{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 250,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.004,
      "grad_norm": 1.954319715499878,
      "learning_rate": 1e-05,
      "loss": 2.411,
      "step": 1
    },
    {
      "epoch": 0.008,
      "grad_norm": 1.7826515436172485,
      "learning_rate": 9.960000000000001e-06,
      "loss": 2.2813,
      "step": 2
    },
    {
      "epoch": 0.012,
      "grad_norm": 1.8655924797058105,
      "learning_rate": 9.920000000000002e-06,
      "loss": 2.2412,
      "step": 3
    },
    {
      "epoch": 0.016,
      "grad_norm": 1.745436668395996,
      "learning_rate": 9.88e-06,
      "loss": 2.449,
      "step": 4
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.694860816001892,
      "learning_rate": 9.84e-06,
      "loss": 2.3644,
      "step": 5
    },
    {
      "epoch": 0.024,
      "grad_norm": 1.674206018447876,
      "learning_rate": 9.800000000000001e-06,
      "loss": 2.3375,
      "step": 6
    },
    {
      "epoch": 0.028,
      "grad_norm": 1.4836173057556152,
      "learning_rate": 9.760000000000001e-06,
      "loss": 2.2718,
      "step": 7
    },
    {
      "epoch": 0.032,
      "grad_norm": 1.6038180589675903,
      "learning_rate": 9.72e-06,
      "loss": 2.32,
      "step": 8
    },
    {
      "epoch": 0.036,
      "grad_norm": 1.4479186534881592,
      "learning_rate": 9.68e-06,
      "loss": 2.316,
      "step": 9
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.392088770866394,
      "learning_rate": 9.640000000000001e-06,
      "loss": 2.2769,
      "step": 10
    },
    {
      "epoch": 0.044,
      "grad_norm": 1.4886748790740967,
      "learning_rate": 9.600000000000001e-06,
      "loss": 2.1541,
      "step": 11
    },
    {
      "epoch": 0.048,
      "grad_norm": 1.4993741512298584,
      "learning_rate": 9.56e-06,
      "loss": 2.2039,
      "step": 12
    },
    {
      "epoch": 0.052,
      "grad_norm": 1.4934766292572021,
      "learning_rate": 9.52e-06,
      "loss": 2.192,
      "step": 13
    },
    {
      "epoch": 0.056,
      "grad_norm": 1.4041507244110107,
      "learning_rate": 9.48e-06,
      "loss": 2.1539,
      "step": 14
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.3733670711517334,
      "learning_rate": 9.440000000000001e-06,
      "loss": 2.0952,
      "step": 15
    },
    {
      "epoch": 0.064,
      "grad_norm": 1.3157683610916138,
      "learning_rate": 9.4e-06,
      "loss": 2.1532,
      "step": 16
    },
    {
      "epoch": 0.068,
      "grad_norm": 1.329785943031311,
      "learning_rate": 9.360000000000002e-06,
      "loss": 2.2528,
      "step": 17
    },
    {
      "epoch": 0.072,
      "grad_norm": 1.3144254684448242,
      "learning_rate": 9.32e-06,
      "loss": 2.1163,
      "step": 18
    },
    {
      "epoch": 0.076,
      "grad_norm": 1.3946971893310547,
      "learning_rate": 9.280000000000001e-06,
      "loss": 2.1822,
      "step": 19
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.2859883308410645,
      "learning_rate": 9.240000000000001e-06,
      "loss": 2.1111,
      "step": 20
    },
    {
      "epoch": 0.084,
      "grad_norm": 1.2906239032745361,
      "learning_rate": 9.200000000000002e-06,
      "loss": 2.1035,
      "step": 21
    },
    {
      "epoch": 0.088,
      "grad_norm": 1.3045598268508911,
      "learning_rate": 9.16e-06,
      "loss": 2.0066,
      "step": 22
    },
    {
      "epoch": 0.092,
      "grad_norm": 1.3252729177474976,
      "learning_rate": 9.12e-06,
      "loss": 2.1423,
      "step": 23
    },
    {
      "epoch": 0.096,
      "grad_norm": 1.444812297821045,
      "learning_rate": 9.080000000000001e-06,
      "loss": 1.9729,
      "step": 24
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.274637222290039,
      "learning_rate": 9.040000000000002e-06,
      "loss": 1.9568,
      "step": 25
    },
    {
      "epoch": 0.104,
      "grad_norm": 1.3475300073623657,
      "learning_rate": 9e-06,
      "loss": 2.0642,
      "step": 26
    },
    {
      "epoch": 0.108,
      "grad_norm": 1.1989250183105469,
      "learning_rate": 8.96e-06,
      "loss": 1.9397,
      "step": 27
    },
    {
      "epoch": 0.112,
      "grad_norm": 1.2486416101455688,
      "learning_rate": 8.920000000000001e-06,
      "loss": 2.0845,
      "step": 28
    },
    {
      "epoch": 0.116,
      "grad_norm": 1.170324683189392,
      "learning_rate": 8.880000000000001e-06,
      "loss": 1.9076,
      "step": 29
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.1869423389434814,
      "learning_rate": 8.84e-06,
      "loss": 1.9553,
      "step": 30
    },
    {
      "epoch": 0.124,
      "grad_norm": 1.3021348714828491,
      "learning_rate": 8.8e-06,
      "loss": 2.0035,
      "step": 31
    },
    {
      "epoch": 0.128,
