{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.7843866171003717,
  "eval_steps": 20,
  "global_step": 600,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 4.999999514321732e-06,
      "loss": 1.0024,
      "step": 1
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999998057287116e-06,
      "loss": 0.9077,
      "step": 2
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999995628896718e-06,
      "loss": 0.8987,
      "step": 3
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.99999222915148e-06,
      "loss": 0.8454,
      "step": 4
    },
    {
      "epoch": 0.01,
      "learning_rate": 4.999987858052726e-06,
      "loss": 0.8209,
      "step": 5
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999982515602153e-06,
      "loss": 0.7772,
      "step": 6
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.999976201801837e-06,
      "loss": 0.8463,
      "step": 7
    },
    {
      "epoch": 0.02,
      "learning_rate": 4.9999689166542295e-06,
      "loss": 0.7919,
      "step": 8
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.999960660162164e-06,
      "loss": 0.7842,
      "step": 9
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.999951432328846e-06,
      "loss": 0.7671,
      "step": 10
    },
    {
      "epoch": 0.03,
      "learning_rate": 4.9999412331578625e-06,
      "loss": 0.8076,
      "step": 11
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.999930062653175e-06,
      "loss": 0.7818,
      "step": 12
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.999917920819125e-06,
      "loss": 0.7552,
      "step": 13
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.9999048076604286e-06,
      "loss": 0.7159,
      "step": 14
    },
    {
      "epoch": 0.04,
      "learning_rate": 4.999890723182183e-06,
      "loss": 0.7466,
      "step": 15
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.999875667389858e-06,
      "loss": 0.7511,
      "step": 16
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.999859640289305e-06,
      "loss": 0.7242,
      "step": 17
    },
    {
      "epoch": 0.05,
      "learning_rate": 4.999842641886752e-06,
      "loss": 0.7401,
      "step": 18
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.9998246721888025e-06,
      "loss": 0.724,
      "step": 19
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.999805731202437e-06,
      "loss": 0.7502,
      "step": 20
    },
    {
      "epoch": 0.06,
      "eval_loss": 0.7227846384048462,
      "eval_runtime": 39.5283,
      "eval_samples_per_second": 43.994,
      "eval_steps_per_second": 2.758,
      "step": 20
    },
    {
      "epoch": 0.06,
      "learning_rate": 4.999785818935018e-06,
      "loss": 0.7096,
      "step": 21
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.99976493539428e-06,
      "loss": 0.7067,
      "step": 22
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.999743080588338e-06,
      "loss": 0.719,
      "step": 23
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.999720254525684e-06,
      "loss": 0.7228,
      "step": 24
    },
    {
      "epoch": 0.07,
      "learning_rate": 4.999696457215186e-06,
      "loss": 0.7068,
      "step": 25
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.99967168866609e-06,
      "loss": 0.7037,
      "step": 26
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9996459488880215e-06,
      "loss": 0.7121,
      "step": 27
    },
    {
      "epoch": 0.08,
      "learning_rate": 4.9996192378909785e-06,
      "loss": 0.7234,
      "step": 28
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.999591555685342e-06,
      "loss": 0.6974,
      "step": 29
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.999562902281866e-06,
      "loss": 0.6859,
      "step": 30
    },
    {
      "epoch": 0.09,
      "learning_rate": 4.999533277691686e-06,
      "loss": 0.7148,
      "step": 31
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.999502681926309e-06,
      "loss": 0.677,
      "step": 32
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.9994711149976254e-06,
      "loss": 0.6884,
      "step": 33
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.999438576917899e-06,
      "loss": 0.7021,
      "step": 34
    },
    {
      "epoch": 0.1,
      "learning_rate": 4.999405067699773e-06,
      "loss": 0.68,
      "step": 35
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.999370587356267e-06,
      "loss": 0.6944,
      "step": 36
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.999335135900778e-06,
      "loss": 0.7073,
      "step": 37
    },
    {
      "epoch": 0.11,
      "learning_rate": 4.999298713347079e-06,
      "loss": 0.6861,
      "step": 38
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.9992613197093246e-06,
      "loss": 0.714,
      "step": 39
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.999222955002041e-06,
      "loss": 0.7165,
      "step": 40
    },
    {
      "epoch": 0.12,
      "eval_loss": 0.6958964467048645,
      "eval_runtime": 39.5063,
      "eval_samples_per_second": 44.018,
      "eval_steps_per_second": 2.759,
      "step": 40
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.999183619240137e-06,
      "loss": 0.677,
      "step": 41
    },
    {
      "epoch": 0.12,
      "learning_rate": 4.999143312438893e-06,
      "loss": 0.6901,
      "step": 42
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.999102034613974e-06,
      "loss": 0.6868,
      "step": 43
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.999059785781415e-06,
      "loss": 0.6457,
      "step": 44
    },
    {
      "epoch": 0.13,
      "learning_rate": 4.999016565957633e-06,
      "loss": 0.7124,
      "step": 45
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.99897237515942e-06,
      "loss": 0.6921,
      "step": 46
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.998927213403946e-06,
      "loss": 0.7235,
      "step": 47
    },
    {
      "epoch": 0.14,
      "learning_rate": 4.998881080708759e-06,
      "loss": 0.6866,
      "step": 48
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.998833977091783e-06,
      "loss": 0.6991,
      "step": 49
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.998785902571319e-06,
      "loss": 0.6874,
      "step": 50
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.998736857166048e-06,
      "loss": 0.689,
      "step": 51
    },
    {
      "epoch": 0.15,
      "learning_rate": 4.998686840895025e-06,
      "loss": 0.6745,
      "step": 52
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.998635853777683e-06,
      "loss": 0.6948,
      "step": 53
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.998583895833834e-06,
      "loss": 0.6492,
      "step": 54
    },
    {
      "epoch": 0.16,
      "learning_rate": 4.998530967083664e-06,
      "loss": 0.6781,
      "step": 55
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.99847706754774e-06,
      "loss": 0.6466,
      "step": 56
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.998422197247003e-06,
      "loss": 0.6823,
      "step": 57
    },
    {
      "epoch": 0.17,
      "learning_rate": 4.998366356202773e-06,
      "loss": 0.7007,
      "step": 58
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.998309544436745e-06,
      "loss": 0.6563,
      "step": 59
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.998251761970997e-06,
      "loss": 0.6936,
      "step": 60
    },
    {
      "epoch": 0.18,
      "eval_loss": 0.6835957765579224,
      "eval_runtime": 39.5096,
      "eval_samples_per_second": 44.015,
      "eval_steps_per_second": 2.759,
      "step": 60
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.9981930088279755e-06,
      "loss": 0.7045,
      "step": 61
    },
    {
      "epoch": 0.18,
      "learning_rate": 4.998133285030511e-06,
      "loss": 0.6713,
      "step": 62
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.998072590601808e-06,
      "loss": 0.6591,
      "step": 63
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.998010925565449e-06,
      "loss": 0.7107,
      "step": 64
    },
    {
      "epoch": 0.19,
      "learning_rate": 4.997948289945392e-06,
      "loss": 0.6633,
      "step": 65
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.997884683765977e-06,
      "loss": 0.6693,
      "step": 66
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.997820107051915e-06,
      "loss": 0.6733,
      "step": 67
    },
    {
      "epoch": 0.2,
      "learning_rate": 4.997754559828297e-06,
      "loss": 0.6679,
      "step": 68
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.997688042120592e-06,
      "loss": 0.6516,
      "step": 69
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.997620553954645e-06,
      "loss": 0.6691,
      "step": 70
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.997552095356677e-06,
      "loss": 0.6721,
      "step": 71
    },
    {
      "epoch": 0.21,
      "learning_rate": 4.997482666353287e-06,
      "loss": 0.7046,
      "step": 72
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.997412266971452e-06,
      "loss": 0.6813,
      "step": 73
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.997340897238525e-06,
      "loss": 0.6672,
      "step": 74
    },
    {
      "epoch": 0.22,
      "learning_rate": 4.9972685571822355e-06,
      "loss": 0.7085,
      "step": 75
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.997195246830692e-06,
      "loss": 0.672,
      "step": 76
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.9971209662123774e-06,
