937914977596926,
      "learning_rate": 1e-06,
      "loss": 2.2108,
      "step": 74
    },
    {
      "epoch": 0.8982035928143712,
      "grad_norm": 0.595528112324968,
      "learning_rate": 1e-06,
      "loss": 2.2022,
      "step": 75
    },
    {
      "epoch": 0.9101796407185628,
      "grad_norm": 0.5883119960964677,
      "learning_rate": 1e-06,
      "loss": 2.2084,
      "step": 76
    },
    {
      "epoch": 0.9221556886227545,
      "grad_norm": 0.5773396259001046,
      "learning_rate": 1e-06,
      "loss": 2.2036,
      "step": 77
    },
    {
      "epoch": 0.9341317365269461,
      "grad_norm": 0.5734709642037124,
      "learning_rate": 1e-06,
      "loss": 2.2052,
      "step": 78
    },
    {
      "epoch": 0.9461077844311377,
      "grad_norm": 0.5591056938189867,
      "learning_rate": 1e-06,
      "loss": 2.2089,
      "step": 79
    },
    {
      "epoch": 0.9580838323353293,
      "grad_norm": 0.546274882638652,
      "learning_rate": 1e-06,
      "loss": 2.1942,
      "step": 80
    },
    {
      "epoch": 0.9700598802395209,
      "grad_norm": 0.5480518878076608,
      "learning_rate": 1e-06,
      "loss": 2.2069,
      "step": 81
    },
    {
      "epoch": 0.9820359281437125,
      "grad_norm": 0.5463287286169074,
      "learning_rate": 1e-06,
      "loss": 2.1974,
      "step": 82
    },
    {
      "epoch": 0.9940119760479041,
      "grad_norm": 0.533820388108904,
      "learning_rate": 1e-06,
      "loss": 2.199,
      "step": 83
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.533820388108904,
      "learning_rate": 1e-06,
      "loss": 2.2047,
      "step": 84
    },
    {
      "epoch": 1.0119760479041917,
      "grad_norm": 0.8062312296444792,
      "learning_rate": 1e-06,
      "loss": 2.1951,
      "step": 85
    },
    {
      "epoch": 1.0239520958083832,
      "grad_norm": 0.5284897388941314,
      "learning_rate": 1e-06,
      "loss": 2.193,
      "step": 86
    },
    {
      "epoch": 1.035928143712575,
      "grad_norm": 0.5229421018335979,
      "learning_rate": 1e-06,
      "loss": 2.1932,
      "step": 87
    },
    {
      "epoch": 1.0479041916167664,
      "grad_norm": 0.5133887468703301,
      "learning_rate": 1e-06,
      "loss": 2.1943,
      "step": 88
    },
    {
      "epoch": 1.0598802395209581,
      "grad_norm": 0.5171326387183323,
      "learning_rate": 1e-06,
      "loss": 2.2006,
      "step": 89
    },
    {
      "epoch": 1.0718562874251496,
      "grad_norm": 0.51794405572636,
      "learning_rate": 1e-06,
      "loss": 2.1955,
      "step": 90
    },
    {
      "epoch": 1.0838323353293413,
      "grad_norm": 0.499854985040916,
      "learning_rate": 1e-06,
      "loss": 2.2038,
      "step": 91
    },
    {
      "epoch": 1.095808383233533,
      "grad_norm": 0.507043821717436,
      "learning_rate": 1e-06,
      "loss": 2.1898,
      "step": 92
    },
    {
      "epoch": 1.1077844311377245,
      "grad_norm": 0.49951015907518004,
      "learning_rate": 1e-06,
      "loss": 2.1974,
      "step": 93
    },
    {
      "epoch": 1.1197604790419162,
      "grad_norm": 0.48701630934015266,
      "learning_rate": 1e-06,
      "loss": 2.19,
      "step": 94
    },
    {
      "epoch": 1.1317365269461077,
      "grad_norm": 0.5023244374647904,
      "learning_rate": 1e-06,
      "loss": 2.1901,
      "step": 95
    },
    {
      "epoch": 1.1437125748502994,
      "grad_norm": 0.4893947097377309,
      "learning_rate": 1e-06,
      "loss": 2.1959,
      "step": 96
    },
    {
      "epoch": 1.1556886227544911,
      "grad_norm": 0.4921551531091861,
      "learning_rate": 1e-06,
      "loss": 2.1856,
      "step": 97
    },
    {
      "epoch": 1.1676646706586826,
      "grad_norm": 0.4775299084079388,