      "grad_norm": 1.2392538785934448,
      "learning_rate": 8.76e-06,
      "loss": 1.9291,
      "step": 32
    },
    {
      "epoch": 0.132,
      "grad_norm": 1.1870639324188232,
      "learning_rate": 8.720000000000001e-06,
      "loss": 1.8562,
      "step": 33
    },
    {
      "epoch": 0.136,
      "grad_norm": 1.2068073749542236,
      "learning_rate": 8.68e-06,
      "loss": 1.8835,
      "step": 34
    },
    {
      "epoch": 0.14,
      "grad_norm": 1.216802716255188,
      "learning_rate": 8.64e-06,
      "loss": 1.9927,
      "step": 35
    },
    {
      "epoch": 0.144,
      "grad_norm": 1.2364400625228882,
      "learning_rate": 8.6e-06,
      "loss": 1.9287,
      "step": 36
    },
    {
      "epoch": 0.148,
      "grad_norm": 1.190116047859192,
      "learning_rate": 8.560000000000001e-06,
      "loss": 1.8866,
      "step": 37
    },
    {
      "epoch": 0.152,
      "grad_norm": 1.259717583656311,
      "learning_rate": 8.52e-06,
      "loss": 1.9072,
      "step": 38
    },
    {
      "epoch": 0.156,
      "grad_norm": 1.1407251358032227,
      "learning_rate": 8.48e-06,
      "loss": 1.8916,
      "step": 39
    },
    {
      "epoch": 0.16,
      "grad_norm": 1.2043702602386475,
      "learning_rate": 8.44e-06,
      "loss": 1.9885,
      "step": 40
    },
    {
      "epoch": 0.164,
      "grad_norm": 1.1877334117889404,
      "learning_rate": 8.400000000000001e-06,
      "loss": 1.8913,
      "step": 41
    },
    {
      "epoch": 0.168,
      "grad_norm": 1.1940908432006836,
      "learning_rate": 8.36e-06,
      "loss": 1.9593,
      "step": 42
    },
    {
      "epoch": 0.172,
      "grad_norm": 1.2312895059585571,
      "learning_rate": 8.32e-06,
      "loss": 1.853,
      "step": 43
    },
    {
      "epoch": 0.176,
      "grad_norm": 1.228988528251648,
      "learning_rate": 8.28e-06,
      "loss": 1.8425,
      "step": 44
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.1870458126068115,
      "learning_rate": 8.24e-06,
      "loss": 1.8729,
      "step": 45
    },
    {
      "epoch": 0.184,
      "grad_norm": 1.1809366941452026,
      "learning_rate": 8.2e-06,
      "loss": 1.869,
      "step": 46
    },
    {
      "epoch": 0.188,
      "grad_norm": 1.2264615297317505,
      "learning_rate": 8.16e-06,
      "loss": 1.709,
      "step": 47
    },
    {
      "epoch": 0.192,
      "grad_norm": 1.2154760360717773,
      "learning_rate": 8.120000000000002e-06,
      "loss": 1.8711,
      "step": 48
    },
    {
      "epoch": 0.196,
      "grad_norm": 1.2827329635620117,
      "learning_rate": 8.08e-06,
      "loss": 1.7218,
      "step": 49
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.321017861366272,
      "learning_rate": 8.040000000000001e-06,
      "loss": 1.8414,
      "step": 50
    },
    {
      "epoch": 0.204,
      "grad_norm": 1.2692463397979736,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.8819,
      "step": 51
    },
    {
      "epoch": 0.208,
      "grad_norm": 1.2398897409439087,
      "learning_rate": 7.960000000000002e-06,
      "loss": 1.8504,
      "step": 52
    },
    {
      "epoch": 0.212,
      "grad_norm": 1.1805490255355835,
      "learning_rate": 7.92e-06,
      "loss": 1.7266,
      "step": 53
    },
    {
      "epoch": 0.216,
      "grad_norm": 1.3034391403198242,
      "learning_rate": 7.88e-06,
      "loss": 1.9034,
      "step": 54
    },
    {
      "epoch": 0.22,
      "grad_norm": 1.2424261569976807,
      "learning_rate": 7.840000000000001e-06,
      "loss": 1.8717,
      "step": 55
    },
    {
      "epoch": 0.224,
      "grad_norm": 1.2809594869613647,
      "learning_rate": 7.800000000000002e-06,
      "loss": 1.842,
      "step": 56
    },
    {
      "epoch": 0.228,
      "grad_norm": 1.2217411994934082,
      "learning_rate": 7.76e-06,
      "loss": 1.8669,
      "step": 57
    },
    {
      "epoch": 0.232,
      "grad_norm": 1.245792269706726,
      "learning_rate": 7.72e-06,
      "loss": 1.7957,
      "step": 58
    },
    {
      "epoch": 0.236,
      "grad_norm": 1.4041963815689087,
      "learning_rate": 7.680000000000001e-06,
      "loss": 1.8658,
      "step": 59
    },
    {
      "epoch": 0.24,
      "grad_norm": 1.2613027095794678,
      "learning_rate": 7.640000000000001e-06,
      "loss": 1.7077,
      "step": 60
    },
    {
      "epoch": 0.244,
      "grad_norm": 1.2692285776138306,
      "learning_rate": 7.600000000000001e-06,
      "loss": 1.8825,
      "step": 61
    },
    {
      "epoch": 0.248,
      "grad_norm": 1.2766786813735962,
      "learning_rate": 7.5600000000000005e-06,
      "loss": 1.7079,
      "step": 62
    },
    {
      "epoch": 0.252,
      "grad_norm": 1.2243366241455078,
      "learning_rate": 7.520000000000001e-06,
      "loss": 1.6271,
      "step": 63
    },
    {
      "epoch": 0.256,
