{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9970149253731343,
  "eval_steps": 42,
  "global_step": 167,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01,
      "learning_rate": 2e-05,
      "loss": 1.6541,
      "step": 1
    },
    {
      "epoch": 0.01,
      "eval_loss": 1.7634071111679077,
      "eval_runtime": 14.5059,
      "eval_samples_per_second": 56.46,
      "eval_steps_per_second": 28.264,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4e-05,
      "loss": 1.6887,
      "step": 2
    },
    {
      "epoch": 0.02,
      "learning_rate": 6e-05,
      "loss": 1.828,
      "step": 3
    },
    {
      "epoch": 0.02,
      "learning_rate": 8e-05,
      "loss": 1.589,
      "step": 4
    },
    {
      "epoch": 0.03,
      "learning_rate": 0.0001,
      "loss": 1.927,
      "step": 5
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00012,
      "loss": 1.6362,
      "step": 6
    },
    {
      "epoch": 0.04,
      "learning_rate": 0.00014,
      "loss": 1.8546,
      "step": 7
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00016,
      "loss": 1.5843,
      "step": 8
    },
    {
      "epoch": 0.05,
      "learning_rate": 0.00018,
      "loss": 1.5592,
      "step": 9
    },
    {
      "epoch": 0.06,
      "learning_rate": 0.0002,
      "loss": 1.5539,
      "step": 10
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001999988602302209,
      "loss": 1.4449,
      "step": 11
    },
    {
      "epoch": 0.07,
      "learning_rate": 0.0001999954409468652,
      "loss": 1.8818,
      "step": 12
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.0001999897422278767,
      "loss": 1.6656,
      "step": 13
    },
    {
      "epoch": 0.08,
      "learning_rate": 0.00019998176420316002,
      "loss": 1.4607,
      "step": 14
    },
    {
      "epoch": 0.09,
      "learning_rate": 0.0001999715070545774,
      "loss": 1.4013,
      "step": 15
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019995897101594454,
      "loss": 1.5258,
      "step": 16
    },
    {
      "epoch": 0.1,
      "learning_rate": 0.00019994415637302547,
      "loss": 1.404,
      "step": 17
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019992706346352577,
      "loss": 1.3919,
      "step": 18
    },
    {
      "epoch": 0.11,
      "learning_rate": 0.00019990769267708516,
      "loss": 1.355,
      "step": 19
    },
    {
      "epoch": 0.12,
      "learning_rate": 0.00019988604445526827,
      "loss": 1.3763,
      "step": 20
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.000199862119291555,
      "loss": 1.3314,
      "step": 21
    },
    {
      "epoch": 0.13,
      "learning_rate": 0.00019983591773132882,
      "loss": 1.4246,
      "step": 22
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019980744037186469,
      "loss": 1.5723,
      "step": 23
    },
    {
      "epoch": 0.14,
      "learning_rate": 0.00019977668786231534,
      "loss": 1.2536,
      "step": 24
    },
    {
      "epoch": 0.15,
      "learning_rate": 0.0001997436609036963,
      "loss": 1.3087,
      "step": 25
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.0001997083602488702,
      "loss": 1.2783,
      "step": 26
    },
    {
      "epoch": 0.16,
      "learning_rate": 0.00019967078670252945,
      "loss": 1.2792,
      "step": 27
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019963094112117785,
      "loss": 1.2476,
      "step": 28
    },
    {
      "epoch": 0.17,
      "learning_rate": 0.00019958882441311126,
      "loss": 1.265,
      "step": 29
    },
    {
      "epoch": 0.18,
      "learning_rate": 0.00019954443753839667,
      "loss": 1.0884,
      "step": 30
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019949778150885042,
      "loss": 1.3294,
      "step": 31
    },
    {
      "epoch": 0.19,
      "learning_rate": 0.00019944885738801518,
      "loss": 1.3434,
      "step": 32
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019939766629113566,
      "loss": 1.1457,
      "step": 33
    },
    {
      "epoch": 0.2,
      "learning_rate": 0.00019934420938513313,
      "loss": 1.2138,