      "loss": 0.6817,
      "step": 77
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.997045715356153e-06,
      "loss": 0.6671,
      "step": 78
    },
    {
      "epoch": 0.23,
      "learning_rate": 4.996969494291258e-06,
      "loss": 0.6941,
      "step": 79
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.996892303047306e-06,
      "loss": 0.6579,
      "step": 80
    },
    {
      "epoch": 0.24,
      "eval_loss": 0.6751722693443298,
      "eval_runtime": 39.5352,
      "eval_samples_per_second": 43.986,
      "eval_steps_per_second": 2.757,
      "step": 80
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.996814141654291e-06,
      "loss": 0.6922,
      "step": 81
    },
    {
      "epoch": 0.24,
      "learning_rate": 4.996735010142581e-06,
      "loss": 0.681,
      "step": 82
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.9966549085429204e-06,
      "loss": 0.6792,
      "step": 83
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.9965738368864345e-06,
      "loss": 0.6483,
      "step": 84
    },
    {
      "epoch": 0.25,
      "learning_rate": 4.996491795204623e-06,
      "loss": 0.6644,
      "step": 85
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.996408783529361e-06,
      "loss": 0.6983,
      "step": 86
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.996324801892904e-06,
      "loss": 0.6903,
      "step": 87
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.99623985032788e-06,
      "loss": 0.6619,
      "step": 88
    },
    {
      "epoch": 0.26,
      "learning_rate": 4.996153928867298e-06,
      "loss": 0.6652,
      "step": 89
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.996067037544542e-06,
      "loss": 0.6716,
      "step": 90
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.995979176393372e-06,
      "loss": 0.6627,
      "step": 91
    },
    {
      "epoch": 0.27,
      "learning_rate": 4.995890345447928e-06,
      "loss": 0.6508,
      "step": 92
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.9958005447427225e-06,
      "loss": 0.6599,
      "step": 93
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.995709774312647e-06,
      "loss": 0.673,
      "step": 94
    },
    {
      "epoch": 0.28,
      "learning_rate": 4.99561803419297e-06,
      "loss": 0.641,
      "step": 95
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.995525324419338e-06,
      "loss": 0.6521,
      "step": 96
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.995431645027772e-06,
      "loss": 0.6697,
      "step": 97
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.995336996054668e-06,
      "loss": 0.6851,
      "step": 98
    },
    {
      "epoch": 0.29,
      "learning_rate": 4.9952413775368034e-06,
      "loss": 0.6923,
      "step": 99
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.9951447895113305e-06,
      "loss": 0.6363,
      "step": 100
    },
    {
      "epoch": 0.3,
      "eval_loss": 0.6683968305587769,
      "eval_runtime": 39.5326,
      "eval_samples_per_second": 43.989,
      "eval_steps_per_second": 2.757,
      "step": 100
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.995047232015776e-06,
      "loss": 0.6792,
      "step": 101
    },
    {
      "epoch": 0.3,
      "learning_rate": 4.994948705088047e-06,
      "loss": 0.6318,
      "step": 102
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.994849208766424e-06,
      "loss": 0.6595,
      "step": 103
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.994748743089566e-06,
      "loss": 0.6378,
      "step": 104
    },
    {
      "epoch": 0.31,
      "learning_rate": 4.994647308096509e-06,
      "loss": 0.66,
      "step": 105
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.9945449038266645e-06,
      "loss": 0.6639,
      "step": 106
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.99444153031982e-06,
      "loss": 0.667,
      "step": 107
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.99433718761614e-06,
      "loss": 0.6599,
      "step": 108
    },
    {
      "epoch": 0.32,
      "learning_rate": 4.994231875756169e-06,
      "loss": 0.6432,
      "step": 109
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.9941255947808226e-06,
      "loss": 0.6605,
      "step": 110
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.9940183447313964e-06,
      "loss": 0.685,
      "step": 111
    },
    {
      "epoch": 0.33,
      "learning_rate": 4.993910125649561e-06,
      "loss": 0.6442,
      "step": 112
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.993800937577365e-06,
      "loss": 0.6691,
      "step": 113
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.993690780557232e-06,
      "loss": 0.6888,
      "step": 114
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.993579654631963e-06,
      "loss": 0.644,
      "step": 115
    },
    {
      "epoch": 0.34,
      "learning_rate": 4.993467559844734e-06,
      "loss": 0.6655,
      "step": 116
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.993354496239101e-06,
      "loss": 0.6807,
      "step": 117
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.993240463858993e-06,
      "loss": 0.6774,
      "step": 118
    },
    {
      "epoch": 0.35,
      "learning_rate": 4.993125462748714e-06,
      "loss": 0.6882,
      "step": 119
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.993009492952951e-06,
      "loss": 0.6522,
      "step": 120
    },
    {
      "epoch": 0.36,
      "eval_loss": 0.6635560989379883,
      "eval_runtime": 39.5158,
      "eval_samples_per_second": 44.008,
      "eval_steps_per_second": 2.758,
      "step": 120
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.99289255451676e-06,
      "loss": 0.6465,
      "step": 121
    },
    {
      "epoch": 0.36,
      "learning_rate": 4.9927746474855785e-06,
      "loss": 0.6759,
      "step": 122
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.992655771905217e-06,
      "loss": 0.6687,
      "step": 123
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.992535927821865e-06,
      "loss": 0.6463,
      "step": 124
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.992415115282085e-06,
      "loss": 0.6463,
      "step": 125
    },
    {
      "epoch": 0.37,
      "learning_rate": 4.992293334332821e-06,
      "loss": 0.6412,
      "step": 126
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.9921705850213865e-06,
      "loss": 0.6528,
      "step": 127
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.992046867395478e-06,
      "loss": 0.668,
      "step": 128
    },
    {
      "epoch": 0.38,
      "learning_rate": 4.9919221815031625e-06,
      "loss": 0.6377,
      "step": 129
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.991796527392888e-06,
      "loss": 0.6498,
      "step": 130
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.991669905113476e-06,
      "loss": 0.6552,
      "step": 131
    },
    {
      "epoch": 0.39,
      "learning_rate": 4.991542314714122e-06,
      "loss": 0.6648,
      "step": 132
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.991413756244404e-06,
      "loss": 0.6717,
      "step": 133
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.99128422975427e-06,
      "loss": 0.6821,
      "step": 134
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.9911537352940485e-06,
      "loss": 0.6653,
      "step": 135
    },
    {
      "epoch": 0.4,
      "learning_rate": 4.99102227291444e-06,
      "loss": 0.6698,
      "step": 136
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.990889842666525e-06,
      "loss": 0.6763,
      "step": 137
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.990756444601757e-06,
      "loss": 0.6918,
      "step": 138
    },
    {
      "epoch": 0.41,
      "learning_rate": 4.990622078771968e-06,
      "loss": 0.6492,
      "step": 139
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.990486745229364e-06,
      "loss": 0.6223,
      "step": 140
    },
    {
      "epoch": 0.42,
      "eval_loss": 0.6595442295074463,
      "eval_runtime": 39.5303,
      "eval_samples_per_second": 43.992,
      "eval_steps_per_second": 2.757,
      "step": 140
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.990350444026528e-06,
      "loss": 0.6477,
      "step": 141
    },
    {
      "epoch": 0.42,
      "learning_rate": 4.99021317521642e-06,
      "loss": 0.6559,
      "step": 142
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.990074938852373e-06,
      "loss": 0.6681,
      "step": 143
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.989935734988098e-06,
      "loss": 0.6726,
      "step": 144
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.9897955636776824e-06,
      "loss": 0.6502,
      "step": 145
    },
    {
      "epoch": 0.43,
      "learning_rate": 4.9896544249755885e-06,
      "loss": 0.6779,
      "step": 146
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.989512318936654e-06,
      "loss": 0.6774,
      "step": 147
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.9893692456160955e-06,
      "loss": 0.6677,
      "step": 148
    },
    {
      "epoch": 0.44,
      "learning_rate": 4.9892252050695e-06,
      "loss": 0.6616,
      "step": 149
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.989080197352834e-06,
      "loss": 0.6497,
      "step": 150
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.988934222522442e-06,
      "loss": 0.6399,
      "step": 151
    },
    {
      "epoch": 0.45,
      "learning_rate": 4.9887872806350376e-06,
      "loss": 0.6145,
      "step": 152