      "grad_norm": 1.1690571308135986,
      "learning_rate": 7.48e-06,
      "loss": 1.658,
      "step": 64
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.285218596458435,
      "learning_rate": 7.440000000000001e-06,
      "loss": 1.8225,
      "step": 65
    },
    {
      "epoch": 0.264,
      "grad_norm": 1.2221527099609375,
      "learning_rate": 7.4e-06,
      "loss": 1.7738,
      "step": 66
    },
    {
      "epoch": 0.268,
      "grad_norm": 1.266739010810852,
      "learning_rate": 7.360000000000001e-06,
      "loss": 1.8241,
      "step": 67
    },
    {
      "epoch": 0.272,
      "grad_norm": 1.1950359344482422,
      "learning_rate": 7.32e-06,
      "loss": 1.707,
      "step": 68
    },
    {
      "epoch": 0.276,
      "grad_norm": 1.2839792966842651,
      "learning_rate": 7.280000000000001e-06,
      "loss": 1.6992,
      "step": 69
    },
    {
      "epoch": 0.28,
      "grad_norm": 1.2620984315872192,
      "learning_rate": 7.24e-06,
      "loss": 1.774,
      "step": 70
    },
    {
      "epoch": 0.284,
      "grad_norm": 1.3442317247390747,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.6569,
      "step": 71
    },
    {
      "epoch": 0.288,
      "grad_norm": 1.1748533248901367,
      "learning_rate": 7.16e-06,
      "loss": 1.6679,
      "step": 72
    },
    {
      "epoch": 0.292,
      "grad_norm": 1.2641892433166504,
      "learning_rate": 7.1200000000000004e-06,
      "loss": 1.7939,
      "step": 73
    },
    {
      "epoch": 0.296,
      "grad_norm": 1.3012604713439941,
      "learning_rate": 7.08e-06,
      "loss": 1.8023,
      "step": 74
    },
    {
      "epoch": 0.3,
      "grad_norm": 1.231961965560913,
      "learning_rate": 7.04e-06,
      "loss": 1.6496,
      "step": 75
    },
    {
      "epoch": 0.304,
      "grad_norm": 1.1863617897033691,
      "learning_rate": 7e-06,
      "loss": 1.724,
      "step": 76
    },
    {
      "epoch": 0.308,
      "grad_norm": 1.3211452960968018,
      "learning_rate": 6.96e-06,
      "loss": 1.774,
      "step": 77
    },
    {
      "epoch": 0.312,
      "grad_norm": 1.2411987781524658,
      "learning_rate": 6.92e-06,
      "loss": 1.747,
      "step": 78
    },
    {
      "epoch": 0.316,
      "grad_norm": 1.2533900737762451,
      "learning_rate": 6.88e-06,
      "loss": 1.6799,
      "step": 79
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.239896297454834,
      "learning_rate": 6.8400000000000014e-06,
      "loss": 1.7044,
      "step": 80
    },
    {
      "epoch": 0.324,
      "grad_norm": 1.3009883165359497,
      "learning_rate": 6.800000000000001e-06,
      "loss": 1.7974,
      "step": 81
    },
    {
      "epoch": 0.328,
      "grad_norm": 1.3433125019073486,
      "learning_rate": 6.760000000000001e-06,
      "loss": 1.7764,
      "step": 82
    },
    {
      "epoch": 0.332,
      "grad_norm": 1.2757320404052734,
      "learning_rate": 6.720000000000001e-06,
      "loss": 1.8176,
      "step": 83
    },
    {
      "epoch": 0.336,
      "grad_norm": 1.4214569330215454,
      "learning_rate": 6.680000000000001e-06,
      "loss": 1.7098,
      "step": 84
    },
    {
      "epoch": 0.34,
      "grad_norm": 1.3198415040969849,
      "learning_rate": 6.640000000000001e-06,
      "loss": 1.7805,
      "step": 85
    },
    {
      "epoch": 0.344,
      "grad_norm": 1.2718086242675781,
      "learning_rate": 6.600000000000001e-06,
      "loss": 1.7335,
      "step": 86
    },
    {
      "epoch": 0.348,
      "grad_norm": 1.220406174659729,
      "learning_rate": 6.560000000000001e-06,
      "loss": 1.7863,
      "step": 87
    },
    {
      "epoch": 0.352,
      "grad_norm": 1.254685878753662,
      "learning_rate": 6.520000000000001e-06,
      "loss": 1.6722,
      "step": 88
    },
    {
      "epoch": 0.356,
      "grad_norm": 1.4736641645431519,
      "learning_rate": 6.480000000000001e-06,
      "loss": 1.8828,
      "step": 89
    },
    {
      "epoch": 0.36,
      "grad_norm": 1.276246428489685,
      "learning_rate": 6.440000000000001e-06,
      "loss": 1.6934,
      "step": 90
    },
    {
      "epoch": 0.364,
      "grad_norm": 1.2888675928115845,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.7737,
      "step": 91
    },
    {
      "epoch": 0.368,
      "grad_norm": 1.3010715246200562,
      "learning_rate": 6.360000000000001e-06,
      "loss": 1.7787,
      "step": 92
    },
    {
      "epoch": 0.372,
      "grad_norm": 1.3261510133743286,
      "learning_rate": 6.3200000000000005e-06,
      "loss": 1.6233,
      "step": 93
    },
    {
      "epoch": 0.376,
      "grad_norm": 1.306959867477417,
      "learning_rate": 6.280000000000001e-06,
      "loss": 1.6648,
      "step": 94
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.3729215860366821,
      "learning_rate": 6.24e-06,