      "step": 34
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019928848788857887,
      "loss": 1.2118,
      "step": 35
    },
    {
      "epoch": 0.21,
      "learning_rate": 0.00019923050307166655,
      "loss": 1.1426,
      "step": 36
    },
    {
      "epoch": 0.22,
      "learning_rate": 0.00019917025625618292,
      "loss": 1.6279,
      "step": 37
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.000199107748815478,
      "loss": 1.5021,
      "step": 38
    },
    {
      "epoch": 0.23,
      "learning_rate": 0.00019904298217443366,
      "loss": 1.3728,
      "step": 39
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019897595780943102,
      "loss": 1.2034,
      "step": 40
    },
    {
      "epoch": 0.24,
      "learning_rate": 0.00019890667724831707,
      "loss": 1.3718,
      "step": 41
    },
    {
      "epoch": 0.25,
      "learning_rate": 0.00019883514207036956,
      "loss": 1.2512,
      "step": 42
    },
    {
      "epoch": 0.25,
      "eval_loss": 0.8978323936462402,
      "eval_runtime": 14.6352,
      "eval_samples_per_second": 55.961,
      "eval_steps_per_second": 28.015,
      "step": 42
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.00019876135390626122,
      "loss": 1.1787,
      "step": 43
    },
    {
      "epoch": 0.26,
      "learning_rate": 0.0001986853144380224,
      "loss": 1.1917,
      "step": 44
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019860702539900287,
      "loss": 1.1933,
      "step": 45
    },
    {
      "epoch": 0.27,
      "learning_rate": 0.00019852648857383222,
      "loss": 1.1922,
      "step": 46
    },
    {
      "epoch": 0.28,
      "learning_rate": 0.00019844370579837927,
      "loss": 1.3017,
      "step": 47
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.00019835867895971014,
      "loss": 1.1193,
      "step": 48
    },
    {
      "epoch": 0.29,
      "learning_rate": 0.0001982714099960452,
      "loss": 1.1572,
      "step": 49
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019818190089671508,
      "loss": 1.3277,
      "step": 50
    },
    {
      "epoch": 0.3,
      "learning_rate": 0.00019809015370211502,
      "loss": 1.0658,
      "step": 51
    },
    {
      "epoch": 0.31,
      "learning_rate": 0.0001979961705036587,
      "loss": 1.1656,
      "step": 52
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019789995344373024,
      "loss": 1.4204,
      "step": 53
    },
    {
      "epoch": 0.32,
      "learning_rate": 0.00019780150471563558,
      "loss": 1.1551,
      "step": 54
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.0001977008265635525,
      "loss": 1.0993,
      "step": 55
    },
    {
      "epoch": 0.33,
      "learning_rate": 0.00019759792128247922,
      "loss": 1.1311,
      "step": 56
    },
    {
      "epoch": 0.34,
      "learning_rate": 0.00019749279121818235,
      "loss": 1.2163,
      "step": 57
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019738543876714334,
      "loss": 1.3178,
      "step": 58
    },
    {
      "epoch": 0.35,
      "learning_rate": 0.00019727586637650373,
      "loss": 1.3744,
      "step": 59
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019716407654400952,
      "loss": 1.1413,
      "step": 60
    },
    {
      "epoch": 0.36,
      "learning_rate": 0.00019705007181795416,
      "loss": 1.0372,
      "step": 61
    },
    {
      "epoch": 0.37,
      "learning_rate": 0.00019693385479712048,
      "loss": 1.1601,
      "step": 62
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019681542813072145,
      "loss": 1.0976,
      "step": 63
    },
    {
      "epoch": 0.38,
      "learning_rate": 0.00019669479451833976,
      "loss": 1.1584,
      "step": 64
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019657195670986637,
      "loss": 1.0962,
      "step": 65
    },
    {
      "epoch": 0.39,
      "learning_rate": 0.00019644691750543767,
      "loss": 1.1044,
      "step": 66
    },
    {
      "epoch": 0.4,
      "learning_rate": 0.0001963196797553718,
      "loss": 1.2431,
      "step": 67
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019619024636010363,