      "learning_rate": 1e-06,
      "loss": 2.1946,
      "step": 98
    },
    {
      "epoch": 1.1796407185628743,
      "grad_norm": 0.47443238852305514,
      "learning_rate": 1e-06,
      "loss": 2.1829,
      "step": 99
    },
    {
      "epoch": 1.1916167664670658,
      "grad_norm": 0.4738686464339643,
      "learning_rate": 1e-06,
      "loss": 2.1882,
      "step": 100
    },
    {
      "epoch": 1.2035928143712575,
      "grad_norm": 0.47247955693487775,
      "learning_rate": 1e-06,
      "loss": 2.1789,
      "step": 101
    },
    {
      "epoch": 1.215568862275449,
      "grad_norm": 0.48664618836275864,
      "learning_rate": 1e-06,
      "loss": 2.1901,
      "step": 102
    },
    {
      "epoch": 1.2275449101796407,
      "grad_norm": 0.624671707718351,
      "learning_rate": 1e-06,
      "loss": 2.1786,
      "step": 103
    },
    {
      "epoch": 1.2395209580838324,
      "grad_norm": 0.47270583079574985,
      "learning_rate": 1e-06,
      "loss": 2.1815,
      "step": 104
    },
    {
      "epoch": 1.251497005988024,
      "grad_norm": 0.4850659145115984,
      "learning_rate": 1e-06,
      "loss": 2.1766,
      "step": 105
    },
    {
      "epoch": 1.2634730538922156,
      "grad_norm": 0.4774338329878164,
      "learning_rate": 1e-06,
      "loss": 2.1798,
      "step": 106
    },
    {
      "epoch": 1.2754491017964071,
      "grad_norm": 0.4703506888310317,
      "learning_rate": 1e-06,
      "loss": 2.1784,
      "step": 107
    },
    {
      "epoch": 1.2874251497005988,
      "grad_norm": 0.4518841904928292,
      "learning_rate": 1e-06,
      "loss": 2.1739,
      "step": 108
    },
    {
      "epoch": 1.2994011976047903,
      "grad_norm": 0.43979454708832033,
      "learning_rate": 1e-06,
      "loss": 2.1723,
      "step": 109
    },
    {
      "epoch": 1.311377245508982,
      "grad_norm": 0.42560783774660166,
      "learning_rate": 1e-06,
      "loss": 2.1654,
      "step": 110
    },
    {
      "epoch": 1.3233532934131738,
      "grad_norm": 0.4266096810118197,
      "learning_rate": 1e-06,
      "loss": 2.1714,
      "step": 111
    },
    {
      "epoch": 1.3353293413173652,
      "grad_norm": 0.42819974246838616,
      "learning_rate": 1e-06,
      "loss": 2.172,
      "step": 112
    },
    {
      "epoch": 1.347305389221557,
      "grad_norm": 0.4339005043697042,
      "learning_rate": 1e-06,
      "loss": 2.1701,
      "step": 113
    },
    {
      "epoch": 1.3592814371257484,
      "grad_norm": 0.41711410890047346,
      "learning_rate": 1e-06,
      "loss": 2.1516,
      "step": 114
    },
    {
      "epoch": 1.3712574850299402,
      "grad_norm": 0.4161851963765622,
      "learning_rate": 1e-06,
      "loss": 2.1695,
      "step": 115
    },
    {
      "epoch": 1.3832335329341316,
      "grad_norm": 0.42232760575717626,
      "learning_rate": 1e-06,
      "loss": 2.1619,
      "step": 116
    },
    {
      "epoch": 1.3952095808383234,
      "grad_norm": 0.4108856947054096,
      "learning_rate": 1e-06,
      "loss": 2.1709,
      "step": 117
    },
    {
      "epoch": 1.407185628742515,
      "grad_norm": 0.4063084876440514,
      "learning_rate": 1e-06,
      "loss": 2.1659,
      "step": 118
    },
    {
      "epoch": 1.4191616766467066,
      "grad_norm": 0.39591659891238995,
      "learning_rate": 1e-06,
      "loss": 2.1682,
      "step": 119
    },
    {
      "epoch": 1.4311377245508983,
      "grad_norm": 0.3858440857290615,
      "learning_rate": 1e-06,
      "loss": 2.1664,
      "step": 120
    },
    {
      "epoch": 1.4431137724550898,
      "grad_norm": 0.39406408386479896,
      "learning_rate": 1e-06,
      "loss": 2.1545,
      "step": 121
    },
    {
      "epoch": 1.4550898203592815,