      "loss": 1.7446,
      "step": 95
    },
    {
      "epoch": 0.384,
      "grad_norm": 1.442742943763733,
      "learning_rate": 6.200000000000001e-06,
      "loss": 1.705,
      "step": 96
    },
    {
      "epoch": 0.388,
      "grad_norm": 1.2511957883834839,
      "learning_rate": 6.16e-06,
      "loss": 1.6899,
      "step": 97
    },
    {
      "epoch": 0.392,
      "grad_norm": 1.3324456214904785,
      "learning_rate": 6.120000000000001e-06,
      "loss": 1.6001,
      "step": 98
    },
    {
      "epoch": 0.396,
      "grad_norm": 1.2704485654830933,
      "learning_rate": 6.08e-06,
      "loss": 1.6467,
      "step": 99
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.3349323272705078,
      "learning_rate": 6.040000000000001e-06,
      "loss": 1.9362,
      "step": 100
    },
    {
      "epoch": 0.404,
      "grad_norm": 1.3596888780593872,
      "learning_rate": 6e-06,
      "loss": 1.6858,
      "step": 101
    },
    {
      "epoch": 0.408,
      "grad_norm": 1.2084500789642334,
      "learning_rate": 5.9600000000000005e-06,
      "loss": 1.6745,
      "step": 102
    },
    {
      "epoch": 0.412,
      "grad_norm": 1.3298012018203735,
      "learning_rate": 5.92e-06,
      "loss": 1.6407,
      "step": 103
    },
    {
      "epoch": 0.416,
      "grad_norm": 1.2951877117156982,
      "learning_rate": 5.8800000000000005e-06,
      "loss": 1.6904,
      "step": 104
    },
    {
      "epoch": 0.42,
      "grad_norm": 1.3563202619552612,
      "learning_rate": 5.84e-06,
      "loss": 1.6854,
      "step": 105
    },
    {
      "epoch": 0.424,
      "grad_norm": 1.3635480403900146,
      "learning_rate": 5.8e-06,
      "loss": 1.6669,
      "step": 106
    },
    {
      "epoch": 0.428,
      "grad_norm": 1.2384741306304932,
      "learning_rate": 5.76e-06,
      "loss": 1.676,
      "step": 107
    },
    {
      "epoch": 0.432,
      "grad_norm": 1.3344753980636597,
      "learning_rate": 5.72e-06,
      "loss": 1.7118,
      "step": 108
    },
    {
      "epoch": 0.436,
      "grad_norm": 1.2847405672073364,
      "learning_rate": 5.68e-06,
      "loss": 1.644,
      "step": 109
    },
    {
      "epoch": 0.44,
      "grad_norm": 1.3353115320205688,
      "learning_rate": 5.64e-06,
      "loss": 1.783,
      "step": 110
    },
    {
      "epoch": 0.444,
      "grad_norm": 1.2775030136108398,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.6135,
      "step": 111
    },
    {
      "epoch": 0.448,
      "grad_norm": 1.4320266246795654,
      "learning_rate": 5.560000000000001e-06,
      "loss": 1.5901,
      "step": 112
    },
    {
      "epoch": 0.452,
      "grad_norm": 1.2850722074508667,
      "learning_rate": 5.5200000000000005e-06,
      "loss": 1.5889,
      "step": 113
    },
    {
      "epoch": 0.456,
      "grad_norm": 1.4107635021209717,
      "learning_rate": 5.480000000000001e-06,
      "loss": 1.7243,
      "step": 114
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.3406022787094116,
      "learning_rate": 5.4400000000000004e-06,
      "loss": 1.7539,
      "step": 115
    },
    {
      "epoch": 0.464,
      "grad_norm": 1.4117956161499023,
      "learning_rate": 5.400000000000001e-06,
      "loss": 1.7506,
      "step": 116
    },
    {
      "epoch": 0.468,
      "grad_norm": 1.3653512001037598,
      "learning_rate": 5.36e-06,
      "loss": 1.6322,
      "step": 117
    },
    {
      "epoch": 0.472,
      "grad_norm": 1.3492501974105835,
      "learning_rate": 5.320000000000001e-06,
      "loss": 1.7073,
      "step": 118
    },
    {
      "epoch": 0.476,
      "grad_norm": 1.3545348644256592,
      "learning_rate": 5.28e-06,
      "loss": 1.7101,
      "step": 119
    },
    {
      "epoch": 0.48,
      "grad_norm": 1.2072592973709106,
      "learning_rate": 5.240000000000001e-06,
      "loss": 1.6332,
      "step": 120
    },
    {
      "epoch": 0.484,
      "grad_norm": 1.3392893075942993,
      "learning_rate": 5.2e-06,
      "loss": 1.6766,
      "step": 121
    },
    {
      "epoch": 0.488,
      "grad_norm": 1.4758343696594238,
      "learning_rate": 5.1600000000000006e-06,
      "loss": 1.7023,
      "step": 122
    },
    {
      "epoch": 0.492,
      "grad_norm": 1.2837586402893066,
      "learning_rate": 5.12e-06,
      "loss": 1.5553,
      "step": 123
    },
    {
      "epoch": 0.496,
      "grad_norm": 1.3341403007507324,
      "learning_rate": 5.0800000000000005e-06,
      "loss": 1.5714,
      "step": 124
    },
    {
      "epoch": 0.5,
      "grad_norm": 1.4433372020721436,
      "learning_rate": 5.04e-06,
      "loss": 1.758,
      "step": 125
    },
    {
      "epoch": 0.504,
      "grad_norm": 1.3581253290176392,
      "learning_rate": 5e-06,
      "loss": 1.5949,
      "step": 126
    },
    {
      "epoch": 0.508,