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.988639371747717e-06,
      "loss": 0.695,
      "step": 153
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.988490495917948e-06,
      "loss": 0.6569,
      "step": 154
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.9883406532035735e-06,
      "loss": 0.657,
      "step": 155
    },
    {
      "epoch": 0.46,
      "learning_rate": 4.9881898436628165e-06,
      "loss": 0.6438,
      "step": 156
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.988038067354272e-06,
      "loss": 0.6654,
      "step": 157
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.987885324336911e-06,
      "loss": 0.6643,
      "step": 158
    },
    {
      "epoch": 0.47,
      "learning_rate": 4.98773161467008e-06,
      "loss": 0.6412,
      "step": 159
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.987576938413504e-06,
      "loss": 0.6371,
      "step": 160
    },
    {
      "epoch": 0.48,
      "eval_loss": 0.6561623215675354,
      "eval_runtime": 39.5223,
      "eval_samples_per_second": 44.0,
      "eval_steps_per_second": 2.758,
      "step": 160
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.987421295627279e-06,
      "loss": 0.6445,
      "step": 161
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.987264686371881e-06,
      "loss": 0.6584,
      "step": 162
    },
    {
      "epoch": 0.48,
      "learning_rate": 4.987107110708158e-06,
      "loss": 0.6544,
      "step": 163
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.986948568697335e-06,
      "loss": 0.6247,
      "step": 164
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.9867890604010125e-06,
      "loss": 0.6767,
      "step": 165
    },
    {
      "epoch": 0.49,
      "learning_rate": 4.986628585881167e-06,
      "loss": 0.6595,
      "step": 166
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.986467145200148e-06,
      "loss": 0.6309,
      "step": 167
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.986304738420684e-06,
      "loss": 0.6716,
      "step": 168
    },
    {
      "epoch": 0.5,
      "learning_rate": 4.9861413656058755e-06,
      "loss": 0.641,
      "step": 169
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.9859770268192e-06,
      "loss": 0.6891,
      "step": 170
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.98581172212451e-06,
      "loss": 0.6505,
      "step": 171
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.985645451586035e-06,
      "loss": 0.6502,
      "step": 172
    },
    {
      "epoch": 0.51,
      "learning_rate": 4.985478215268377e-06,
      "loss": 0.6353,
      "step": 173
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.985310013236514e-06,
      "loss": 0.6867,
      "step": 174
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.985140845555799e-06,
      "loss": 0.656,
      "step": 175
    },
    {
      "epoch": 0.52,
      "learning_rate": 4.984970712291963e-06,
      "loss": 0.6503,
      "step": 176
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.98479961351111e-06,
      "loss": 0.6861,
      "step": 177
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.984627549279717e-06,
      "loss": 0.6341,
      "step": 178
    },
    {
      "epoch": 0.53,
      "learning_rate": 4.984454519664639e-06,
      "loss": 0.6204,
      "step": 179
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.984280524733107e-06,
      "loss": 0.6576,
      "step": 180
    },
    {
      "epoch": 0.54,
      "eval_loss": 0.6528674364089966,
      "eval_runtime": 39.5337,
      "eval_samples_per_second": 43.988,
      "eval_steps_per_second": 2.757,
      "step": 180
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.9841055645527234e-06,
      "loss": 0.6314,
      "step": 181
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.9839296391914696e-06,
      "loss": 0.6408,
      "step": 182
    },
    {
      "epoch": 0.54,
      "learning_rate": 4.9837527487176975e-06,
      "loss": 0.6288,
      "step": 183
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.983574893200139e-06,
      "loss": 0.6423,
      "step": 184
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.983396072707898e-06,
      "loss": 0.6718,
      "step": 185
    },
    {
      "epoch": 0.55,
      "learning_rate": 4.983216287310453e-06,
      "loss": 0.6591,
      "step": 186
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.983035537077659e-06,
      "loss": 0.6423,
      "step": 187
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.982853822079746e-06,
      "loss": 0.6556,
      "step": 188
    },
    {
      "epoch": 0.56,
      "learning_rate": 4.982671142387316e-06,
      "loss": 0.6323,
      "step": 189
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.982487498071349e-06,
      "loss": 0.6533,
      "step": 190
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.9823028892031985e-06,
      "loss": 0.6631,
      "step": 191
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.982117315854594e-06,
      "loss": 0.664,
      "step": 192
    },
    {
      "epoch": 0.57,
      "learning_rate": 4.981930778097637e-06,
      "loss": 0.6493,
      "step": 193
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.981743276004805e-06,
      "loss": 0.6734,
      "step": 194
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.981554809648952e-06,
      "loss": 0.6283,
      "step": 195
    },
    {
      "epoch": 0.58,
      "learning_rate": 4.981365379103306e-06,
      "loss": 0.6392,
      "step": 196
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.981174984441466e-06,
      "loss": 0.6378,
      "step": 197
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.980983625737411e-06,
      "loss": 0.6466,
      "step": 198
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.98079130306549e-06,
      "loss": 0.6427,
      "step": 199
    },
    {
      "epoch": 0.59,
      "learning_rate": 4.980598016500431e-06,
      "loss": 0.6068,
      "step": 200
    },
    {
      "epoch": 0.59,
      "eval_loss": 0.6502168774604797,
      "eval_runtime": 39.5276,
      "eval_samples_per_second": 43.995,
      "eval_steps_per_second": 2.758,
      "step": 200
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.980403766117332e-06,
      "loss": 0.645,
      "step": 201
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.980208551991668e-06,
      "loss": 0.6227,
      "step": 202
    },
    {
      "epoch": 0.6,
      "learning_rate": 4.980012374199288e-06,
      "loss": 0.6326,
      "step": 203
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.9798152328164165e-06,
      "loss": 0.6256,
      "step": 204
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.97961712791965e-06,
      "loss": 0.6248,
      "step": 205
    },
    {
      "epoch": 0.61,
      "learning_rate": 4.97941805958596e-06,
      "loss": 0.6727,
      "step": 206
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.979218027892696e-06,
      "loss": 0.6513,
      "step": 207
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.979017032917576e-06,
      "loss": 0.6224,
      "step": 208
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.9788150747386965e-06,
      "loss": 0.6665,
      "step": 209
    },
    {
      "epoch": 0.62,
      "learning_rate": 4.978612153434527e-06,
      "loss": 0.6644,
      "step": 210
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.9784082690839095e-06,
      "loss": 0.6526,
      "step": 211
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.978203421766064e-06,
      "loss": 0.6274,
      "step": 212
    },
    {
      "epoch": 0.63,
      "learning_rate": 4.97799761156058e-06,
      "loss": 0.6677,
      "step": 213
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.9777908385474256e-06,
      "loss": 0.6453,
      "step": 214
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.97758310280694e-06,
      "loss": 0.6374,
      "step": 215
    },
    {
      "epoch": 0.64,
      "learning_rate": 4.977374404419838e-06,
      "loss": 0.6428,
      "step": 216
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.977164743467206e-06,
      "loss": 0.6282,
      "step": 217
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.976954120030508e-06,
      "loss": 0.6553,
      "step": 218
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.976742534191581e-06,
      "loss": 0.6646,
      "step": 219
    },
    {
      "epoch": 0.65,
      "learning_rate": 4.976529986032632e-06,
      "loss": 0.6222,
      "step": 220
    },
    {
      "epoch": 0.65,
      "eval_loss": 0.6474757790565491,
      "eval_runtime": 39.5181,
      "eval_samples_per_second": 44.005,
      "eval_steps_per_second": 2.758,
      "step": 220
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.976316475636248e-06,
      "loss": 0.6518,
      "step": 221
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.9761020030853854e-06,
      "loss": 0.6461,
      "step": 222
    },
    {
      "epoch": 0.66,
      "learning_rate": 4.975886568463376e-06,
      "loss": 0.6306,
      "step": 223
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.975670171853926e-06,
      "loss": 0.6416,
      "step": 224
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.9754528133411144e-06,
      "loss": 0.6922,
      "step": 225
    },
    {
      "epoch": 0.67,
      "learning_rate": 4.975234493009394e-06,
      "loss": 0.6384,
      "step": 226
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.975015210943591e-06,
      "loss": 0.6433,
      "step": 227