      "loss": 1.1651,
      "step": 68
    },
    {
      "epoch": 0.41,
      "learning_rate": 0.00019605862027011856,
      "loss": 1.0513,
      "step": 69
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019592480448588542,
      "loss": 1.0175,
      "step": 70
    },
    {
      "epoch": 0.42,
      "learning_rate": 0.00019578880205778793,
      "loss": 1.1306,
      "step": 71
    },
    {
      "epoch": 0.43,
      "learning_rate": 0.00019565061608605526,
      "loss": 1.3121,
      "step": 72
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019551024972069126,
      "loss": 1.266,
      "step": 73
    },
    {
      "epoch": 0.44,
      "learning_rate": 0.00019536770616140276,
      "loss": 1.1099,
      "step": 74
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.0001952229886575266,
      "loss": 1.1012,
      "step": 75
    },
    {
      "epoch": 0.45,
      "learning_rate": 0.00019507610050795558,
      "loss": 1.1272,
      "step": 76
    },
    {
      "epoch": 0.46,
      "learning_rate": 0.0001949270450610631,
      "loss": 1.2016,
      "step": 77
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019477582571462705,
      "loss": 1.1746,
      "step": 78
    },
    {
      "epoch": 0.47,
      "learning_rate": 0.00019462244591575222,
      "loss": 1.1349,
      "step": 79
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.0001944669091607919,
      "loss": 1.4311,
      "step": 80
    },
    {
      "epoch": 0.48,
      "learning_rate": 0.00019430921899526787,
      "loss": 1.1033,
      "step": 81
    },
    {
      "epoch": 0.49,
      "learning_rate": 0.00019414937901378982,
      "loss": 1.2491,
      "step": 82
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.0001939873928599734,
      "loss": 1.1044,
      "step": 83
    },
    {
      "epoch": 0.5,
      "learning_rate": 0.00019382326422635705,
      "loss": 1.1008,
      "step": 84
    },
    {
      "epoch": 0.5,
      "eval_loss": 0.8307072520256042,
      "eval_runtime": 14.6668,
      "eval_samples_per_second": 55.841,
      "eval_steps_per_second": 27.954,
      "step": 84
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.0001936569968543179,
      "loss": 1.2317,
      "step": 85
    },
    {
      "epoch": 0.51,
      "learning_rate": 0.00019348859453398646,
      "loss": 1.2317,
      "step": 86
    },
    {
      "epoch": 0.52,
      "learning_rate": 0.00019331806110416027,
      "loss": 1.0989,
      "step": 87
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019314540045221626,
      "loss": 1.0466,
      "step": 88
    },
    {
      "epoch": 0.53,
      "learning_rate": 0.00019297061651402236,
      "loss": 1.0798,
      "step": 89
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001927937132738476,
      "loss": 1.1175,
      "step": 90
    },
    {
      "epoch": 0.54,
      "learning_rate": 0.0001926146947642712,
      "loss": 1.1292,
      "step": 91
    },
    {
      "epoch": 0.55,
      "learning_rate": 0.000192433565066091,
      "loss": 1.0464,
      "step": 92
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019225032830823011,
      "loss": 1.1549,
      "step": 93
    },
    {
      "epoch": 0.56,
      "learning_rate": 0.00019206498866764288,
      "loss": 1.1129,
      "step": 94
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.00019187755036921978,
      "loss": 0.9965,
      "step": 95
    },
    {
      "epoch": 0.57,
      "learning_rate": 0.0001916880176856909,
      "loss": 1.0767,
      "step": 96
    },
    {
      "epoch": 0.58,
      "learning_rate": 0.0001914963949375288,
      "loss": 1.1546,
      "step": 97
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.0001913026864928498,
      "loss": 0.9627,
      "step": 98
    },
    {
      "epoch": 0.59,
      "learning_rate": 0.00019110689676731454,
      "loss": 1.0039,
      "step": 99
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019090903022402729,
      "loss": 1.066,
      "step": 100
    },
    {
      "epoch": 0.6,
      "learning_rate": 0.00019070909137343408,
      "loss": 1.0654,