      "grad_norm": 1.378012776374817,
      "learning_rate": 4.960000000000001e-06,
      "loss": 1.722,
      "step": 127
    },
    {
      "epoch": 0.512,
      "grad_norm": 1.400965929031372,
      "learning_rate": 4.92e-06,
      "loss": 1.7045,
      "step": 128
    },
    {
      "epoch": 0.516,
      "grad_norm": 1.4368276596069336,
      "learning_rate": 4.880000000000001e-06,
      "loss": 1.5844,
      "step": 129
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.3200892210006714,
      "learning_rate": 4.84e-06,
      "loss": 1.6877,
      "step": 130
    },
    {
      "epoch": 0.524,
      "grad_norm": 1.4182710647583008,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.5604,
      "step": 131
    },
    {
      "epoch": 0.528,
      "grad_norm": 1.2968662977218628,
      "learning_rate": 4.76e-06,
      "loss": 1.6281,
      "step": 132
    },
    {
      "epoch": 0.532,
      "grad_norm": 1.2928485870361328,
      "learning_rate": 4.7200000000000005e-06,
      "loss": 1.621,
      "step": 133
    },
    {
      "epoch": 0.536,
      "grad_norm": 1.3902649879455566,
      "learning_rate": 4.680000000000001e-06,
      "loss": 1.6301,
      "step": 134
    },
    {
      "epoch": 0.54,
      "grad_norm": 1.3287855386734009,
      "learning_rate": 4.6400000000000005e-06,
      "loss": 1.6373,
      "step": 135
    },
    {
      "epoch": 0.544,
      "grad_norm": 1.374890685081482,
      "learning_rate": 4.600000000000001e-06,
      "loss": 1.6926,
      "step": 136
    },
    {
      "epoch": 0.548,
      "grad_norm": 1.2487736940383911,
      "learning_rate": 4.56e-06,
      "loss": 1.611,
      "step": 137
    },
    {
      "epoch": 0.552,
      "grad_norm": 1.3028439283370972,
      "learning_rate": 4.520000000000001e-06,
      "loss": 1.6176,
      "step": 138
    },
    {
      "epoch": 0.556,
      "grad_norm": 1.3260806798934937,
      "learning_rate": 4.48e-06,
      "loss": 1.6203,
      "step": 139
    },
    {
      "epoch": 0.56,
      "grad_norm": 1.3496484756469727,
      "learning_rate": 4.440000000000001e-06,
      "loss": 1.7806,
      "step": 140
    },
    {
      "epoch": 0.564,
      "grad_norm": 1.2870110273361206,
      "learning_rate": 4.4e-06,
      "loss": 1.6348,
      "step": 141
    },
    {
      "epoch": 0.568,
      "grad_norm": 1.481292963027954,
      "learning_rate": 4.360000000000001e-06,
      "loss": 1.6622,
      "step": 142
    },
    {
      "epoch": 0.572,
      "grad_norm": 1.426375389099121,
      "learning_rate": 4.32e-06,
      "loss": 1.6248,
      "step": 143
    },
    {
      "epoch": 0.576,
      "grad_norm": 1.3465576171875,
      "learning_rate": 4.2800000000000005e-06,
      "loss": 1.5603,
      "step": 144
    },
    {
      "epoch": 0.58,
      "grad_norm": 1.3932470083236694,
      "learning_rate": 4.24e-06,
      "loss": 1.6432,
      "step": 145
    },
    {
      "epoch": 0.584,
      "grad_norm": 1.2891041040420532,
      "learning_rate": 4.2000000000000004e-06,
      "loss": 1.562,
      "step": 146
    },
    {
      "epoch": 0.588,
      "grad_norm": 1.3476612567901611,
      "learning_rate": 4.16e-06,
      "loss": 1.6593,
      "step": 147
    },
    {
      "epoch": 0.592,
      "grad_norm": 1.3233203887939453,
      "learning_rate": 4.12e-06,
      "loss": 1.5696,
      "step": 148
    },
    {
      "epoch": 0.596,
      "grad_norm": 1.3516829013824463,
      "learning_rate": 4.08e-06,
      "loss": 1.6378,
      "step": 149
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.2899479866027832,
      "learning_rate": 4.04e-06,
      "loss": 1.6015,
      "step": 150
    },
    {
      "epoch": 0.604,
      "grad_norm": 1.4173705577850342,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.681,
      "step": 151
    },
    {
      "epoch": 0.608,
      "grad_norm": 1.3100056648254395,
      "learning_rate": 3.96e-06,
      "loss": 1.5746,
      "step": 152
    },
    {
      "epoch": 0.612,
      "grad_norm": 1.4304648637771606,
      "learning_rate": 3.920000000000001e-06,
      "loss": 1.5667,
      "step": 153
    },
    {
      "epoch": 0.616,
      "grad_norm": 1.4166439771652222,
      "learning_rate": 3.88e-06,
      "loss": 1.6874,
      "step": 154
    },
    {
      "epoch": 0.62,
      "grad_norm": 1.3523306846618652,
      "learning_rate": 3.8400000000000005e-06,
      "loss": 1.6085,
      "step": 155
    },
    {
      "epoch": 0.624,
      "grad_norm": 1.4200947284698486,
      "learning_rate": 3.8000000000000005e-06,
      "loss": 1.6213,
      "step": 156
    },
    {
      "epoch": 0.628,
      "grad_norm": 1.3680000305175781,
      "learning_rate": 3.7600000000000004e-06,
      "loss": 1.6323,
      "step": 157
    },
    {
      "epoch": 0.632,
      "grad_norm": 1.2544093132019043,
      "learning_rate": 3.7200000000000004e-06,