      "grad_norm": 0.3822517420137481,
      "learning_rate": 1e-06,
      "loss": 2.1645,
      "step": 122
    },
    {
      "epoch": 1.467065868263473,
      "grad_norm": 0.37432990540151057,
      "learning_rate": 1e-06,
      "loss": 2.1533,
      "step": 123
    },
    {
      "epoch": 1.4790419161676647,
      "grad_norm": 0.35952783539679156,
      "learning_rate": 1e-06,
      "loss": 2.1602,
      "step": 124
    },
    {
      "epoch": 1.4910179640718564,
      "grad_norm": 0.349483918037425,
      "learning_rate": 1e-06,
      "loss": 2.1629,
      "step": 125
    },
    {
      "epoch": 1.5029940119760479,
      "grad_norm": 0.3490604286181681,
      "learning_rate": 1e-06,
      "loss": 2.1552,
      "step": 126
    },
    {
      "epoch": 1.5149700598802394,
      "grad_norm": 0.33963339160823175,
      "learning_rate": 1e-06,
      "loss": 2.153,
      "step": 127
    },
    {
      "epoch": 1.5269461077844313,
      "grad_norm": 0.33753223564447027,
      "learning_rate": 1e-06,
      "loss": 2.1568,
      "step": 128
    },
    {
      "epoch": 1.5389221556886228,
      "grad_norm": 0.3277900338924429,
      "learning_rate": 1e-06,
      "loss": 2.1392,
      "step": 129
    },
    {
      "epoch": 1.5508982035928143,
      "grad_norm": 0.32271967472163604,
      "learning_rate": 1e-06,
      "loss": 2.1585,
      "step": 130
    },
    {
      "epoch": 1.562874251497006,
      "grad_norm": 0.32956474924020723,
      "learning_rate": 1e-06,
      "loss": 2.1505,
      "step": 131
    },
    {
      "epoch": 1.5748502994011977,
      "grad_norm": 0.32470897469456195,
      "learning_rate": 1e-06,
      "loss": 2.1517,
      "step": 132
    },
    {
      "epoch": 1.5868263473053892,
      "grad_norm": 0.31917230445024986,
      "learning_rate": 1e-06,
      "loss": 2.1443,
      "step": 133
    },
    {
      "epoch": 1.5988023952095807,
      "grad_norm": 0.31698015491909903,
      "learning_rate": 1e-06,
      "loss": 2.1335,
      "step": 134
    },
    {
      "epoch": 1.6107784431137726,
      "grad_norm": 0.31923463116678646,
      "learning_rate": 1e-06,
      "loss": 2.1442,
      "step": 135
    },
    {
      "epoch": 1.622754491017964,
      "grad_norm": 0.31790389854102113,
      "learning_rate": 1e-06,
      "loss": 2.1452,
      "step": 136
    },
    {
      "epoch": 1.6347305389221556,
      "grad_norm": 0.31099968418112267,
      "learning_rate": 1e-06,
      "loss": 2.1399,
      "step": 137
    },
    {
      "epoch": 1.6467065868263473,
      "grad_norm": 0.30776386838369674,
      "learning_rate": 1e-06,
      "loss": 2.1349,
      "step": 138
    },
    {
      "epoch": 1.658682634730539,
      "grad_norm": 0.3168082274335414,
      "learning_rate": 1e-06,
      "loss": 2.142,
      "step": 139
    },
    {
      "epoch": 1.6706586826347305,
      "grad_norm": 0.3052089279296624,
      "learning_rate": 1e-06,
      "loss": 2.1574,
      "step": 140
    },
    {
      "epoch": 1.6826347305389222,
      "grad_norm": 0.3070848321728449,
      "learning_rate": 1e-06,
      "loss": 2.1463,
      "step": 141
    },
    {
      "epoch": 1.694610778443114,
      "grad_norm": 0.3085315997419007,
      "learning_rate": 1e-06,
      "loss": 2.1392,
      "step": 142
    },
    {
      "epoch": 1.7065868263473054,
      "grad_norm": 0.31067743980701024,
      "learning_rate": 1e-06,
      "loss": 2.1402,
      "step": 143
    },
    {
      "epoch": 1.718562874251497,
      "grad_norm": 0.2989320995928163,
      "learning_rate": 1e-06,
      "loss": 2.1445,
      "step": 144
    },
    {
      "epoch": 1.7305389221556886,
      "grad_norm": 0.2982955647213182,
      "learning_rate": 1e-06,
      "loss": 2.1431,
      "step": 145