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.9747949672289075e-06,
      "loss": 0.6179,
      "step": 228
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.974573761950916e-06,
      "loss": 0.6767,
      "step": 229
    },
    {
      "epoch": 0.68,
      "learning_rate": 4.9743515951955655e-06,
      "loss": 0.6406,
      "step": 230
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.974128467049177e-06,
      "loss": 0.6374,
      "step": 231
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.973904377598443e-06,
      "loss": 0.6378,
      "step": 232
    },
    {
      "epoch": 0.69,
      "learning_rate": 4.973679326930434e-06,
      "loss": 0.63,
      "step": 233
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.973453315132592e-06,
      "loss": 0.6733,
      "step": 234
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.973226342292732e-06,
      "loss": 0.6531,
      "step": 235
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.972998408499041e-06,
      "loss": 0.6445,
      "step": 236
    },
    {
      "epoch": 0.7,
      "learning_rate": 4.972769513840083e-06,
      "loss": 0.6307,
      "step": 237
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.972539658404793e-06,
      "loss": 0.6201,
      "step": 238
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.972308842282478e-06,
      "loss": 0.6496,
      "step": 239
    },
    {
      "epoch": 0.71,
      "learning_rate": 4.9720770655628216e-06,
      "loss": 0.6283,
      "step": 240
    },
    {
      "epoch": 0.71,
      "eval_loss": 0.6447574496269226,
      "eval_runtime": 39.5185,
      "eval_samples_per_second": 44.005,
      "eval_steps_per_second": 2.758,
      "step": 240
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.9718443283358785e-06,
      "loss": 0.6369,
      "step": 241
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.971610630692077e-06,
      "loss": 0.6612,
      "step": 242
    },
    {
      "epoch": 0.72,
      "learning_rate": 4.9713759727222184e-06,
      "loss": 0.62,
      "step": 243
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.971140354517477e-06,
      "loss": 0.6574,
      "step": 244
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.970903776169403e-06,
      "loss": 0.6248,
      "step": 245
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.970666237769913e-06,
      "loss": 0.6576,
      "step": 246
    },
    {
      "epoch": 0.73,
      "learning_rate": 4.970427739411303e-06,
      "loss": 0.6548,
      "step": 247
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.970188281186241e-06,
      "loss": 0.6369,
      "step": 248
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.969947863187764e-06,
      "loss": 0.6373,
      "step": 249
    },
    {
      "epoch": 0.74,
      "learning_rate": 4.969706485509287e-06,
      "loss": 0.6432,
      "step": 250
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.969464148244595e-06,
      "loss": 0.632,
      "step": 251
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.9692208514878445e-06,
      "loss": 0.6077,
      "step": 252
    },
    {
      "epoch": 0.75,
      "learning_rate": 4.968976595333569e-06,
      "loss": 0.6217,
      "step": 253
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.9687313798766714e-06,
      "loss": 0.6337,
      "step": 254
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.968485205212429e-06,
      "loss": 0.6033,
      "step": 255
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.9682380714364895e-06,
      "loss": 0.6411,
      "step": 256
    },
    {
      "epoch": 0.76,
      "learning_rate": 4.967989978644877e-06,
      "loss": 0.6525,
      "step": 257
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.967740926933985e-06,
      "loss": 0.6295,
      "step": 258
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.9674909164005805e-06,
      "loss": 0.6217,
      "step": 259
    },
    {
      "epoch": 0.77,
      "learning_rate": 4.967239947141803e-06,
      "loss": 0.6687,
      "step": 260
    },
    {
      "epoch": 0.77,
      "eval_loss": 0.6423989534378052,
      "eval_runtime": 39.5124,
      "eval_samples_per_second": 44.012,
      "eval_steps_per_second": 2.759,
      "step": 260
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.966988019255167e-06,
      "loss": 0.6373,
      "step": 261
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.9667351328385535e-06,
      "loss": 0.6775,
      "step": 262
    },
    {
      "epoch": 0.78,
      "learning_rate": 4.966481287990223e-06,
      "loss": 0.6396,
      "step": 263
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.966226484808804e-06,
      "loss": 0.6435,
      "step": 264
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.965970723393297e-06,
      "loss": 0.6212,
      "step": 265
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.965714003843079e-06,
      "loss": 0.6087,
      "step": 266
    },
    {
      "epoch": 0.79,
      "learning_rate": 4.965456326257894e-06,
      "loss": 0.6403,
      "step": 267
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.965197690737862e-06,
      "loss": 0.6155,
      "step": 268
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.964938097383472e-06,
      "loss": 0.6329,
      "step": 269
    },
    {
      "epoch": 0.8,
      "learning_rate": 4.96467754629559e-06,
      "loss": 0.6584,
      "step": 270
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.9644160375754495e-06,
      "loss": 0.6187,
      "step": 271
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.964153571324658e-06,
      "loss": 0.627,
      "step": 272
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.963890147645195e-06,
      "loss": 0.6162,
      "step": 273
    },
    {
      "epoch": 0.81,
      "learning_rate": 4.9636257666394115e-06,
      "loss": 0.6269,
      "step": 274
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.963360428410031e-06,
      "loss": 0.627,
      "step": 275
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.963094133060148e-06,
      "loss": 0.6189,
      "step": 276
    },
    {
      "epoch": 0.82,
      "learning_rate": 4.9628268806932315e-06,
      "loss": 0.6563,
      "step": 277
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.962558671413119e-06,
      "loss": 0.6775,
      "step": 278
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.962289505324021e-06,
      "loss": 0.6539,
      "step": 279
    },
    {
      "epoch": 0.83,
      "learning_rate": 4.962019382530521e-06,
      "loss": 0.6355,
      "step": 280
    },
    {
      "epoch": 0.83,
      "eval_loss": 0.6408971548080444,
      "eval_runtime": 39.5077,
      "eval_samples_per_second": 44.017,
      "eval_steps_per_second": 2.759,
      "step": 280
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.9617483031375716e-06,
      "loss": 0.6297,
      "step": 281
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.961476267250501e-06,
      "loss": 0.6523,
      "step": 282
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.961203274975005e-06,
      "loss": 0.6365,
      "step": 283
    },
    {
      "epoch": 0.84,
      "learning_rate": 4.960929326417153e-06,
      "loss": 0.6268,
      "step": 284
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.9606544216833865e-06,
      "loss": 0.6205,
      "step": 285
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.960378560880516e-06,
      "loss": 0.6789,
      "step": 286
    },
    {
      "epoch": 0.85,
      "learning_rate": 4.960101744115727e-06,
      "loss": 0.6482,
      "step": 287
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.959823971496575e-06,
      "loss": 0.6485,
      "step": 288
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.959545243130984e-06,
      "loss": 0.6342,
      "step": 289
    },
    {
      "epoch": 0.86,
      "learning_rate": 4.959265559127253e-06,
      "loss": 0.6549,
      "step": 290
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.958984919594053e-06,
      "loss": 0.6364,
      "step": 291
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.9587033246404215e-06,
      "loss": 0.6296,
      "step": 292
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.958420774375772e-06,
      "loss": 0.6016,
      "step": 293
    },
    {
      "epoch": 0.87,
      "learning_rate": 4.958137268909887e-06,
      "loss": 0.644,
      "step": 294
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.95785280835292e-06,
      "loss": 0.6439,
      "step": 295
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.957567392815396e-06,
      "loss": 0.6293,
      "step": 296
    },
    {
      "epoch": 0.88,
      "learning_rate": 4.957281022408212e-06,
      "loss": 0.6798,
      "step": 297
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.956993697242634e-06,
      "loss": 0.6547,
      "step": 298
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.956705417430301e-06,
      "loss": 0.6492,
      "step": 299
    },
    {
      "epoch": 0.89,
      "learning_rate": 4.9564161830832214e-06,
      "loss": 0.6338,
      "step": 300
    },
    {
      "epoch": 0.89,
      "eval_loss": 0.639053225517273,
      "eval_runtime": 39.5137,
      "eval_samples_per_second": 44.01,
      "eval_steps_per_second": 2.759,
      "step": 300
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.956125994313775e-06,
      "loss": 0.6629,
      "step": 301
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.955834851234712e-06,
      "loss": 0.6254,
      "step": 302