      "loss": 1.5722,
      "step": 158
    },
    {
      "epoch": 0.636,
      "grad_norm": 1.284311056137085,
      "learning_rate": 3.6800000000000003e-06,
      "loss": 1.538,
      "step": 159
    },
    {
      "epoch": 0.64,
      "grad_norm": 1.3962759971618652,
      "learning_rate": 3.6400000000000003e-06,
      "loss": 1.6742,
      "step": 160
    },
    {
      "epoch": 0.644,
      "grad_norm": 1.3595976829528809,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 1.6504,
      "step": 161
    },
    {
      "epoch": 0.648,
      "grad_norm": 1.4007598161697388,
      "learning_rate": 3.5600000000000002e-06,
      "loss": 1.6943,
      "step": 162
    },
    {
      "epoch": 0.652,
      "grad_norm": 1.404727578163147,
      "learning_rate": 3.52e-06,
      "loss": 1.6085,
      "step": 163
    },
    {
      "epoch": 0.656,
      "grad_norm": 1.4727367162704468,
      "learning_rate": 3.48e-06,
      "loss": 1.5892,
      "step": 164
    },
    {
      "epoch": 0.66,
      "grad_norm": 1.340226411819458,
      "learning_rate": 3.44e-06,
      "loss": 1.7069,
      "step": 165
    },
    {
      "epoch": 0.664,
      "grad_norm": 1.3784148693084717,
      "learning_rate": 3.4000000000000005e-06,
      "loss": 1.5993,
      "step": 166
    },
    {
      "epoch": 0.668,
      "grad_norm": 1.386871099472046,
      "learning_rate": 3.3600000000000004e-06,
      "loss": 1.5739,
      "step": 167
    },
    {
      "epoch": 0.672,
      "grad_norm": 1.4597012996673584,
      "learning_rate": 3.3200000000000004e-06,
      "loss": 1.7895,
      "step": 168
    },
    {
      "epoch": 0.676,
      "grad_norm": 1.5027787685394287,
      "learning_rate": 3.2800000000000004e-06,
      "loss": 1.6557,
      "step": 169
    },
    {
      "epoch": 0.68,
      "grad_norm": 1.4223504066467285,
      "learning_rate": 3.2400000000000003e-06,
      "loss": 1.6052,
      "step": 170
    },
    {
      "epoch": 0.684,
      "grad_norm": 1.4609079360961914,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 1.7185,
      "step": 171
    },
    {
      "epoch": 0.688,
      "grad_norm": 1.4065134525299072,
      "learning_rate": 3.1600000000000002e-06,
      "loss": 1.6011,
      "step": 172
    },
    {
      "epoch": 0.692,
      "grad_norm": 1.3931232690811157,
      "learning_rate": 3.12e-06,
      "loss": 1.5843,
      "step": 173
    },
    {
      "epoch": 0.696,
      "grad_norm": 1.4128152132034302,
      "learning_rate": 3.08e-06,
      "loss": 1.6525,
      "step": 174
    },
    {
      "epoch": 0.7,
      "grad_norm": 1.4391388893127441,
      "learning_rate": 3.04e-06,
      "loss": 1.6026,
      "step": 175
    },
    {
      "epoch": 0.704,
      "grad_norm": 1.4180413484573364,
      "learning_rate": 3e-06,
      "loss": 1.5877,
      "step": 176
    },
    {
      "epoch": 0.708,
      "grad_norm": 1.3166316747665405,
      "learning_rate": 2.96e-06,
      "loss": 1.6256,
      "step": 177
    },
    {
      "epoch": 0.712,
      "grad_norm": 1.3945341110229492,
      "learning_rate": 2.92e-06,
      "loss": 1.5426,
      "step": 178
    },
    {
      "epoch": 0.716,
      "grad_norm": 1.4100629091262817,
      "learning_rate": 2.88e-06,
      "loss": 1.4844,
      "step": 179
    },
    {
      "epoch": 0.72,
      "grad_norm": 1.5133711099624634,
      "learning_rate": 2.84e-06,
      "loss": 1.6189,
      "step": 180
    },
    {
      "epoch": 0.724,
      "grad_norm": 1.3762165307998657,
      "learning_rate": 2.8000000000000003e-06,
      "loss": 1.6345,
      "step": 181
    },
    {
      "epoch": 0.728,
      "grad_norm": 1.4408543109893799,
      "learning_rate": 2.7600000000000003e-06,
      "loss": 1.7058,
      "step": 182
    },
    {
      "epoch": 0.732,
      "grad_norm": 1.4354008436203003,
      "learning_rate": 2.7200000000000002e-06,
      "loss": 1.7113,
      "step": 183
    },
    {
      "epoch": 0.736,
      "grad_norm": 1.3285670280456543,
      "learning_rate": 2.68e-06,
      "loss": 1.5993,
      "step": 184
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.3333245515823364,
      "learning_rate": 2.64e-06,
      "loss": 1.5739,
      "step": 185
    },
    {
      "epoch": 0.744,
      "grad_norm": 1.5411490201950073,
      "learning_rate": 2.6e-06,
      "loss": 1.6264,
      "step": 186
    },
    {
      "epoch": 0.748,
      "grad_norm": 1.3106950521469116,
      "learning_rate": 2.56e-06,
      "loss": 1.555,
      "step": 187
    },
    {
      "epoch": 0.752,
      "grad_norm": 1.3158583641052246,
      "learning_rate": 2.52e-06,
      "loss": 1.5946,
      "step": 188
    },
    {
      "epoch": 0.756,
      "grad_norm": 1.4075291156768799,
      "learning_rate": 2.4800000000000004e-06,
      "loss": 1.565,
      "step": 189
    },
    {
      "epoch": 0.76,