    },
    {
      "epoch": 1.7425149700598803,
      "grad_norm": 0.29925296385799993,
      "learning_rate": 1e-06,
      "loss": 2.1283,
      "step": 146
    },
    {
      "epoch": 1.7544910179640718,
      "grad_norm": 0.3015654043734243,
      "learning_rate": 1e-06,
      "loss": 2.1357,
      "step": 147
    },
    {
      "epoch": 1.7664670658682635,
      "grad_norm": 0.30091222118288874,
      "learning_rate": 1e-06,
      "loss": 2.1317,
      "step": 148
    },
    {
      "epoch": 1.7784431137724552,
      "grad_norm": 0.30288018639543524,
      "learning_rate": 1e-06,
      "loss": 2.1289,
      "step": 149
    },
    {
      "epoch": 1.7904191616766467,
      "grad_norm": 0.2940090172709131,
      "learning_rate": 1e-06,
      "loss": 2.135,
      "step": 150
    },
    {
      "epoch": 1.8023952095808382,
      "grad_norm": 0.2943497577009154,
      "learning_rate": 1e-06,
      "loss": 2.141,
      "step": 151
    },
    {
      "epoch": 1.81437125748503,
      "grad_norm": 0.28667775972376125,
      "learning_rate": 1e-06,
      "loss": 2.1407,
      "step": 152
    },
    {
      "epoch": 1.8263473053892216,
      "grad_norm": 0.2927289770957084,
      "learning_rate": 1e-06,
      "loss": 2.1293,
      "step": 153
    },
    {
      "epoch": 1.8383233532934131,
      "grad_norm": 0.2958951815085863,
      "learning_rate": 1e-06,
      "loss": 2.1282,
      "step": 154
    },
    {
      "epoch": 1.8502994011976048,
      "grad_norm": 0.2965499758116299,
      "learning_rate": 1e-06,
      "loss": 2.1287,
      "step": 155
    },
    {
      "epoch": 1.8622754491017965,
      "grad_norm": 0.2920320753533295,
      "learning_rate": 1e-06,
      "loss": 2.1318,
      "step": 156
    },
    {
      "epoch": 1.874251497005988,
      "grad_norm": 0.28603541435698676,
      "learning_rate": 1e-06,
      "loss": 2.1395,
      "step": 157
    },
    {
      "epoch": 1.8862275449101795,
      "grad_norm": 0.2824672679392089,
      "learning_rate": 1e-06,
      "loss": 2.1222,
      "step": 158
    },
    {
      "epoch": 1.8982035928143712,
      "grad_norm": 0.2859965178914711,
      "learning_rate": 1e-06,
      "loss": 2.1325,
      "step": 159
    },
    {
      "epoch": 1.910179640718563,
      "grad_norm": 0.29491238806087866,
      "learning_rate": 1e-06,
      "loss": 2.1308,
      "step": 160
    },
    {
      "epoch": 1.9221556886227544,
      "grad_norm": 0.28099144782715074,
      "learning_rate": 1e-06,
      "loss": 2.125,
      "step": 161
    },
    {
      "epoch": 1.9341317365269461,
      "grad_norm": 0.2847751193649672,
      "learning_rate": 1e-06,
      "loss": 2.1375,
      "step": 162
    },
    {
      "epoch": 1.9461077844311379,
      "grad_norm": 0.28542718365406394,
      "learning_rate": 1e-06,
      "loss": 2.13,
      "step": 163
    },
    {
      "epoch": 1.9580838323353293,
      "grad_norm": 0.28194319978617144,
      "learning_rate": 1e-06,
      "loss": 2.1362,
      "step": 164
    },
    {
      "epoch": 1.9700598802395208,
      "grad_norm": 0.28496688347361787,
      "learning_rate": 1e-06,
      "loss": 2.1214,
      "step": 165
    },
    {
      "epoch": 1.9820359281437125,
      "grad_norm": 0.28383383257004224,
      "learning_rate": 1e-06,
      "loss": 2.1383,
      "step": 166
    },
    {
      "epoch": 1.9820359281437125,
      "step": 166,
      "total_flos": 58170361774080.0,
      "train_loss": 2.2099866565451562,
      "train_runtime": 2944.772,
      "train_samples_per_second": 11.335,
      "train_steps_per_second": 0.056
    }
  ],
  "logging_steps": 1,
  "max_steps": 166,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 58170361774080.0,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}