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.955542753959156e-06,
      "loss": 0.6427,
      "step": 303
    },
    {
      "epoch": 0.9,
      "learning_rate": 4.955249702600598e-06,
      "loss": 0.6149,
      "step": 304
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.954955697272899e-06,
      "loss": 0.6363,
      "step": 305
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.954660738090297e-06,
      "loss": 0.6476,
      "step": 306
    },
    {
      "epoch": 0.91,
      "learning_rate": 4.954364825167392e-06,
      "loss": 0.677,
      "step": 307
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.9540679586191605e-06,
      "loss": 0.6239,
      "step": 308
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.953770138560947e-06,
      "loss": 0.6511,
      "step": 309
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.95347136510847e-06,
      "loss": 0.6352,
      "step": 310
    },
    {
      "epoch": 0.92,
      "learning_rate": 4.9531716383778115e-06,
      "loss": 0.6302,
      "step": 311
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.9528709584854316e-06,
      "loss": 0.643,
      "step": 312
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.952569325548156e-06,
      "loss": 0.6185,
      "step": 313
    },
    {
      "epoch": 0.93,
      "learning_rate": 4.952266739683182e-06,
      "loss": 0.6017,
      "step": 314
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.9519632010080765e-06,
      "loss": 0.6292,
      "step": 315
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.951658709640778e-06,
      "loss": 0.6513,
      "step": 316
    },
    {
      "epoch": 0.94,
      "learning_rate": 4.951353265699594e-06,
      "loss": 0.6489,
      "step": 317
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.951046869303202e-06,
      "loss": 0.6368,
      "step": 318
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.950739520570652e-06,
      "loss": 0.6547,
      "step": 319
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.9504312196213596e-06,
      "loss": 0.6711,
      "step": 320
    },
    {
      "epoch": 0.95,
      "eval_loss": 0.637545108795166,
      "eval_runtime": 39.5156,
      "eval_samples_per_second": 44.008,
      "eval_steps_per_second": 2.758,
      "step": 320
    },
    {
      "epoch": 0.95,
      "learning_rate": 4.950121966575115e-06,
      "loss": 0.6619,
      "step": 321
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.949811761552074e-06,
      "loss": 0.6505,
      "step": 322
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.949500604672767e-06,
      "loss": 0.6282,
      "step": 323
    },
    {
      "epoch": 0.96,
      "learning_rate": 4.949188496058089e-06,
      "loss": 0.6256,
      "step": 324
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.94887543582931e-06,
      "loss": 0.6062,
      "step": 325
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.9485614241080655e-06,
      "loss": 0.6364,
      "step": 326
    },
    {
      "epoch": 0.97,
      "learning_rate": 4.948246461016362e-06,
      "loss": 0.6439,
      "step": 327
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.9479305466765796e-06,
      "loss": 0.6166,
      "step": 328
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.94761368121146e-06,
      "loss": 0.64,
      "step": 329
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.947295864744121e-06,
      "loss": 0.6348,
      "step": 330
    },
    {
      "epoch": 0.98,
      "learning_rate": 4.946977097398049e-06,
      "loss": 0.6365,
      "step": 331
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.946657379297096e-06,
      "loss": 0.6683,
      "step": 332
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.946336710565489e-06,
      "loss": 0.6458,
      "step": 333
    },
    {
      "epoch": 0.99,
      "learning_rate": 4.946015091327819e-06,
      "loss": 0.6634,
      "step": 334
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.94569252170905e-06,
      "loss": 0.6629,
      "step": 335
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.9453690018345144e-06,
      "loss": 0.6152,
      "step": 336
    },
    {
      "epoch": 1.0,
      "learning_rate": 4.945044531829913e-06,
      "loss": 0.6139,
      "step": 337
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.944719111821316e-06,
      "loss": 0.5501,
      "step": 338
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.944392741935162e-06,
      "loss": 0.5941,
      "step": 339
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.944065422298262e-06,
      "loss": 0.5949,
      "step": 340
    },
    {
      "epoch": 1.01,
      "eval_loss": 0.638019323348999,
      "eval_runtime": 39.5312,
      "eval_samples_per_second": 43.991,
      "eval_steps_per_second": 2.757,
      "step": 340
    },
    {
      "epoch": 1.01,
      "learning_rate": 4.943737153037792e-06,
      "loss": 0.572,
      "step": 341
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.943407934281298e-06,
      "loss": 0.5997,
      "step": 342
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.943077766156698e-06,
      "loss": 0.5769,
      "step": 343
    },
    {
      "epoch": 1.02,
      "learning_rate": 4.942746648792274e-06,
      "loss": 0.5817,
      "step": 344
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.942414582316679e-06,
      "loss": 0.5676,
      "step": 345
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.942081566858938e-06,
      "loss": 0.5879,
      "step": 346
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.941747602548439e-06,
      "loss": 0.5621,
      "step": 347
    },
    {
      "epoch": 1.03,
      "learning_rate": 4.941412689514941e-06,
      "loss": 0.569,
      "step": 348
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.941076827888575e-06,
      "loss": 0.6097,
      "step": 349
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.9407400177998335e-06,
      "loss": 0.5921,
      "step": 350
    },
    {
      "epoch": 1.04,
      "learning_rate": 4.940402259379585e-06,
      "loss": 0.5743,
      "step": 351
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.940063552759061e-06,
      "loss": 0.57,
      "step": 352
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.9397238980698645e-06,
      "loss": 0.5717,
      "step": 353
    },
    {
      "epoch": 1.05,
      "learning_rate": 4.939383295443966e-06,
      "loss": 0.6106,
      "step": 354
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.939041745013703e-06,
      "loss": 0.5952,
      "step": 355
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.938699246911783e-06,
      "loss": 0.585,
      "step": 356
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.938355801271282e-06,
      "loss": 0.5651,
      "step": 357
    },
    {
      "epoch": 1.06,
      "learning_rate": 4.938011408225642e-06,
      "loss": 0.5774,
      "step": 358
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.937666067908675e-06,
      "loss": 0.5878,
      "step": 359
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.937319780454559e-06,
      "loss": 0.5681,
      "step": 360
    },
    {
      "epoch": 1.07,
      "eval_loss": 0.6371431350708008,
      "eval_runtime": 39.5244,
      "eval_samples_per_second": 43.998,
      "eval_steps_per_second": 2.758,
      "step": 360
    },
    {
      "epoch": 1.07,
      "learning_rate": 4.936972545997844e-06,
      "loss": 0.5938,
      "step": 361
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.936624364673444e-06,
      "loss": 0.6068,
      "step": 362
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.936275236616641e-06,
      "loss": 0.5925,
      "step": 363
    },
    {
      "epoch": 1.08,
      "learning_rate": 4.935925161963089e-06,
      "loss": 0.587,
      "step": 364
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.9355741408488045e-06,
      "loss": 0.5683,
      "step": 365
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.9352221734101745e-06,
      "loss": 0.5803,
      "step": 366
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.934869259783955e-06,
      "loss": 0.5782,
      "step": 367
    },
    {
      "epoch": 1.09,
      "learning_rate": 4.934515400107266e-06,
      "loss": 0.613,
      "step": 368
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.934160594517598e-06,
      "loss": 0.5732,
      "step": 369
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.933804843152808e-06,
      "loss": 0.5916,
      "step": 370
    },
    {
      "epoch": 1.1,
      "learning_rate": 4.933448146151122e-06,
      "loss": 0.6108,
      "step": 371
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.933090503651129e-06,
      "loss": 0.5972,
      "step": 372
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.93273191579179e-06,
      "loss": 0.582,
      "step": 373
    },
    {
      "epoch": 1.11,
      "learning_rate": 4.932372382712432e-06,
      "loss": 0.61,
      "step": 374
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.932011904552749e-06,
      "loss": 0.5777,
      "step": 375
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.931650481452801e-06,
      "loss": 0.6123,
      "step": 376
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.931288113553017e-06,
      "loss": 0.5762,
      "step": 377
    },
    {
      "epoch": 1.12,
      "learning_rate": 4.930924800994192e-06,
      "loss": 0.5837,
      "step": 378
    },
    {
      "epoch": 1.13,
      "learning_rate": 4.930560543917489e-06,
      "loss": 0.5738,
      "step": 379