      "grad_norm": 1.310943603515625,
      "learning_rate": 2.4400000000000004e-06,
      "loss": 1.5143,
      "step": 190
    },
    {
      "epoch": 0.764,
      "grad_norm": 1.434760570526123,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 1.659,
      "step": 191
    },
    {
      "epoch": 0.768,
      "grad_norm": 1.3629409074783325,
      "learning_rate": 2.3600000000000003e-06,
      "loss": 1.607,
      "step": 192
    },
    {
      "epoch": 0.772,
      "grad_norm": 1.3260722160339355,
      "learning_rate": 2.3200000000000002e-06,
      "loss": 1.4663,
      "step": 193
    },
    {
      "epoch": 0.776,
      "grad_norm": 1.4491920471191406,
      "learning_rate": 2.28e-06,
      "loss": 1.594,
      "step": 194
    },
    {
      "epoch": 0.78,
      "grad_norm": 1.4487640857696533,
      "learning_rate": 2.24e-06,
      "loss": 1.5447,
      "step": 195
    },
    {
      "epoch": 0.784,
      "grad_norm": 1.5706510543823242,
      "learning_rate": 2.2e-06,
      "loss": 1.6544,
      "step": 196
    },
    {
      "epoch": 0.788,
      "grad_norm": 1.368772268295288,
      "learning_rate": 2.16e-06,
      "loss": 1.515,
      "step": 197
    },
    {
      "epoch": 0.792,
      "grad_norm": 1.4399783611297607,
      "learning_rate": 2.12e-06,
      "loss": 1.6139,
      "step": 198
    },
    {
      "epoch": 0.796,
      "grad_norm": 1.3945013284683228,
      "learning_rate": 2.08e-06,
      "loss": 1.4373,
      "step": 199
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.3934296369552612,
      "learning_rate": 2.04e-06,
      "loss": 1.6531,
      "step": 200
    },
    {
      "epoch": 0.804,
      "grad_norm": 1.404791235923767,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 1.5855,
      "step": 201
    },
    {
      "epoch": 0.808,
      "grad_norm": 1.3408340215682983,
      "learning_rate": 1.9600000000000003e-06,
      "loss": 1.4074,
      "step": 202
    },
    {
      "epoch": 0.812,
      "grad_norm": 1.465818166732788,
      "learning_rate": 1.9200000000000003e-06,
      "loss": 1.6122,
      "step": 203
    },
    {
      "epoch": 0.816,
      "grad_norm": 1.3890620470046997,
      "learning_rate": 1.8800000000000002e-06,
      "loss": 1.6707,
      "step": 204
    },
    {
      "epoch": 0.82,
      "grad_norm": 1.3814433813095093,
      "learning_rate": 1.8400000000000002e-06,
      "loss": 1.5917,
      "step": 205
    },
    {
      "epoch": 0.824,
      "grad_norm": 1.4209574460983276,
      "learning_rate": 1.8000000000000001e-06,
      "loss": 1.6357,
      "step": 206
    },
    {
      "epoch": 0.828,
      "grad_norm": 1.2836953401565552,
      "learning_rate": 1.76e-06,
      "loss": 1.5397,
      "step": 207
    },
    {
      "epoch": 0.832,
      "grad_norm": 1.5015844106674194,
      "learning_rate": 1.72e-06,
      "loss": 1.6291,
      "step": 208
    },
    {
      "epoch": 0.836,
      "grad_norm": 1.3769359588623047,
      "learning_rate": 1.6800000000000002e-06,
      "loss": 1.5962,
      "step": 209
    },
    {
      "epoch": 0.84,
      "grad_norm": 1.430960774421692,
      "learning_rate": 1.6400000000000002e-06,
      "loss": 1.6396,
      "step": 210
    },
    {
      "epoch": 0.844,
      "grad_norm": 1.3863214254379272,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 1.6696,
      "step": 211
    },
    {
      "epoch": 0.848,
      "grad_norm": 1.364683985710144,
      "learning_rate": 1.56e-06,
      "loss": 1.4985,
      "step": 212
    },
    {
      "epoch": 0.852,
      "grad_norm": 1.4108574390411377,
      "learning_rate": 1.52e-06,
      "loss": 1.5946,
      "step": 213
    },
    {
      "epoch": 0.856,
      "grad_norm": 1.4607338905334473,
      "learning_rate": 1.48e-06,
      "loss": 1.585,
      "step": 214
    },
    {
      "epoch": 0.86,
      "grad_norm": 1.480090856552124,
      "learning_rate": 1.44e-06,
      "loss": 1.5559,
      "step": 215
    },
    {
      "epoch": 0.864,
      "grad_norm": 1.4284939765930176,
      "learning_rate": 1.4000000000000001e-06,
      "loss": 1.5759,
      "step": 216
    },
    {
      "epoch": 0.868,
      "grad_norm": 1.5613925457000732,
      "learning_rate": 1.3600000000000001e-06,
      "loss": 1.7214,
      "step": 217
    },
    {
      "epoch": 0.872,
      "grad_norm": 1.457170009613037,
      "learning_rate": 1.32e-06,
      "loss": 1.5808,
      "step": 218
    },
    {
      "epoch": 0.876,
      "grad_norm": 1.364310383796692,
      "learning_rate": 1.28e-06,
      "loss": 1.5733,
      "step": 219
    },
    {
      "epoch": 0.88,
      "grad_norm": 1.4274003505706787,
      "learning_rate": 1.2400000000000002e-06,
      "loss": 1.5918,
      "step": 220
    },
    {
      "epoch": 0.884,
      "grad_norm": 1.4450329542160034,
      "learning_rate": 1.2000000000000002e-06,