      "step": 101
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019050708477322018,
      "loss": 1.3323,
      "step": 102
    },
    {
      "epoch": 0.61,
      "learning_rate": 0.00019030301502820596,
      "loss": 1.1247,
      "step": 103
    },
    {
      "epoch": 0.62,
      "learning_rate": 0.0001900968867902419,
      "loss": 1.0261,
      "step": 104
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018988870475810282,
      "loss": 1.0935,
      "step": 105
    },
    {
      "epoch": 0.63,
      "learning_rate": 0.00018967847367738048,
      "loss": 1.1043,
      "step": 106
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018946619834037546,
      "loss": 1.1982,
      "step": 107
    },
    {
      "epoch": 0.64,
      "learning_rate": 0.00018925188358598813,
      "loss": 1.0445,
      "step": 108
    },
    {
      "epoch": 0.65,
      "learning_rate": 0.00018903553429960802,
      "loss": 1.086,
      "step": 109
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018881715541300276,
      "loss": 1.1509,
      "step": 110
    },
    {
      "epoch": 0.66,
      "learning_rate": 0.00018859675190420537,
      "loss": 1.1473,
      "step": 111
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.00018837432879740114,
      "loss": 1.1677,
      "step": 112
    },
    {
      "epoch": 0.67,
      "learning_rate": 0.0001881498911628127,
      "loss": 1.006,
      "step": 113
    },
    {
      "epoch": 0.68,
      "learning_rate": 0.00018792344411658468,
      "loss": 1.0503,
      "step": 114
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00018769499282066717,
      "loss": 1.163,
      "step": 115
    },
    {
      "epoch": 0.69,
      "learning_rate": 0.00018746454248269777,
      "loss": 1.1443,
      "step": 116
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.0001872320983558831,
      "loss": 0.9785,
      "step": 117
    },
    {
      "epoch": 0.7,
      "learning_rate": 0.000186997665738879,
      "loss": 1.0605,
      "step": 118
    },
    {
      "epoch": 0.71,
      "learning_rate": 0.0001867612499756697,
      "loss": 1.0203,
      "step": 119
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00018652285645544603,
      "loss": 1.146,
      "step": 120
    },
    {
      "epoch": 0.72,
      "learning_rate": 0.00018628249061248262,
      "loss": 1.12,
      "step": 121
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00018604015792601396,
      "loss": 1.1499,
      "step": 122
    },
    {
      "epoch": 0.73,
      "learning_rate": 0.00018579586392010943,
      "loss": 1.1273,
      "step": 123
    },
    {
      "epoch": 0.74,
      "learning_rate": 0.0001855496141635476,
      "loss": 1.0404,
      "step": 124
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.00018530141426968902,
      "loss": 1.1066,
      "step": 125
    },
    {
      "epoch": 0.75,
      "learning_rate": 0.0001850512698963485,
      "loss": 1.0685,
      "step": 126
    },
    {
      "epoch": 0.75,
      "eval_loss": 0.8026405572891235,
      "eval_runtime": 14.5968,
      "eval_samples_per_second": 56.108,
      "eval_steps_per_second": 28.088,
      "step": 126
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.000184799186745666,
      "loss": 1.0494,
      "step": 127
    },
    {
      "epoch": 0.76,
      "learning_rate": 0.00018454517056397661,
      "loss": 1.1905,
      "step": 128
    },
    {
      "epoch": 0.77,
      "learning_rate": 0.0001842892271416797,
      "loss": 1.2034,
      "step": 129
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00018403136231310684,
      "loss": 1.2088,
      "step": 130
    },
    {
      "epoch": 0.78,
      "learning_rate": 0.00018377158195638876,
      "loss": 0.9303,
      "step": 131
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00018350989199332154,
      "loss": 1.1574,
      "step": 132
    },
    {
      "epoch": 0.79,
      "learning_rate": 0.00018324629838923132,
      "loss": 1.1673,
      "step": 133
    },
    {
      "epoch": 0.8,
      "learning_rate": 0.00018298080715283858,
      "loss": 1.1204,
      "step": 134