    },
    {
      "epoch": 1.13,
      "learning_rate": 4.930195342464437e-06,
      "loss": 0.587,
      "step": 380
    },
    {
      "epoch": 1.13,
      "eval_loss": 0.6362231373786926,
      "eval_runtime": 39.5188,
      "eval_samples_per_second": 44.004,
      "eval_steps_per_second": 2.758,
      "step": 380
    },
    {
      "epoch": 1.13,
      "learning_rate": 4.929829196776932e-06,
      "loss": 0.5699,
      "step": 381
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.9294621069972385e-06,
      "loss": 0.5855,
      "step": 382
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.929094073267985e-06,
      "loss": 0.5666,
      "step": 383
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.9287250957321685e-06,
      "loss": 0.5724,
      "step": 384
    },
    {
      "epoch": 1.14,
      "learning_rate": 4.928355174533153e-06,
      "loss": 0.598,
      "step": 385
    },
    {
      "epoch": 1.15,
      "learning_rate": 4.92798430981467e-06,
      "loss": 0.5712,
      "step": 386
    },
    {
      "epoch": 1.15,
      "learning_rate": 4.9276125017208144e-06,
      "loss": 0.5902,
      "step": 387
    },
    {
      "epoch": 1.15,
      "learning_rate": 4.927239750396049e-06,
      "loss": 0.5906,
      "step": 388
    },
    {
      "epoch": 1.16,
      "learning_rate": 4.926866055985205e-06,
      "loss": 0.5757,
      "step": 389
    },
    {
      "epoch": 1.16,
      "learning_rate": 4.9264914186334775e-06,
      "loss": 0.5972,
      "step": 390
    },
    {
      "epoch": 1.16,
      "learning_rate": 4.926115838486431e-06,
      "loss": 0.5932,
      "step": 391
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.925739315689991e-06,
      "loss": 0.5793,
      "step": 392
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.9253618503904566e-06,
      "loss": 0.609,
      "step": 393
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.924983442734487e-06,
      "loss": 0.602,
      "step": 394
    },
    {
      "epoch": 1.17,
      "learning_rate": 4.924604092869109e-06,
      "loss": 0.6133,
      "step": 395
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.924223800941718e-06,
      "loss": 0.5706,
      "step": 396
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.923842567100072e-06,
      "loss": 0.6194,
      "step": 397
    },
    {
      "epoch": 1.18,
      "learning_rate": 4.923460391492298e-06,
      "loss": 0.6161,
      "step": 398
    },
    {
      "epoch": 1.19,
      "learning_rate": 4.923077274266886e-06,
      "loss": 0.5833,
      "step": 399
    },
    {
      "epoch": 1.19,
      "learning_rate": 4.922693215572695e-06,
      "loss": 0.5706,
      "step": 400
    },
    {
      "epoch": 1.19,
      "eval_loss": 0.6345230340957642,
      "eval_runtime": 39.5154,
      "eval_samples_per_second": 44.008,
      "eval_steps_per_second": 2.758,
      "step": 400
    },
    {
      "epoch": 1.19,
      "learning_rate": 4.922308215558948e-06,
      "loss": 0.5776,
      "step": 401
    },
    {
      "epoch": 1.2,
      "learning_rate": 4.921922274375232e-06,
      "loss": 0.6127,
      "step": 402
    },
    {
      "epoch": 1.2,
      "learning_rate": 4.921535392171504e-06,
      "loss": 0.5659,
      "step": 403
    },
    {
      "epoch": 1.2,
      "learning_rate": 4.9211475690980825e-06,
      "loss": 0.5987,
      "step": 404
    },
    {
      "epoch": 1.2,
      "learning_rate": 4.920758805305654e-06,
      "loss": 0.5821,
      "step": 405
    },
    {
      "epoch": 1.21,
      "learning_rate": 4.92036910094527e-06,
      "loss": 0.5623,
      "step": 406
    },
    {
      "epoch": 1.21,
      "learning_rate": 4.919978456168347e-06,
      "loss": 0.6118,
      "step": 407
    },
    {
      "epoch": 1.21,
      "learning_rate": 4.919586871126667e-06,
      "loss": 0.6078,
      "step": 408
    },
    {
      "epoch": 1.22,
      "learning_rate": 4.9191943459723764e-06,
      "loss": 0.5703,
      "step": 409
    },
    {
      "epoch": 1.22,
      "learning_rate": 4.918800880857991e-06,
      "loss": 0.585,
      "step": 410
    },
    {
      "epoch": 1.22,
      "learning_rate": 4.9184064759363865e-06,
      "loss": 0.5796,
      "step": 411
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.9180111313608055e-06,
      "loss": 0.5782,
      "step": 412
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.917614847284858e-06,
      "loss": 0.5682,
      "step": 413
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.917217623862516e-06,
      "loss": 0.575,
      "step": 414
    },
    {
      "epoch": 1.23,
      "learning_rate": 4.916819461248119e-06,
      "loss": 0.6286,
      "step": 415
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.916420359596369e-06,
      "loss": 0.587,
      "step": 416
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.916020319062334e-06,
      "loss": 0.5912,
      "step": 417
    },
    {
      "epoch": 1.24,
      "learning_rate": 4.9156193398014464e-06,
      "loss": 0.5933,
      "step": 418
    },
    {
      "epoch": 1.25,
      "learning_rate": 4.915217421969505e-06,
      "loss": 0.5765,
      "step": 419
    },
    {
      "epoch": 1.25,
      "learning_rate": 4.914814565722671e-06,
      "loss": 0.5567,
      "step": 420
    },
    {
      "epoch": 1.25,
      "eval_loss": 0.6341472864151001,
      "eval_runtime": 39.5152,
      "eval_samples_per_second": 44.008,
      "eval_steps_per_second": 2.758,
      "step": 420
    },
    {
      "epoch": 1.25,
      "learning_rate": 4.9144107712174724e-06,
      "loss": 0.5904,
      "step": 421
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.914006038610799e-06,
      "loss": 0.5786,
      "step": 422
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.913600368059908e-06,
      "loss": 0.6183,
      "step": 423
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.913193759722419e-06,
      "loss": 0.5825,
      "step": 424
    },
    {
      "epoch": 1.26,
      "learning_rate": 4.912786213756316e-06,
      "loss": 0.5825,
      "step": 425
    },
    {
      "epoch": 1.27,
      "learning_rate": 4.912377730319951e-06,
      "loss": 0.5916,
      "step": 426
    },
    {
      "epoch": 1.27,
      "learning_rate": 4.9119683095720325e-06,
      "loss": 0.6113,
      "step": 427
    },
    {
      "epoch": 1.27,
      "learning_rate": 4.911557951671641e-06,
      "loss": 0.5842,
      "step": 428
    },
    {
      "epoch": 1.28,
      "learning_rate": 4.911146656778219e-06,
      "loss": 0.5973,
      "step": 429
    },
    {
      "epoch": 1.28,
      "learning_rate": 4.91073442505157e-06,
      "loss": 0.597,
      "step": 430
    },
    {
      "epoch": 1.28,
      "learning_rate": 4.910321256651863e-06,
      "loss": 0.6115,
      "step": 431
    },
    {
      "epoch": 1.28,
      "learning_rate": 4.909907151739634e-06,
      "loss": 0.6106,
      "step": 432
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.909492110475778e-06,
      "loss": 0.5963,
      "step": 433
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.909076133021558e-06,
      "loss": 0.5695,
      "step": 434
    },
    {
      "epoch": 1.29,
      "learning_rate": 4.908659219538598e-06,
      "loss": 0.6013,
      "step": 435
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.908241370188887e-06,
      "loss": 0.5798,
      "step": 436
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.907822585134777e-06,
      "loss": 0.6025,
      "step": 437
    },
    {
      "epoch": 1.3,
      "learning_rate": 4.907402864538984e-06,
      "loss": 0.5943,
      "step": 438
    },
    {
      "epoch": 1.31,
      "learning_rate": 4.906982208564588e-06,
      "loss": 0.6074,
      "step": 439
    },
    {
      "epoch": 1.31,
      "learning_rate": 4.90656061737503e-06,
      "loss": 0.59,
      "step": 440
    },
    {
      "epoch": 1.31,
      "eval_loss": 0.6325353384017944,
      "eval_runtime": 39.5204,
      "eval_samples_per_second": 44.003,
      "eval_steps_per_second": 2.758,
      "step": 440
    },
    {
      "epoch": 1.31,
      "learning_rate": 4.906138091134118e-06,
      "loss": 0.5754,
      "step": 441
    },
    {
      "epoch": 1.31,
      "learning_rate": 4.905714630006022e-06,
      "loss": 0.5871,
      "step": 442
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.9052902341552715e-06,
      "loss": 0.5681,
      "step": 443
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.904864903746765e-06,
      "loss": 0.5601,
      "step": 444
    },
    {
      "epoch": 1.32,
      "learning_rate": 4.904438638945761e-06,
      "loss": 0.5848,
      "step": 445
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.904011439917881e-06,
      "loss": 0.5901,
      "step": 446
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.903583306829111e-06,
      "loss": 0.5771,
      "step": 447
    },
    {
      "epoch": 1.33,
      "learning_rate": 4.903154239845798e-06,
      "loss": 0.5802,
      "step": 448
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.902724239134653e-06,
      "loss": 0.5727,
      "step": 449
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.9022933048627496e-06,
      "loss": 0.5939,
      "step": 450
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.901861437197524e-06,
      "loss": 0.5802,
      "step": 451
    },
    {
      "epoch": 1.34,
      "learning_rate": 4.901428636306776e-06,
      "loss": 0.6126,
      "step": 452
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.9009949023586665e-06,
      "loss": 0.6091,
      "step": 453