      "loss": 1.574,
      "step": 221
    },
    {
      "epoch": 0.888,
      "grad_norm": 1.4518463611602783,
      "learning_rate": 1.1600000000000001e-06,
      "loss": 1.5178,
      "step": 222
    },
    {
      "epoch": 0.892,
      "grad_norm": 1.3471320867538452,
      "learning_rate": 1.12e-06,
      "loss": 1.5961,
      "step": 223
    },
    {
      "epoch": 0.896,
      "grad_norm": 1.5115176439285278,
      "learning_rate": 1.08e-06,
      "loss": 1.5624,
      "step": 224
    },
    {
      "epoch": 0.9,
      "grad_norm": 1.3841177225112915,
      "learning_rate": 1.04e-06,
      "loss": 1.5607,
      "step": 225
    },
    {
      "epoch": 0.904,
      "grad_norm": 1.419216275215149,
      "learning_rate": 1.0000000000000002e-06,
      "loss": 1.6114,
      "step": 226
    },
    {
      "epoch": 0.908,
      "grad_norm": 1.4189485311508179,
      "learning_rate": 9.600000000000001e-07,
      "loss": 1.5479,
      "step": 227
    },
    {
      "epoch": 0.912,
      "grad_norm": 1.3959101438522339,
      "learning_rate": 9.200000000000001e-07,
      "loss": 1.6098,
      "step": 228
    },
    {
      "epoch": 0.916,
      "grad_norm": 1.460270643234253,
      "learning_rate": 8.8e-07,
      "loss": 1.5402,
      "step": 229
    },
    {
      "epoch": 0.92,
      "grad_norm": 1.4265800714492798,
      "learning_rate": 8.400000000000001e-07,
      "loss": 1.5805,
      "step": 230
    },
    {
      "epoch": 0.924,
      "grad_norm": 1.356236457824707,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.6396,
      "step": 231
    },
    {
      "epoch": 0.928,
      "grad_norm": 1.4282077550888062,
      "learning_rate": 7.6e-07,
      "loss": 1.6725,
      "step": 232
    },
    {
      "epoch": 0.932,
      "grad_norm": 1.5110477209091187,
      "learning_rate": 7.2e-07,
      "loss": 1.6143,
      "step": 233
    },
    {
      "epoch": 0.936,
      "grad_norm": 1.4182950258255005,
      "learning_rate": 6.800000000000001e-07,
      "loss": 1.5751,
      "step": 234
    },
    {
      "epoch": 0.94,
      "grad_norm": 1.4530798196792603,
      "learning_rate": 6.4e-07,
      "loss": 1.634,
      "step": 235
    },
    {
      "epoch": 0.944,
      "grad_norm": 1.4195228815078735,
      "learning_rate": 6.000000000000001e-07,
      "loss": 1.5055,
      "step": 236
    },
    {
      "epoch": 0.948,
      "grad_norm": 1.4488164186477661,
      "learning_rate": 5.6e-07,
      "loss": 1.61,
      "step": 237
    },
    {
      "epoch": 0.952,
      "grad_norm": 1.4380940198898315,
      "learning_rate": 5.2e-07,
      "loss": 1.5302,
      "step": 238
    },
    {
      "epoch": 0.956,
      "grad_norm": 1.4326223134994507,
      "learning_rate": 4.800000000000001e-07,
      "loss": 1.6128,
      "step": 239
    },
    {
      "epoch": 0.96,
      "grad_norm": 1.437170386314392,
      "learning_rate": 4.4e-07,
      "loss": 1.6482,
      "step": 240
    },
    {
      "epoch": 0.964,
      "grad_norm": 1.435649037361145,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 1.5889,
      "step": 241
    },
    {
      "epoch": 0.968,
      "grad_norm": 1.5094983577728271,
      "learning_rate": 3.6e-07,
      "loss": 1.6749,
      "step": 242
    },
    {
      "epoch": 0.972,
      "grad_norm": 1.35372793674469,
      "learning_rate": 3.2e-07,
      "loss": 1.5732,
      "step": 243
    },
    {
      "epoch": 0.976,
      "grad_norm": 1.4316813945770264,
      "learning_rate": 2.8e-07,
      "loss": 1.569,
      "step": 244
    },
    {
      "epoch": 0.98,
      "grad_norm": 1.419772982597351,
      "learning_rate": 2.4000000000000003e-07,
      "loss": 1.6188,
      "step": 245
    },
    {
      "epoch": 0.984,
      "grad_norm": 1.3961282968521118,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 1.5361,
      "step": 246
    },
    {
      "epoch": 0.988,
      "grad_norm": 1.4259065389633179,
      "learning_rate": 1.6e-07,
      "loss": 1.6011,
      "step": 247
    },
    {
      "epoch": 0.992,
      "grad_norm": 1.5136369466781616,
      "learning_rate": 1.2000000000000002e-07,
      "loss": 1.6597,
      "step": 248
    },
    {
      "epoch": 0.996,
      "grad_norm": 1.4152812957763672,
      "learning_rate": 8e-08,
      "loss": 1.6362,
      "step": 249
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.4813553094863892,
      "learning_rate": 4e-08,
      "loss": 1.5665,
      "step": 250
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.6056512594223022,
      "eval_runtime": 73.6777,
      "eval_samples_per_second": 6.786,
      "eval_steps_per_second": 0.855,
      "step": 250
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 0,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.0019312328704e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}