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018271342433612113,
      "loss": 1.0752,
      "step": 135
    },
    {
      "epoch": 0.81,
      "learning_rate": 0.00018244415603417603,
      "loss": 1.0121,
      "step": 136
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00018217300838508073,
      "loss": 1.0975,
      "step": 137
    },
    {
      "epoch": 0.82,
      "learning_rate": 0.00018189998756975318,
      "loss": 0.9982,
      "step": 138
    },
    {
      "epoch": 0.83,
      "learning_rate": 0.00018162509981181084,
      "loss": 1.1922,
      "step": 139
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.0001813483513774289,
      "loss": 0.9532,
      "step": 140
    },
    {
      "epoch": 0.84,
      "learning_rate": 0.00018106974857519736,
      "loss": 1.0813,
      "step": 141
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001807892977559774,
      "loss": 0.9656,
      "step": 142
    },
    {
      "epoch": 0.85,
      "learning_rate": 0.0001805070053127563,
      "loss": 1.1161,
      "step": 143
    },
    {
      "epoch": 0.86,
      "learning_rate": 0.00018022287768050202,
      "loss": 1.0143,
      "step": 144
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.0001799369213360163,
      "loss": 1.1242,
      "step": 145
    },
    {
      "epoch": 0.87,
      "learning_rate": 0.00017964914279778715,
      "loss": 1.0747,
      "step": 146
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.00017935954862584018,
      "loss": 1.1551,
      "step": 147
    },
    {
      "epoch": 0.88,
      "learning_rate": 0.0001790681454215891,
      "loss": 0.9538,
      "step": 148
    },
    {
      "epoch": 0.89,
      "learning_rate": 0.00017877493982768527,
      "loss": 1.0621,
      "step": 149
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.0001784799385278661,
      "loss": 1.0229,
      "step": 150
    },
    {
      "epoch": 0.9,
      "learning_rate": 0.000178183148246803,
      "loss": 0.9991,
      "step": 151
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00017788457574994778,
      "loss": 1.0045,
      "step": 152
    },
    {
      "epoch": 0.91,
      "learning_rate": 0.00017758422784337863,
      "loss": 1.0675,
      "step": 153
    },
    {
      "epoch": 0.92,
      "learning_rate": 0.00017728211137364489,
      "loss": 0.962,
      "step": 154
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.000176978233227611,
      "loss": 1.0145,
      "step": 155
    },
    {
      "epoch": 0.93,
      "learning_rate": 0.00017667260033229953,
      "loss": 0.9576,
      "step": 156
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00017636521965473323,
      "loss": 1.0692,
      "step": 157
    },
    {
      "epoch": 0.94,
      "learning_rate": 0.00017605609820177617,
      "loss": 1.2074,
      "step": 158
    },
    {
      "epoch": 0.95,
      "learning_rate": 0.00017574524301997423,
      "loss": 1.1489,
      "step": 159
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00017543266119539422,
      "loss": 0.9962,
      "step": 160
    },
    {
      "epoch": 0.96,
      "learning_rate": 0.00017511835985346253,
      "loss": 0.8922,
      "step": 161
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.00017480234615880247,
      "loss": 0.9248,
      "step": 162
    },
    {
      "epoch": 0.97,
      "learning_rate": 0.0001744846273150713,
      "loss": 1.1621,
      "step": 163
    },
    {
      "epoch": 0.98,
      "learning_rate": 0.00017416521056479577,
      "loss": 1.0516,
      "step": 164
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00017384410318920697,
      "loss": 1.0086,
      "step": 165
    },
    {
      "epoch": 0.99,
      "learning_rate": 0.00017352131250807467,
      "loss": 1.0909,
      "step": 166
    },
    {
      "epoch": 1.0,
      "learning_rate": 0.00017319684587954002,
      "loss": 1.1085,
      "step": 167
    }
  ],
  "logging_steps": 1,
  "max_steps": 668,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 4,
  "save_steps": 167,
  "total_flos": 3.4795134369398784e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}