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.90056023552172e-06,
      "loss": 0.5896,
      "step": 454
    },
    {
      "epoch": 1.35,
      "learning_rate": 4.900124635964823e-06,
      "loss": 0.5885,
      "step": 455
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.899688103857223e-06,
      "loss": 0.5761,
      "step": 456
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.899250639368534e-06,
      "loss": 0.603,
      "step": 457
    },
    {
      "epoch": 1.36,
      "learning_rate": 4.898812242668727e-06,
      "loss": 0.5811,
      "step": 458
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.89837291392814e-06,
      "loss": 0.5833,
      "step": 459
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.8979326533174696e-06,
      "loss": 0.5829,
      "step": 460
    },
    {
      "epoch": 1.37,
      "eval_loss": 0.6320897340774536,
      "eval_runtime": 39.5185,
      "eval_samples_per_second": 44.005,
      "eval_steps_per_second": 2.758,
      "step": 460
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.897491461007777e-06,
      "loss": 0.5855,
      "step": 461
    },
    {
      "epoch": 1.37,
      "learning_rate": 4.897049337170483e-06,
      "loss": 0.5877,
      "step": 462
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.896606281977372e-06,
      "loss": 0.5679,
      "step": 463
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.8961622956005895e-06,
      "loss": 0.5822,
      "step": 464
    },
    {
      "epoch": 1.38,
      "learning_rate": 4.895717378212644e-06,
      "loss": 0.6133,
      "step": 465
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.895271529986404e-06,
      "loss": 0.5935,
      "step": 466
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.8948247510951004e-06,
      "loss": 0.5794,
      "step": 467
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.894377041712327e-06,
      "loss": 0.5675,
      "step": 468
    },
    {
      "epoch": 1.39,
      "learning_rate": 4.8939284020120365e-06,
      "loss": 0.5841,
      "step": 469
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.893478832168545e-06,
      "loss": 0.6006,
      "step": 470
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.893028332356531e-06,
      "loss": 0.5886,
      "step": 471
    },
    {
      "epoch": 1.4,
      "learning_rate": 4.892576902751031e-06,
      "loss": 0.5754,
      "step": 472
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.892124543527446e-06,
      "loss": 0.5897,
      "step": 473
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.891671254861535e-06,
      "loss": 0.5957,
      "step": 474
    },
    {
      "epoch": 1.41,
      "learning_rate": 4.891217036929422e-06,
      "loss": 0.5853,
      "step": 475
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.890761889907589e-06,
      "loss": 0.5753,
      "step": 476
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.89030581397288e-06,
      "loss": 0.5786,
      "step": 477
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.8898488093025005e-06,
      "loss": 0.5841,
      "step": 478
    },
    {
      "epoch": 1.42,
      "learning_rate": 4.889390876074016e-06,
      "loss": 0.5829,
      "step": 479
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.8889320144653525e-06,
      "loss": 0.5696,
      "step": 480
    },
    {
      "epoch": 1.43,
      "eval_loss": 0.6306838989257812,
      "eval_runtime": 39.5161,
      "eval_samples_per_second": 44.007,
      "eval_steps_per_second": 2.758,
      "step": 480
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.888472224654798e-06,
      "loss": 0.6056,
      "step": 481
    },
    {
      "epoch": 1.43,
      "learning_rate": 4.888011506821e-06,
      "loss": 0.5949,
      "step": 482
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.887549861142967e-06,
      "loss": 0.5899,
      "step": 483
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.887087287800069e-06,
      "loss": 0.5888,
      "step": 484
    },
    {
      "epoch": 1.44,
      "learning_rate": 4.8866237869720334e-06,
      "loss": 0.5751,
      "step": 485
    },
    {
      "epoch": 1.45,
      "learning_rate": 4.886159358838952e-06,
      "loss": 0.6141,
      "step": 486
    },
    {
      "epoch": 1.45,
      "learning_rate": 4.885694003581275e-06,
      "loss": 0.5674,
      "step": 487
    },
    {
      "epoch": 1.45,
      "learning_rate": 4.885227721379811e-06,
      "loss": 0.6058,
      "step": 488
    },
    {
      "epoch": 1.45,
      "learning_rate": 4.8847605124157315e-06,
      "loss": 0.558,
      "step": 489
    },
    {
      "epoch": 1.46,
      "learning_rate": 4.884292376870567e-06,
      "loss": 0.585,
      "step": 490
    },
    {
      "epoch": 1.46,
      "learning_rate": 4.88382331492621e-06,
      "loss": 0.6116,
      "step": 491
    },
    {
      "epoch": 1.46,
      "learning_rate": 4.883353326764907e-06,
      "loss": 0.5761,
      "step": 492
    },
    {
      "epoch": 1.47,
      "learning_rate": 4.882882412569272e-06,
      "loss": 0.5612,
      "step": 493
    },
    {
      "epoch": 1.47,
      "learning_rate": 4.882410572522273e-06,
      "loss": 0.5834,
      "step": 494
    },
    {
      "epoch": 1.47,
      "learning_rate": 4.881937806807241e-06,
      "loss": 0.604,
      "step": 495
    },
    {
      "epoch": 1.48,
      "learning_rate": 4.881464115607866e-06,
      "loss": 0.5949,
      "step": 496
    },
    {
      "epoch": 1.48,
      "learning_rate": 4.880989499108196e-06,
      "loss": 0.5843,
      "step": 497
    },
    {
      "epoch": 1.48,
      "learning_rate": 4.880513957492641e-06,
      "loss": 0.5648,
      "step": 498
    },
    {
      "epoch": 1.48,
      "learning_rate": 4.880037490945968e-06,
      "loss": 0.59,
      "step": 499
    },
    {
      "epoch": 1.49,
      "learning_rate": 4.879560099653306e-06,
      "loss": 0.5811,
      "step": 500
    },
    {
      "epoch": 1.49,
      "eval_loss": 0.6309075355529785,
      "eval_runtime": 39.5278,
      "eval_samples_per_second": 43.994,
      "eval_steps_per_second": 2.758,
      "step": 500
    },
    {
      "epoch": 1.49,
      "learning_rate": 4.879081783800141e-06,
      "loss": 0.5881,
      "step": 501
    },
    {
      "epoch": 1.49,
      "learning_rate": 4.87860254357232e-06,
      "loss": 0.605,
      "step": 502
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.878122379156045e-06,
      "loss": 0.5986,
      "step": 503
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.8776412907378845e-06,
      "loss": 0.5791,
      "step": 504
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.877159278504759e-06,
      "loss": 0.5823,
      "step": 505
    },
    {
      "epoch": 1.5,
      "learning_rate": 4.876676342643953e-06,
      "loss": 0.5889,
      "step": 506
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.876192483343106e-06,
      "loss": 0.5844,
      "step": 507
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.875707700790218e-06,
      "loss": 0.581,
      "step": 508
    },
    {
      "epoch": 1.51,
      "learning_rate": 4.875221995173649e-06,
      "loss": 0.5877,
      "step": 509
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.8747353666821155e-06,
      "loss": 0.5731,
      "step": 510
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.874247815504693e-06,
      "loss": 0.6024,
      "step": 511
    },
    {
      "epoch": 1.52,
      "learning_rate": 4.873759341830816e-06,
      "loss": 0.5948,
      "step": 512
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.873269945850279e-06,
      "loss": 0.5826,
      "step": 513
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.87277962775323e-06,
      "loss": 0.6059,
      "step": 514
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.872288387730182e-06,
      "loss": 0.591,
      "step": 515
    },
    {
      "epoch": 1.53,
      "learning_rate": 4.871796225972e-06,
      "loss": 0.5979,
      "step": 516
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.871303142669911e-06,
      "loss": 0.6112,
      "step": 517
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.870809138015499e-06,
      "loss": 0.551,
      "step": 518
    },
    {
      "epoch": 1.54,
      "learning_rate": 4.870314212200705e-06,
      "loss": 0.5821,
      "step": 519
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.86981836541783e-06,
      "loss": 0.5708,
      "step": 520
    },
    {
      "epoch": 1.55,
      "eval_loss": 0.6294764280319214,
      "eval_runtime": 39.5161,
      "eval_samples_per_second": 44.007,
      "eval_steps_per_second": 2.758,
      "step": 520
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.8693215978595305e-06,
      "loss": 0.5718,
      "step": 521
    },
    {
      "epoch": 1.55,
      "learning_rate": 4.868823909718823e-06,
      "loss": 0.5724,
      "step": 522
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.868325301189079e-06,
      "loss": 0.6142,
      "step": 523
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.86782577246403e-06,
      "loss": 0.5738,
      "step": 524
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.867325323737765e-06,
      "loss": 0.5721,
      "step": 525
    },
    {
      "epoch": 1.56,
      "learning_rate": 4.866823955204728e-06,
      "loss": 0.568,
      "step": 526
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.866321667059724e-06,
      "loss": 0.5848,
      "step": 527
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.865818459497911e-06,
      "loss": 0.5624,
      "step": 528
    },
    {
      "epoch": 1.57,
      "learning_rate": 4.865314332714808e-06,
      "loss": 0.5815,
      "step": 529
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.86480928690629e-06,
      "loss": 0.5705,
      "step": 530
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.864303322268588e-06,
      "loss": 0.5526,
      "step": 531
    },
    {
      "epoch": 1.58,
      "learning_rate": 4.863796438998293e-06,
      "loss": 0.6057,
      "step": 532
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.863288637292347e-06,
      "loss": 0.5767,
      "step": 533
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.862779917348055e-06,
      "loss": 0.5796,
      "step": 534
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.862270279363076e-06,
      "loss": 0.5988,
      "step": 535
    },
    {
      "epoch": 1.59,
      "learning_rate": 4.861759723535427e-06,
      "loss": 0.5678,
      "step": 536
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.861248250063478e-06,
      "loss": 0.6022,
      "step": 537
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.860735859145961e-06,
      "loss": 0.5624,
      "step": 538
    },
    {
      "epoch": 1.6,
      "learning_rate": 4.860222550981961e-06,
      "loss": 0.5853,
      "step": 539
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.859708325770919e-06,
      "loss": 0.5812,
      "step": 540
    },
    {
      "epoch": 1.61,
      "eval_loss": 0.6281893253326416,
      "eval_runtime": 39.5326,
      "eval_samples_per_second": 43.989,
      "eval_steps_per_second": 2.757,
      "step": 540
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.859193183712635e-06,
      "loss": 0.5717,
      "step": 541
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.858677125007262e-06,
      "loss": 0.5839,
      "step": 542
    },
    {
      "epoch": 1.61,
      "learning_rate": 4.858160149855312e-06,
      "loss": 0.5661,
      "step": 543
    },
    {
      "epoch": 1.62,
      "learning_rate": 4.8576422584576515e-06,
      "loss": 0.6015,
      "step": 544
    },
    {
      "epoch": 1.62,
      "learning_rate": 4.857123451015503e-06,
      "loss": 0.5926,
      "step": 545
    },
    {
      "epoch": 1.62,
      "learning_rate": 4.856603727730446e-06,
      "loss": 0.5964,
      "step": 546
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.856083088804415e-06,
      "loss": 0.5646,
      "step": 547
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.8555615344397e-06,
      "loss": 0.5834,
      "step": 548
    },
    {
      "epoch": 1.63,
      "learning_rate": 4.8550390648389475e-06,
      "loss": 0.5774,
      "step": 549
    },
    {
      "epoch": 1.64,
      "learning_rate": 4.854515680205159e-06,
      "loss": 0.6089,
      "step": 550
    },
    {
      "epoch": 1.64,
      "learning_rate": 4.853991380741692e-06,
      "loss": 0.5577,
      "step": 551
    },
    {
      "epoch": 1.64,
      "learning_rate": 4.853466166652259e-06,
      "loss": 0.5546,
      "step": 552
    },
    {
      "epoch": 1.64,
      "learning_rate": 4.852940038140927e-06,
      "loss": 0.5816,
      "step": 553
    },
    {
      "epoch": 1.65,
      "learning_rate": 4.8524129954121215e-06,
      "loss": 0.5693,
      "step": 554
    },
    {
      "epoch": 1.65,
      "learning_rate": 4.851885038670618e-06,
      "loss": 0.5674,
      "step": 555
    },
    {
      "epoch": 1.65,
      "learning_rate": 4.851356168121554e-06,
      "loss": 0.6169,
      "step": 556
    },
    {
      "epoch": 1.66,
      "learning_rate": 4.850826383970416e-06,
      "loss": 0.5778,
      "step": 557
    },
    {
      "epoch": 1.66,
      "learning_rate": 4.850295686423048e-06,
      "loss": 0.583,
      "step": 558
    },
    {
      "epoch": 1.66,
      "learning_rate": 4.849764075685649e-06,
      "loss": 0.6038,
      "step": 559
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.849231551964771e-06,
      "loss": 0.6001,
      "step": 560
    },
    {
      "epoch": 1.67,
      "eval_loss": 0.6277775168418884,
      "eval_runtime": 39.5297,
      "eval_samples_per_second": 43.992,
      "eval_steps_per_second": 2.757,
      "step": 560
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.848698115467324e-06,
      "loss": 0.589,
      "step": 561
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.84816376640057e-06,
      "loss": 0.5979,
      "step": 562
    },
    {
      "epoch": 1.67,
      "learning_rate": 4.847628504972127e-06,
      "loss": 0.5883,
      "step": 563
    },
    {
      "epoch": 1.68,
      "learning_rate": 4.8470923313899655e-06,
      "loss": 0.5967,
      "step": 564
    },
    {
      "epoch": 1.68,
      "learning_rate": 4.846555245862413e-06,
      "loss": 0.5845,
      "step": 565
    },
    {
      "epoch": 1.68,
      "learning_rate": 4.84601724859815e-06,
      "loss": 0.5994,
      "step": 566
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.845478339806211e-06,
      "loss": 0.6005,
      "step": 567
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.844938519695985e-06,
      "loss": 0.5915,
      "step": 568
    },
    {
      "epoch": 1.69,
      "learning_rate": 4.844397788477215e-06,
      "loss": 0.6007,
      "step": 569
    },
    {
      "epoch": 1.7,
      "learning_rate": 4.843856146359999e-06,
      "loss": 0.5915,
      "step": 570
    },
    {
      "epoch": 1.7,
      "learning_rate": 4.843313593554787e-06,
      "loss": 0.5874,
      "step": 571
    },
    {
      "epoch": 1.7,
      "learning_rate": 4.842770130272384e-06,
      "loss": 0.5903,
      "step": 572
    },
    {
      "epoch": 1.7,
      "learning_rate": 4.842225756723949e-06,
      "loss": 0.5684,
      "step": 573
    },
    {
      "epoch": 1.71,
      "learning_rate": 4.841680473120994e-06,
      "loss": 0.5802,
      "step": 574
    },
    {
      "epoch": 1.71,
      "learning_rate": 4.841134279675386e-06,
      "loss": 0.5567,
      "step": 575
    },
    {
      "epoch": 1.71,
      "learning_rate": 4.8405871765993435e-06,
      "loss": 0.5836,
      "step": 576
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.840039164105439e-06,
      "loss": 0.5579,
      "step": 577
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.8394902424065995e-06,
      "loss": 0.5779,
      "step": 578
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.838940411716104e-06,
      "loss": 0.5678,
      "step": 579
    },
    {
      "epoch": 1.72,
      "learning_rate": 4.838389672247585e-06,
      "loss": 0.5684,
      "step": 580
    },
    {
      "epoch": 1.72,
      "eval_loss": 0.6262981295585632,
      "eval_runtime": 39.5368,
      "eval_samples_per_second": 43.984,
      "eval_steps_per_second": 2.757,
      "step": 580
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.83783802421503e-06,
      "loss": 0.5697,
      "step": 581
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.837285467832775e-06,
      "loss": 0.5936,
      "step": 582
    },
    {
      "epoch": 1.73,
      "learning_rate": 4.836732003315513e-06,
      "loss": 0.6041,
      "step": 583
    },
    {
      "epoch": 1.74,
      "learning_rate": 4.836177630878289e-06,
      "loss": 0.5739,
      "step": 584
    },
    {
      "epoch": 1.74,
      "learning_rate": 4.835622350736499e-06,
      "loss": 0.5788,
      "step": 585
    },
    {
      "epoch": 1.74,
      "learning_rate": 4.835066163105896e-06,
      "loss": 0.5989,
      "step": 586
    },
    {
      "epoch": 1.75,
      "learning_rate": 4.834509068202578e-06,
      "loss": 0.6027,
      "step": 587
    },
    {
      "epoch": 1.75,
      "learning_rate": 4.833951066243004e-06,
      "loss": 0.572,
      "step": 588
    },
    {
      "epoch": 1.75,
      "learning_rate": 4.83339215744398e-06,
      "loss": 0.5737,
      "step": 589
    },
    {
      "epoch": 1.75,
      "learning_rate": 4.832832342022666e-06,
      "loss": 0.5881,
      "step": 590
    },
    {
      "epoch": 1.76,
      "learning_rate": 4.832271620196575e-06,
      "loss": 0.5722,
      "step": 591
    },
    {
      "epoch": 1.76,
      "learning_rate": 4.8317099921835695e-06,
      "loss": 0.5751,
      "step": 592
    },
    {
      "epoch": 1.76,
      "learning_rate": 4.831147458201867e-06,
      "loss": 0.5972,
      "step": 593
    },
    {
      "epoch": 1.77,
      "learning_rate": 4.830584018470036e-06,
      "loss": 0.5689,
      "step": 594
    },
    {
      "epoch": 1.77,
      "learning_rate": 4.830019673206997e-06,
      "loss": 0.5537,
      "step": 595
    },
    {
      "epoch": 1.77,
      "learning_rate": 4.829454422632021e-06,
      "loss": 0.5974,
      "step": 596
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.828888266964733e-06,
      "loss": 0.5989,
      "step": 597
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.82832120642511e-06,
      "loss": 0.5825,
      "step": 598
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.827753241233475e-06,
      "loss": 0.5909,
      "step": 599
    },
    {
      "epoch": 1.78,
      "learning_rate": 4.827184371610511e-06,
      "loss": 0.5897,
      "step": 600
    },
    {
      "epoch": 1.78,
      "eval_loss": 0.6251489520072937,
      "eval_runtime": 39.5127,
      "eval_samples_per_second": 44.011,
      "eval_steps_per_second": 2.759,
      "step": 600
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 5040,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 50,
  "total_flos": 2.1880457610955588e+19,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}